Anomaly Detection for Enhanced Safety in Chemical Warehouses using ESP8266, Sensor Fusion, and Firebase Realtime Database

Chemical warehouses require continuous monitoring of environmental conditions to ensure safety and prevent potential hazards. This paper proposes a real-time anomaly detection system for chemical warehouses using a combination of Internet of Things (IoT) devices, sensor fusion, and Machine Learning (ML). The system leverages an ESP8266 microcontroller to collect data from sensors like DHT22 (temperature and humidity) and MQ-135 (gas concentration). Firebase Realtime Database provides a platform for storing sensor data. An Isolation Forest (IF) model, trained on historical sensor data, identifies anomalies in real time, enabling early detection of potential safety issues. The paper presents the system design, implementation details, and experimental results, demonstrating its effectiveness in anomaly detection for improved chemical warehouse safety.