Publication Type : Conference Paper
Publisher : International Conference on Information Communication and Embedded Systems (ICICES2014)
Source : International Conference on Information Communication and Embedded Systems (ICICES2014) (2014)
Keywords : Accidents, Automobile drivers, Automobiles, Cross validation, driver information systems, driver stress level, ECG, ECG signals, Electrocardiography, Electromyography, EMG, EMG signals, Feature extraction, Feature space, Kernel, kNN, KNN classifier, medical signal processing, nonlinear feature separation, pertinent feature extraction, Radial Basis Function, radial basis function kernel support vector machine, Radial basis function networks, road accidents, Road safety, signal classification, Stress, stress classification, Support vector machine classification, Support vector machines, SVM, SVM classifier
Campus : Coimbatore
School : School of Engineering
Center : Computational Engineering and Networking
Department : Computer Science, Electronics and Communication
Year : 2014
Abstract : Classification of stress is imperative especially with regard to automobile drivers since stress level of the driver forms a major factor for accidents. This paper deciphered the classification of stress of automobile drivers using Radial Basis Function Kernel Support Vector Machine (SVM) classifier. The nonlinear separation of features in feature space was deciphered by this kernel trick. Pertinent feature extraction was done from ECG and EMG signals of the driver. Features extracted intuitively showed correlation with stress. This was made solid after getting a high classification accuracy of 100% using SVM using 10 fold cross validation. SVM performance was compared with that of kNN classifier and cross validation showed that kNN had only 81.26, 62.13 and 88.93% of classification rate, sensitivity and specificity where for SVM these parameters were 100%.
Cite this Research Publication : Dr. Soman K. P., Sathiya, A., and Suganthi, N., “Classification of Stress of Automobile drivers using Radial Basis Function Kernel Support Vector Machine”, in International Conference on Information Communication and Embedded Systems (ICICES2014), 2014.