IOT-BASED ANOMALY DETECTION WITH ESP32 AND THINGSPEAK INTEGRATION

Abstract

  Machine learning (ML) and deep learning (DL) are often used techniques for detecting anomalies (AD). Anomaly detection in Internet-connected devices is crucial due to the significant rise in their numbers, the increasing need for IoT devices in various settings, and the shift towards smart infrastructure and the Industrial IoT (IIoT). This paper provides a comprehensive overview of anomaly detection techniques specifically designed for sensor networks and the Internet of Things (IoT). This paper provides a clear definition of the term "anomaly" and examines many sources that offer similar meanings. The objective of this paper is to detect and classify anomalies of data generated by wireless sensor networks in which we consider different kinds of sensors like DHT11, Moisture sensor, Gas sensor, and LDR these kinds of sensors are used which play an important role in home appliances. Create a WSN node using ESP32 and load data on ThingSpeak. In this study, we discuss the main concerns and difficulties encountered when applying deep anomaly detection approaches to resource-constrained devices in real-world IoT scenarios.