<![CDATA[Internet of Things (IoT) real-time monitoring systems commonly rely on centralized cloud-based architectures for data processing and management. Although cloud computing offers flexibility and scalability, its dependency on remote servers often leads to latency issues, especially in local network environments with limited bandwidth and unstable internet connectivity. High latency can negatively affect system responsiveness and reduce the effectiveness of real-time decision-making. This study aims to implement an edge intelligence architecture to reduce latency in local Internet of Things-based monitoring systems. The proposed approach shifts part of the data processing and decision-making tasks to edge nodes located closer to data sources. Sensor data are processed locally using threshold-based analysis before being transmitted to the central server for storage and visualization purposes. System performance is evaluated by comparing latency and response time between a fully cloud-based IoT system and an edge intelligence-based system. The experimental results indicate that local data processing at the edge significantly reduces latency and improves system reliability, particularly in local network conditions. Therefore, the edge intelligence architecture is considered an effective solution for enhancing the performance of IoT monitoring systems that require fast and reliable responses.]]>
Copyrights © 2026
