Recognizing slow eye movement for driver fatigue detection with machine learning approach

Abstract

Slow eye movement (SEM) regarded as a sign of onset of sleep is very significant for detecting driver fatigue, but its characteristics and detection algorithm have been rarely involved in the study of driver fatigue detection. In this study, some new features were extracted based on wavelet singularity analysis and statistics to detect SEMs. Six subjects participated in this simulated driving experiment, and for each subject, a more than 2 hours electro-oculogram (EOG) session was recorded. Each session was divided into SEM epochs and non-SEM epochs according to the common judgments made by the two of three experts by the visual recognition criteria of SEMs. Regarding the problem of detecting SEMs as an imbalance classification problem, and through the under-sampling and over-sampling methods a 2s horizontal electro-oculogram (HEO) signal could finally be recognized as the category of SEMs or non-SEMs with the classifiers SVM, GELM, and KNN respectively. Results prove that the proposed features was a little better than the wavelet energy features, and through the combination of the wavelet energy features and the new features based on wavelet singularity analysis and statistics, the classification results were improved obviously.

Detection and Evaluation of Driver Distraction Using Machine Learning and Fuzzy Logic

“…The suggested methodology has a certain advantage over other DD detection methods described in Section II. Particularly, as compared to the methods, where the behavioral and psychological attributes are applied [6][7][8][9][10][11][12][13][14][15][16][17][18], the proposed approach does not require additional devices, such as cameras and neuroscan systems. Those devices increase the system cost [8], what in its turn is a potential resistance for system application in a commercial passenger vehicle.…”

“…Fuzzy expert system combined eye and face regions for the DD level fatigue estimation in [14]. Different machine learning methods, in particular SVM, k-nearest neighbor (k-NN), and graph-regularized extreme learning machine were compared in [15]. The complex method designed in [7] connects the principle component analysis, the linear discriminate analysis, and SVM.…”

A novel approach to driving fatigue detection using forehead EOG

“…The wavelet methods have been used in EOG features extraction [4], [10]. As the wavelet transform is sensitive to singularity, it obtains a better result than the derivative method in detecting blink and saccade.…”

Study on the Effect of Man-Machine Response Mode to Relieve Driving Fatigue Based on EEG and EOG

“…There have been many studies on mental fatigue based on human physiological signal characteristics [7,8]. Previous studies have showed that human mental fatigue is associated with eye movement characteristics [9,10,11]. Di Stasi et al found that the saccadic eye movement parameters are sensitive indicators for human mental fatigue [12].…”