Keynote: A Cross-Domain Machine Learning Framework for Pervasive Sensing
Nirmalya Roy · 2020
Recognizing human activity and behavior is a well-known research problem. State-of-the-art machine learning approaches, a variety of smart home sensor systems, and Internet-of-Things (IoT) devices are in place to help aid activity discovery, recognition, and inference processes. However, the current approaches work with single user, a predefined set of devices and in a specific smart environment. Scaling, adapting, and crossing the boundaries beyond those presumed settings in presence of limited or unlabeled datasets posit challenging research avenues to investigate. In this talk, I will first articulate the underpinning challenges across heterogenous IoT devices, different users and environments. I will discuss our work on addressing those challenges using deep learning-based domain adaptation and transfer learning-based techniques, and present experimental results using real datasets collected from different IoT devices such as smartphones, smartwatches, and diverse users. I will conclude this talk with our ongoing work in this area and future research directions.