Mental stress detection using heart rate variability and morphologic variability of EeG signals

Mental stress is one of the major risk factors for many diseases such as hypertension, coronary artery disease, heart attack, stroke, even sudden death. Conventionally, interviews, questionnaires or behavior observation are used to detect mental stress in an individual. In our study, we have investigated objective characteristics, like various short term heart rate variability (HRV) measures and morphologic variability (MV) of ECG signals for detecting mental stress. A number of HRV measures were investigated, both in time domain and frequency domain. Experiments involved 16 recordings of ECG signals during mental stress state and normal state, included in a multi-parameter data base on physionet.org portal. Results revealed that the HRV measures named mHR, mRR, normalized VLF/LF/HF, difference between normalized LF and normalized HF, and SVI are effective metrics for mental stress detection. Better results were obtained by using MV analysis and a decision-support module based on both methods, HRV and MV.