Fusion-Inception-Aux: An Auxiliary-Supervised Multi-Scale Fusion Network for Distributed Acoustic Sensing Event Recognition
Year: 2026
Type: article
Abstract: Distributed acoustic sensing (DAS) event recognition is challenging because disturbance events may have similar temporal waveforms, heterogeneous channel responses, and strict false-alarm requirements in practical monitoring systems. This paper proposes Fusion-Inception-Aux, an auxiliary-supervised dual-branch framework for DAS event classification. The model uses inception-style temporal encoders to extract multi-scale disturbance features from two channel groups and applies auxiliary branch supervision to improve branch-wise representation learning. The final decision is obtained by adaptive aggregation of the branch-level and fused predictions. To avoid evaluation leakage, channel grouping is selected only from the training partition, and the main comparison is conducted under matched data splits, preprocessing settings, and training budgets. Experiments are conducted on a six-class, 12-channel Phi-OTDR dataset with 12,335 training samples and 3,084 test samples. Under five-seed evaluation, Fusion-Inception-Aux achieves $0.9964 \pm 0.0015$ accuracy and $0.9964 \pm 0.0016$ macro-F1, compared with $0.9936 \pm 0.0004$ accuracy and $0.9934 \pm 0.0004$ macro-F1 for the Fusion-CNN baseline. With the full training recipe, the proposed model reaches $0.9979 \pm 0.0004$ accuracy and $0.9978 \pm 0.0005$ macro-F1. Ablation results indicate that multi-scale Inception encoding and auxiliary supervision are the most important components, while the PatchX interaction module provides no consistent additional gain under the current setting. External validation on a three-class Mendeley DAS subset achieves $0.9844 \pm 0.0061$ accuracy and $0.9844 \pm 0.0061$ macro-F1, showing comparable performance on an independent public dataset. Complexity profiling further shows that Fusion-Inception-Aux improves recognition accuracy over Fusion-CNN with a moderate increase in model size and inference cost.
Source: IEEE photonics journal
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,075
OpenAlex ID: W7204445790