PhD Forum: Recognizing Human Posture from Time-Changing Wearable Sensor Data Streams

This work stems from the project with National Institutes of Health on elderly human posture recognition in their real-world wearable sensor data streams. The problem presented several challenges: near real-time posture recognition, skewed class distribution, time-changing data streams and sensor management. To tackle these challenges, in this project, we present our design integrates with resampling, cost-sensitive classifier and incremental learning for time- changing wearable sensor data streams as well as sensor management for the determination of the least possible number of sensors and their best positions to be deployed on human body.