Pervasive Computing
Robust algorithms for wearable systems
The growing ubiquity of sensor-equipped wearables such as mobile devises, pedometers, EEGs (electroencephalogram), and smartphones is making it possible to capture information about human behavior in real-time. This growth is leading to increased development and deployment of mobile sensing applications. Despite their enormous potential, however, currently existing wearables are designed for controlled environments, lab settings, and small trials with configuration-specific protocols. Scaling these systems up and extending their applications in real-world, dynamic environments brings about major challenges. We have just began developing robust machine learning and signal processing algorithms and frameworks that aim to address these challenges.
Papers
- R. Saeedi and A.H. Gebremedhin. A Signal-level Transfer Learning Framework for Autonomous Reconfiguration of Wearable Systems, IEEE Transactions on Mobile Computing, Vol 19, No 3, 513-527, 2020.
Abstract Paper
- S. Norgaard, R. Saeedi, K. Sasani, and A.H. Gebremedhin, Synthetic Sensor Data Generation for Health Applications: A Supervised Deep Learning Approach, IEEE Engineering in Medicine and Biology Society Conference (EMBC 2018).
Abstract Paper
- R. Saeedi, K. Sasani, S. Norgaard and A.H. Gebremedhin, Personalized Human Activity Recognition using Wearables: A Manifold Learning-based Knowledge Transfer, IEEE Engineering in Medicine and Biology Society Conference (EMBC 2018).
Abstract Paper
- R. Saeedi, S. Norgaard and A.H. Gebremedhin, A Closed-loop Deep Learning Architecture for Robust Activity Recognition using Wearable Sensors, 2017 IEEE International Conference on Big Data (BigData 2017).
Abstract Paper