Posture tracking using machine learning and Home Hospital e-Health Centers for barrier-free and cross-border Telemedicine
Malta, June 2019. Maksym Gaiduk and Ralf Seepold presented the results from the IBH Lab running at the Lake Konstanz at the 11th International KES Conference.
Maksym Gaiduk
The number of home office workers sitting many hours increase. Maksym Gaiduk presented a sensor chair that is tracking users' sitting behavior which the help of pressure sensors and tries to avoid wrong postures which may cause diseases. The system provides live monitoring of the pressure distribution via the web interface, as well as sitting posture prediction in real time. Posture analysis is realized through a machine-learning algorithm using a decision tree classifier that is compared to a random forest. Data acquisition and aggregation for the learning process happens with a mobile app adding users biometrical data and the taken sitting posture as label. The sensor chair is able to differentiate between an arched back, a neutral posture or a laid back position taken on the chair. The classifier achieves an accuracy of 97.4% on our test set and is comparable to the performance of the random forest with 98.9%.
The goal of the Home Hospital e-Health Centers, presented b y Ralf Seepold, is to develop the concept of home e-health centers for barrier-free and cross-border telemedicine. AAL technologies are already present on the market but there is still a gap to close until they can be used for ordinary patient needs. The general idea needs to be accompanied by new services, which should be brought together in order to provide full coverage of service for the users. Sleep and stress were chosen as predominant diseases for a detailed study within this project because of their widespread influence in the population. The executed scientific study of available home devices analyzing sleep has provided the necessary to select appropriate devices.