Publication

Investigation of cluster validity indices for unsupervised human activity discovery

Simple item page
dc.contributor.authorOng, Wee-Hong
dc.contributor.authorKoseki, Takafumi
dc.contributor.authorPalafox, Leon
dc.date.accessioned2026-10-23T06:18:38Z
dc.date.available2026-10-23T06:18:38Z
dc.date.issued2013
dc.description.abstractAn approach for unsupervised human activity discovery has been proposed in this paper. The approach automatically discover unknown activities from unlabeled data and has the ability to reject random activities. This ability will enable intelligent systems to discover and learn new activities autonomously. K-means is used to cluster a pool of unlabeled activity observations into groups of different activities. The system requires no prior knowledge of how many activities to be discovered. It uses cluster validity indices to automatically estimate the required number of clusters and further evaluate cluster homogeneity to accept clusters with homogenous activity and reject clusters with random activities. Experimental results showed the potential of the approach and identified suitable validity indices to achieve unsupervised human activity discovery.
dc.format.extent7 pages
dc.identifier.urihttps://repository.ubd.edu.bn/handle/123456789/4785
dc.language.isoen
dc.publisherCSREA Press
dc.sourceProceedings of the 2013 International Conference on Artificial Intelligence
dc.subject.lcshHuman activity recognition
dc.subject.lcshCluster analysis
dc.subject.lcshMachine learning
dc.subject.lcshComputer vision
dc.subject.lcshComputer algorithms
dc.titleInvestigation of cluster validity indices for unsupervised human activity discovery
dc.typeArticle
dspace.entity.typePublication
Collections:
Academic Publication (SDS)
Files:

Browse