The rapid proliferation of Internet of Things (IoT) devices has fundamentally transformed environmental and infrastructure monitoring paradigms. This paper presents a comprehensive IoT-based smart monitoring system that integrates heterogeneous sensor technologies - including temperature, humidity, air quality, motion, vibration, and pressure sensors - with an adaptive data fusion and anomaly detection framework. The proposed system employs a Long Short-Term Memory (LSTM)-based deep learning model augmented with Kalman filtering for real-time signal processing, achieving a detection accuracy of 97.8% and a false alarm rate of only 1.4%. A 90-day deployment across 124 sensor nodes in a smart building environment validates the practical effectiveness of the system. Comparative analysis demonstrates that the proposed approach outperforms existing threshold-based, statistical, and classical machine learning methods across all evaluated performance metrics.
Sobirjonova et al. (Sun,) studied this question.