Hybrid KAN-MLP Architecture Improves Human Activity Recognition from Wearable Sensors
Researchers have proposed a hybrid neural network architecture called KAN-MLP-Mixer that combines Kolmogorov-Arnold Networks (KANs) with conventional multi-layer perceptrons (MLPs) to improve inertial measurement unit (IMU)-based human activity recognition (HAR). KANs excel at learning complex functions on clean data but struggle with the noisy, real-world sensor data typical of wearable devices, while MLPs are more noise-tolerant and computationally efficient. The hybrid model achieves a 5.33% average macro F1 score improvement over pure-MLP baselines across eight public HAR datasets, suggesting a practical path to deploying more accurate activity recognition in wearable technology.
The study, posted to arXiv, systematically investigates where and how KAN modules can be inserted into deep HAR networks to maximize benefit without sacrificing the noise robustness and efficiency of standard MLPs. The proposed KAN-MLP-Mixer uses a KAN-based input embedding layer to capture complex input patterns, retains MLP layers for intermediate feature mixing, and introduces a novel LarctanKAN module for final activity classification. Evaluated across eight public HAR benchmark datasets, the hybrid architecture achieves an average macro F1 score relative improvement of 5.33% over pure-MLP models and significantly outperforms both standalone KAN and standalone MLP baselines. The researchers also demonstrate that integrating this hybrid strategy into other state-of-the-art HAR architectures consistently boosts their performance, suggesting broad applicability. The findings highlight that indiscriminately replacing all MLP components with KANs degrades both accuracy and computational efficiency, and that strategic, selective placement is key. The work addresses a recognized open challenge in the field: how to harness KANs' function-approximation precision while preserving the practical robustness needed for real-world wearable sensing environments.
What's missing
The study is a preprint and has not yet undergone formal peer review. It is also unclear how the model performs on out-of-distribution populations or activity sets not represented in the eight benchmark datasets.
What different sources said
- arXiv cs.AICenter
KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognition
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.