Payal Mohapatra
Northwestern University
Bio
Payal Mohapatra is a PhD candidate in the Department of Electrical and Computer Engineering at Northwestern University. Her research interests lie in designing algorithms for real-world, human-centric applications, with a focus on healthcare, continuous sensing, and audio domains, using methods inspired by machine learning, signal processing, and embedded systems. She has won challenges hosted by IEEE ICASSP (2022), ACM Multimedia (2023), and Analog Devices (2017). Her work has been featured in IEEE ICASSP, IEEE I2MTC, ISCA Interspeech, and other venues. She was a DAC Young Fellow in 2021 and conducted research at Meta Reality Labs during the summers of 2023 and 2024. Before starting her PhD, she was an IC Design Engineer at Analog Devices Incorporated and earned her Master’s in Electrical Engineering from the Indian Institute of Technology Madras.
Areas of Research
- Machine Learning
Empowering Real-World Sensing: Algorithms for Imperfect Time-Series
Wearables, smartphones, and continuous sensing applications are ubiquitous today. While they have achieved tremendous success through improved computation, smaller form factors, and advanced sensing capabilities, the analytics for these applications still lag behind those in the language and vision domains. This disparity arises because real-world time series data are messy, generally non-interpretable in their raw format, and noisy, among other challenges. Through my research, I aim to address these challenges in audio and sensing applications, particularly: 1) the lack of data and labels, 2) the dynamic nature of modalities–signal nonstationarity and missingness, and 3) factors for resource-constrained edge deployment of these frameworks. I seek to tackle these issues with a focus on inclusivity and real-time deployability, going beyond mere performance enhancement. In one of my studies on fatigue monitoring, conducted with 45 subjects using real manufacturing setups and a wearable sensing framework, we found that the major challenge is the subjective nature of perceived fatigue scores among participants. This requires an ordinality-aware modeling technique and must be lightweight to support real-time demonstration on actual factory floors. To overcome data unreliability, including missingness of some modalities and labels for minority audio applications such as dysfluency detection, I have designed methods using self-supervised learning and resilient multimodal architectures. I also systematically design algorithms to address signal nonstationarity with minimal design overhead across a wide range of time-series sensing applications. Continuous health monitoring devices stand to benefit directly from such dedicated, data-driven frameworks. I aim to evaluate my design frameworks for their on-device deployment capability to enable real-time applicability and enhance user privacy. One of my current goals is to support an evolving family of wearables with upgraded sensors and modalities, delivering optimal performance with minimal learning time by leveraging previously collected data.