No abstract

No abstract

Alcoholism is a socio-economical syndrome in which human being may lose his/her health and wealth. The paper reports a novel approach for the rapid detection of alcoholism using Electroencephalogram (EEG) sensor. The proposed method employs absolute gamma band power used as a feature and ensemble subspace K-NN used as a classifier to categorize alcoholics and normal subject. Furthermore, an Improved Binary Gravitational Search Algorithm (IBGSA) is reported as an optimization tool to select the optimum EEG channels for the rapid screening of alcoholism. The results obtained by the proposed method are compared with the optimization algorithms like a genetic algorithm (GA), binary particle swarm optimization (BPSO), and binary gravitational search algorithm (BGSA). Fitness function for these optimization algorithms is evaluated using accuracy obtained from ensemble subspace K-NN classifier. The proposed IBGSA methodology provides a detection accuracy of 92.50% with only 13 EEG channels. Thus, it is the best candidate to bridge the trade-off of detection accuracy and the number of channels used for detection.

Paper contains emotion recognition system based on facial expression using Geometric approach. A human emotion recognition system consists of three steps: face detection, facial feature extraction and facial expression classification. In this paper, we used an anthropometric model to detect facial feature points. The detected feature points are group into two class static points and dynamic points. The distance between static points and dynamic points is used as a feature vector. Distance changes as we track these points in image sequence from neutral state to corresponding emotion. These distance vectors are used for input to classifier. SVM (Support Vector Machine) and RBFNN (Radial Basis Function Neural Network) used as classifier. Experimental results shows that the proposed approach is an effective method to recognize human emotions through facial expression with an emotion average recognition rate 91 % for experiment purpose the Cohn Kanade databases is used.

No abstract