Recognition of Physiological Patterns During Activities of Daily Living Using Wearable Biosignal Sensors

This chapter evaluates the use of wearable biosignal sensors to recognize physiological patterns during activities of daily living (ADLs). The study involves 10 subjects performing 22 different activities, with data collected using electromyography (EMG), electrocardiography (ECG), and piezoelectric respiration (PZT) sensors. The analysis focuses on muscle activation, heart rate, and respiratory rate to identify patterns that can predict fall risks. The results show distinctive patterns between high-intensity and low-intensity activities, with muscle activation increasing with movement speed. The study concludes that these data can be used to develop reactive and proactive algorithms for fall prediction, filling a gap in the literature by providing a comprehensive dataset for future research.