Traffic lights play an important role in efficient traffic management, especially in crowded cities. Optimizing traffic helps to reduce crowding, save time, and ensure the smooth flow of traffic. Metaheuristic algorithms have a proven ability to optimize smart traffic management systems. This paper investigates the effectiveness of two metaheuristic algorithms: particle swarm optimization (PSO) and grey wolf optimization (GWO). In addition, we posit a hybrid PSO-GWO method of optimizing traffic light control using IoT-enabled data from sensors. In this study, we aimed to enhance the movement of traffic, minimize delays, and improve overall traffic precision. Our results demonstrate that the hybrid PSO-GWO method outperforms individual PSO and GWO algorithms, achieving superior traffic movement precision (0.925173), greater delay reduction (0.994543), and higher throughput improvement (0.89912) than standalone methods. PSO excels in reducing wait times (0.7934), while GWO shows reasonable performance across a range of metrics. The hybrid approach leverages the power of both PSO and GWO algorithms, proving to be the most effective solution for smart traffic management. This research highlights using hybrid optimization techniques and IoT (Internet of Things) in developing traffic control systems.

Gesture recognition has emerged as a promising approach to enhance human-machine interaction, especially in robotics and assistive devices. This study presents a real-time gesture-controlled robotic system that combines deep learning and machine learning techniques to recognize hand gestures and map them to servo motor movements. A convolutional neural network (CNN) was used to classify six predefined hand gestures: a closed fist and five individual finger extensions. To enhance classification accuracy and generalization, CNNs are tuned using hyperparameter tuning techniques, such as Particle Swarm Optimization (PSO), Grey Wolf Optimization (GWO), and Brown Bear Optimization (BBO). These methods efficiently explore the hyperparameter space—such as learning rate, filter size, and batch size—reducing manual trial and error in control. Among these proposed models tested, the BBO-CNN has been achieved the highest performance with a classification accuracy of 99.98%, outperforming both PSO-CNN (99.89%) and GWO-CNN (99.44%). The model CNN without optimization achieved an accuracy of 97.50%. The combination of advanced deep learning models and embedded control demonstrates the feasibility and effectiveness of gesture-based robotics applications.