Files

Abstract

Personal health monitoring systems are emerging as promising solutions to develop ultra-small, portable devices that can continuously monitor and process several vital body parameters. In this work, we present a wearable device for physical and emotional health monitoring. The device obtains user’s key physiological signals: ECG, respiration, Impedance Cardiogram (ICG), blood pressure and skin conductance and derives the user’s emotion states as well. We have developed embedded algorithms that process the bio-signals in real-time to detect any abnormalities (cardiac arrhythmias and morphology changes) in the ECG and to detect key parameters (such as the Pre- Ejection Period and fluid status level) from the ICG. We present a novel method to detect continuous beat-by-beat blood pressure from the ECG and ICG signals, as well as a realtime embedded emotion classifier that computes the emotion levels of the user. Emotions are classified according to their attractiveness (positive valence) or their averseness (negative valence) in the horizontal valence dimension. The excitement level induced by the emotions is represented by high to low positions in the vertical arousal dimension of the valence-arousal space. The signals are measured either intermittently by touching the metal electrodes on the device (for point-of-care testing) or continuously, using a chest strap for long term monitoring. The processed data from device is sent to a mobile phone using a Bluetooth Low Energy protocol. Our results show that the device can monitor the signals continuously, providing accurate detection of the motion state, for over 72 hours on a single battery charge.

Details

PDF