Recommendation systems for decision support in Internet of Things (IoT) environments play a key role in the development of effective intelligent solutions, providing adaptive cybersecurity management and resource optimization for IoT platforms. Special attention is given to the characteristics of IoT data, which are generated from numerous sources such as sensors, communication devices, and other infrastructure elements, resulting in large volumes of heterogeneous data. This study investigates modern recommendation methods, including collaborative filtering, content-based approaches, deep neural networks, and ensemble learning, as well as their effectiveness in real-world IoT environments. Particular focus is placed on challenges related to algorithm scalability, performance, and energy optimization in low-power devices. The aim of this research is to develop an adaptive recommendation model to support decision-making in IoT environments with a high level of cybersecurity. To achieve this, the study analyzes recent scientific research and solutions in the field of IoT and recommendation systems, examines contemporary platforms implementing similar approaches, identifies technologie
📖 افتح في inklap 🔗 DOI 📮 اطلب بحثاً