TY - GEN
T1 - Driving conditions recognition using heart rate variability indexes
AU - Wang, Jeen-Shing
AU - Chung, Pau-Choo
AU - Wang, Wei Hsin
AU - Lin, Che-Wei
PY - 2010/12/28
Y1 - 2010/12/28
N2 - This study presents a physiological recognition strategy based on HRV-parameter-based recognition strategy. The strategy consists of the following processes: 1) feature generation, 2) feature selection, 3) feature extraction, and 4) classifier construction for recognition. In the feature generation processes, the parameter-based strategy calculates features from five-minute HRV analysis results. In the feature selection process, the strategy adopts the best individual N (BIN) as the search strategy and the kernel-based class separability (KBCS) as the selection criterion. Sequentially, principal component analysis (PCA) and linear discriminant analysis (LDA) are adopted in the feature extraction process. Finally, a k-nearest neighbor (k-NN) algorithm is used for the recognition. The feasibility of the recognition strategy is verified by driving condition recognition. The simulation results demonstrate that the proposed strategy can achieve satisfactory recognition rates for recognizing driving conditions. The results show that the feature extraction process or feature selection process has respective physical meaning in the proposed strategies.
AB - This study presents a physiological recognition strategy based on HRV-parameter-based recognition strategy. The strategy consists of the following processes: 1) feature generation, 2) feature selection, 3) feature extraction, and 4) classifier construction for recognition. In the feature generation processes, the parameter-based strategy calculates features from five-minute HRV analysis results. In the feature selection process, the strategy adopts the best individual N (BIN) as the search strategy and the kernel-based class separability (KBCS) as the selection criterion. Sequentially, principal component analysis (PCA) and linear discriminant analysis (LDA) are adopted in the feature extraction process. Finally, a k-nearest neighbor (k-NN) algorithm is used for the recognition. The feasibility of the recognition strategy is verified by driving condition recognition. The simulation results demonstrate that the proposed strategy can achieve satisfactory recognition rates for recognizing driving conditions. The results show that the feature extraction process or feature selection process has respective physical meaning in the proposed strategies.
UR - http://www.scopus.com/inward/record.url?scp=78650487376&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=78650487376&partnerID=8YFLogxK
U2 - 10.1109/IIHMSP.2010.100
DO - 10.1109/IIHMSP.2010.100
M3 - Conference contribution
AN - SCOPUS:78650487376
SN - 9780769542225
T3 - Proceedings - 2010 6th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2010
SP - 389
EP - 392
BT - Proceedings - 2010 6th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2010
T2 - 6th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2010
Y2 - 15 October 2010 through 17 October 2010
ER -