Evaluation of P300 based Lie Detection Algorithm

Lie detection mechanism is used to evaluate the ethical and moral values of people. In general, these moral and ethical values are difficult to determine. Earlier technique like polygraph does not provide accuracy in determining mental behaviour. Lately, it is possible to study psychological response of a person using electroencephalogram (EEG). Based on this, we develop a standalone solution that can detect brain signals using EEG. To this end, we extract the desired features from the brain signals acquired through sixteen electrodes using various extraction techniques. Then, we implement linear discriminant analysis (LDA) classification technique to differentiate the positive and negative samples from the signals obtained from sensors in order to achieve a decision for either guilty subject or innocent subject accordingly. The whole work is designed with the help of MATLAB and Xilinx tool. For efficiency, the whole system is implemented on FPGA. The amount of correct deception detection in guilty and innocent subjects are 85%. It is easy and more convenient approach than other previously used methods.