Non-Compression Auto-Encoder for Detecting Road Surface Abnormality via Vehicle Driving Noise

TL;DR

This paper introduces a novel deep learning auto-encoder model that detects road surface abnormalities in real-time using vehicle noise, achieving higher accuracy and faster decisions than previous models.

Contribution

The paper presents the non-compression auto-encoder (NCAE), a new architecture that captures temporal causality in vehicle noise for effective road surface anomaly detection.

Findings

Achieved 4.20% higher AUROC than existing models.

Demonstrated 2.99 times faster decision-making.

Validated effectiveness through experimental results.

Abstract

Road accident can be triggered by wet road because it decreases skid resistance. To prevent the road accident, detecting road surface abnomality is highly useful. In this paper, we propose the deep learning based cost-effective real-time anomaly detection architecture, naming with non-compression auto-encoder (NCAE). The proposed architecture can reflect forward and backward causality of time series information via convolutional operation. Moreover, the above architecture shows higher anomaly detection performance of published anomaly detection model via experiments. We conclude that NCAE as a cutting-edge model for road surface anomaly detection with 4.20\% higher AUROC and 2.99 times faster decision than before.