Real-time automatic detection of accelerative cardiac defense response

Cardiac Defense Response (CDR) is a basic psychophysiological response that precedes the emotion of fear. In the context of on automatic emotion recognition, it is a relevant effort the definition of algorithms to identify the CDR because if it is maintained for long periods of time can pose to health risk, hinder the normal functioning of the involved organs and eventually develop into severe psychophysical disorders, such as hysteria and schizophrenia. Therefore, providing tools for automatic identification of this defense mechanism can help psychologists in understanding the patient's mental and health status. This work proposes a novel algorithm specifically designed to detect the CDR in real-time by analyzing the ECG signal acquired by means of a wearable sensor and processed by a personal mobile device. Hence, a key advantage of the proposed approach is that it is suitable for embedded implementations on current commercial wearable sensing and mobile computing devices. It is based on the extraction of specific features from a signal directly generated from the ECG which are compared against an ad-hoc computed reference CDR template. The algorithm has been tested on real ECG traces, a number of them containing full activation of the CDR pattern, and the results obtained show 67% sensitivity, 83% specificity, and 80% precision.