Lightweight Anomaly Detection Scheme Using Incremental Principal Component Analysis and Support Vector Machine.

Nurfazrina M Zamry,Eman H Alkhammash,Fuad A Ghaleb,Faisal Saeed,Murad A Rassam,Anazida Zainal

doi:10.3390/s21238017

Abstract

Wireless Sensors Networks have been the focus of significant attention from research and development due to their applications of collecting data from various fields such as smart cities, power grids, transportation systems, medical sectors, military, and rural areas. Accurate and reliable measurements for insightful data analysis and decision-making are the ultimate goals of sensor networks for critical domains. However, the raw data collected by WSNs usually are not reliable and inaccurate due to the imperfect nature of WSNs. Identifying misbehaviours or anomalies in the network is important for providing reliable and secure functioning of the network. However, due to resource constraints, a lightweight detection scheme is a major design challenge in sensor networks. This paper aims at designing and developing a lightweight anomaly detection scheme to improve efficiency in terms of reducing the computational complexity and communication and improving memory utilization overhead while maintaining high accuracy. To achieve this aim, one-class learning and dimension reduction concepts were used in the design. The One-Class Support Vector Machine (OCSVM) with hyper-ellipsoid variance was used for anomaly detection due to its advantage in classifying unlabelled and multivariate data. Various One-Class Support Vector Machine formulations have been investigated and Centred-Ellipsoid has been adopted in this study due to its effectiveness. Centred-Ellipsoid is the most effective kernel among studies formulations. To decrease the computational complexity and improve memory utilization, the dimensions of the data were reduced using the Candid Covariance-Free Incremental Principal Component Analysis (CCIPCA) algorithm. Extensive experiments were conducted to evaluate the proposed lightweight anomaly detection scheme. Results in terms of detection accuracy, memory utilization, computational complexity, and communication overhead show that the proposed scheme is effective and efficient compared few existing schemes evaluated. The proposed anomaly detection scheme achieved the accuracy higher than 98%, with (nd) memory utilization and no communication overhead.

Highlights

Introduction conditions of the Creative CommonsWith the advancement of digital technology from the past few decades, every digital equipment and appliance is expected to be embedded with tiny yet powerful device called sensor nodes
This paper focuses on designing a lightweight anomaly detection scheme to provide reliable data collection while consuming less energy using one-class learning schemes and dimension reduction concepts
Designing an effective anomaly detection scheme for Wireless Sensor Networks (WSNs) is crucial yet challenging due to the limited resources

Summary

Introduction

Introduction conditions of the Creative CommonsWith the advancement of digital technology from the past few decades, every digital equipment and appliance is expected to be embedded with tiny yet powerful device called sensor nodes. In the world of modern wireless telecommunications, IoT is a revolutionary paradigm that is rapidly growing [1] When these sensor nodes communicate together to collect a large amount of data from the targeted area via the wireless channel, they are called Wireless Sensor Networks (WSNs). It is defined by [4] as the process of identifying data patterns that vary from anticipated behaviour When it comes to WSNs, anomaly detection has been widely employed across a wide range of industries such as the military and environmental sectors [5]. This is due to the characteristic of low-cost, small in size, and multi-functional sensor nodes; it helps to achieve the need for fast and cheap data collection

Objectives

Results

Conclusion