Design and Implementation of an ML and IoT Based Adaptive Traffic-Management System for Smart Cities

Abstract

The rapid growth in the number of vehicles has led to traffic congestion, pollution, and delays in logistic transportation in metropolitan areas. IoT has been an emerging innovation, moving the universe towards automated processes and intelligent management systems. This is a critical contribution to automation and smart civilizations. Effective and reliable congestion management and traffic control help save many precious resources. An IoT-based ITM system set of sensors is embedded in automatic vehicles and intelligent devices to recognize, obtain, and transmit data. Machine learning (ML) is another technique to improve the transport system. The existing transport-management solutions encounter several challenges resulting in traffic congestion, delay, and a high fatality rate. This research work presents the design and implementation of an Adaptive Traffic-management system (ATM) based on ML and IoT. The design of the proposed system is based on three essential entities: vehicle, infrastructure, and events. The design utilizes various scenarios to cover all the possible issues of the transport system. The proposed ATM system also utilizes the machine-learning-based DBSCAN clustering method to detect any accidental anomaly. The proposed ATM model constantly updates traffic signal schedules depending on traffic volume and estimated movements from nearby crossings. It significantly lowers traveling time by gradually moving automobiles across green signals and decreases traffic congestion by generating a better transition. The experiment outcomes reveal that the proposed ATM system significantly outperformed the conventional traffic-management strategy and will be a frontrunner for transportation planning in smart-city-based transport systems. The proposed ATM solution minimizes vehicle waiting times and congestion, reduces road accidents, and improves the overall journey experience.

Evaluating the Influence of Data Entropy in the Use of a Smart Equipment for Traffic Management at Border Check Point

“…In other cases, the development of IoT components dedicated to the automotive industry allows the creation of system architecture that encompasses the integration of an IoT sensor. The traffic management equipment developed using this technology allows the implementation of reliable algorithm for data acquisition and processing [9][10][11].…”

Improved Mayfly Optimization and LightGBM Classifier for Smart City Traffic Prediction

“…The mode position of the mayfly of a grouped data is given in the following equation (9) pmode = {Calculate M using eq. (8), i f data is multiclassvel with max. f requency, i f data is ungrouped (9) The updated velocity will be calculated using the following equation (10).…”

Machine learning based IoT system for secure traffic management and accident detection in smart cities

“…There are 1.35 million mortality cases reported each year globally, accounting for 2.2 percent of the global population ( Lilhore et al, 2022 ). Each year, more deaths and instances of permanent impairment are due to everyday traffic accidents.…”