Center for Undergraduate Research in Viterbi Engineering (CURVE) Fellowship
![Image](https://viterbiundergrad.usc.edu/wp-content/uploads/2020/11/FH_VSE-CURVE_Card-Blk_CMYK-2.jpg)
Research Labs
Below are open research opportunities for labs participating in the 2024-25 CURVE program. While research labs are organized by department, students are welcome to explore opportunities outside of their own major. Position availability and project details are subject to change. Select research labs will offer information sessions to share more details about upcoming projects.
Aerospace & Mechanical Engineering
-
- Principal Investigator: Bo Jin
- Website: https://composites.usc.edu
- Projects
- Additive Manufacturing of Structures with High Compressive Strength
- Project Description: We are designing structures for high compressive strength, and they are all 3D printed. The structure should reach/beyond 10k lb. compressive strength and will need to be as tall/light as possible. We will support multiple advanced 3D printers with large print-bed and bed-heating functions for shape/warping compensations, and unlimited printing materials for the project. Satisfying structures will attend the annual SAMPE AMC additive manufacturing contest from which we have won a national 3rd in the past. Great honor and a positive plus to student’s resume.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: With the help of faculty and veteran students, conduct meetings and the design of your structures. Design the CAD models using whichever software you are familiar with or trained by veteran students. Print the structures using the lab printers and maintain successful printing processes.
- Preferred Majors: Aerospace & Mechanical Engineering,Astronautical Engineering,Civil & Environmental Engineering,Industrial & Systems Engineering
- Preferred Skillsets: No prerequisite skills required. In-person lab participation required.
- Additive Manufacturing of Structures with High Compressive Strength
- Manufacturing, Processing, Testing, and Machine Learning Predictions of Composite Materials Voids and Structural Strength
- Project Description: This project focuses on employing machine learning algorithms to detect voids in aerospace composite materials, utilizing data from micro-CT imaging to predict material and structural performance for aerospace and automotive parts.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: Work with external industrial advisors and conduct manufacturing, processing, and testing of composite materials and structures, and work with graduate students from USC CS department to apply machine learning algorithms developed to predict material void
- Preferred Majors: Aerospace & Mechanical Engineering, Astronautical Engineering, Civil & Environmental Engineering, Computer Science, Electrical & Computer Engineering, Industrial & Systems Engineering
- Principal Investigator: Yong Chen
- Website: https://viterbi-web.usc.edu/~yongchen/
- Projects:
- 3D Printing Research
- Project Description: Participate in novel 3D printing process, material, and machine development and work with Ph.D. students.
- Open to: CURVE First-Time Researchers
- Student Responsibilities:
- Help to design prototype components
- Perform experiments and analyze data
- Preferred Majors: Aerospace & Mechanical Engineering
- Preferred Skillsets: Students are desired to be interested in hands-on work.
- 3D Printing Research
- Principal Investigator: Geoffrey Spedding
- Website: https://drydenwt.usc.edu/
- Projects
- Aerodynamics of wings at low Reynolds number
- Project Description: Establish separation lines and points of flow control for a small wing. Three-dimensional descriptions and control will be required
- Open to: CURVE First-Time Researchers
- Student Responsibilities: Learn instrumentation and how to run a sweep through incidence angles while taking and analysing force coefficient data.
- Preferred Majors: Aerospace Engineering
- Preferred Skillsets: Matlab, basic Aero, such as from AME 105
- Aerodynamics of wings at low Reynolds number
-
- Principal Investigator: Quan Nguyen
- Website: https://sites.usc.edu/quann/
- Projects:
- Design and System Integration of Humanoid Robot
- Project Description: The project is aiming to develop a humanoid robot platform that consists of 5 degrees of freedom for each leg and 4 degrees of freedom for each arm. In addition, the project aims to incorporate different sensors besides design optimization to improve the robustness and functionality of the humanoid robot.
- Open to: CURVE First-Time Researchers, CURVE Continuing Researchers
- Student Responsibilities: Students will be responsible for improving the design of the current HECTOR platform and integrating various sensors and systems to improve the overall performance of the robot.
- Preferred Majors: Mechanical Engineering, Electrical and Computer Engineering, Computer Science
- Preferred Skillsets: CAD (solidworks), embedded system programming, C++, ROS.
- Design and System Integration of Humanoid Robot
- Principal Investigator: Matthew Gilpin
- Website: https://sites.usc.edu/inspr/
- Projects
- Multi-Axis Thrust Measurement System
- Project Description: The goal of this project is to develop a multi-axis thrust measurement system for an integrated multi-thruster pod. It is relatively simple to measure thrust in multiple axis for large thrusters and at steady state. However, this project aims for transient measurements at the < 1N scale which will require either dynamic analysis of a multi-axis pendulum or vibrational analysis of a multi-load cell array.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Students on this project will be responsible for design, fabrication and operation of the thrust measurement system which will incorporate either standard torsional thrust stand hardware or a load cell array. Testing will be performed in-lab using a compressed gas mock-thruster. The project will ultimately be delivered to the AFRL for use in the evaluation of flight hardware.
- Preferred Majors: Aerospace & Mechanical Engineering,Astronautical Engineering
- Preferred Skillsets: LabView, MATLAB, Arduino, basic electronics, Dynamics, Physics 152
- Multi-Axis Thrust Measurement System
- Index of Refraction Measurement to Determine In-Situ Viscocity
- Project Description: Variations in the propellant viscosity for 1 N class thrusters creates unique challenges for diagnostic development and system characterization. This project aims to measure variations in the index of refraction of a fluid via non-invasive means to gather real-time information on changes in propellant viscosity.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Students on this project will help construct the flow apparatus and operate borrowed AFRL hardware for the measurement of viscosity for simulated propellant. If successful, experimental hardware from USC will be delivered to AFRL for in-situ measurements of flight-like hardware.
- Preferred Majors: Aerospace & Mechanical Engineering,Astronautical Engineering
- Preferred Skillsets: LabView, MATLAB, Fluid Dynamics, Phys 152
- Principal Investigator: Hangbo Zhao
- Website: https://sites.usc.edu/zhaogroup/
- Projects
- Thermal conductivity of liquid metal-based composite materials
- Project Description: Liquid metal is a fluid with metallic properties (high electrical conductivity and thermal conductivity). The project aims to experimentally study the thermal conductivity of liquid metal-based composite materials, which have high mechanical stretchability and thermal conductivity.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: The student will learn basic material processing and mechanical/electrical/thermal characterization.
- Preferred Majors: Materials Science and Engineering, Mechanical Engineering
- Preferred Skillsets: Heat transfer knowledge; Hands on experiences in materials processing or characterization
- Thermal conductivity of liquid metal-based composite materials
Alfred E. Mann Department of Biomedical Engineering
- Principal Investigator: Ellis Meng
- Website: https://biomems.usc.edu
- Projects
- Biomedical Microsystems Lab Research Experience
- Project Description: There are two parts to this project. One involves developing a wireless biomarker sensing system that is non-invasive and intended to be worn. The second project involves development of a sensor for monitoring blood flow that can be used in conjunction with an implanted shunt for patients born with an underdeveloped heart.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: The student will particpate in research meetings with their graduate student mentor. They will conduct research tasks related to simulating different coil geometries needed for the wireless sensing system. They will also perform circuit deisgn and printed circuit board fabrication.
- Preferred Majors: Biomedical Engineering ,Electrical & Computer Engineering
- Preferred Skillsets: Student should have basic knowledge of circuits (theoretical and practical hands on skills). Previous coursework with exposure to circuit design and/or wireless commmunication technology is preferred.
- Biomedical Microsystems Lab Research Experience
- Principal Investigator: Megan McCain
- Website: https://livingsystemsengineering.usc.edu
- Projects:
- Engineering Organs on Chips
- Project Description: Our lab engineers microscale human tissues as new models for human disease modeling and drug screening. We do this by culturing cells on surfaces or in fluidic devices that mimic key features of native human tissues and enable quantitative readouts of tissue structure and physiology. Our core interests are in muscle (heart, skeletal, uterus), but we also develop models of other systems (kidney, brain) with collaborators.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities:
- Microfabrication of culture surfaces or fluidic devices, including hydrogel fabrication, 3-D printing, laser engraving, microfluidic device assembly, etc.
- Analysis of microscopy images
- Students that demonstrate excellent lab skills will be trained in cell culture
- Preferred Majors: Biomedical Engineer
- Preferred Skillsets: CAD, MATLAB, wet lab experience
- Engineering Organs on Chips
- Principal Investigator: Maral Mousavi
- Website: https://sites.usc.edu/mousavi/
- Projects:
- Developing neural interfaces for neurotransmitter detection
- Project Description: This project aims to develop neural interfaces for sensing neurotransmitters such as dopamine and acetylcholine. There are two parts to this project. One involves developing carbon-based neural interfaces. The second project involves sensor modification for monitoring dopamine and acetylcholine
- Open to: CURVE First-Time Researchers
- Student Responsibilities: Students will learn basic material processing and electrical and electrochemical characterization.
- Preferred Majors: Biomedical Engineering Engineering, Chemical Engineering and Mechanical Engineering
- Preferred Skillsets: Chemistry knowledge, Electrochemistry knowledge, Hands-on experience in electrical/chemical characterization,
- Developing neural interfaces for neurotransmitter detection
- Principal Investigator: Dong Song
- Website: https://slab.usc.edu/people.html
- Projects
- Neural modulation with TMS
- Project Description: Transcranial magnetic stimulation (TMS) is a non-invasive tool commonly used clinically to treat a wide range of neurological and neuropsychiatric conditions such as epilepsy, Alzheimer's disease, Parkinson's disease, and focal hand dystonia. Short pulses of electric current are delivered to a coil placed close to the scalp. Even with low-intensity stimulations, TMS still shows neuromodulation effects in both humans and rodents. It is also an ideal tool for studying functional connectivity and neural plasticity of various networks and nervous system. By monitoring neural activities and the animal's behavior before and after rTMS stimulation, we can gain a more comprehensive understanding of the underlying mechanism of the modulation effects of rTMS on neurons and neural circuits.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities:
- Each undergraduate researcher is expected to spend eight to ten hours per week (twenty to twenty-five hours per week for the summer semester) for each semester on the project.
- Undergraduate students will work independently to conduct behavioral experiments on rodents. They will start by pre-training the animal to let it get familiar with being handled and restricted during TMS.
- Undergraduate students will deliver TMS stimulation to the animal following the graduate student's instruction.
- Undergraduate students will assist in analyzing data collected from the TMS experiment.
- Preferred Majors: Biomedical Engineering, Chemical Engineering, Computer Science, Electrical & Computer Engineering
- Preferred Skillsets:
- GPA greater than 3.5
- Proficient in using Word, Excel, and PPT
- Preferred to have animal experiment experience
- Know how to use Matlab
- Neural modulation with TMS
-
- Electrophysiological Studies on Behaving Animals
- Project Description: Neural signals recorded with chronically implanted MEAs are correlated with the animal's behavior in multiple experiment paradigms. Three sets of behavioral experiments are conducted to study different aspects and features of the hippocampal circuit. First, a free exploring experiment conducted in an open field allows for studying hippocampal functions during naturalistic behaviors. Second, the open field is further modified into a 4-compartment arena with visual cues and removable dividers. By sequentially removing each wall, the animal will explore a dynamic environment with novel geometric shapes and visual cues. We also implemented a virtual reality (VR) system for mice and developed a set of open fields with enriched stimuli. The animal will be encouraged to continue exploring these novel environments, and neural plasticity will be induced. The physical and VR DEN tasks make it possible to investigate hippocampal neural responses to spatial novelty and to identify plasticity rules involved in navigation. Third, the DNMS task is a classic paradigm for studying the hippocampus's memory functions. Simultaneously recorded neural activities from multiple hippocampal sub-regions while the animal is learning and performing the DNMS task can provide valuable insight into the dynamic of memory formation.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities:
- Each undergraduate researcher is expected to spend eight to ten hours per week (twenty to twenty-five hours per week for the summer semester) for each semester on the project.
- Undergraduate students will work independently to conduct behavioral experiments on rodents. They will start by pre-training the animal to let it get familiar with being handled. They will also be in charge of feeding the animal and measuring the body weight of the animal according to the food and water restriction protocol.
- Undergraduate students will assist the graduate student in conducting the DEN and virtual DEN tasks.
- Undergraduate students will assist the graduate student in training animals to perform the DNMS task.
- Undergraduate students will assist in analyzing behavioral and neural data collected from animals.
- Preferred Majors: Biomedical Engineering,Chemical Engineering
- Preferred Skillsets:
- GPA greater than 3.5
- Proficient in using Word, Excel, and PPT
- Preferred to have animal experiment experience
- Know how to use Matlab
- Electrophysiological Studies on Behaving Animals
- Principal Investigator: Jennifer Treweek
- Website: sites.usc.edu/treweek-lab/
- Projects
- 3D imaging and analysis of the intact rodent eye
- Project Description: The goal of this project is to trace cellular connectivity from the retina-to-brain in intact tissue specimens. This project entails the dissection, tissue-clearing, labeling, and imaging of the rodent eye, optic nerve, and visual centers in the brain.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Wetlab work: tissue dissection, hydrogel-embedding, histology (antibody labeling), tissue-clearing, and confocal imaging
- Drylab work: computational image analysis of the retina (cell counting in different retinal layers, quantification of retinal layer thickness, tract tracing, etc)
- Preferred Majors: Biomedical Engineering
- Preferred Skillsets: basic wetlab skills (pipetting, calculating dilutions, making stock solutions, use of a chemical fume hood)
- desired but not required: working with tissue specimens (e.g., histology, light microscopy)
- 3D imaging and analysis of the intact rodent eye
- Optimizing viral vectors for gene delivery to the rodent brain
- Project Description: The goal of this project is to achieve widespread, brainwide expression of neuronal activity sensors through the use of blood-brain-barrier (BBB)-crossing adeno-associated virus (rAAV) vectors. This project entails producing high-quality, high-titer viral vectors using triple transfection in mammalian cell culture. In addition, this project could include a drylab component: i.e., the creation of an electronic database that document the viral vectors which achieve experimental success - based on a set of evaluation parameters.
- Open to: CURVE First-Time Researchers
- Student Responsibilities:
- Wetlab student: DNA plasmid production and purification, mammalian cell culture, virus purification via density gradient columns and centrifugation, histology of rAAV-transduced brain tissues (antibody-labeling, slide-mounting, confocal imaging)
- Drylab student: creation of a website to host lab data on experimental parameters and AAV success metrics; also computational image analysis for counting AAV-transduced cells in brain regions-of-interest
- Preferred Majors: Biomedical Engineering
- Preferred Skillsets: Preferred skills/experiences are related to tasks in job description:
- Wetlab student: basic wetlab skills (e.g., pipetting, preparing dilutions and stock solutions, working in a bisafety cabinet and/or knowledge of celll culture techniques would be ideal); knowledge of basic histology "best-practices" would also be ideal
- Drylab student: basic computer skills (website creation, methods for tabulating datasets, etc); basic analytical skills; for computational image analysis, skills related to either automated/semi-automated methods for cell counting and image analysis - e.g., using imageJ/fiji)
- Principal Investigator: Francisco Valero-Cuevas
- Website: https://valerolab.org
- Projects
- Deficient dynamic neuromuscular control explains risky landing mechanics: A pilot project to assess and manage the risk of ACL injury in women
- Project Description: We seek to democratize the evaluation of risk for anterior cruciate ligament (ACL) injuries of the knee (200,000+ per year in the US alone) that disproportionately affect amateur athletes who are girls and women. These injuries often lead to reinjury, lifetime reduction of physical activity, and early-onset osteoarthritis of the knee. Specialized biomechanics labs have found that excessive inward “knocking†of the knees (dynamic knee valgus) when landing from a drop has been asso- ciated with risk of ACL injury, mostly in amateur athletes. These labs are, however, out of reach of those amateur athletes who suffer the majority of injuries. Simple phone-based motion capture tools (OpenCap) developed by the Wu Tsai Human Performance Alliance offer great promise to perform these measurements in any amateur setting at a global scale. Our pilot project seeks to demonstrate that increased knee valgus during landing in amateur athletes is associated with worse neuromuscular control of the leg (as per the Leg Dexterity Test) compared to elite athletes (Aim 1, Year 1). Moreover, training with the Leg Dexterity system will improve landing mechanics (Aim 2, Year 2). Thus, this small project seeks to bring a rigorous neuromechanical foundation to the phone-based OpenCap evaluation of ACL injury in amateur athletes. Our results will enable appropriately large studies to deploy simple means to evaluate the risk of ACL injury, and train neuromuscular control to mitigate the risk of ACL injuries, for better lifelong health of millions of girls and women worldwide.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Data collection in elite and amateur athletes
- Preferred Majors: Aerospace & Mechanical Engineering, Biomedical Engineering, Computer Science, Electrical & Computer Engineering
- Preferred Skillsets: Interest in women's health, neuromuscular systems and elite performance.
- Deficient dynamic neuromuscular control explains risky landing mechanics: A pilot project to assess and manage the risk of ACL injury in women
- Principal Investigator: Vinay Duddalwar
- Website: https://sites.usc.edu/uscradiomicslab/
- Projects
- AI-Powered Interface for a Rapid Segmentation of Renal Masses Using MedSam
- Project Description: The rapid and accurate segmentation of renal masses from medical scans is crucial for timely diagnosis and treatment planning. This project aims to develop a user-friendly interface that leverages the capabilities of MedSam, an advanced medical image segmentation tool. The interface will streamline the process of importing new scans and quickly applying MedSam's segmentation algorithms to identify renal masses.
- Objectives:
- Interface Development: Design and implement an intuitive interface that allows medical professionals to easily upload and manage new scans.
- Integration with MedSam: Seamlessly integrate MedSam into the interface to facilitate the rapid and accurate segmentation of renal masses.
- Workflow Optimization: Ensure the interface supports a smooth workflow, from scan import to segmentation and review, reducing the time and effort required for each step.
- Validation and Testing: Conduct extensive testing with a variety of scans to ensure the robustness and accuracy of the segmentation process.
- Open to: CURVE First-Time Researchers
- Student Responsibilities:
- Interface Design: Collaborate on designing the user interface, ensuring it is intuitive and user-friendly.
- Coding and Implementation: Write code for the interface and integrate it with MedSam's API.
- Testing and Debugging: Perform rigorous testing of the interface with various types of scans, identify bugs, and implement fixes.
- Data Management: Handle the import and organizing data for testing and validation purposes.
- User Support: Develop user manuals and conduct training sessions for medical professionals to help them use the new interface effectively.
- Feedback Integration: Collect feedback from initial users and incorporate suggestions for improvement into the interface design.
- Preferred Majors: Biomedical Engineering,Computer Science,Electrical & Computer Engineering
- Preferred Skillsets:
- Programming Skills: Proficiency in languages such as Python, TensorFlow, PyTorch, JavaScript, or similar.
- Experience with web development frameworks (e.g., React, Angular, Django).
- API Integration: Familiarity with integrating third-party APIs. Understanding of RESTful services and how to interact with them.
- Medical Imaging Knowledge:
- Basic understanding of medical imaging formats (e.g., DICOM, NII).
- Knowledge of image processing and segmentation techniques.
- Testing and Debugging:
- Strong skills in testing software applications.
- Ability to identify and fix bugs efficiently.
- Data Management:
- Skills in handling and organizing large datasets.
- Experience with databases and data storage solutions.
- Communication Skills
- Ability to write clear documentation and user guides.
- Effective verbal communication for training and support.
- AI-Powered Interface for a Rapid Segmentation of Renal Masses Using MedSam
- Evaluating Machine Learning Model Sustainability Through Carbon Footprint Estimation
- Project Description: This project aims to evaluate the sustainability of machine learning models by estimating their carbon footprint. It involves a detailed analysis of the energy consumption and associated carbon emissions during various stages, including training, validation, and deployment. By identifying the most resource-intensive processes and exploring optimization techniques, the project seeks to develop guidelines for reducing the environmental impact of AI technologies. The ultimate goal is to promote the adoption of sustainable practices in the machine learning community, thereby contributing to the broader effort of mitigating climate change through responsible and eco-friendly AI development.
- Objectives:
- Carbon Footprint Estimation Framework: Adopting a comprehensive framework for estimating the carbon footprint of ML models, considering factors such as energy consumption during training, hardware efficiency, and operational emissions.
- Data Collection and Analysis: Collect data on energy usage and resource consumption from various ML model training and deployment scenarios.
- Comparative Analysis: Evaluate and compare the carbon footprints of different ML models and algorithms to identify more sustainable options.
- Optimization Strategies: Propose and test strategies for reducing the carbon footprint of ML models without compromising their performance, such as optimizing code, using energy-efficient hardware, and adopting greener data centers.
- Awareness and Reporting: Create tools and guidelines for researchers and practitioners to report the carbon footprints of their ML models transparently.
- Open to: CURVE First-Time Researchers
- Student Responsibilities:
- Data Gathering: Collect and organize data on energy consumption and resource usage from ML model training and deployment processes.
- Framework Development: Assist in developing the framework for estimating the carbon footprints of various ML models.
- Analysis and Reporting: Conduct comparative analyses of different models and document their carbon footprints.
- Optimization Testing: Implement and test various strategies to reduce the carbon footprints of ML models.
- Tool Creation: Help develop tools for researchers to estimate and report the carbon footprints of their models.
- Documentation and Communication: Prepare detailed reports and presentations on findings, and create guidelines for sustainable ML practices.
- Preferred Majors: Biomedical Engineering,Computer Science,Electrical & Computer Engineering
- Preferred Skillsets
- Programming Skills: Proficiency in languages such as Python, TensorFlow, PyTorch, JavaScript, or similar.
- Experience with web development frameworks (e.g., React, Angular, Django).
- API Integration: Familiarity with integrating third-party APIs. Understanding of RESTful services and how to interact with them.
- Medical Imaging Knowledge:
- Basic understanding of medical imaging formats (e.g., DICOM, NII).
- Knowledge of image processing and segmentation techniques.
- Testing and Debugging:
- Strong skills in testing software applications.
- Ability to identify and fix bugs efficiently.
- Data Management:
- Skills in handling and organizing large datasets.
- Experience with databases and data storage solutions.
- Communication Skills
- Ability to write clear documentation and user guides.
- Effective verbal communication for training and support.
Mork Family Department of Chemical Engineering and Materials Science
- Principal Investigator: Shaama Mallikarjun Sharada
- Website: https://sharada-lab.usc.edu/
- Projects
- Designing green chemistry pathways for carbon dioxide utilization
- Project Description: Our goal is to identify sustainable, light-driven routes for CO2 utilization. Prior experiments show that upon activation by light and subsequent reduction, a simple organic chromophore, p-terphenyl, can reduce and transform CO2 into valuable molecules such as amino acids. These photoredox reactions are attractive because organic chromophores are metal-free and can access highly reactive states upon excitation and quenching that are otherwise energy-intensive. However, the steps of the photoredox cycle and the reasons for the low turnover numbers of these catalysts are poorly understood. My group uses state-of-the-art quantum chemistry methods and automated workflows to delineate mechanisms of steps constituting the catalytic cycle and leverage these insights to drive the discovery of viable chromophores.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: The student will learn how to create models of molecular systems, simulate chemical reactions using supercomputers and quantum chemistry software, and analyze data using Python.
- Preferred Majors: Chemical Engineering
- Preferred Skillsets: No pre-reqs
- Designing green chemistry pathways for carbon dioxide utilization
- Principal Investigator: Luis Francisco Villalobos
- Website: https://www.villaloboslab.com
- Projects
- Rational design of symmetric polymeric membrane adsorbers for single-pass capture of trace contaminants
- Project Description: This project proposes the rational design of symmetric polymeric membrane adsorbers to enhance water purification techniques, specifically targeting the efficient removal of PFAS and boron. Utilizing Anodic Aluminum Oxide (AAO) as a model system for its structured porosity, undergraduate researchers will optimize ligand selection and confinement for selective contaminant capture. They will then apply this knowledge to develop a scalable process to make porous membrane adsorbers with a high density of binding sites and controlled pore size using polymerization-induced phase separation.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities:
- Conduct experiments on the synthesis of symmetric membrane adsorbers using polymerization-induced phase separation techniques.
- Characterize membrane materials through transport measurements.
- Perform membrane performance testing with simulated and real water samples, focusing on the removal of PFAS and boron.
- Analyze experimental data to develop structure-property relationships for the adsorptive capabilities of membranes.
- Test membranes under realistic conditions to evaluate the impact of competing species on contaminant removal efficiency.
- Take part in group activities for collaborative learning and research
- Preferred Majors: Chemical Engineering
- Preferred Skillsets:
- CHE350: Introduction to Separation Processes
- CHE444: Chemical Engineering Lab
- Rational design of symmetric polymeric membrane adsorbers for single-pass capture of trace contaminants
Sonny Astani Department of Civil and Environmental Engineering
- Principal Investigator: Jiachen Zhang
- Website: https://sites.usc.edu/jzhang/
- Projects
- Assessing Health Disparities Arising from Air Pollutant Emissions Linked to Port-Related Activities: A Case Study of the Ports of Los Angeles and Long Beach
- Project Description: Port-related activities, encompassing the operation of vessels, trucks, and cargo handling equipment, are a significant source of air pollutants, leading to respiratory and cardiovascular diseases. Low-income, often minority-populated communities are more likely to be located near ports or freeways, and are therefore at a greater risk of exposure to air pollutants from port-related emissions. We propose a case study on the Ports of Los Angeles (LA) and Long Beach (LB), which have served as vital gateways for freight movement in the United States, handling 40 percent of the cargo entering the nation. This proposed research will develop a modeling framework to assess the air quality and health impacts of port-related emissions at a high spatial resolution and investigate the unequal burden of adverse environmental health impacts in disadvantaged communities. Utilizing this modeling framework, we will quantify the surge in primary particulate matter (PM) emissions resulting from port congestion in 2021, a situation driven by the COVID-19 pandemic and disruptions in the supply chain. Subsequently, we will for the first time assess the resultant health impacts of excess PM emissions on nearby communities. The insights gained from our research will provide insights for implementing measures aimed at mitigating the disproportionate exposure of disadvantaged communities to emissions from port-related activities.
- Open to: CURVE First-Time Researchers
- Student Responsibilities:
- Collect and analyze weather and air quality observation data
- Compare the model output with observational data and visualize the results
- Collect and analyze massive amount of spatial data related to the emissions of locomotives and ocean-going vessels
- Literature review in health impact assessment
- Preferred Majors: Aerospace & Mechanical Engineering,Chemical Engineering,Civil & Environmental Engineering,Computer Science,Electrical & Computer Engineering
- Preferred Skillsets:
- Courses related to air pollution, climate change, and spatial data science
- Programming skills (Python)
- ArcGIS or QGIS
- Abilities to handle big data
- Assessing Health Disparities Arising from Air Pollutant Emissions Linked to Port-Related Activities: A Case Study of the Ports of Los Angeles and Long Beach
- Principal Investigator: Burcin Becerik-Gerber
- Website: https://www.i-lab.usc.edu
- Projects
- Behavior-driven building safety & emergency management for campus communities
- Project Description: This project is to design and test a framework for mathematically modeling realistic human behavior and incorporating these models into simulations for campus communities. Potential users of these models (building designers, emergency managers, first responders, etc.) need the simulation outcomes to be reliable to support good decision-making.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Support the development a behavior modeling framework that incorporates diverse personal, social, and environmental factors.
- Preferred Majors: Civil & Environmental Engineering,Computer Science,Electrical & Computer Engineering
- Preferred Skillsets: Experience with game engines (e.g., Unity, Unreal Engine), CAD Software (e.g., Revit); knowledge in statistical analysis techniques and programming languages such as Python or MATLAB
- Behavior-driven building safety & emergency management for campus communities
- Principal Investigator: Daniel McCurry
- Website: https://mccurrylab.com
- Projects
- Contaminant removal and transformation in wastewater reuse systems
- Project Description: Research activities in our lab focus on enabling safe water reuse by minimizing the presence of harmful contaminants in recycled wastewater. Our major research efforts include developing new chemical technologies for oxidation of trace organic contaminants, identifying the precursors and transformation pathways of disinfection byproducts formed during water treatment and wastewater reuse, and developing new analytical techniques for identification and quantification of chemical pollutants using mass spectrometry. Our research primarily takes place in the BHE Water Lab, and relies heavily chemical analytical instrumentation, including an ion mobility QTOF mass spectrometer, a gas chromatograph/triple quadrupole mass spectrometer, and an inductively-coupled plasma mass spectrometer. These tools allow us to quantify chemicals at extremely low concentrations (e.g., parts per trillion) and to identify previously unknown compounds in water samples.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Assisting graduate students with experiments on water treatment, water reuse, and quantification of trace contaminants in water. Specific responsibilities will include preparing for and setting up batch water treatment experiments, sample preparation for mass spectrometry-based identification and quantification of pollutants, and analyzing data produced by analytical instruments. Especially dedicated students may eventually have the opportunity to advance to a fully-independent project advised directly by the PI.
- Preferred Majors: Biomedical Engineering,Chemical Engineering,Civil & Environmental Engineering
- Preferred Skillsets: General chemistry lab skills.
- Some exposure to analytical chemistry is helpful but not required.
- General chemistry coursework (e.g., CHEM105 here or AP equivalent)
- Contaminant removal and transformation in wastewater reuse systems
- Environmental fate of wildfire-associated heavy metals
- Project Description: Our recent research has found that aerial wildfire suppression potentially contributes toxic heavy metals to the environment. This project will involve bench-scale experiments and possibly field sampling to determine the fate and transport of these metals in the environment between soil and aqueous phases, and to evaluate the potential for surface water contamination by fire suppressant application.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Assisting graduate students with experiments on the fate of heavy metals from wildfire suppressants applied aerially to wildfire sites. Specific responsibilities will include preparing for and setting up bench-scale soil column experiments, sample preparation for mass spectrometry-based and quantification of metals, and analyzing data produced by analytical instruments. The project may include field sampling of burn sites with evidence of aerial application of fire retardants, depending on fire season intensity and site access. Especially dedicated students may eventually have the opportunity to advance to a fully-independent project advised directly by the PI.
- Preferred Majors: Biomedical Engineering,Chemical Engineering,Civil & Environmental Engineering
- Preferred Skillsets: General chemistry lab skills
- Some exposure to analytical chemistry is helpful but not required
- General chemistry coursework (e.g., CHEM105 here or AP equivalent)
- Principal Investigator: Thomas Petersen
- Website: https://sites.google.com/usc.edu/petersen-lab/home
- Projects
- Modeling liquid-vapor transport through porous media
- Project Description: The coupling between fluid and solid (such as membranes, soils, and cement) plays a vital role in the transport efficiency of separation processes and the mechanical deformation and durability of the porous medium. In this project, we aim to develop a continuum mechanics formulation for the transport of liquid and vapor phases through a soft, porous solid. The goal is to link the thermodynamic properties of the fluid phase, which constitutes a mixture of water molecules and ions, to a reaction-advection-diffusion equation for the salt solution. Simultaneously, the local osmotic pressure of the fluid will be linked to the deformation of the porous matrix. The goal is to use model predictions to rationalize experimental results on membranes and soil columns.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: Help run (code) and design continuum mechanics models of fluid and solid transport. Produce output in the form of figures and data.
- Preferred Majors: Aerospace & Mechanical Engineering,Chemical Engineering,Civil & Environmental Engineering
- Preferred Skillsets: Solid mechanics, fluid mechanics, thermodynamics, electrochemistry, python/MATLAB (or experience with another coding language)
- Modeling liquid-vapor transport through porous media
- Principal Investigator: Sifat Muin
- Website: https://www.sifatmuin.com/
- Projects
- Simulated Ground Motion Application
- Project Description: We will use simulated ground motion to generate structural responses and compare them to actual recorded ground motions
- Open to: CURVE First-Time Researchers
- Student Responsibilities:
- Running analysis
- Generating results
- Meeting with PI
- Preferred Majors: Aerospace & Mechanical Engineering,Civil & Environmental Engineering
- Simulated Ground Motion Application
-
- Printed Sensor Project
- Project Description: We will develop and test structural health monitoring sensors.
- Open to: CURVE First-Time Researchers
- Student Responsibilities:
- Running experiments
- Generating results
- Meeting PI
- Preferred Majors: Aerospace & Mechanical Engineering,Civil & Environmental Engineering,Electrical & Computer Engineering
- Printed Sensor Project
-
- Community Sentiment Analysis for Earthquake Resilience
- Project Description: We use social computing methods in order to identify vulnerable population post earthquake
- Open to: CURVE Continuing Researchers
- Preferred Majors: Civil & Environmental Engineering
- Community Sentiment Analysis for Earthquake Resilience
- Principal Investigator: Amy Childress
- Website: https://rewater.usc.edu/
- Projects
- Systems of Potable Water Reuse and Desalination
- Project Description: Childress' research team seeks holistic and realistic solutions to the problem of finite water resources. Her team studies: pressureâ€driven membrane processes for contaminant and energy challenges; innovative membrane materials and processes, integrating systems of desalination and water reuse; and membrane surface and material characterization. Her team has carried out laboratory research, process development, and field applications to assess the energy, recovery, and water quality advantages of novel processes and systems.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: CURVE students will work with PhD students on my team to carry out research that spans from fundamental surface characterization to innovative processes for water treatment to conceptual analyses of large-scale facility integration
- Preferred Majors: Chemical Engineering,Civil & Environmental Engineering
- Systems of Potable Water Reuse and Desalination
- Principal Investigator: Ruolin Li
- Website: https://ruolinli.me/
- Projects:
- Re-engineering Transportation Systems for AV Integration
- Project Description: The enhanced controllability of autonomous vehicles opens up a myriad of possibilities. For example, autonomous vehicles can be platooned with shorter headways, which increase road capacities, or they can act on information as altruistic decision-makers, thereby improving societal benefits. Autonomous vehicles and existing transportation infrastructure are also intricately linked. The challenge lies in managing or reshaping our current infrastructure to accommodate AVs efficiently and economically. How can we adapt our roads, signaling systems, and urban planning to meet the demands of AV technology? Insights into the dynamic interaction between robotic AVs and infrastructure optimization can guide us in creating cost-effective, efficient solutions that pave the way for the future of transportation.
- Open to: CURVE First-Time Researchers ,CURVE Continuing Researchers
- Student Responsibilities: Literature review, Coding numerical examples
- Preferred Majors: Electrical & Computer Engineering, Industrial and Systems Engineering, Civil & Environmental Engineering, Computer Science, Aerospace & Mechanical Engineering
- Preferred Skillsets: Interest in reading maths, Proficient programming for optimization in python or MATLAB
- Re-engineering Transportation Systems for AV Integration
-
- React and Interact: Harmonizing AVs with Humans
- Project Description: Modeling human behavior in transportation systems is crucial yet challenging. Imagine drivers mischievously cutting in front of slowly moving autonomous vehicles just for fun! The impact of autonomous vehicles is significantly influenced by human reaction
- Open to: CURVE First-Time Researchers ,CURVE Continuing Researchers
- Student Responsibilities: Literature review, Running SUMO simulations
- Preferred Majors: Civil & Environmental Engineering, Electrical & Computer Engineering, Industrial and Systems Engineering, Computer Science, Aerospace & Mechanical Engineering
- Preferred Skillsets: Interest in reading maths, Basic programming experience in python, Prior experience with traffic simulation softwares, especially SUMO
- React and Interact: Harmonizing AVs with Humans
- Principal Investigator: Adam Smith
- Website: https://www.smithresearchusc.com
- Projects
- Investigating Bioelectrochemical Systems as Biosensors in Engineered Water Treatment
- Project Description: The project uses exoelectrogenic microorganisms to generate an electrical signal in the presence of organic matter. This can be utilized as a biosensor to provide real-time monitoring of aggregate organics in engineered systems, such as bioreactors used for wastewater treatment.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: The student will assist a PhD student in operating and monitoring bench-scale bioelectrochemical systems. The student will be able to learn analytical chemistry and molecular biology techniques.
- Preferred Majors: Chemical Engineering,Civil & Environmental Engineering
- Preferred Skillsets: Chemistry and biology
- Investigating per- and polyfluoroalkyl substances (PFAS; forever chemicals) in various environmental matrices and bench-scale bioreactors
- Project Description: This project investigates the fate of PFAS across water reclamation processes at the full-scale and in bench-scale systems in the lab. We also quantify PFAS in a community engagement process focusing on drinking water and dust samples.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: The student will assist PhD students in operating and monitoring bench-scale bioreactors and quantifying PFAS using analytical chemistry.
- Preferred Majors: Chemical Engineering,Civil & Environmental Engineering
- Preferred Skillsets: Chemistry and biology
- Investigating Bioelectrochemical Systems as Biosensors in Engineered Water Treatment
-
- Using Membrane Biofilm Reactors to Discover Novel Microorganisms that Transform Greenhouse Gases
- Project Description: Membrane Biofilm Reactors allow for delivery of a gas through a membrane with a biofilm adhered to the surface that can utilize that substrate. We are using these systems to enrich and isolate for novel microorganisms that transform greenhouse gases inclu
- Open to: CURVE First-Time Researchers
- Student Responsibilities: The student will assist with bioreactor operation and monitoring using analytical chemistry and molecular biology techniques.
- Preferred Majors: Civil & Environmental Engineering
- Preferred Skillsets: Chemistry and biology
- Using Membrane Biofilm Reactors to Discover Novel Microorganisms that Transform Greenhouse Gases
- Principal Investigator: Kandis Leslie Gilliard-AbdulAziz
- Website: https://the-sustainable-lab.com
- Projects
- Transformation of Carbon Waste into Riches
- Project Description: Development of oxidic materials for the selective capture of carbon dioxide. Synthesis of nanocatalysts to transform captured CO2 to methanol, synthesis gas, or elemental carbon. This work has the potential to make a significant impact in the field of carbon waste transformation.
- Open to: CURVE First-Time Researchers, CURVE Continuing Researchers
- Student Responsibilities:
- Synthesis of nanoparticulate catalysts
- Characterization of nanoparticulate catalysts
- Read and summarize current journal articles
- Preferred Majors: Chemistry, Chemical Engineering, Environmental Engineering, Civil Egineering, Material Science, Computer Science
- Preferred Skillsets:
- General Chem 1 preferred
- Works well in teams
- Strong communication skills
- Transformation of Carbon Waste into Riches
Thomas Lord Department of Computer Science
- Principal Investigator: Yue Zhao
- Website: https://viterbi-web.usc.edu/~yzhao010/lab.html
- Projects
- OpenAD: An Integrated Open-Source Ecosystem for Anomaly Detection
- Project Description: With the pervasive integration of Artificial Intelligence (AI) in critical sectors such as healthcare, security, and finance, anomaly detection (AD) has emerged as a pivotal AI component. Its role in discerning rare or anomalous events is instrumental for enhancing system reliability and robustness across varied data contexts. Notwithstanding the significant strides made by AD in domains like threat detection, rare disease identification, and fraud detection, its academic usages and real-world deployment encounters challenges in accessibility, community-building, development, and sustainability. Primarily, existing open-source AD frameworks tend to operate independently, circumscribing their adaptability to multifaceted data types and hampering collaborative synergies. Secondly, the development and user community of AD lacks a unified structure, thus denying equal exposure and support that individual systems might offer. Lastly, a sustainable ecosystem, both technically and policy-wise, remains elusive, thereby hindering the formulation of enduring strategies vital for fostering robust open-source AD systems. The goal of this project is to analyze these challenges and design comprehensive solutions, aiming for a holistic open-source anomaly detection ecosystem called OPENAD that serves national and societal imperatives.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Primarily it will be around build open-source Python/Pytorch libraries in the domain of anomaly detection (a subfield of machine learning)
- Preferred Majors: Computer Science,Electrical & Computer Engineering
- Preferred Skillsets:
- Python and PyTorch
- Software Engineering
- The use of Git and Github
- OpenAD: An Integrated Open-Source Ecosystem for Anomaly Detection
- Principal Investigator: Bistra Dilkina
- Website: https://research.usc.edu/news/2022/02/center-for-ai-in-society/
- Projects:
- AI for Wildlife Conservation
- Project Description: CAIS is searching for undergraduates interested in the intersection of computer science and wildlife conservation. We have several ongoing collaborations in this domain that involve data collection, processing, visualization, and ML/AI. Prior projects have used AI to predict wildlife trafficking routes and measure awareness of commonly poached species on social media platforms, as well as modeling species distributions across space and under projected climate change.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: CURVE researchers will have the opportunity to own certain portions of the project process (ex: data collection, data cleaning, etc.) as well as the opportunity to collaborate with PhD students/faculty on adopting AI methodology to the wildlife conservation domain.
- Preferred Majors: Computer Science
- Preferred Skillsets: We are looking for students with experience coding in Python (and popular toolkits such as pandas, numpy, scikit-learn, and matplotlib) and some experience with AI methodology (clustering, classification, etc.).
- Principal Investigator: Shahram Ghandeharizadeh
- Website: https://www.flslab.org
- Projects
- Flying Light Specks
- Project Description: Students will be paired with a Ph.D. student to pursue a number of activities:
- Maintain and upgrade the lab web site with scientific data and illustrations. Assist in disseminating findings.
- Design and implement drones using a 3D printer.
- Fly drones in different formations and help troubleshoot factors impacting their behavior (see https://www.youtube.com/watch?v=NNlWn9VW894 for an example),
- Analyze scientific data gathered from experiments.
- Draw illustrations, both 2D and 3D.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Work in close collaboration with a Ph.D. student. Attend regularly scheduled meetings on Fridays at lunch time. Assist with running events hosted by the FLS lab, e.g., the Holodecks conference in December 2024.
- Preferred Majors: Aerospace & Mechanical Engineering,Computer Science
- Preferred Skillsets:
- Be willing to learn
- Manage time to complete tasks
- Communicate effectively
- Be able to use email and generate calendar invites.
- Knowledge of a programming language such as Python or Matlab
- Use Google Scholar as a library to learn new concepts and ideas
- Problem solve using ChatGPT, Google Gemini, or a similar tool.
- Project Description: Students will be paired with a Ph.D. student to pursue a number of activities:
- Flying Light Specks
- Principal Investigator: Jesse Thomason
- Website: https://glamor-usc.github.io/
- Projects
- GLAMOR: Grounding Language in Actions, Multimodal Observations and Robots
- Project Description: We bring together natural language processing and robotics to connect language to the world (RoboNLP). Our lab is broadly interested in connecting language to agent perception and action, and lifelong learning through interaction.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: Attending weekly research planning syncs with a PhD student mentor, occasionally presenting in the GLAMOR lab meeting about progress, writing research software, designing and conducting experiments.
- Preferred Majors: Computer Science
- Preferred Skillsets: Fluency with python, interest in or knowledge of deep learning and machine learning coding libraries, interest in or knowledge of robot hardware and software systems like ROS.
- GLAMOR: Grounding Language in Actions, Multimodal Observations and Robots
- Principal Investigator: Heather Culbertson
- Website: https://sites.usc.edu/culbertson/
- Projects
- Haptics for Virtual Reality and Social Interactions
- Project Description: Haptics Robotics and Virtual Interaction (HARVI) Lab investigates touch based interactions between humans and technology. The student will be immersed in an exploration of the Human-computer Interaction (HCI) based research, with a special emphasis on Virtual Reality (VR) and social haptics. The project will facilitate the acquisition of knowledge about the fundamentals of VR, software, and algorithms that enable digital real-time interactive communication. It will also give insights into wearable systems aimed to create touch illusions.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: Student is expected to gain hands-on coding experience, display a keen interest in developing the technical skills (Unity 3D, C#, App development) required to design, implement, and troubleshoot game engines and VR platforms.
- Preferred Majors: Aerospace & Mechanical Engineering,Computer Science,Electrical & Computer Engineering
- Preferred Skillsets: Prior experience with algorithms in Unity or any other game engine is preferred, but not a requirement. The student's motivation, comprehensive approach to learning, combined with a deep curiosity for cutting-edge VR technology and wearables, forms the foundation for future academic pursuit in Human-computer Interaction.
- Haptics for Virtual Reality and Social Interactions
- Principal Investigator: Emilio Ferrara
- Website: https://election-integrity.online/
- Projects
- 2024 Election Integrity Initiative
- Project Description: This project aims to leverage publicly available datasets from social media and political ads to analyze patterns and discover insights into electoral processes. By using data analysis and machine learning practices, the project seeks to protect democratic processes by monitoring and analyzing online media to identify and combat malicious interference. We strive to ensure the integrity of elections and public discourse through cutting-edge research and advanced echnological solutions.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities:
- Data Collection and Preprocessing of Databases
- Data Analysis: Conduct exploratory data analysis to identify trends, patterns, and anomalies within the datasets.
- Machine Learning Model Development: Develop and train machine learning models to detect irregularities in electoral data.
- Data Visualization: Create interactive visualizations to present findings in a clear and accessible manner.
- Report Writing: Document methodologies, findings, and insights in a comprehensive report.
- Collaboration: Work collaboratively with team members and mentors, participating in regular meetings and updates.
- Preferred Majors: Computer Science
- Preferred Skillsets:
- Data Science: Proficiency in data analysis and machine learning, with coursework or experience in statistics, data mining, and predictive modeling.
- Programming Skills: Experience with programming languages such as Python or R, particularly in data manipulation and machine learning libraries (e.g., Pandas, Scikit-learn, TensorFlow).
- Data Visualization: Knowledge of data visualization tools and libraries such as Tableau, Matplotlib, or Plotly.
- Critical Thinking: Ability to think critically about data and methodologies, ensuring the integrity and validity of findings.
- Communication Skills: Strong written and verbal communication skills to document and present findings effectively.
- 2024 Election Integrity Initiative
- Principal Investigator: Cyrus Shahabi
- Website: https://imsc.usc.edu/
- Projects
- Trajectory data analysis
- Project Description: We have a variety of projects, all of which involve analyzing and/or learning from data. The data topics include highway traffic, GPS trajectories, place visits, maps, news, and people. When we choose a particular project, your tasks will include downloading the relevant data and understanding its coverage and statistics. Then we will define a specific project for deeper analysis or machine learning from the data, possibly involving multiple data sources and deep neural nets. For instance, we are interested in what fraction of human travel is periodic vs. unpredictable. We are looking for good ways to compress terabytes of trajectory data so it fits in a database yet remains easy to query. We want to know how to detect visits in GPS trajectory data and decide which point of interest the person visited. We are curious about how news stories, both historical and current, can be used to predict new events. For CURVE students, we tend to choose projects that are not on the critical path of ongoing research, but still have the potential to contribute to an onging, larger project in our lab.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Develop a code framework to understand and make novel inferences from data.
- Preferred Majors: Computer Science
- Preferred Skillsets: Python, machine learning, handling large datasets
- Trajectory data analysis
- Principal Investigator: Mohammad Soleymani
- Website: https://ihp-lab.org/
- Projects
- Multimodal Learning for Behavior Generation and Perception
- Project Description: In this project, we aim to train large foundational models for understanding and generating behaviors. Behaviors of interest include facial expressions, speech and spoken language. We are mainly interested in generating visual behaviors such as facial motions. Recent advances in generative AI enable perception approaches that can work with prompt tuning. We plan to work on prompt and instruction tuning for large vision-language and audiovisual models for understanding and generating nonverbal behaviors for social communication.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Research involves collecting, curating, and annotating data, developing machine learning code base (PyTorch), performing experiments on GPU cluster or servers and writing scientific reports and papers.
- Preferred Majors: Computer Science
- Preferred Skillsets: Machine learning, python; PyTorch, Linux, C#
- Multimodal Learning for Behavior Generation and Perception
- Principal Investigator: Maja Mataric
- Website: https://uscinteractionlab.web.app/
- Projects
- A Haptic Feedback Device for Guided Mindfulness Exercises with a Socially Assistive Robot
- Project Description: Prior studies have explored the applications of both physical feedback devices and socially assistive robots (SARs) to aid users during mindfulness exercises, but no study has explored the potential of combining these two modalities during mindfulness practice. This work aims to design a physical device that gives appropriate haptic feedback through motor movements to guide users through a mindfulness exercise led by a socially assistive robot. Students working on this project will generate and prototype designs for the device that meet the following goals: low-cost and easily fabricated by non-expert users, cohesive with the design of the Blossom robot platform, and easily synced to different mindfulness exercises.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Students will use an arduino microcontroller and various electronic components to build and program the device. They will explore existing haptic mindfulness devices and design a device for the Blossom robot. They may use different fabrication techniques to build the device such as 3d printing, laser cutting, or crochet.
- Preferred Majors: Aerospace & Mechanical Engineering
- Preferred Skillsets: CAD modeling (especially Fusion 360), 3d printing, technical writing
- A Haptic Feedback Device for Guided Mindfulness Exercises with a Socially Assistive Robot
-
- Designing Compelling Robotic Study Companions for Students with ADHD
- Project Description: Prior studies have shown that college students with ADHD respond positively to simple social robots that monitor attention and provide immediate feedback during periods of inattention or impulsivity. In feedback from a recent pilot study of in-dorm study companion robots, participants identified increased interactivity and positive rewards as potential ways to motivate users to complete more study sessions with a study companion robot. This work aims to incorporate different modes of interaction (e.g. touch, speech) and positive rewards (e.g. visual light displays, opportunities to customize the robot) on a simple, low-cost social robot in an effort to increase adherence to regular study sessions. We will evaluate these behaviors by measuring their effect on students' engagement as they complete a schoolwork task.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: Students will use python to program behaviors for a Blossom socially assistive robot. They will also use electronic components such as touch sensors and LED lights to add functionality to the robot. They will design a user study to evaluate these added capabilities and measure their effect on user adherence.
- Preferred Majors: Aerospace & Mechanical Engineering
- Preferred Skillsets: CAD modeling (especially Fusion 360), python.
- Designing Compelling Robotic Study Companions for Students with ADHD
-
- Peer Mediation Practice with Socially Assistive Robots for Elementary School Students
- Project Description: Peer mediation is a model of conflict resolution used in many K-12 schools across the United States. This model lets students serve as peer mediators to help other students resolve conflicts. Peer mediation has been shown to be an empowering form of conflict resolution for the mediators; however, mediators are usually chosen by teachers and peers for their leadership quality and positive social behavior. For students who are not usually chosen to be peer mediators, or for those who do not have access to a peer mediation program, socially assistive robots (SARs) may provide a way for practicing this valuable skill. The goal of the study is to help evaluate the use of SARs in peer mediation role-play practice in improving self-perception of 3rd to 5th grade students. The study insights will help determine if SARs are a useful tool in helping 3rd to 5th graders practice conflict resolution skills. The collected data will help determine how to improve SARs to make the interaction more realistic and impactful.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: Students will assist with data collection on-site at participating elementary school (this will involve setting up camera equipment and setting up Raspberry Pi computers connecting with the Blossom robot) curating and maintaining video, audio, and structured data, statistical analysis of data, reporting findings in an academic paper.
- Preferred Majors: Computer Science, Electrical & Computer Engineering
- Preferred Skillsets: Python programming; experience with Amazon Web Services (AWS) applications for storage (S3) and full stack app development; experience with data analysis; experience with statistical analysis; experience with Raspberry Pi and internet of things (IoT); any experience with social/behavioral projects is a plus.
- Peer Mediation Practice with Socially Assistive Robots for Elementary School Students
- Multimodal Models of Engagement and Cohesion in Group Therapy
- Project Description: Group interaction is a many-step process with multiple interactors. An autonomous facilitator requires an understanding of the processes and interaction states of the group. We propose to develop automated models for understanding individual and group processes at three levels, as follows.
- Speaker. An autonomous facilitator should be able to identify the active speaker(s) and facilitate turn-taking in the group.
- Interaction and engagement. Automated understanding of social processes in group interaction is an important building block for an autonomous facilitator. A group facilitator should understand the context and state of the conversation to guide it effectively. Moreover, individual-level measurements of engagement are important for recognizing higher-level group constructs, like group cohesion. In the context of this proposal, this will involve automated coding of interaction.
- Group cohesion. Group cohesion is defined by the level of social connectedness in a group. An automated measurement of cohesion will require understanding emotional and social engagement and group structure.
- Open to: CURVE First-Time Researchers, CURVE Continuing Researchers
- Student Responsibilities: Develop multimodal models (in Pytorch) of engagement and group cohesion from a dataset of group therapy interactions with a robot facilitator. Clean and segment study data. Write academic papers with findings.
- Preferred Majors: Computer Science
- Preferred Skillsets: Python, data processing, technical writing
- Project Description: Group interaction is a many-step process with multiple interactors. An autonomous facilitator requires an understanding of the processes and interaction states of the group. We propose to develop automated models for understanding individual and group processes at three levels, as follows.
- Socially Assistive Robot-Administered Cognitive Behavioral Therapy
- Project Description: There is a mental health epidemic that is disproportionately impacting university-age young adults. However, mental health systems are strained and unable to meet the demand for access to care. There are also a multitude of barriers to receiving mental health care, such as accessibility and stigma. Thus it is important to develop technologies that can assist in overcoming these barriers. This project aims to develop a Socially Assistive Robot (SAR) that can guide students through Cognitive Behavioral Therapy (CBT) at-home exercises. We will develop SAR-guided CBT exercises through co-design sessions with expert therapists and test them through a user study with university students.
- Open to: CURVE First-Time Researchers, CURVE Continuing Researchers
- Student Responsibilities: Develop movements and behaviors on the Blossom Robot. Language model prompt engineering. Develop SAR-guided CBT exercises in collaboration with trained therapists. Learn to run co-design sessions as well as a user study to test the exercises.
- Preferred Majors: Computer Science
- Preferred Skillsets: Python programming, AWS, ability to work directly with participants
- Using Multimodal Machine Learning to Model Early Life Stress in Infancy and Early Childhood
- Project Description: Adverse Childhood Experiences (ACEs) can include violence, abuse, and growing up in a family with mental health or substance use problems. ACEs are linked to chronic health problems, mental illness, and substance misuse in adulthood. Using data collected by the Children’s Hospital of Los Angeles’ (CHLA) Levitt Lab, we will model ACEs using audio and visual interactions between mothers and children, mother emotional state questionnaires, mitochondrial data, heart rate variation, and other modalities. Additionally, students may be involved in the creation of socially assistive robots to add social and emotional learning interventions in early childhood to mitigate the social and emotional negative effects of ACEs.
- Open to: CURVE First-Time Researchers, CURVE Continuing Researchers
- Student Responsibilities: Students will use Python to collect, clean, and model multimodal information collected from CHLA. This effort will include the use of classical machine learning, as well as more advanced multimodal fusion modeling techniques. Students might also use the QTRobot to develop interventions and collect affective data such as audio and video for further multimodal analysis.
- Preferred Majors: Computer Science, Electrical & Computer Engineering
- Preferred Skillsets: Experience with python and some experience with data or statistics. Preferred – not required.
- Play and Learn: Design Socially Assistive AI for Children with Speech Articulation Needs and Their Care Ecosystem.
- Project Description: It’s estimated that almost 50%, around 6 million, of U.S. children with speech disorders went untreated in the past year, negatively influencing their academic performance and social interactions [1]. This highlights the urgent need for more accessible speech therapy options. For children undergoing speech therapy, adherence to low-dose high-frequency in-home practices is vital for treatment efficacy, yet many parents, already stretched thin by their responsibilities, find it challenging to provide consistent engagement. for their children. In this project, we aim to simplify speech therapy practices for families with personalized learning powered by socially assistive AI.
- Open to: CURVE First-Time Researchers, CURVE Continuing Researchers
- Student Responsibilities: Developing the software agents and robots either in React Native or in Python; Helping deploy and evaluate the software agents and robots; Data collection for a speech dataset in the setting of speech articulation learning; Training and evaluating machine learning models for phoneme recognition models.
- Preferred Majors: Computer Science
- Preferred Skillsets: React Native, Python, Pytorch
- Principal Investigator: Erdem Biyik
- Website: https://liralab.usc.edu/
- Projects
- Robot Learning from Natural Human Feedback
- Project Description: Most of the existing robot learning algorithms rely on human feedback that is explicitly designed to teach the robots. However, humans leak a lot of information even when they are not trying to teach. For example, their gestures, gaze, facial expressions etc. carry information about what they want the robot to do. The goal of this project is to enable robots use such natural feedback by utilizing machine learning techniques.
- Open to: CURVE
- Student Responsibilities: Implementation of algorithms, deployment on simulation and real robot platforms.
- Preferred Majors: Computer Science
- Preferred Skillsets: machine learning, Python
- Robot Learning from Natural Human Feedback
- Principal Investigator: Jieyu Zhao
- Website: https://jyzhao.net
- Projects
- Applying LLMs for Social Good Applications
- Project Description: The rise of large language models (LLMs) like GPT-3/4 has opened up new possibilities for leveraging advanced natural language processing across a wide variety of applications. This project aims to explore how LLMs can be applied to drive positive social impact across areas such as education, healthcare, sustainability, and support for underserved communities. Potential Application Areas include but not limit to: education, healthcare, accessibility and social service.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities:
- Read research paper
- Run experiments to do analysis
- Join project meeting to present the work
- Preferred Majors: Computer Science
- Preferred Skillsets:
- Python
- Pytorch
- HuggingFace
- Applying LLMs for Social Good Applications
- Investigating Cultural Bias in Large Language Model
- Project Description: Recent studies have found evidence of societal biases encoded in the training data of large language models, leading to outputs that reflect stereotypes or marginalization of certain cultures or demographic groups. For open-domain dialogue, question answering, task assistance and other interactive applications, such cultural biases pose ethical risks and could perpetuate harm against underrepresented groups. A rigorous investigation is needed to audit LLMs for cultural biases and quantify the extent of the issue across different models and domains. We aim to answer: Which types of cultural biases are most prevalent (stereotyping, marginalization, under/over-representation etc.) in LLMs? How does cultural bias in LLMs relate to the geographic sources and demographic makeup of their training data?
- Open to: CURVE Continuing Researchers
- Student Responsibilities:
- Literature review
- Design/Run experiments to verify the hypothesis
- Join project meeting
- Present the research work
- Preferred Majors: Computer Science
- Preferred Skillsets:
- Strong background in natural language processing (NLP) and machine learning (ML).
- Proficiency in data analysis using Python, R, or similar tools.
- Experience with large language models like BERT, GPT-3.5, etc.
- Familiar with HuggingFace Library.
- Strong communication and writing abilities.
- Principal Investigator: Harsha Madhyastha, Ramesh Govindan
- Website: https://nsl.usc.edu/
- Projects
- Reviving Dead Links on the Web (PI: Harsha Madhyastha)
- Project Description: A key feature of the web is that the links on any page enable visitors to discover other related pages. One would expect any link to break only when the page it is pointing to no longer exists. Instead, the web is littered with millions of broken links today merely because, when a website is reorganized and the URLs for its pages change, links which specify the old URLs for these pages often cease to work. To ensure that the effort that has gone into creating appropriate links all across the web does not go to waste, we have developed a system called FABLE (https://nsl.usc.edu/projects/fable/). Given any broken link, FABLE helps resurrect that link by discovering the linked page’s new URL, if the page still exists on the web. Thus far, FABLE has been used to patch tens of thousands of broken external links on Wikipedia. In this project, you will help expand FABLE's reach to the web at large, not just Wikipedia.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: The FABLE system has 4 main components: 1) finding links on the web which no longer work, 2) discovering new URLs at which the linked pages now exist, 3) verifying discovered URL replacements, and 4) rewriting broken links to use verified URL replacements. In this project, the student will primarily help with stages 3 and 4. We currently have solutions for both of these which work on Wikipedia (e.g., on the site https://fable.toolforge.org/, Wikipedia users judge the correctness of the URL replacements identified by FABLE). In this project, the student will design and develop corresponding solutions for other sites on the web.
- Preferred Majors: Computer Science
- Preferred Skillsets:
- Experience working with APIs of public cloud-hosted services.
- Programming experience with scripting languages such as Python.
- Familiarity with web development and protocols that underlie the web
- 3D Video Analytics (PI: Ramesh Govindan)
- Project Description: The rise of Augmented/Virtual Reality (AR/VR) has paved the way for next-generation immersive 3D media. This creates new research opportunities to scale 2D computer vision technology to 3D. We want to investigate how to apply computer vision models to perform tasks like object detection, tracking, etc., on 3D video from a computer systems perspective. We are looking for undergraduate student(s) who will work in NSL (Networked Systems Laboratory) to build research prototypes and push the state-of-the-art.
- Open to: CURVE First-Time Researchers, CURVE Continuing Researchers
- Student Responsibilities: Students will be exposed to cutting-edge tools for research and development in the intersection of AR/VR and Computer Vision. They will be responsible for the following:
- Apply 3D computer vision models on 3D video.
- Develop algorithms to optimize for latency and throughput of 3D analytics.
- Work with Ph.D. students on an existing codebase to integrate the above algorithms.
- Read existing literature in related areas.
- Preferred Majors: Electrical & Computer Engineering
- Preferred Skillsets: These are the preferred (not necessary) skillsets that we are looking for:
- Programming in C++ and Python.
- Machine learning frameworks like Pytorch or Tensorflow.
- Some experience with 3D representations like point clouds, meshes, and/or NeRFs.
- XR development in Unity/Unreal
- Reviving Dead Links on the Web (PI: Harsha Madhyastha)
- Principal Investigator: Daniel Seita
- Website: https://slurm-lab-usc.github.io/
- Projects
- Leveraging GPT for Contact Reasoning in Robotics
- Project Description: When robots operate in their environment, we normally wish for robots to avoid making any contact with obstacles. For example, we might want a robot arm to reach into a cluttered closet to grab a target item, and we would normally want the robot to avoid contact with anything other than that target item. But, what if it is OK to make some type of contacts? Sometimes it might even be necessary to make contact with obstacles in order to reach a target. Humans frequently make incidental contact with obstacles all the time, such as when we reach into backpacks to retrieve an item buried in it while making contact with other things in the bag. In this project, we will implement machine learning algorithms to create robots comfortable with making appropriate contact with environmental obstacles.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: The student will develop simulation environments of a robot manipulator in a cluttered setup to test our algorithms. Then we will move to a physical setup that closely mirrors the simulation environment.
- Preferred Majors: Aerospace & Mechanical Engineering,Computer Science,Electrical & Computer Engineering
- Preferred Skillsets: Python programming, basic knowledge of how to use models such as GPT-4, basic understanding of robot motion planning algorithms (such as RRT) or be willing to learn about them.
- Leveraging GPT for Contact Reasoning in Robotics
Ming Hsieh Department of Electrical and Computer Engineering
- Principal Investigator: Christopher Torng
- Website: https://acorn-research.usc.edu/
- Projects
- Specializing Communication at the Inter-Chiplet Boundary for Energy-Efficient Machine Learning
- Project Description: An open chiplet ecosystem would allow heterogeneous integration of chips in a compact, advanced package. Building a chiplet ecosystem represents a tremendous paradigm shift in the time and cost of assembling future computing systems and constitutes a key thrust in the CHIPS and Science Act research strategy. How can we build chiplet-based systems to be simpler, faster, and more efficient when domain-specific hardware accelerators are communicating across inter-chiplet interfaces?
- Open to: CURVE First-Time Researchers
- Student Responsibilities: Depending on the student's interests and abilities, the candidate can design hardware blocks in Verilog, write flow scripts in Python/Tcl, and more generally have an opportunity to explore compiler-level work (how to run software on this accelerator) or VLSI-level work (how to build a chip for this accelerator)
- Preferred Majors: Electrical & Computer Engineering
- Preferred Skillsets: Have initiative and curiosity, Work well in teams, have prior programming experience in Python, Have prior programming experience in any hardware description language (e.g., Verilog), Have taken some VLSI coursework
- Specializing Communication at the Inter-Chiplet Boundary for Energy-Efficient Machine Learning
- Enabling Rapid Chip Design with Agile Flow Tools
- Project Description: Achieving high code reuse in physical design flows is challenging but increasingly necessary to build complex digital chips. We present a vision and framework based on modular flow generators that encapsulates coarse-grained and fine-grained reusable code in modular nodes and assembles them into complete flows. These agile flow tools are being designed to enable students across the country in R1/R2 universities to successfully build chips in advanced technologies.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: Depending on the student's interests and abilities, the candidate can work with physical design flow tools using Tcl and Python, or experiment with designing small hardware blocks pushed from RTL to GDS in a commercial digital ASIC tool flow.
- Preferred Majors: Electrical & Computer Engineering
- Preferred Skillsets: Have initiative and curiosity, Work well in teams, have prior programming experience in Python, Have prior programming experience in any hardware description language (e.g., Verilog), Have taken some VLSI coursework
- Principal Investigator: Justin Haldar
- Website: https://mr.usc.edu/
- Projects
- Faster and Better Magnetic Resonance Imaging
- Project Description: Magnetic resonance imaging (MRI) technologies provide unique capabilities to probe the mysteries of biological systems, and have enabled novel insights into anatomy, metabolism, and physiology in both health and disease. However, while MRI is decades old, is associated with multiple Nobel prizes (in physics, chemistry, and medicine), and has already revolutionized fields like medicine and neuroscience, current MRI methods are still very far from achieving the full potential of the MRI signal. Specifically, modern MRI methods suffer due to long data acquisition times, limited signal-to-noise ratio, high monetary costs, and various other practical and experimental limitations — this limits the amount of information we can extract from living human subjects, and often precludes the use of advanced experimental methods that could otherwise increase our understanding by orders-of-magnitude. Our research group addresses such limitations from a signal processing perspective, developing novel methods for data acquisition, image reconstruction, and parameter estimation that combine: (1) the modeling and manipulation of physical imaging processes; (2) the use of novel constrained signal and image models; (3) novel theory to characterize signal estimation frameworks; and (4) fast computational algorithms and hardware. Methods we developed have enabled substantial acceleration of routine modern MRI exams, and have also enabled the development of highly-informative next-generation MRI experiments that were previously impractical. Our approaches are often based on jointly designing data acquisition and image reconstruction methods to exploit the inherent structure that can be found within high-dimensional data, and we do our best to take full advantage of the "blessings of dimensionality" while mitigating the associated "curses."
- We are seeking excellent students with a strong background in signal processing, with an interest in developing methods to improve existing advanced MR methods and an interest in enabling/exploring innovative next generation imaging approaches.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: To be determined based on the student's level of preparation
- Preferred Majors: Electrical & Computer Engineering
- Preferred Skillsets: Good performance in Digital Signal Processing (EE483) strongly recommended
- Faster and Better Magnetic Resonance Imaging
- Principal Investigator: Hossein Hashemi
- Website: https://hhlab.usc.edu
- Projects
- Analog Integrated Circuit Tape-Out Experience
- Project Description: We plan to incorporate analog integrated circuit tape-out experience in the undergraduate curriculum.
- Open to: CURVE Continuing Researchers
- Student Responsibilities: The students will work on design, simulations, layout, verification, tape-out, and measurements of analog integrated circuits in a commercial foundry CMOS process. The projects results will guide the new modules that will be added to the new curriculum.
- Preferred Majors: Electrical & Computer Engineering
- Preferred Skillsets: Experience in design and measurements of analog integrated circuits with preference over printed-circuit board experience (as opposed to breadboard).
- Analog Integrated Circuit Tape-Out Experience
- Principal Investigator: Yasser Khan
- Website: https://khan.usc.edu
- Projects
- Ingestible sensor systems
- Project Description: We're developing a smart capsule equipped with sensors to identify specific chemicals in the digestive system.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Sensor design and fabrication, electronics characterization, printed circuit board design, development and debugging, embedded system coding.
- Preferred Majors: Aerospace & Mechanical Engineering,Biomedical Engineering,Electrical & Computer Engineering
- Preferred Skillsets: Programming, hands-on lab experiments, electronics, AI/ML models
- Ingestible sensor systems
- MRI-compatible wearables
- Project Description: We will be building a wearable sensor system that works inside the MRI environment. This wearable will provide physiological data while we will capture MR images using the MRI.
- Open to: CURVE Continuing Researchers
- Student Responsibilities: Sensor design and fabrication, electronics characterization, printed circuit board design, development and debugging, embedded system coding.
- Preferred Majors: Aerospace & Mechanical Engineering,Biomedical Engineering,Electrical & Computer Engineering
- Preferred Skillsets: Programming, hands-on lab experiments, electronics, AI/ML models
- Organic electrochemical transistors based sensors and circuits
- Project Description: OECTs are transistors that can be used as sensors as well. We want to show OECTs and their system-level implementation for near- and in-sensor computing
- Open to: CURVE Continuing Researchers
- Student Responsibilities: Sensor design and fabrication, electronics characterization, printed circuit board design, development and debugging, embedded system coding.
- Preferred Majors: Electrical & Computer Engineering
- Preferred Skillsets: Programming, hands-on lab experiments, electronics, AI/ML models
- Wearables for mental health
- Project Description: We will develop wearable technologies for capturing physiological and chemical markers relevant to mental health.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Sensor design and fabrication, electronics characterization, printed circuit board design, development and debugging, embedded system coding.
- Preferred Majors: Aerospace & Mechanical Engineering,Biomedical Engineering,Electrical & Computer Engineering
- Preferred Skillsets: Programming, hands-on lab experiments, electronics, AI/ML models
- Closed-loop wearable sensing and drug delivery
- Project Description: This project will explore designs for wearable that can sense chemicals in the body and deliver drug in a closed-loop manner.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Sensor design and fabrication, electronics characterization, printed circuit board design, development and debugging, embedded system coding.
- Preferred Majors: Aerospace & Mechanical Engineering,Biomedical Engineering,Electrical & Computer Engineering
- Preferred Skillsets: Programming, hands-on lab experiments, electronics, AI/ML models
- Principal Investigator: Sandeep Gupta
- Faculty Website
- Projects
- Computer-Aided Discoveries: Methods and Applications
- Project Description: Developing new methods and algorithms to discover new non-intuitive designs that provide significant improvements over today’s best-known designs. Primary applications for the design of digital hardware and software systems.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Developing programs to simulate digital hardware and using these programs to explore known and non-intuitive designs. Also, developing inductive methods and tools to discover new properties from the results of these explorations.
- Preferred Majors: Computer Science,Electrical & Computer Engineering,Industrial & Systems Engineering
- Preferred Skillsets:
- Curiosity and desire to explore new ideas
- Logical and mathematical reasoning
- Programming and using programs to solve new problems
- Computer-Aided Discoveries: Methods and Applications
- Principal Investigator: Feifei Qian
- Website: https://sites.google.com/usc.edu/roboland
- Projects
- Robot Locomotion and Navigation on Extreme Terrains
- Project Description: Physical environments can provide a variety of interaction opportunities for robots to exploit towards their locomotion goals. However, it is unclear how to even extract information about --much less exploit-- these opportunities from physical properties (e.g., shape, size, distribution) of the environment. This project integrates mechanical engineering, electrical engineering, computer science, and physics, to discover the general principles governing the interactions between bio-inspired robots and their locomotion environments, and uses these principles to create novel control, sensing, and navigation strategies for robots to effectively move through non-flat, non-rigid, complex terrains. For example, how can a bio-inspired multi-legged robot intelligently exploit obstacle disturbances to generate desired locomotion dynamics? How to develop quadrupedal robots that can sensitively “feel†terrain properties and adapt their locomotion or sampling strategies on earth and planetary surfaces?
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Selected candidate will assist in development of robotic platforms (Arduino, Raspberry Pi, SolidWorks, 3D Printing), locomotion experiment data collection and analysis (motion capture tracking, force measurements), modelling and simulation (Python or C++).
- Preferred Majors: Aerospace & Mechanical Engineering,Astronautical Engineering,Biomedical Engineering,Chemical Engineering,Civil & Environmental Engineering,Computer Science,Electrical & Computer Engineering,Industrial & Systems Engineering
- Preferred Skillsets: We have multiple positions within the project, each focusing on different skillsets. Some of the relevant skillsets that may be helpful (you do NOT need to know all of them):
- Mechanical design/manufacture (e.g., power tools, CNC, laser cutting; Makerspace training is a plus); OR
- Programming (python, C++; or web development using Java); OR
- Electrical system design; OR
- Physics (mechanics and forces)
- Robot Locomotion and Navigation on Extreme Terrains
- Obstacle-aided locomotion and navigation
- Project Description: This project explores how robots can exploit different features of their physical environments to achieve desired movements. Can multi-legged robots and snake-like robots intelligently collide with obstacles on purpose to robustly move towards desired directions? Can a robot effectively turn itself by jamming the soft sand with its tail? In this project we will perform robot locomotion experiments to understand the complex interactions between robots and their environments and use these interaction models to create novel strategies that can enable effective locomotion and navigation through challenging environments.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Selected candidate will assist in development of robotic platforms (Arduino, Raspberry Pi, SolidWorks, 3D Printing), locomotion experiment data collection and analysis (motion capture tracking, force measurements), modelling and simulation (Python or C++).
- Preferred Majors: Aerospace & Mechanical Engineering,Astronautical Engineering,Biomedical Engineering,Chemical Engineering,Civil & Environmental Engineering,Computer Science,Electrical & Computer Engineering,Industrial & Systems Engineering
- Preferred Skillsets: We have multiple positions within the project, each focusing on different skillsets. Some of the relevant skillsets that may be helpful (you do NOT need to know all of them):
- Mechanical design/manufacture (e.g., power tools, CNC, laser cutting; Makerspace training is a plus); OR
- Programming (python, C++; or web development using Java); OR
- Electrical system design; OR
- Physics (mechanics and forces)
- Robot-assisted earth and planetary exploration
- Project Description: This project focuses on developing robots that can use their legs as terrain sensors to help geoscientists and planetary scientists collect and interpret information at high spatial and temporal resolution. To achieve this, we will build robot legs that can sensitively “feel” the responses of desert sand or near-shore mud. We will design different interaction-based sensing protocols for the robot legs and test these protocols in lab experiments. Once the sensing capabilities are developed and tested, we will take the robots to field trips, where the robots work alongside human scientists and learn how human make sampling decisions and adapt exploration strategies based on dynamic incoming measurements. Going forward, these understandings will help enable our robots with cognitive “reasoning” capabilities to flexibly support human teammates’ scientific objectives during collaborative exploration missions.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Selected candidate will assist in development of robotic platforms (Arduino, Raspberry Pi, SolidWorks, 3D Printing), locomotion experiment data collection and analysis (motion capture tracking, force measurements), modelling and simulation (Python or C++).
- Preferred Majors: Aerospace & Mechanical Engineering,Astronautical Engineering,Biomedical Engineering,Chemical Engineering,Civil & Environmental Engineering,Computer Science,Electrical & Computer Engineering,Industrial & Systems Engineering
- Preferred Skillsets: We have multiple positions within the project, each focusing on different skillsets. Some of the relevant skillsets that may be helpful (you do NOT need to know all of them):
- Mechanical design/manufacture (e.g., power tools, CNC, laser cutting; Makerspace training is a plus); OR
- Programming (python, C++; or web development using Java); OR
- Electrical system design; OR
- Physics (mechanics and forces)
- Principal Investigator: Antonio Ortega
- Research Website
- Projects
- Applications of Graph Signal Processing
- Project Description: Graph signal processing (GSP) studies signals that are observed on graphs, where each graph contains a series nodes connected by edges. Examples of graphs include transportation networks (road, rail), infrastructure networks (water distribution or the electrical grid), and information networks (the web or Wikipedia). Additionally, conventional signals (images, audio) can be analyzed based on graph models, and graphs can be used to describe datasets to design machine learning algorithms. This project involves students in specific research directions where new GSP methods are developed and their application to some of this problems of interest is explored. My Google Scholar profile has an up-to-date list of our publications. Interested students can learn more about our ongoing work in this area.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: In my lab, students are exposed to real research problems and trained to become independent researchers with the goal of submitting papers for publication. Depending on their interests, they will be paired up with a PhD student or will work with me directly. They will typically have to review existing literature on a topic of interest, implement an existing method, and then develop new methods and compare them to the state-of-the-art techniques.
- Preferred Majors: Electrical & Computer Engineering
- Preferred Skillsets: Linear algebra (EE 141L) and some programming experience (e.g., Matlab or Python) are important. Initiative, curiosity, independent thinking.
- Applications of Graph Signal Processing
- Principal Investigator: Murali Annavaram
- Website: https://scip-lab.usc.edu
- Projects
- Resource Efficient Algorithm and System Design of Large Language Models
- Project Description: Large Language Models (LLMs), including GPT-4, LLaMA, and PaLM, have demonstrated exceptional capabilities in natural language understanding, generation, and complex reasoning tasks. Despite their impressive performance, these models face significant challenges due to their substantial computational and memory demands during training and inference. Addressing these efficiency challenges is crucial for the broader adoption and application of LLMs. This research project aims to develop and evaluate novel efficiency techniques for LLMs, spanning from pre-training and fine-tuning to serving. Depending on the student's interests, we will explore specific directions and techniques, and subsequently propose and build resource-efficient algorithms and systems of LLMs.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Investigate the state of the art, reproduce experiments, and improve and implement ideas.
- Preferred Skillsets: Pytorch/Huggingface, machine learning and natural language processing, LLM architectures.
- Resource Efficient Algorithm and System Design of Large Language Models
-
- Efficient Retrieval Augmented Generation
- Project Description: This ongoing research project involves a student in analyzing bottlenecks of Retrieval Augmented Language Models (RALMs), designing, and experimenting with innovative ideas to enhance their efficiency in terms of inference throughput and latency. RALMs, significant in the era of Large Language Models (LLMs), currently face challenges with long context sizes, resulting in extraordinarily high latency for text generation, which limits their practical utility. This project could lead to a publication, potentially paving the way for the student to pursue a research career.
- Open to: CURVE Continuing Researchers
- Student Responsibilities: Experimenting and implementing some ideas for RALM efficiency using PyTorch
- Preferred Skillsets: Programming Experience in Python, Decent Experience in PyTorch, Applied Knowledge of Recent Deep Learning Models (LLMs), Good Analytical Skills
- Efficient Retrieval Augmented Generation
-
- Energy Implications of Training and Serving Deep Learning Models
- Project Description: This is an ongoing research project where the student will take part in measuring and analyzing the energy consumed by deep learning training and serving pipelines. As there is no agreement in the literature on how to measure the energy precisely while using Machine Learning backends like PyTorch, we plan to conduct multiple experiments to build a stronger case for our proposed methodology. Our primary focus will be on recommendation models and large language models, which could be extended to other classes of deep learning models. This project could result in a publication that will pave the way for the student to pursue a research career.
- Student Responsibilities: Measure the energy budget for training and serving various deep learning models
- Skills and Competencies:
- Knowledge of UNIX environment
- Programming Experience in Python and C++
- Decent Experience in PyTorch
- Good analytical skills
- Applied knowledge of recent Deep Learning Models (LLMs, Rec Sys)
- Energy Implications of Training and Serving Deep Learning Models
- Principal Investigator: Mahdi Soltanolkotabi
- Website: https://sites.usc.edu/aif4s/
- Projects
- Teaching Generative AI spatial Reasoning
- Project Description: Generative AI agents, such as ChatGPT, are getting better and better at understanding and reasoning about images. But can they tell left from right? Do they understand if an object is closer or further away in an image? In this project, we stress-test the spatial reasoning capabilities of multimodal large language models by carefully designing a benchmark datasets to evaluate various aspects of their understanding of 3D space. We leverage diffusion-based editing tools to create synthetic images that can probe state-of-the-art multimodal models on a fine-grained scale. Based on our findings we quantify the limitations of current generative AI agents and analyze its impact on reliability in everyday tasks.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities:
- Exploring solutions for diffusion-based image editing. (requires Python, Pytorch coding experience)
- Develop Python framework to generate synthetic benchmark data for generative AI models
- Evaluate existing open source and API-only models on the new benchmark
- Write a technical paper on the methodology, possibly leading to publication at strong machine learning venues
- Preferred Majors: Computer Science,Electrical & Computer Engineering
- Preferred Skillsets: Python and Pytorch
- Teaching Generative AI spatial Reasoning
- Principal Investigator: Andreas Molisch
- Website: https://wides.usc.edu
- Projects
- Midband Propagation Channel Measurements
- Project Description: In this project, we will explore the propagation channel in the upper midband (10-14 GHz) spectrum, an important area of interest for 6G communication development. Accurate channel measurements are essential for understanding the behavior of radio waves in different environments, which in turn is crucial for designing efficient and reliable wireless communication systems. Participants in this work will gain hands-on experience with advanced measurement techniques, data analysis, and the application of theoretical principles in real-world scenarios. This involvement will not only enhance the research skills of participants but also position them at the forefront of next-generation communication technologies and offer them an opportunity to contribute significantly to the future of wireless communication. Students with an Electrical Engineering background and a specific interest in Wireless Communication, particularly the physical layer and signal processing, are encouraged to participate.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: Students will participate in the measurement campaigns and execute measurement tasks under instruction from PostDocs and senior Phd students.
- Preferred Majors: Electrical & Computer Engineering
- Preferred Skillsets: Interest in (and preferably experience in) RF measurements
- Midband Propagation Channel Measurements
- AI and machine learning for object detection in point clouds with applications to ray tracing
- Project Description: Point cloud data has become more popular in recent years in digitizing three-dimensional (3D) real-world environments for many applications due to the high accuracy and high level of detail point clouds can provide. Some of these applications include augmented and virtual reality, self-driving cars, and ray tracing. In our project, we will use point cloud data as a basis for ray tracing applications in wireless communications and develop acceleration methods for ray tracing. One important method is object detection from the unstructured raw point cloud data. Naïve clustering algorithms could be used, but more accurate methods are necessary. For that reason, we will investigate the use of AI and machine learning tools for object detection in point clouds, surveying the literature for the most recent models, implementing, and training them for our scenarios. The student is expected to review the basic methods for object detection, conduct a thorough literature review for the state-of-the-art methods, and implement the method that best fits our application and scenarios in a timely manner. Familiarity with and experience in advanced neural network structures such as convolution neural networks and transformers is preferred. No familiarity with ray tracing or wireless communications is required.
- Open to: CURVE First-Time Researchers
- Student Responsibilities:
- Conduct literature review of state-of-the-art methods in point cloud object detection.
- Implement and train machine learning models to perform object detection on available point clouds.
- Write weekly progress reports to present in weekly meetings.
- Preferred Majors: Computer Science, Electrical Engineering, Computer Engineering
- Preferred Skillsets: Understanding of machine learning and AI, convolutional neural networks, transformers. Knowledge and experience in Python machine learning libraries are highly preferred. Prior work on Image processing, machine learning for image processing, or point cloud processing is a plus. Self-motivated problem-solving thinking and ability to innovate are highly preferred. Knowledge of C/C++ is a plus.
Daniel J. Epstein Department of Industrial and Systems Engineering
- Principal Investigator: Qiang Huang
- Website: https://huanglab.usc.edu/
- Info Session Date/Time: 7/10/2024 10:00 - 11:00 am
- Projects
- Software Development for Automated Product Qualification for 3D Printing
- Project Description: Help PhD students to develop AI for smart 3D printing
- Open to: CURVE First-Time Researchers
- Student Responsibilities: Conduct literature survey, develop software, write reports
- Preferred Majors: Aerospace & Mechanical Engineering,Computer Science,Industrial & Systems Engineering
- Preferred Skillsets: programing skills
- Software Development for Automated Product Qualification for 3D Printing
- Principal Investigator: Randolph Hall
- Website: https://create.usc.edu/
- Projects
- Spare Parts Supply Chains
- Project Description: Global supply chains for spare parts in presence of uncertain demand.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: Support for literature review and application of bibliometric tools for assessment of literature. Students will learn to use VOS Viewer as an analytical tool.
- Preferred Majors: Industrial & Systems Engineering
- Preferred Skillsets: Ideally experience with data analytic tools, including Excel or statistical software.
- Spare Parts Supply Chains
-
- Innovation at the Interface
- Project Description: Participation in preparation of book on university/industry innovation, to be published by Springer. The book examines best practices for conducting collaborative research involving companies and universities.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: Student would assist in preparation of book with 20 chapters contributed by multiple authors.
- Preferred Majors: Industrial & Systems Engineering
- Preferred Skillsets: English language writing/editing. Experience with graphical tools for creating and editing figures and tables.
- Innovation at the Interface
- Principal Investigator: Shinyi Wu
- Faculty Profile
- Projects
- Empowering Chinese American Patients with Chronic Rhinosinusitis: Developing and Pilot-testing a Bilingual Patient Decision-Support Web Application
- Project Description: This study proposes to develop a bilingual, interactive web application (app) specifically for Chinese American patients with Chronic Rhinosinusitis (CRS), a condition affecting 16% of the U.S. adult population annually. CRS significantly impacts quality of life (QOL), with patients often reporting lower QOL scores than those with congestive heart failure or chronic obstructive pulmonary disease. Endoscopic sinus surgery (ESS) is a recommended option for CRS patients unresponsive to medical therapy and has been shown to improve symptoms and QOL. However, there is a notable gap in CRS research and resources tailored for the Chinese American community, leading to surgical hesitancy and suboptimal outcomes. Our research involving 134 patients (29.1% Chinese Americans) at USC indicates a stark contrast in ESS uptake between white and Chinese American CRS patients (Odds Ratio(OR) = 7.92; 95% CI: 2.95-21.28; p<0.001). The project aims to empower Chinese American CRS patients through developing a versatile, bilingual web app accessible on multiple platforms (mobile, laptop, desktop computers) that features two key components to aid CRS patient decision-making: educational materials and AI-generated, relatable patient testimonials based on real patient experiences. This approach is designed to facilitate informed decision-making by overcoming language barriers and enhancing user engagement. The web app's goal is to reduce surgical hesitancy and improve treatment decisions. Upon the app's completion, a pilot study with 20 Chinese American CRS patients will assess the app’s influence on treatment choices and its usability. Feedback from this study will refine the app to ensure it effectively supports informed treatment decisions. Subsequently, additional funding will be sought for an extensive trial to rigorously test the app's effectiveness in a broader context.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: Creating (though primarily maintaining) a bilingual, interactive web application aimed at offering patient educational materials and testimonials to aid individuals dealing with Chronic Rhinosinusitis in making well-informed treatment decisions promptly and effectively.
- Preferred Majors: Computer Science,Industrial & Systems Engineering
- Preferred Skillsets: JavaScript, HTML, NodeJS, AWS, GitHub
- Empowering Chinese American Patients with Chronic Rhinosinusitis: Developing and Pilot-testing a Bilingual Patient Decision-Support Web Application
- Principal Investigator: Yalda Khashe
- Faculty Profile
- Projects
- Hospitals at Home: The Role of AI in Patient Safety
- Project Description: This research project will explore the pivotal role of artificial intelligence (AI) in enhancing patient safety. This innovative healthcare approach brings hospital-level care to patients' homes, aiming to reduce costs and improve patient outcomes. AI technologies, including predictive analytics, remote monitoring, and decision support systems, play a crucial role in identifying potential risks, ensuring timely interventions, and providing personalized care. This project will explore how AI can optimize clinical workflows, improve medication management, and enhance patient safety in a home-based care environment. Through this research, students will gain hands-on experience with cutting-edge AI tools and contribute to developing safer, more efficient healthcare delivery systems.
- Open to: CURVE First-Time Researchers
- Student Responsibilities:
- Literature Review: Research and summarize existing "Hospital at Home" models and AI applications in patient safety, identifying knowledge gaps.
- Data Collection and Analysis: Gather and analyze data from various sources using statistical tools to gain insights.
- AI Tool Exploration: Evaluate and document the effectiveness of AI technologies in patient safety.
- Case Studies: Develop case studies on AI's impact in hospital-at-home settings, covering patient outcomes and cost analysis.
- Collaboration: Work with team members, advisors, and experts, contributing to meetings and discussions.
- Report Writing: Write research reports, papers, and presentations with clear organization and thorough referencing.
- Presentations: Prepare and deliver research presentations using visual aids.
- Ethics and Compliance: Follow ethical guidelines and institutional policies in all research activities.
- Preferred Majors: Industrial & Systems Engineering
- Preferred Skillsets:
- Research Proficiency: Strong ability to conduct comprehensive literature reviews, including online research using academic databases and other credible sources.
- Data Analysis: Skilled in using statistical tools and software for data collection, processing, and analysis.
- Academic Writing: Excellent writing skills for drafting research reports, papers, and documentation.
- Communication: Clear and effective communication skills for presenting complex ideas and findings.
- Collaboration: Effective teamwork and interpersonal skills for working with diverse groups, including peers, advisors, and industry experts.
- Critical Thinking: Strong problem-solving abilities, critical thinking, and innovative approach to research challenges.
- Attention to Detail: High accuracy and thoroughness in research, documentation, and data analysis.
- Ethical Awareness: Understanding and adherence to ethical guidelines and compliance in research activities.
- Time Management: Efficient in managing time, prioritizing tasks, and meeting deadlines in a research-focused environment.
- Hospitals at Home: The Role of AI in Patient Safety
USC Information Sciences Institute
- Principal Investigator: Jose-Luis Ambite
- Website: https://www.isi.edu/centers-ai4health/
- Projects
- Federated Learning / Deep learning for Neuroimaging
- Project Description: Secure Federated learning trains a neural network across multiple sites without sharing data (and maintaining its privacy). We will apply deep learning and federated learning methods to neuroimaging domains.
- Open to: CURVE First-Time Researchers,CURVE Continuing Researchers
- Student Responsibilities: Read papers. Run experiments.
- Preferred Majors: Computer Science
- Preferred Skillsets: Python, Keras Tensorflow or Pytorch
- Federated Learning / Deep learning for Neuroimaging
- Principal Investigator: Mayank Kejriwal
- Website: https://aicomplex.github.io
- Projects
- Evaluating commonsense reasoning using large language models
- Project Description: This project will aim to conduct experiments on large language models assessing their commonsense reasoning abilities.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: The student will work with me and a graduate student to design and run these experiments.
- Preferred Majors: Computer Science,Industrial & Systems Engineering
- Preferred Skillsets: Some experience with coding and/or the student having 'played' with ChatGPT and other such models.
- Evaluating commonsense reasoning using large language models
- Principal Investigator: Young Cho
- Website: https://ecet.wpengine.com/
- Projects
- Methane Concentration Detection near Urban Oil Field using Mobile Internet-of-Things
- Project Description: The United States has a documented history of over 4 million wells drilled since 1859. However, the Interstate Oil & Gas Compact Commission suggests there are an additional 300,000 to 800,000 undocumented wells. Of the total, just above 900,000 wells remain productive. This leaves an estimated 3-4 million wells as idle or abandoned, which often leak potent greenhouse gases, harmful toxins, and ozone-forming emissions, yet remain under-monitored or not monitored at all. The Environmental Protection Agency has reported that abandoned oil and gas wells contribute to methane emissions amounting to 280,000 metric tons per year. Research from the University of Southern California indicates the damage from leaks in urban oil fields close to their campus is comparable to the health risks associated with passive smoking or residing near heavy traffic. Notably, the Information Sciences Institute at USC is situated adjacent to the Inglewood oil field -- one of the nation's largest urban oil field -- covering around 1000 acres and comprising over 1600 wells that are new, active, or idle. Over a million people reside within a five-mile radius of this field. Community advocates argue that noxious emissions from the field are causally linked to cardiovascular and pulmonary diseases, cancers, congenital disabilities, and increased mortality rates. Despite the risks to the population's health and significant greenhouse gases, there is no initiative for continuous and systematic measurement of emissions from the Inglewood oil field and the neighboring communities. Deploying a functional sensor infrastructure is one of the biggest challenges for monitoring gas and pollutant emissions from oil wells. There is a distinct lack of accessible sensor solutions that combine affordability, durability, ease of deployment, self-sustaining, and zero maintenance. Given the imminent need to develop a community-wide monitoring solution for the highly populated Del Rey neighborhood near Inglewood Oil Field, our vision for the stage 2 pilot project is to develop the first large-scale practical and least invasive solution for a 24/7 environment (namely methane gas and air quality) monitoring. Specifically, we will redesign, build, and deploy USC-ISI’s self-sustaining industrial IoT units to monitor methane concentration, air quality, and other environmental factors. These units will be used to collect data at scale from moving vehicles and static locations managed by our community partners in the neighborhood. Data will be transmitted to our cloud servers via a state-of-the-art IoT network, ensuring reliable and timely data flow. Furthermore, we will develop a cloud-based platform and algorithms to integrate, calibrate, and model the dynamic emission patterns and environmental changes in the neighborhoods surrounding the oil field.
- Open to: CURVE First-Time Researchers
- Student Responsibilities:
- (1) The students will assist in designing an enclosure for the mobile IoTs that will minimize the interfering effects of wind on the methane sensors.
- (2) The students will mount the resulting IoT on vehicles to collect data and automatically store the data in the cloud servers.
- (3) The students will assist in the development of algorithms that will estimate and display the methane concentration on a given area.
- Preferred Majors: Computer Science,Electrical & Computer Engineering,Industrial & Systems Engineering
- Preferred Skillsets:
- Mechanical design experience.
- IoT end-to-end solution experience.
- Methane Concentration Detection near Urban Oil Field using Mobile Internet-of-Things
USC Stevens Neuroimaging and Informatics Institute
- Principal Investigator: Dominique Duncan
- Website: https://sites.usc.edu/duncanlab/
- Projects
- Post-traumatic epilepsy and machine learning
- Project Description: We are analyzing both clinical and preclinical EEG and MRI data from TBI patients, some of whom develop epilepsy. We are using machine learning and other methods to identify biomarkers of epileptogenesis.
- Open to: CURVE First-Time Researchers
- Student Responsibilities: QC, preprocessing, artifact removal, programming, interpreting analysis results
- Preferred Majors: Biomedical Engineering,Computer Science,Electrical & Computer Engineering
- Preferred Skillsets: Matlab, python, EEG or MRI analysis, machine learning
- Post-traumatic epilepsy and machine learning