Personal State and Emotion Monitoring by Wearable Computing and Machine Learning

One of the major scientific undertakings over the past few years has been exploring the interaction between humans and machines in mobile environments. Wearable computers, embedded in clothing or seamlessly integrated into everyday devices, have an incredible advantage to become the main gateway to personal health management. Current state of the art devices are capable in monitoring basic physical or physiological parameters. Traditional health systems procedures depend on the physical presence of the patient and a medical specialist that not only is a reason of overall costs but also reduces the quality of patients' lives, particularly elderly patients. Usually, patients have to go through the following steps for the traditional procedure: Firstly, patients need to visit the clinic, get registered at reception, wait for the turn, go to the lab for the physiological measurement, wait for the medical experts call, to finally receive feedback from the medical expert. In this work, we examined how to utilize existing technology in order to develop an e-health monitoring system especially for heart patients. This system should support the interaction between the patient and the physician even when the patient is not in the clinic. The supporting wearable health monitoring system WHMS should recognize physical activities, emotional states and transmit this information to the physician along with relevant physiological data; in this way patients do not need to visit the clinic every time for the physician's feed-back. After the discussion with medical experts, we identified relevant physical activities, emotional states and physiological data needed for the patients' examinations. A prototype of this concept for a health monitoring system of the proposed solution was implemented taking into account physical activities, emotional states and physiological data.