An efficient AI model for highway vehicle speed limit violation detection and real-time law-enforcing functionality

Abstract

Traffic control at toll exit booths is unable to promptly apprehend speeders. Therefore, speeders get more self-assurance for overspeeding. According to different studies, data loss and transportation errors are significant challenges for traffic management systems. It significantly impacts data retrieval and anticipated outcomes. The integrity of data collection may be impacted by partial or whole data loss due to distinct transit problems. Consequently, due to the distorted data, the accuracy of detecting the overspeeding cars or drivers may be disrupted. However, the current literature fails to offer any integrated approach to resolve such issues. Therefore, this study offers an improved method for educating drivers against speeding. A challan is automatically issued following three highway speed offenses. It notifies the motorist before issuing the citation. The neighboring integrated network devices relay challan information to the traffic control office as the motorist passes the toll booth, traffic signal, or roadside site. Consequently, enhancing the psychological influence of exit booth enforcement on offenders to ensure compliance with payment. These psychological impacts dissuade speeders and augment fines. This project essentially involves a real-time, Internet of Things (IoT)-based artificial intelligence (AI) methodology for mitigating highway speeding. Enhanced simulated annealing (SA) improves the detection of speed limit violations and ensures data integrity. It features an effective error control mechanism to reduce transmission errors and data loss. The experimental results indicate that it offers greater predictive accuracy for speeds, displaying improved precision, recall, F1-score, and area under the ROC curve (AUC) score relative to current methodologies. Its power to produce improved information processing and diminished cyclomatic complexity (CC) confirms its temporal efficiency. The diminished information percentage, along with packet loss and an increased signal-to-noise ratio (SNR) value, illustrates its capacity to enhance data integrity.