Intelligent Connectivity in Cyber-Physical and Social Networks for Optimizing Smart Mobility and Traffic Management
Dr. M. RajaProfessor and Head, Department of Artificial Intelligence and Data Science, Paavai Engineering College, Namakkal, India. drrajameyyanrvr@gmail.com0009-0003-5551-6098
Dr. P. Sundara Bala MuruganAssociate Professor, Department of Management Studies, St. Joseph’s Institute of Technology, Chennai, Tamil Nadu, India. sundarabalamurugan@gmail.com0009-0002-7440-0181
Dr. M. RajapriyaAssistant Professor, Department of Management Studies, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, Tamil Nadu, India. rajapriya.m19@gmail.com0000-0003-3757-2179
Komiljon AynaqulovDoctoral Researcher, Department of Agricultural Product Processing Technologies, Gulistan State University, Uzbekistan. komiljonaynaqulov@gmail.com0009-0007-1851-3372
Mushtariy AkhmedovaPhD Student, Jizzakh State Pedagogical University, Uzbekistan. mushtariy.axmedova@jdpu.uz0009-0002-8559-4946
Dr. R. UdayakumarProfessor & Director, Kalinga University, India. rsukumar2007@gmail.com; directoripr@kalingauniversity.ac.in0000-0002-1395-583X
Keywords: Traffic Management, Cyber-Physical, Smart Mobility, Social Networks, Traffic Prediction, Aquila Optimizer Tuned Deep Residual Network (AO-DeepResNet).
Abstract
With the rapid development of urban populations and growing traffic congestion, intelligent connectivity in cyber-physical and social networks is essential for improving smart mobility and traffic management. This research establishes an advanced approach to optimizing smart mobility and traffic management systems by incorporating intelligent connectivity within cyber-physical and social networks. The research proposes a novel method calledAquila optimizer tuned deep residual network (AO-DeepResNet), which associates the Aquila optimizer (AO) with deep residual neural networks (DeepResNet) for optimizing smart mobility and traffic management. AO is used to enhance the parameters of DeepResNet, extensively improving the traffic prediction accuracy and mobility management. The dataset comprises real-time traffic patterns, vehicle telemetry, ride-sharing demand, public transport efficiency, social media sentiment, and environmental features. The findings demonstrate that the proposed method AO-DeepResNet outperforms existing methods in terms of F1 score (97.21%), and accuracy (98.5%). Therefore, the proposed AO-DeepResNet method significantly enhanced the smart mobility and traffic management.