Self-Adaptation of Activity Recognition Systems to New Sensors
This addresses the challenge of dynamic sensor environments for activity recognition systems, though it appears incremental as it builds on existing machine learning principles.
The paper tackles the problem of adapting activity recognition systems to new sensors without requiring extensive user input, presenting an opportunistic approach that uses unsupervised clustering and semi-supervised learning, with evaluations on over 3000 sensor combinations showing potential benefits.
Traditional activity recognition systems work on the basis of training, taking a fixed set of sensors into account. In this article, we focus on the question how pattern recognition can leverage new information sources without any, or with minimal user input. Thus, we present an approach for opportunistic activity recognition, where ubiquitous sensors lead to dynamically changing input spaces. Our method is a variation of well-established principles of machine learning, relying on unsupervised clustering to discover structure in data and inferring cluster labels from a small number of labeled dates in a semi-supervised manner. Elaborating the challenges, evaluations of over 3000 sensor combinations from three multi-user experiments are presented in detail and show the potential benefit of our approach.