Time Series Anomaly Detection with CNN for Environmental Sensors in Healthcare-IoT

TL;DR

This paper introduces a CNN-based method for detecting anomalies in environmental sensor time series data within healthcare-IoT, achieving high accuracy in simulated attack scenarios.

Contribution

It presents a novel application of CNNs for anomaly detection in healthcare-IoT environmental sensors, validated through simulation of DDoS attacks.

Findings

92% accuracy in anomaly detection

Effective detection of simulated DDoS attacks

Demonstrates CNN suitability for healthcare-IoT security

Abstract

This research develops a new method to detect anomalies in time series data using Convolutional Neural Networks (CNNs) in healthcare-IoT. The proposed method creates a Distributed Denial of Service (DDoS) attack using an IoT network simulator, Cooja, which emulates environmental sensors such as temperature and humidity. CNNs detect anomalies in time series data, resulting in a 92\% accuracy in identifying possible attacks.