WIRELESS SENSOR NETWORK-BASED REAL-TIME INTELLIGENT TRANSPORTATION SYSTEM FOR STORAGE CONDITIONS ASSESSMENT IN SUPPLY CHAIN MANAGEMENT

Abstract

The research delves into various aspects of an intelligent transportation system, including optimizing coverage paths, assessing storage conditions for fruits and vegetables, enhancing transportation efficiency and predicting risks within the supply chain. India has the highest rate of traffic accidents in the world. Accounting for 11% of global road accidents. By analyzing this data, decisions have been made to enhance pedestrian safety. Furthermore, computer vision technology has been employed for pedestrian image analysis within the context of intelligent transportation. A novel itinerary planning system called the Data Gatherer (IPS-DG) has been developed to optimize energy consumption and route length for vehicles within wireless sensor networks. This solution surpasses existing protocols, improving energy efficiency, path planning, and network lifespan. Shifting our attention to the storage conditions of fruits and vegetables, an Internet of Things (IoT)-enabled sensor network has been integrated into the intelligent transportation system to monitor crucial environmental parameters during the transportation of fruits and vegetables within the supply chain network. We have developed a real time system that achieves an impressive 98.05% accuracy. This approach paves the way for future research aimed at minimizing losses in the fruits and vegetables in the supply chain. Furthermore, the research explores an integrated model for assessing supply chain risks. A machine learning-based model evaluates and predicts risks throughout the supply chain, contributing to effective risk management. The model incorporates algorithms such as support vector machines, random forests, decision trees, and others, achieving an impressive accuracy rate of 99%. In summary, our research contributes to improving pedestrian safety, transportation efficiency, storage condition assessment, and risk management within complex supply chain networks. These findings provide valuable insights for future research directions across diverse domains.