Enhanced human behavior recognition using HMM and Evaluative Rectification

Doulamis, N; Voulodimos, A; Kosmopoulos, D; Varvarigou, T

dc.contributor.author	Doulamis, N	en
dc.contributor.author	Voulodimos, A	en
dc.contributor.author	Kosmopoulos, D	en
dc.contributor.author	Varvarigou, T	en
dc.date.accessioned	2014-03-01T02:46:47Z
dc.date.available	2014-03-01T02:46:47Z
dc.date.issued	2010	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32846
dc.subject	Behavior recognition	en
dc.subject	Hidden Markov Models	en
dc.subject	Relevance feedback	en
dc.subject	Work flow classification	en
dc.subject.other	Automobile manufacturers	en
dc.subject.other	Behavior modeling	en
dc.subject.other	Behavior recognition	en
dc.subject.other	Classification framework	en
dc.subject.other	Classification rates	en
dc.subject.other	Classification results	en
dc.subject.other	Gaining momentum	en
dc.subject.other	Human behavior recognition	en
dc.subject.other	Industrial environments	en
dc.subject.other	Learning process	en
dc.subject.other	Real world environments	en
dc.subject.other	Relevance feedback	en
dc.subject.other	Research problems	en
dc.subject.other	Time series classifications	en
dc.subject.other	Work-flows	en
dc.subject.other	Automobile manufacture	en
dc.subject.other	Feedback	en
dc.subject.other	Hidden Markov models	en
dc.subject.other	Time series	en
dc.subject.other	Behavioral research	en
dc.title	Enhanced human behavior recognition using HMM and Evaluative Rectification	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1145/1877868.1877880	en
heal.identifier.secondary	http://dx.doi.org/10.1145/1877868.1877880	en
heal.publicationDate	2010	en
heal.abstract	Human behavior recognition and real world environments monitoring constitute challenging research problems rapidly gaining momentum over the last years. Methods for time series classification like the Hidden Markov Models have been employed in the past for similar tasks, however in many challenging cases they fail, since some behaviors are much more difficult to model than others. This happens particularly in cases that there is scarcity of labelled data. In this paper we introduce a novel re-adjustment framework of behavior recognition and classification by allowing the user incorporation in the learning process. The proposed Evaluative Rectification approach aims at dynamically correcting erroneous classification results to enhance the behavior modeling and therefore the overall classification rates. We evaluate the performance of the examined approach in a challenging real-life industrial environment of an automobile manufacturer. Our experiments indicate a significant outperformance of the proposed Evaluative Rectification scheme compared with traditional classification frameworks, such as Hidden Markov Models.	en
heal.journalName	ARTEMIS'10 - Proceedings of the 1st ACM Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams, Co-located with ACM Multimedia 2010	en
dc.identifier.doi	10.1145/1877868.1877880	en
dc.identifier.spage	39	en
dc.identifier.epage	44	en