A Dual-Optimized Framework for AI-Driven Data Generation and Secure Internet of Vehicles Network Integration

The rapid evolution of Artificial Intelligence (AI), particularly in robotics and deep learning, has unlocked new opportunities for autonomous data generation within intelligent vehicular networks. This study presents a Comparative Study on Automatic Data Generation Optimization Technology (CS-ADGOT). This dual-optimized framework combines robotic precision with Convolutional Neural Network (CNN)-based adaptive learning to enhance both data synthesis and secure communication in Internet of Vehicles (IoV) environments. Unlike traditional approaches, CS-ADGOT simultaneously supports (i) structured acquisition and generation of high-dimensional Internet of Things (IoT) data, (ii) automated real-time vehicular interaction through robotic modules, and (iii) AI-driven optimization for network efficiency and security. The framework was rigorously evaluated against advanced baselines, including the Robotic Multi-Goal Optimization Technique (RMGOT), the Deep Learning-based Dual-Goal Optimization Technique (DL-DGOT), the Adaptive Multi-Goal Optimization Technique (AMGOT), and CNN-based models, using metrics such as accuracy, recall, specificity, and miss rate. Experimental results highlight CS-ADGOT's superiority, achieving up to 94.0% accuracy, 95.68% recall, 98.01% specificity, while reducing miss rates to just 2%. Furthermore, CS-ADGOT converges faster and produces higher-quality synthetic IoV data than competing methods, underscoring its potential as a reliable, adaptive, and secure solution for next-generation intelligent mobility systems.