Novel Dual-Encoder Architecture with Fuzzy Fusion Improves Underwater Acoustic Classification
Researchers have proposed a parameter-efficient dual-encoder neural network that simultaneously processes acoustic waveforms and spectrograms for underwater sound classification. The architecture combines pre-trained backbones with a novel differentiable Choquet integral fusion mechanism to balance temporal and spectral signal representations. The approach achieves higher classification accuracy than single-encoder baselines while reducing trainable parameters and offering interpretability into how the model weighs different signal types.
A new neural architecture for underwater acoustic classification has been introduced in a preprint submitted to arXiv, targeting the challenge of noisy and non-stationary underwater acoustic environments. The dual-encoder design processes both raw waveforms and spectrograms in parallel, using pre-trained model backbones with parameter-efficient fine-tuning to enable domain adaptation without full model retraining. A key innovation is the use of a differentiable fuzzy aggregation mechanism based on the Choquet integral, which learns to dynamically weight the two representations depending on which is least corrupted by channel distortions. This gating mechanism provides interpretability by revealing class-specific patterns in how the network shifts reliance between temporal and spectral features. Evaluations on the DeepShip and ShipsEar benchmark datasets confirm improvements over single-encoder baselines. The parameter-efficient design also reduces overfitting risk on the typically limited datasets available in underwater acoustics, and lowers the computational cost compared to fully fine-tuning large foundation models.
What's missing
The paper does not report statistical significance tests or confidence intervals for the classification improvements, making it difficult to assess whether gains are robust. It is also unclear how the architecture performs under real-world deployment conditions beyond the two benchmark datasets.
What different sources said
- arXiv cs.LGCenter
Parameter-efficient Dual-encoder Architecture with Differentiable Choquet Integral Fusion for Underwater Acoustic Classification
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.