Physiological Detection of Anxiety

Anxiety detection from physiological signal has great significance in the healthcare application. Anxiety has
negative valence and it keeps individual concentrated on
negative emotions. Physiological features of Electrocardiogram signal quantify the anxiety response in individuals. Pan Tompkins algorithm is used for detecting the R peaks in the signal and then determines the interbeat intervals or R-R intervals. Support vector machine (SVM) and Kalman filter are used to detect anxious and non-anxious data. System performance is evaluated on ECG signals from the database for both methods. The system detects physiological changes related to the anxiety stimuli. From the results it can be concluded that the system can detect anxiety state with an accuracy of 71.1 % and 69.35 % using SVM classifier and Kalman filter respectively. The system detects anxiety and it can support individuals with anxiety disorders.