Title
Macro-Class Selection For Hierarchical K-Nn Classification Of Inertial Sensor Data
Keywords
Hierarchical classification; Human activity recognition; Macro-class selection
Abstract
Quality classifiers can be difficult to implement on the limited resources of an embedded system, especially if the data contains many confusing classes. This can be overcome by using a hierarchical set of classifiers in which specialized feature sets are used at each node to distinguish within the macro-classes defined by the hierarchy. This method exploits the fact that similar classes according to one feature set may be dissimilar according to another, allowing normally confused classes to be grouped and handled separately. However, determining these macro-classes of similarity is not straightforward when the selected feature set has yet to be determined. In this paper, we present a new greedy forward selection algorithm to simultaneously determine good macro-classes and the features that best distinguish them. The algorithm is tested on two human activity recognition datasets: CMU-MMAC (29 classes), and a custom dataset collected from a commodity smartphone for this paper (9 classes). In both datasets, we employ statistical features obtained from on-body IMU sensors. Classification accuracy using the selected macro-classes was increased 69% and 12% respectively over our non-hierarchical baselines.
Publication Date
6-15-2012
Publication Title
PECCS 2012 - Proceedings of the 2nd International Conference on Pervasive Embedded Computing and Communication Systems
Number of Pages
106-114
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
Copyright Status
Unknown
Socpus ID
84862121779 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84862121779
STARS Citation
McCall, Corey; Reddy, Kishore; and Shah, Mubarak, "Macro-Class Selection For Hierarchical K-Nn Classification Of Inertial Sensor Data" (2012). Scopus Export 2010-2014. 4234.
https://stars.library.ucf.edu/scopus2010/4234