Resource-aware Time Series Imaging Classification for Wireless Link Layer Anomalies

TL;DR

This paper introduces a resource-efficient deep learning model for wireless link anomaly detection using time-series image transformations, significantly outperforming existing methods in accuracy and efficiency.

Contribution

It presents a novel resource-aware deep learning architecture utilizing recurrence plots for wireless anomaly detection, outperforming traditional and mainstream models in accuracy and computational efficiency.

Findings

Recurrence plot-based model outperforms Gramian angular field-based model by 14 percentage points.

Model surpasses classical ML with dynamic time warping by 24 percentage points.

Achieves up to 55 percentage points improvement over the state of the art.

Abstract

The number of end devices that use the last mile wireless connectivity is dramatically increasing with the rise of smart infrastructures and require reliable functioning to support smooth and efficient business processes. To efficiently manage such massive wireless networks, more advanced and accurate network monitoring and malfunction detection solutions are required. In this paper, we perform a first time analysis of image-based representation techniques for wireless anomaly detection using recurrence plots and Gramian angular fields and propose a new deep learning architecture enabling accurate anomaly detection. We elaborate on the design considerations for developing a resource aware architecture and propose a new model using time-series to image transformation using recurrence plots. We show that the proposed model a) outperforms the one based on Grammian angular fields by up to 14 percentage points, b) outperforms classical ML models using dynamic time warping by up to 24 percentage points, c) outperforms or performs on par with mainstream architectures such as AlexNet and VGG11 while having <10 times their weights and up to $\approx$8\% of their computational complexity and d) outperforms the state of the art in the respective application area by up to 55 percentage points. Finally, we also explain on randomly chosen examples how the classifier takes decisions.