DocumentCode :
380894
Title :
Evaluation of heart rate variability by using wavelet transform and a recurrent neural network
Author :
Fukuda, Osamu ; Nagata, Yoshihiko ; Homma, Keiko ; Tsuji, Toshio
Author_Institution :
Nat. Inst. of Adv. Ind. Sci. & Technol., Hiroshima Univ., Japan
Volume :
2
fYear :
2001
fDate :
2001
Firstpage :
1769
Abstract :
The purpose of this paper is to evaluate the physical and mental stress based on the physiological index, and a new evaluation method of heart rate variability is proposed. This method combines the wavelet transform with a recurrent neural network. The features of the proposed method are as follows: 1. The wavelet transform is utilized for the feature extraction so that the local change of heart rate variability in the time-frequency domain can be extracted. 2. In order to learn and evaluate the different patterns of heart rate variability caused by individual variations, body conditions, circadian rhythms and so on, a new recurrent neural network which incorporates a hidden Markov model is used. In the experiments, a mental workload was given to five subjects, and the subjective rating scores of their mental stress were evaluated using heart rate variability. It was confirmed from the experiments that the proposed method could achieve high learning/evaluating performances.
Keywords :
backpropagation; biocontrol; electrocardiography; feature extraction; hidden Markov models; medical signal processing; recurrent neural nets; time series; time-frequency analysis; wavelet transforms; body conditions; circadian rhythms; evaluation method; feature extraction; heart rate variability; hidden Markov model; high learning performance; individual variations; learning; local change; mental stress; mental workload; physical stress; physiological index; recurrent neural network; subjective rating scores; time-frequency domain; wavelet transform; Circadian rhythm; Feature extraction; Heart rate variability; Hidden Markov models; Human factors; Performance evaluation; Recurrent neural networks; Time frequency analysis; Wavelet domain; Wavelet transforms;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE
ISSN :
1094-687X
Print_ISBN :
0-7803-7211-5
Type :
conf
DOI :
10.1109/IEMBS.2001.1020562
Filename :
1020562
Link To Document :
بازگشت