A Daubechies Wavelet Transform Implemented Drowsiness Detection Methodology

Driver drowsiness and loss of vigilance are a major cause of road accidents. Monitoring physiological signals while driving provides the possibility of detecting and warning of drowsiness and fatigue. The aim of this project is to maximize the amount of drowsiness related information extracted from a set of electroencephalogram (EEG) database. In this project, a new feature extraction algorithm is developed to extract the most relevant features required to identify the driver drowsiness/fatigue states. This is achieved by analyzing the corresponding physiological signals from brain. An optimal Fuzzy Wavelet Packet based feature extraction method is implemented so as to determine the instants at which drowsiness occurs. In order to attain high classification accuracy, a Support Vector Machine (SVM) classifier is used and the Receiver Operating Characteristics (ROC) curve shows the classification accuracy and finally, the time required for executing this mechanism is determined. In order to improve the efficiency of the proposed method, a Bootstrapping mechanism which is an extremely attractive tool in the sense of modeling, assumptions and analysis is implemented. For a better classification of cognitive states, a neural network (NN) classifier is implemented and this methodology is found to reduce the computational complexity and an improved classification accuracy of 93%is observed.