Title :
AdaBoost-based sensor fusion for credibility assessment
Author :
Alipour, Hamid ; Zeng, Daniel ; Derrick, Douglas C.
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of Arizona, Tucson, AZ, USA
Abstract :
Individual credibility assessment is an ever-growing requirement in different applications including border crossing, airport checkpoint screening, criminal investigations, etc. In this paper, we describe a heterogeneous sensor fusion algorithm based on the AdaBoost algorithm and a speech emotional recognition technique in order to develop an automatic noninvasive credibility assessment system. Our initial results based on two available sensors show a promising increase in the accuracy and performance of the system.
Keywords :
behavioural sciences computing; emotion recognition; eye; feature extraction; learning (artificial intelligence); object tracking; sensor fusion; speech recognition; AdaBoost algorithm; AdaBoost-based sensor fusion; airport checkpoint screening; automatic noninvasive credibility assessment system; behavioral indicators; border crossing; criminal investigation; eye tracker sensor; feature extraction; heterogeneous sensor fusion algorithm; individual credibility assessment; physiological indicators; speech emotional recognition technique; Accuracy; Biomedical monitoring; Classification algorithms; Emotion recognition; Sensor fusion; Speech; Speech recognition; Adaboost; Credibility Assessment; Data fusion; Sensor Signal Integration;
Conference_Titel :
Intelligence and Security Informatics (ISI), 2012 IEEE International Conference on
Conference_Location :
Arlington, VA
Print_ISBN :
978-1-4673-2105-1
DOI :
10.1109/ISI.2012.6284314
