DocumentCode :
3497774
Title :
A hybrid system ensemble based time series signal classification on driver alertness detection
Author :
Xu, Shen ; Liu, Ruoqian ; Li, Dai ; Murphey, Yi Lu
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of Michigan-Dearborn, Dearborn, MI, USA
fYear :
2011
fDate :
July 31 2011-Aug. 5 2011
Firstpage :
2093
Lastpage :
2099
Abstract :
This paper presents the methodologies developed for solving IJCNN 2011´s Ford Challenge II problem, where the driver´s alertness is to be detected employing physiological, environmental and vehicular data acquired during driving. The solution is based on a thorough four-fold framework consisting of temporal processing, feature creation and extraction, and the training and ensemble of several learning systems, such as neural networks, random forest, support vector machine, trained from diverse features. The selection of input features to a learning machine has always been critique on signal classification. In our approach, the employment of Bayesian network filtered out a set of features and has been proved by the ensemble to be effective. The ensemble technique enhanced the performance of individual systems dramatically. The performance acquired on 30% of the test samples reached an accuracy of 78.34%. These results are significant for a real-world vehicular problem and we are quite confident this solution will become one of the top ones on the competition test data.
Keywords :
belief networks; feature extraction; learning (artificial intelligence); neural nets; signal classification; support vector machines; time series; traffic engineering computing; Bayesian network; IJCNN 2011 Ford Challenge II problem; driver alertness detection; environmental data; feature creation; feature extraction; hybrid system ensemble; machine learning; neural networks; physiological data; random forest; support vector machine; temporal processing; time series signal classification; vehicular data; Artificial neural networks; Feature extraction; Support vector machines; Time series analysis; Training; Training data;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks (IJCNN), The 2011 International Joint Conference on
Conference_Location :
San Jose, CA
ISSN :
2161-4393
Print_ISBN :
978-1-4244-9635-8
Type :
conf
DOI :
10.1109/IJCNN.2011.6033486
Filename :
6033486
Link To Document :
بازگشت