Robust Sensor Fault Detection in Wireless Sensor Networks Using a Hybrid Conditional Generative Adversarial Networks and Convolutional Autoencoder

In the rapidly growing realm of the Internet of Things (IoT), reliance on sensor-generated data has become crucial for the operation of multiple services and systems. As essential components of these systems, wireless sensor networks (WSNs) are installed in a wide range of diverse and often harsh en...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE sensors journal Ročník 25; číslo 8; s. 13912 - 13926
Hlavní autoři: Khan, Rehan, Saeed, Umer, Koo, Insoo
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 15.04.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Accuracy
Artificial neural networks
Classification
Conditional generative adversarial networks (Conditional GANs)
convolutional autoencoder (CAE)
Fault detection
Faults
Feature extraction
Generative adversarial networks
Gramian angular field (GAF)
Internet of Things
Monitoring
Network security
Reliability
sensor faults
Sensor systems
Sensors
Synthetic data
Temperature sensors
Wireless sensor networks
wireless sensor networks (WSNs)
ISSN:1530-437X, 1558-1748
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In the rapidly growing realm of the Internet of Things (IoT), reliance on sensor-generated data has become crucial for the operation of multiple services and systems. As essential components of these systems, wireless sensor networks (WSNs) are installed in a wide range of diverse and often harsh environments. However, these networks are highly prone to a range of faults, including software bugs, communication failures, and hardware malfunctions. Such issues can lead data to data being transmitted incorrectly, endangering the security, reliability, and economic stability of the systems they support. Addressing the challenge of sensor fault detection, we propose a novel hybrid technique to enhance the classification of sensor fault data in WSNs. Our method leverages a publicly available dataset of temperature sensor readings to generate synthetic data by using conditional generative adversarial networks (GANs). These synthetic samples closely resemble common temperature sensor data despite the introduction of artificial sensor faults in WSNs, including hardover, drift, spike, erratic, and stuck faults. In order to capture the temporal dependencies in time-series data, we transform the sensor readings into Gramian angular field (GAF) images, retaining the temporal structure. These GAF images are then processed using a convolutional autoencoder (CAE) to extract rich feature representations, followed by a three-layer artificial neural network (ANN) for the multiclass classification of sensor faults. Our proposed method not only addresses the challenges of data scarcity and imbalance but also enhances accuracy in sensor fault detection. The proposed method demonstrates high accuracy, <inline-formula> <tex-math notation="LaTeX">F1 </tex-math></inline-formula>-score, recall, and sensitivity, achieving 95.93%, 95.84%, 95.88%, and 95.88%, respectively.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1530-437X
1558-1748
DOI:10.1109/JSEN.2025.3547736