Artificial Intelligence (AI) and Large Language Models (LLMs) have significantly transformed knowledge management by enabling intelligent, context-aware, and automated information access. However, standalone LLMs often suffer from limitations such as outdated knowledge, hallucinated responses, lack of domain-specific expertise, and limited transparency, reducing their reliability in enterprise and research applications. Retrieval-Augmented Generation (RAG) has emerged as an effective solution by combining language models with external knowledge retrieval, allowing responses to be generated using up-to-date and relevant information. This study proposes a comprehensive Retrieval-Augmented Generation framework for intelligent knowledge management systems. The framework integrates document acquisition, preprocessing, semantic embedding generation, vector database indexing, document retrieval, prompt augmentation, LLM-based response generation, response validation, and continuous knowledge base updates. It supports diverse knowledge sources, including enterprise databases, technical documents, digital libraries, and research repositories, while incorporating sparse, dense, hybrid retrieval, and neural reranking techniques to improve retrieval accuracy. The proposed framework is evaluated using retrieval precision, recall, F1-score, response relevance, latency, grounding accuracy, and user satisfaction. Results demonstrate improved semantic understanding, reduced hallucinations, enhanced factual correctness, and real-time knowledge updates compared with conventional keyword-based knowledge management systems. The study also discusses future directions, including multimodal RAG, graph-enhanced retrieval, federated knowledge management, continual learning, and autonomous enterprise knowledge assistants, establishing RAG as a robust foundation for trustworthy and intelligent knowledge-driven AI systems.
Louis Pouzin, J. Arsac· International Journal of Mod...· 0 citations
Machine vision has become a key technology in modern industrial automation, enabling fully automated quality inspection in robotic manufacturing systems. Unlike traditional human inspection methods, machine vision offers higher accuracy, consistency, speed, and lower operational costs. These systems use cameras, lighting, lenses, image processing, pattern recognition, and AI techniques to detect defects, verify dimensions, classify products, and monitor manufacturing processes in real time. This survey reviews machine vision-based quality inspection methods in robotic manufacturing up to 2019, covering major applications in industries such as automotive, electronics, aerospace, pharmaceuticals, and food processing. It highlights advancements in feature extraction, defect detection algorithms, classification models, and robotic integration frameworks. The study shows that machine vision significantly improves inspection accuracy, reduces cycle time, and enhances manufacturing consistency, while also discussing challenges such as illumination changes, computational complexity, and system adaptability. Overall, machine vision plays a vital role in smart manufacturing and Industry 4.0 production systems.
Louis Pouzin, J. Arsac· International Journal of Int...· 0 citations
Modern distributed data engineering platforms process massive and diverse datasets, making efficient resource scheduling increasingly challenging. Traditional scheduling algorithms struggle to adapt to dynamic workloads and heterogeneous computing environments, resulting in poor resource utilization and increased execution time. This paper proposes an AI-Based Resource Scheduling Framework that integrates workload prediction, intelligent resource allocation, adaptive scheduling, and continuous performance monitoring. By leveraging machine learning and reinforcement learning, the framework dynamically optimizes scheduling decisions based on workload characteristics, resource availability, and real-time system feedback. Experimental results demonstrate improved resource utilization, reduced scheduling latency, enhanced scalability, lower operational costs, and better workload balancing compared to conventional scheduling approaches, making the framework well-suited for cloud-native and large-scale distributed data engineering environments.
Louis Pouzin· International Journal of Dat...· 0 citations