Advanced Structures & Composites Center

Published: 2023

Publication Name: IEEE Access

Publication URL: doi: 10.1109/ACCESS.2023.3322370

Abstract:

Wireless Sensor Networks (WSNs) encounter a substantial challenge when it comes to
energy conservation. As sensor nodes rely on battery power to operate in unattended environments, and
it can be inconvenient to recharge the batteries. So, maximizing the network’s operational lifetime by
minimizing energy consumption is crucial for improving the quality of service. Anomaly detection is widely
used technique in WSNs to identify anomalies or unusual events. However, timely anomaly detection
can be challenging to execute reliably in real-time. This study presents a methodology that focuses on
energy efficiency when detecting anomalies in real-time settings for multivariate time series data by
utilizing compression of measurement data and reducing operating time without compromising measurement
resolution. This effectively reduces energy consumption. Instead of modeling the time series of each sensor
individually, the proposed deep sequential learning approach models the time series of multiple sensors
concurrently, accounting for potential interactions among them. Additionally, the proposed deep sequential
learning approach eliminates the need for labeled data and can be directly applied to real-world scenarios
where labeling a large data stream is impractical and time-consuming. Finally, experiments with a real-world
WSN demonstrate that the proposed approach is both adequate and robust in practice.