The intelligent decision model for determine the best path of transportation on smart city using random forest algorithm and bayesian optimization (RF-BO)

Abstract

This study investigates various approaches and algorithms in the context of object detection and best path determination for managing vehicular traffic in an urban environment, particularly in Palembang city. This research is a step towards the development of smart city concept. In the object detection analysis, we applied the YOLOv3 method on video footage to identify vehicles, resulting in mAP accuracy rates between 72.72% to 79.35% for both motorcycle and car categories. The total detection accuracy of the model reached 76.03%. Next, we adopted the Random Forest algorithm to classify traffic conditions into three classes: smooth, moderate, and congested. After optimizing the algorithm with Bayesian Optimization, the model accuracy increased from 89% to 92%, while the classification accuracy increased from 91.66% to 92.36%. Results from the application of the A* Heuristic Search algorithm revealed that lane 5 (from SMK PGRI 1 Palembang to Bom Baru Jl Perintis Kemerdekaan Arah Charitas (STMIK MBC)) was selected most frequently in 9 out of 12time trials. The selection of this route was based on an evaluation of traffic levels that tended to be "smooth" and the shortest travel distance compared to other alternative routes. The decision in choosing the optimal path also considers the road width factor, where wider roads have the potential to reduce traffic density and the risk of congestion.