Data-driven approach for effective fatigue detection in drivers during driving events

Abstract

The effectiveness of transportation and the safety of the road depend heavily on drivers during driving events. The way people drive, and the likelihood of accidents or other occurrences may both be strongly impacted by their actions and behaviors. Promoting safe and sensible driving behaviors requires an understanding of the traits and variables that affect drivers during driving incidents. The rising number of traffic accidents highlights the critical necessity to rein in and lessen the prevalence of careless driving. One of the most common causes of these serious mistakes is drowsiness while driving. To combat this problem, algorithms have been created to identify signs of driver weariness and sound an alarm. The developed algorithms have a serious flaw in their accuracy, and it also takes too long to identify driver drowsiness before alerting them. Timeliness and precision are two of the most important factors in preventing traffic mishaps. Multiple datasets have been utilized to improve methods for identifying signs of exhaustion or drowsiness. These data were acquired either through video streaming records of the driver's behavior or from the driver's brain electroencephalogram (EEG) readings. In order to create a high-performance fatigue detection system, this research designs a novel firefly-integrated optimum cascaded convolutional neural network (FI-OCCNN). The suggested approach offers the greatest detection accuracy among the existing classifiers, up to 98.75%. The studies further show that the recommended methods provide the greatest level of detecting precision with the quickest testing time (TT) compared to all other existing and successful tiredness detection techniques.