Qualitative and quantitative evaluation of brain activity in emotional stress

Introduction: This paper proposes a new emotional stress detection system usingmulti-modal bio-signals. Since EEG is the reflection of brain activity and is widelyused in clinical diagnosis and biomedical researches, it is used as the main signal.Methods and Materials: We designed an efficient IAPS acquisition protocol toacquire the EEG and psychophysiological signals under picture inductionenvironment (calm-neutral and negatively excited) for participants. Data such as skinconductance (SC), Blood Volume Pulse (BVP), respiratory rate (RR) and EEG werecontinuously recorded through bio-sensors placed on the participant. In order tochoose the proper EEG channels we used the cognitive model of the brain underemotional stress.Results: After pre-processing the bio-signals, linear features were employed toextract the psychophysiological signals and chaotic (or nonlinear) invariants like;fractal dimension by Higuchi’s algorithm, correlation dimension and approximateentropy were used to extract the characteristics of the EEG signals. For emotionalstress detection, Genetic Algorithm (GA) and Elman neural network are applied todesign the emotional stress classifier are investigated. The results show that,classification accuracy with fusion link between EEG and psychophysiologicalsignals was 82.6% using the Elman classifier in two classes from emotional stressspace.Conclusion: Chaotic analysis can be representing good of human brain andbehaviour in emotional stress states. This is a good improvement in results comparedto other similar published researches.