Reliable emotion recognition system based on dynamic adaptive fusion of forehead biopotentials and physiological signals. Issue 2 (November 2015)

• Record Type: Journal Article
• Authors: Khezri, Mahdi; Firoozabadi, Mohammad; Sharafat, Ahmad Reza
• Is Part Of: Computer methods and programs in biomedicine. Volume 122:Issue 2(2015)
• Page Start: 149
• Page End: 164
• Publication Date: 2015-11
• Subjects: Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2015.07.006
• Languages: English
• ISSNs: 0169-2607

Abstract

<abstract abstract-type="author-highlights" id="abs0005"> <title id="sect0005">Highlights</title> <sec> <p id="spar0005"> <list id="lis0005"> <list-item id="lsti0005"> <label></label> <p id="par0005">A new dynamic fusion method for designing an emotion recognition system is proposed.</p> </list-item> <list-item id="lsti0010"> <label></label> <p id="par0010">A weight is assigned to each classifier based on its performance.</p> </list-item> <list-item id="lsti0015"> <label></label> <p id="par0015">The performance of the classifiers during the training and testing phases is considered.</p> </list-item> <list-item id="lsti0020"> <label></label> <p id="par0020">Static weights in varying contexts such as emotions do not produce acceptable results.</p> </list-item> <list-item id="lsti0025"> <label></label> <p id="par0025">Dynamic weighting strategy improves the performance of the system considerably.</p> </list-item> </list> </p> </sec> </abstract>