HNS-RE2SD

Permanent URI for this communityhttp://dspace.hns-re2sd.dz:4000/handle/123456789/1

Higher National School of Renewable Energies, Environment and Sustainable Development

Browse

Filters

20242

Settings

Subject: search.filters.subject.Aritificial Intelligence

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    AI-Based Security System Using YOLO Algorithms
    (2024-06-15) CHAHI Kamel Eddine
    Throughout the first chapter of this thesis, we have presented a comprehensive examination of security systems, addressing crucial considerations essential for designing robust solutions. We have highlighted key challenges faced by these systems, notably human errors leading to the oversight of significant events, the inherent complexity of system architecture, and the difficulties encountered during system extension and updates. This study offers an effective solution to the aforementioned challenges. By utilizing an AI card such as the Nvidia Jetson Nano, existing security camera systems can be transformed into intelligent and robust entities. This integration enhances their ability to process relevant events with high accuracy while potentially eliminating the need for additional equipment, replaced instead by the fusion of AI algorithms with the visual data captured by the cameras. The YOLOv8 model was trained using a large dataset downloaded from the Roboflow platform. Its images are labeled with seven classes: customer bagpack, null, product, product-picked, regular, shoplifting, and shopping cart. With a large configuration (43.7M parameters), we have obtained a good accuracy (0.9) and satisfactory convergence. However, during testing in different retail environments, challenges arose in accurately detecting certain products.
  • No Thumbnail Available
    Item
    Energy Monitoring
    (Higher National School of Renewable Energies, Environment and Sustainable Development, 2024-06-15) ABD ELMERAIM Raziqa
    This dissertation describes a new AI-based energy conservation solution. It has built-in advanced sensors, wireless connectivity, and AI algorithms that monitor and optimize energy consumption in real time. The device achieves huge energy savings by providing device-level monitoring, predictive analytics, and automated optimization. This holistic solution provides a comprehensive and proactive method for efficient energy management. Real-time energy consumption patterns give users the information they need to make decisions. Predictive analytics that accounts for fluctuations in energy demand allows for proactive adjustments, while automatic optimization constantly focuses on efficiency goals, ensuring that these goals are met with significant reductions in energy consumption. In addition to immediate energy savings, the integrated system promotes sustainable practices and helps reduce carbon footprints. Seamless integration of advanced sensors, predictive analytics, and automatic tuning. This manuscript presents an innovative energy conservation solution that incorporates artificial intelligence. It does this by monitoring and optimizing energy consumption in real-time using advanced sensors, wireless connectivity, and AI-based algorithms. Through device-level monitoring and predictive analytics, energy savings are dramatic. It is a comprehensive and proactive program for efficient energy management. Consumers receive real-time insights into their energy consumption patterns, enabling them to make informed decisions. Predictive analysis of consumer data can anticipate surges or dips in demand, enabling proactive demand management, while automated optimization ensures that the system dynamically achieves efficiency targets over time, delivering significant energy savings. In addition to immediate energy savings, the integrated system promotes sustainable practices and reduces carbon footprints through the seamless integration of advanced sensors, predictive analytics, and automatic tuning. Through the integration of advanced sensors and AI algorithms, our energy conservation solution has yielded tangible results in optimizing power consumption across multiple dimensions. By accurately measuring active, reactive, and apparent power, our system provides comprehensive insights into energy usage patterns, enabling users to make informed decisions in real time. The seamless integration of our AI model with an intuitive application empowers users to proactively manage their energy consumption, leading to substantial reductions in overall power usage. Across various applications, from industrial to residential settings, our solution has consistently delivered significant energy savings, surpassing traditional energy management methods. By harnessing the power of AI and precise power measurement capabilities, our solution promotes efficiency and drives sustainability, contributing to a greener and more resource-efficient future.