Tampere University of Technology

TUTCRIS Research Portal

Dynamic action classification based on iterative data selection and Feedforward Neural networks

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publicationEuropean Signal Processing Conference
PublisherEuropean Signal Processing Conference, EUSIPCO
ISBN (Print)9780992862602
Publication statusPublished - 2013
Publication typeA4 Article in a conference publication
Event2013 21st European Signal Processing Conference, EUSIPCO 2013 - Marrakech, Morocco
Duration: 9 Sep 201313 Sep 2013

Conference

Conference2013 21st European Signal Processing Conference, EUSIPCO 2013
CountryMorocco
CityMarrakech
Period9/09/1313/09/13

Abstract

In this paper we present a dynamic classification scheme involving Single-hidden Layer Feedforward Neural (SLFN) network-based non-linear data mapping and test sample-specific labeled data selection in multiple levels. The number of levels is dynamically determined by the test sample under consideration, while the use of Extreme Learning Machine (ELM) algorithm for SLFN network training leads to fast operation. The proposed dynamic classification scheme has been applied to human action recognition by employing the Bag of Visual Words (BoVW)-based action video representation providing enhanced classification performance compared to the static classification approach.

Keywords

  • Data selection, Dynamic classification, Extreme Learning Machine, Feedforward Neural network