Detecting Anomalies within Smart Buildings using Do-It-Yourself Internet of Things

TL;DR

This paper presents methods for real-time anomaly detection in smart buildings using DIY IoT devices, emphasizing data collection, preprocessing, and handling diverse sensor data for improved cyber-attack detection.

Contribution

It introduces a comprehensive approach to anomaly detection in smart buildings with DIY IoT sensors, including data collection, preprocessing, and handling multi-rate sensor data.

Findings

Effective anomaly detection techniques identified

Challenges in multi-rate sensor data addressed

Strategies for data preprocessing proposed

Abstract

Detecting anomalies at the time of happening is vital in environments like buildings and homes to identify potential cyber-attacks. This paper discussed the various mechanisms to detect anomalies as soon as they occur. We shed light on crucial considerations when building machine learning models. We constructed and gathered data from multiple self-build (DIY) IoT devices with different in-situ sensors and found effective ways to find the point, contextual and combine anomalies. We also discussed several challenges and potential solutions when dealing with sensing devices that produce data at different sampling rates and how we need to pre-process them in machine learning models. This paper also looks at the pros and cons of extracting sub-datasets based on environmental conditions.