Design & analysis of K-means algorithm for cognitive fatigue detection in vehicular driver using Respiration signal

Vehicular drivers and shift workers in industry are at most risk of handling life critical tasks. The drivers traveling long distances or when they are tired, are at risk of a meeting an accident. The early hours of the morning and the middle of the afternoon are the peak times for fatigue driven accidents. The difficulty in determining the incidence of fatigue-related accidents is due, at least in part, to the difficulty in identifying fatigue as a causal or causative factor in accidents. In this paper we propose an alternative approach for fatigue detection in vehicular drivers using Respiration (RSP) signal to reduce the losses of the lives and vehicular accidents those occur due to cognitive fatigue of the driver. We are using basic K-means algorithm with proposed two modifications as classifier for detection of Respiration signal two state fatigue data recorded from the driver. The K-means classifiers [11] were trained and tested for wavelet feature of Respiration signal. The extracted features were treated as individual decision making parameters. From test results it could be found that some of the wavelet features could fetch 100 % classification accuracy.