Machine Learning Based Logistic Decision Support System for Intelligent Vehicles and Transportation Systems

Abstract

One-third of the freight expense is spent on transportation and transport networks, thus significantly impacting the logistics sector's efficiency. Artificial Intelligent logistics strategies are designed to alleviate the impact on metropolitan areas exacerbated by increased freight transport. The city of logistics is widely employed as a modern study area, has a significant social and economic influence, and has extensively explored the key elements and components. Most recent experiments concentrate on traffic management and logistics monitoring, even though no research studies have tried to detect drivers' distractions. Since drivers are one of the major parts of logistic service, this study incorporates existing logistics DSS with the cognitive model for predicting driver distraction. This paper presents a Machine Learning Integrated Decision Support System (MLIDSS) architecture and core components based on simulationoptimization modules to assist the smart logistics DSS with an eye to service delivery driver distraction level. The ML algorithms perform real-time driver distraction predictions for smooth logistics transportation. The viability of such a transportation system is often illustrated in the real world. The findings result in the highest-performing intelligent decision support system compared to existing models.