Biosignal Sensing & Processing

Signal Analysis and Interpretation Lab

main-img.png


The Biosignal Sensing and Processing (BioSP) group is a research team within the Signal Analysis and Interpretation Lab (SAIL) at USC. BioSP brings together students specializing in Computer Science and Electrical Engineering, with a shared interest in analyzing biomedical and behavioral signals with computational methods. BioSP’s research encompasses a wide range of Signal Processing and AI techniques to process and infer from human-centered modalities. To that end, BioSP also coordinates data collection studies in both controlled and naturalistic settings.

In this website you will find comprehensive information on current and past research projects, current and past members of our team, as well as useful resources and publications we share with the community. Our partners span the domains of Psychology and Psychiatry, Neuroscience, Cognitive Science, and Medicine, both within USC and at external institutions.

Sponsors of our work include, or have included, the National Institutes of Health (NIH), the National Science Foundation (NSF), the Defense Advanced Research Projects Agency (DARPA), the Intelligence Advanced Research Projects Activity (IARPA), and Toyota Motor North America.




Highlights

Apr 10, 2026 The BioSP team has 2 papers accepted at ICASSP 2026, on self-supervised emotion encoding from eye movements and point process modeling of skin conductance responses! See you in Barcelona.
Apr 2, 2026 Building on our PRECOG project for studying depression and suicidal ideation, our work on neural responses to affective sentences (Translational Psychiatry) and deep learning for eye movement patterns (npj Digital Medicine) have been published!
Aug 17, 2025 Our team will present a paper at Interspeech 2025 through our collaboration with the TUM Chair of Health Informatics on articulatory feature prediction from surface EMG during speech production.
Aug 6, 2025 Our collaborative work on developing personalized algorithms for sensing mental health symptoms in daily life has been published in npj Mental Health Research!
Jun 27, 2024 Our work on efficient representation learning from ECG signals is accepted for publication at the IEEE Journal of Biomedical and Health Informatics! Excited to work on this project with our collaborators from the Emognition Lab at Wrocław University of Science and Technology.