Incremental kNN Classifier Exploiting Correct-Error Teacher for Activity Recognition

• Published in: 2010 International Conference on Machine Learning and Applications pp. 445 - 450
• Main Authors: Förster, Kilian, Monteleone, S, Calatroni, A, Roggen, D, Troster, G
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2010
• Subjects: Accuracy; Adaptation model; Artificial neural networks; Data models; Stability analysis; Training; Upper bound
• ISBN: 1424492114; 9781424492114
• DOI: 10.1109/ICMLA.2010.72

Non-stationary data distributions are a challenge in activity recognition from body worn motion sensors. Classifier models have to be adapted online to maintain a high recognition performance. Typical approaches for online learning are either unsupervised and potentially unstable, or require ground truth information which may be expensive to obtain. As an alternative we propose a teacher signal that can be provided by the user in a minimally obtrusive way. It indicates if the predicted activity for a feature vector is correct or wrong. To exploit this information we propose a novel incremental online learning strategy to adapt a k-nearest-neighbor classifier from instances that are indicated to be correctly or wrongly classified. We characterize our approach on an artificial dataset with abrupt distribution change that simulates a new user of an activity recognition system. The adapted classifier reaches the same accuracy as a classifier trained specifically for the new data distribution. The learning based on the provided correct - error signal also results in a faster learning speed compared to online learning from ground truth. We validate our approach on a real world gesture recognition dataset. The adapted classifiers achieve an accuracy of 78.6% compared to the subject independent baseline of 68.3%.