# Semi-Supervised Learned Autoencoder for Classification of Events in Distributed Fibre Acoustic Sensors

## TL;DR

This paper introduces a semi-supervised learning method to classify events in acoustic sensors, reducing the need for labeled data and improving system efficiency.

## Contribution

A hybrid autoencoder-classifier model with an integrated loss function for efficient event classification using less labeled data.

## Key findings

- The method achieves comparable recognition performance to baseline models with reduced labeled data.
- The simpler architecture improves system throughput and reduces deployment costs.
- Validation on real-world datasets confirms the effectiveness of the proposed approach.

## Abstract

The global market for infrastructure security systems based on distributed acoustic sensors is rapidly expanding, driven by the need for timely detection and prevention of potential threats. However, deploying these systems is challenging due to the high costs associated with dataset creation. Additionally, advanced signal processing algorithms are necessary for accurately determining the location and nature of detected events. In this paper, we present an enhanced approach based on semi-supervised learning for developing event classification models tailored for real-time and continuous perimeter monitoring of infrastructure facilities. The proposed method leverages a hybrid architecture combining an autoencoder and a classifier to enhance the accuracy and efficiency of event classification. The autoencoder extracts essential features from raw data using unlabeled data, improving the model’s ability to learn meaningful representations. The classifier, trained on labeled data, recognizes and classifies specific events based on these features. The integrated loss function incorporates elements from both the autoencoder and the classifier, guiding the autoencoder to extract features relevant for accurate event classification. Validation using real-world datasets demonstrates that the proposed method achieves recognition performance comparable to the baseline model, while requiring less labeled data and employing a simpler architecture. These results offer practical insights for reducing deployment costs, enhancing system performance, and increasing throughput for new deployments.