Classification of Mental Workload Based on Multiple Features of ECG Signals

Abstract Mental Workload (MW) has become an important problem in the design of man-machine systems, so its related detection and analysis technology has aroused extensive interest and concern. Researches show electrocardiogram (ECG) physiological signals can be an appropriate indicator to reflect the level of human MW. When the operator is in the state of high MW, the cardiac load will increase, and the period and shape of ECG signals accordingly change. Heart Rate Variability (HRV) is the most widely used ECG feature to assess the MW. However, its classification precision is not high enough. In order to improve this, multiple features of ECG signals are extracted to classify the MW in this paper. Besides the RR interval feature of HRV, the other three features, T and P wave power, QRS complex power and Sample Entropy (SampEn) of ECG waveform, are further extracted and applied to assess MW. The Support Vector Machine (SVM) is used to establish the classification model, and the grid search and cross-validation algorithm are used to optimize its parameters. The results show the MW classifier based on multiple features of ECG signals can evidently improve the classification accuracy. This will be helpful to realize a real time and online MW classification using ECG data.