Development of a Real-time System for Detecting Driver"s Cognitive Load using Multi-Layer Artificial Neural Network on ECG Signals

Abstract

Objective: This study developed a real-time system to detect driver"s cognitive load using a multi-layer artificial neural network (MANN) based on electrocardiography (ECG) signals. The real-time system was aimed at classifying driver"s status into either normal or overload.Background: Driving with cognitive load is considered as one of significant factors for traffic accidents. Thus, an early detection of this risky status while driving is needed to prevent vehicle accidents.Method: The ECG signals of this study were measured from 22 participants who performed simulator-based driving experiment under two different conditions (1: normal driving, 2: overload driving (driving while doing a two-back task or an arithmetic task)). A real-time detection system was developed using MANN on the ECG signals and its effectiveness was evaluated for two new participants who drove under the two driving conditions.Results: The MANN model used for the real-time detection system showed perfect accuracy (100%), sensitivity (100%), and specificity (100%) for both of the training and testing data sets. In addition, the proposed real-time detection system successfully detected the change of participant"s status with a reasonable time delay (mean = 4.5 seconds).Conclusion: This study demonstrated that the ECG signals can be used as a biometric measure for the detection of the driver"s cognitive status in real-time.Application: The proposed detection system would be useful for the development of an intelligent vehicle that can provide timely interventions and/or warnings at the early onset of cognitive overload.