Madheswaran Muthusamy

This research examines the use of Deep Q-Networks (DQNs) for the optimization of dynamic processes in intelligent manufacturing systems. Utilizing real-time sensor data and adaptive decision-making, DQNs optimize essential manufacturing parameters, including production rate, energy consumption, and equipment utilization, to improve overall operational efficiency. A case study demonstrates the application of a DQN-based model in a manufacturing setting, resulting in a 15% reduction in production time and a 12% drop in energy consumption relative to conventional rule-based optimization techniques. The model's adaptability to varying conditions, such as demand variations and equipment failures, was assessed by simulation, revealing a 20% enhancement in system responsiveness and an 18% increase in throughput. The findings underscore the efficacy of reinforcement learning in enhancing smart manufacturing processes, delivering real-time, data-driven insights that markedly surpass traditional optimization methods. The results indicate that incorporating DQNs into industrial systems can significantly enhance operational efficiency and resource management, hence advancing Industry 4.0.

A systematic categorization approach for video indexing is presented in this paper. The amount of multimedia information that can be accessed over the internet continues to expand exponentially. Due to this growth and development of multimedia on the internet, particularly videos, there has been a rise in the need for video retrieval. The goal of this work is to discover subsets of characteristics that are suitable for indexing or categorizing video content. The features chosen from the frames of the video have dominant texture characteristics. Several statistical features have been applied for better performance with decision tree classification. The investigation included 1000 videos from different video contents, such as news, cartoon, advertisements, movies, and sports categories. Results show that the overall misclassification rate percentage was below 3%. The capability of indexing the video contents indicates the real power of the proposed system, which can enhance existing indexing services, thereby enriching the tools that are available for video indexing.