Skip to content
Open access

MTFNet: A Lightweight Multi-Scale Time–Frequency Neural Network for Multi-Class Event Recognition in DAS-Based Perimeter Security

Oct 2026 · Italian National Conference on Sensors · Vol 26 · 0 citations · 25 references
Medicine

TL;DR

A lightweight multi-scale time–frequency network (MTFNet) for direct processing of one-dimensional DAS signals is proposed, demonstrating its robustness against additive white Gaussian noise (AWGN) and practical engineering application potential.

Abstract

Distributed Acoustic Sensing (DAS) has emerged as a pivotal technology for perimeter security. However, existing DAS event recognition methods have inherent limitations. Single-domain modeling has limited feature representation, while conventional multi-domain fusion methods require converting one-dimensional signals into two-dimensional images. This conversion adds computational overhead and may discard part of the original phase and amplitude information. In addition, the robustness of lightweight recognizers under low signal-to-noise ratio (SNR) conditions remains insufficiently examined. This paper proposes a lightweight multi-scale time–frequency network (MTFNet) for direct processing of one-dimensional DAS signals. The model adopts a parallel time–frequency dual-branch architecture. The time-domain branch utilizes a lightweight 1D Inception-ResNet variant to capture short-term impulse features and long-range temporal dependencies via multi-scale parallel convolutions and residual connections. The frequency-domain branch performs multi-scale segmented spectral analysis to extract complementary discriminative information at diverse time and frequency resolutions, followed by a lightweight attention-free fusion module for effective time–frequency feature fusion. Experimental results on a self-built dataset covering Wind, Facility Noise, Hammering, Sawing, and Walking events show that MTFNet achieves a recognition accuracy of 99.55% with 0.12 M parameters, outperforming SVM, 1D-CNN, TCN, MS 1D-CNN, CNN-BiLSTM, and attention-based multimodal fusion methods. It maintains an accuracy of 94.06% at an SNR of 0 dB, demonstrating its robustness against additive white Gaussian noise (AWGN) and practical engineering application potential.

Read PDF

Similar papers

Open access Sep 2026

TFPAG-Net: A Time-Frequency Dual-Branch Fusion and PCMCI-Based Association-Guided Network for IIoT Intrusion Detection

The Industrial Internet of Things (IIoT) is being used a lot in important areas like advanced manufacturing, smart energy systems, and intelligent cities. Watching for intrusion detection is very important for the safety of the IIoT. Nevertheless, multivariate sensor sequences frequently demonstrate pronounced physical...

Hao-Ran Lei, Shi-Ming Li, Wen-Tao Li et al. · 0 citations
Conference Nov 2026

Deep learning and frequency-domain feature fusion for wireless communication signal modulation recognition and interference detection

Automatic modulation recognition (AMR) and interference detection are critical tasks in modern wireless communication systems. Existing approaches often rely on either time-domain or frequency-domain features alone, failing to capture the complementary information across both domains. This paper proposes a Frequency-Do...

Yun-Fei Chen · 0 citations
Open access 2026

OSAM-Fusion: A Dual-Branch Feature Fusion Network With Transformer for Open-Set Drone RF Signal Recognition

With the widespread application of drones in both civilian and military fields, reliable identification of their radio frequency (RF) signals has become a critical challenge for ensuring low-altitude airspace security. To address the problem of detecting unknown drone threats in open environments, this paper proposes a...

Zhong-Yan Han, Bing-Bing Zhou, Hao Yang et al. · 0 citations
Open access 2026

DF-CLDNN: An Intrusion Event Recognition Method Based on CLDNN Integrating Adaptive Signal Decomposition and Time–Frequency Features

Results indicate that the proposed DF-CLDNN enhances feature discriminability and measurement quality, providing an effective solution for high-precision event recognition in <inline-formula> <tex-math notation="LaTeX">$\Phi $ </tex-math></inline-formula>-OTDR-based intrusion detection under complex conditions.

Zhi-Niu Xu, Tian-Xiang Dai, Li-Juan Zhao et al. · 0 citations
Open access 2026

Time-Decoupled Spectral Modeling: Wide-Band Recalibration and Adaptive Fusion for Sound Event Detection

Convolutional recurrent neural networks (CRNNs) provide a compact solution for sound event detection (SED), but distant frequency bands interact only through successive local operations in their finite-depth convolutional front-ends. We propose Time-Decoupled Spectral Gating (TDSG), a parameter-efficient module that su...

Qian Weng, Chen-Jie Zeng, Jia-Wen Lin et al. · 0 citations
Open access 2026

Time-Frequency Feature Fusion with Multi-Scale Attention for Underwater Acoustic Target Recognition

Traditional convolutional neural networks (CNNs) for underwater acoustic target recognition (UATR) are limited by restricted local receptive fields, and reliance on frequency-domain inputs alone can discard temporal information present in the raw waveform. This study proposes TFMSUATR, a model that fuses a raw-waveform...

Gang Hu, Yi-Fei Song, Mohamad Farhan Mohamad Mohsin · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.