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

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...