This document discusses discovering human activities from sensor data. It describes deploying over 1000 sensors in skilled nursing and independent living facilities to capture data on activities of daily living (ADLs) like bathing, dressing, eating. Unsupervised machine learning techniques like LDA topic modeling are used to learn relationships between sensors and ADLs in order to summarize what activities occupants are performing based on sensor readings. Tuning of the models, handling of edge cases, and transferring learning across different environments are identified as areas for further work.
Active ageing is the process of optimizing opportunities for health, participation and security in order to enhance quality of life as people age. It applies to both individuals and population groups.