Unsupervised Deep Learning Approaches for Anomaly Detection in IoT Data Streams

The proliferation of IoT devices is primarily responsible for the data deluge that has engulfed multiple industries. Nevertheless, due to the high dimensionality and complexity of IoT data streams, anomaly detection remains a significant challenge. This suggests that an unsupervised deep learning st...

Full description

Saved in:
Bibliographic Details
Published in2023 4th International Conference on Smart Electronics and Communication (ICOSEC) pp. 438 - 443
Main Authors Suresh, Helina Rajini, Neelaveni, R., Kumar, Bonda Kiran, Arunadevi, R., G, Indhumathi, Varun, M
Format Conference Proceeding
LanguageEnglish
Published IEEE 20.09.2023
Subjects
Cybersecurity
Data Streams
Deep learning
Internet of Things
Internet of Things (IoT)
Pattern recognition
Real-time systems
Reliability
Security
Sensor Data
System performance
Online AccessGet full text

Cover

More Information
Summary:The proliferation of IoT devices is primarily responsible for the data deluge that has engulfed multiple industries. Nevertheless, due to the high dimensionality and complexity of IoT data streams, anomaly detection remains a significant challenge. This suggests that an unsupervised deep learning strategy could be used to identify anomalies in IoT data streams. Instead of relying on labeled data, this method employs deep neural networks, which can be trained to recognize anomalies and comprehend complex patterns. Experiments are conducted on a real-world IoT dataset to evaluate the efficacy and accuracy of the proposed method. The results demonstrate its proficiency in detecting anomalies in IoT data streams, paving the way for a safer, more reliable Internet of Things. Using unsupervised deep learning techniques, the method provides a practicable solution to the age-old problem of IoT anomaly identification.
DOI:10.1109/ICOSEC58147.2023.10276180