Feature Weighted Nearest Neighbour Classification for Accelerometer-Based Gesture Recognition (CROSBI ID 589277)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Marasović, Tea ; Papić, Vladan
engleski
Feature Weighted Nearest Neighbour Classification for Accelerometer-Based Gesture Recognition
Understanding human gestures can be posed as a typical classification problem. Within the computer, gestures are represented as time-varying patterns in feature space. These patterns, though variable, are distinct and have associated meanings. In the absence of a priori knowledge of the underlying class probabilities, classification is performed based on some notion of similarity, e.g. distance, among samples. The k-nearest neighbour (kNN) decision rule has often been used in these pattern recognition problems. The use of this particular technique gives rise to multiple issues, one of them being that it operates under the implicit assumption that all features are of equal importance in deciding the class membership of the pattern to be classified, regardless of their "relevancy". This paper presents an accelerometer-based gesture recognition system that utilizes Mahalanobis distance metric learning to derive optimal weighting scheme for nearest neighbour classification. The metric is trained with the goal of separating different classes by large local margins and pulling closer together samples from the same class, based on using as few features as possible. Our experiments on an arbitrary gesture set show that the proposed method leads to significant improvements in recognition accuracies, yielding simultaneously a maximum of feature discrimination.
gesture recognition; metric learning; classification
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
2012.
objavljeno
Podaci o matičnoj publikaciji
Proceedings of SoftCom 2012
Rožić, Nikola ; Begušić, Dinko
Split: Fakultet elektrotehnike, strojarstva i brodogradnje Sveučilišta u Splitu
978-953-290-035-4
Podaci o skupu
SoftCOM 2012
predavanje
11.09.2012-13.09.2012
Split, Hrvatska