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

Mirza Akhi Khatun, Mangolika Bhattacharya, Ciaran Eising, Lubna Luxmi Dhirani

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This research develops a new method to detect anomalies in time series data using Convolutional Neural Net-works (CNNs) in healthcare-IoT. The proposed method creates a Distributed Denial of Service (DDoS) attack using an loT 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.

Original languageEnglish
Title of host publicationProceedings - 2024 IEEE 12th International Conference on Healthcare Informatics, ICHI 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages522-524
Number of pages3
ISBN (Electronic)9798350383737
DOIs
Publication statusPublished - 2024
Event12th IEEE International Conference on Healthcare Informatics, ICHI 2024 - Orlando, United States
Duration: 3 Jun 20246 Jun 2024

Publication series

NameProceedings - 2024 IEEE 12th International Conference on Healthcare Informatics, ICHI 2024

Conference

Conference12th IEEE International Conference on Healthcare Informatics, ICHI 2024
Country/TerritoryUnited States
CityOrlando
Period3/06/246/06/24

Keywords

  • Anomaly Detection
  • Contiki OS
  • Cooja Simulator
  • Cyberattack
  • DDoS Attack
  • Healthcare-IoT (H-IoT)
  • Wireless Sensor Network (WSN)

Fingerprint

Dive into the research topics of 'Time Series Anomaly Detection with CNN for Environmental Sensors in Healthcare-IoT'. Together they form a unique fingerprint.

Cite this