Anomaly Detection in UASN Localization Based on Time Series Analysis and Fuzzy Logic

• Published in: Mobile networks and applications Vol. 25; no. 1; pp. 55 - 67
• Main Authors: Das, Anjana P., Thampi, Sabu M., Lloret, Jaime
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.02.2020; Springer Nature B.V
• Subjects: Anomalies; Communications Engineering; Computer Communication Networks; Computer simulation; Electrical Engineering; Engineering; Fuzzy logic; Fuzzy systems; IT in Business; Localization; Military applications; Networks; Nodes; Regression analysis; Remote sensing; Remote sensors; Sensors; Time series; Underwater acoustics; Underwater resources; Fuzzy logic; Localization; Auto-regression; Time series analysis; Underwater sensor networks; Anomaly detection
• ISSN: 1383-469X; 1572-8153
• DOI: 10.1007/s11036-018-1192-y

Underwater acoustic sensor network (UASN) offers a promising solution for exploring underwater resources remotely. For getting a better understanding of sensed data, accurate localization is essential. As the UASN acoustic channel is open and the environment is hostile, the risk of malicious activities is very high, particularly in time-critical military applications. Since the location estimation with false data ends up in wrong positioning, it is necessary to identify and ignore such data to ensure data integrity. Therefore, in this paper, we propose a novel anomaly detection system for UASN localization. To minimize computational power and storage, we designed separate anomaly detection schemes for sensor nodes and anchor nodes. We propose an auto-regressive prediction-based scheme for detecting anomalies at sensor nodes. For anchor nodes, a fuzzy inference system is designed to identify the presence of anomalous behavior. The detection schemes are implemented at every node for enabling identification of multiple and duplicate anomalies at its origin. We simulated the network, modeled anomalies and analyzed the performance of detection schemes at anchor nodes and sensor nodes. The results indicate that anomaly detection systems offer an acceptable accuracy with high true positive rate and F-Score.