CBARS: cluster based classification for activity recognition systems

Z. Abdallah, M. Gaber, B. Srinivasan, S. Krishnaswamy

Research output: Contribution to conferencePaperpeer-review

131 Downloads (Pure)

Abstract

Activity recognition focuses on inferring current user activities by leveraging sensory data available on today's sensor rich environment. Supervised learning has been applied pervasively for activity recognition. Typical activity recognition techniques process sensory data based on point-by-point approaches. In this paper, we propose a novel Cluster Based Classification for Activity Recognition Systems, CBARS. The novel approach processes activities as clusters to build a robust classification framework. CBARS integrates supervised, unsupervised and active learning and applies hybrid similarity measures technique for recognising activities. Extensive experimental results using real activity recognition dataset have evidenced that our new approach shows improved performance over other existing state-of-the-art learning methods.
Original languageEnglish
Publication statusPublished - 8 Dec 2012
EventProceedings of the First International Conference on Advanced Machine Learning Technologies and Applications - Cairo, Egypt
Duration: 8 Dec 201210 Dec 2012

Conference

ConferenceProceedings of the First International Conference on Advanced Machine Learning Technologies and Applications
Abbreviated titleAMLTA12
Country/TerritoryEgypt
CityCairo
Period8/12/1210/12/12

Fingerprint

Dive into the research topics of 'CBARS: cluster based classification for activity recognition systems'. Together they form a unique fingerprint.

Cite this