Channel-Free Human Activity Recognition via Inductive-Bias-Aware Fusion Design for Heterogeneous IoT Sensor Environments

• URL: http://arxiv.org/abs/2604.21369v1
• Date: Thu, 23 Apr 2026 07:32:36 GMT
• Title: Channel-Free Human Activity Recognition via Inductive-Bias-Aware Fusion Design for Heterogeneous IoT Sensor Environments
• Abstract summary: Human activity recognition (HAR) in Internet of Things (IoT) environments must cope with heterogeneous sensor settings.<n>We investigate strict channel-free HAR, in which a single shared model performs inference without assuming a fixed number, order, or semantic arrangement of input channels.<n>We propose a channel-free HAR framework that combines channel-wise encoding with a shared encoder, metadata-conditioned late fusion, and joint optimization of channel-level and fused predictions.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Human activity recognition (HAR) in Internet of Things (IoT) environments must cope with heterogeneous sensor settings that vary across datasets, devices, body locations, sensing modalities, and channel compositions. This heterogeneity makes conventional channel-fixed models difficult to reuse across sensing environments because their input representations are tightly coupled to predefined channel structures. To address this problem, we investigate strict channel-free HAR, in which a single shared model performs inference without assuming a fixed number, order, or semantic arrangement of input channels, and without relying on sensor-specific input layers or dataset-specific channel templates. We argue that fusion design is the central issue in this setting. Accordingly, we propose a channel-free HAR framework that combines channel-wise encoding with a shared encoder, metadata-conditioned late fusion via conditional batch normalization, and joint optimization of channel-level and fused predictions through a combination loss. The proposed model processes each channel independently to handle varying channel configurations, while sensor metadata such as body location, modality, and axis help recover structural information that channel-independent processing alone cannot retain. In addition, the joint loss encourages both the discriminability of individual channels and the consistency of the final fused prediction. Experiments on PAMAP2, together with robustness analysis on six HAR datasets, ablation studies, sensitivity analysis, efficiency evaluation, and cross-dataset transfer learning, demonstrate three main findings...

Related papers

• Channel-Oriented Design for EEG-to-Music Reconstruction [10.381688641790632]
  We study EEG-to-music reconstruction, where signals are weak, distributed, and highly susceptible to noise and channel variability.<n>Our central finding is that early channel mixing destroys weak but discriminative EEG signals.<n>We propose a channel-oriented design with three key components.
  arXiv  Detail & Related papers  (2026-06-02T04:13:37Z)
• Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings [0.43748379918040853]
  We introduce CHARM, which incorporates channel-level textual descriptions into a Transformer encoder equivariant to channel order.<n>ChaRM is trained with a Joint Embedding Predictive Architecture (JEPA) and a novel loss promoting informative, temporally stable embeddings.<n>Performance is driven primarily by the JEPA objective and conditioning architecture, with text descriptions serving as channel identifiers for cross-dataset generalization.
  arXiv  Detail & Related papers  (2026-05-29T17:48:30Z)
• DC-ViT: Modulating Spatial and Channel Interactions for Multi-Channel Images [9.507520646516719]
  Training and evaluation in multi-channel imaging (MCI) remains challenging due to heterogeneous channel configurations.<n>Recent Multi-Channel Vision Transformers (MC-ViTs) address this by enabling flexible channel inputs, typically by jointly encoding patch tokens from all channels within a unified attention space.<n>We propose Decoupled Vision Transformer (DC-ViT), which explicitly regulates information sharing using Decoupled Self-Attention (DSA)
  arXiv  Detail & Related papers  (2026-03-15T08:31:34Z)
• Channel-Aware Probing for Multi-Channel Imaging [9.507520646516719]
  Training and evaluating vision encoders on Multi-Channel Imaging (MCI) data remains challenging.<n>ChannelAware Probing (CAP) exploits intrinsic inter-channel diversity by controlling feature flow at both encoder and probe levels.
  arXiv  Detail & Related papers  (2026-02-13T08:03:27Z)
• CP Loss: Channel-wise Perceptual Loss for Time Series Forecasting [67.3477355449697]
  We propose a Channel-wise Perceptual Loss (CP Loss) for time-series data.<n>We learn a unique perceptual space for each channel that is adapted to its characteristics.<n>Loss is calculated within these perception spaces to optimize the model.
  arXiv  Detail & Related papers  (2026-01-25T15:31:37Z)
• Environment-Aware Channel Inference via Cross-Modal Flow: From Multimodal Sensing to Wireless Channels [45.969793510760645]
  This treatise investigates pilot-free channel inference that estimates complete CSI directly from multimodal observations.<n>We develop a data-driven framework that formulates the sensing-to-channel mapping as a cross-modal flow matching problem.<n>In experiments, we build a procedural data generator based on Sionna and Blender to support realistic modeling of sensing scenes and wireless propagation.
  arXiv  Detail & Related papers  (2025-12-04T16:35:09Z)
• Latent Diffusion Model-Enabled Low-Latency Semantic Communication in the Presence of Semantic Ambiguities and Wireless Channel Noises [18.539501941328393]
  This paper develops a latent diffusion model-enabled SemCom system to handle outliers in source data.<n>A lightweight single-layer latent space transformation adapter completes one-shot learning at the transmitter.<n>An end-to-end consistency distillation strategy is used to distill the diffusion models trained in latent space.
  arXiv  Detail & Related papers  (2024-06-09T23:39:31Z)
• Physics-informed and Unsupervised Riemannian Domain Adaptation for Machine Learning on Heterogeneous EEG Datasets [53.367212596352324]
  We propose an unsupervised approach leveraging EEG signal physics. We map EEG channels to fixed positions using field, source-free domain adaptation. Our method demonstrates robust performance in brain-computer interface (BCI) tasks and potential biomarker applications.
  arXiv  Detail & Related papers  (2024-03-07T16:17:33Z)
• Channelized Axial Attention for Semantic Segmentation [70.14921019774793]
  We propose the Channelized Axial Attention (CAA) to seamlessly integratechannel attention and axial attention with reduced computationalcomplexity. Our CAA not onlyrequires much less computation resources compared with otherdual attention models such as DANet, but also outperforms the state-of-the-art ResNet-101-based segmentation models on alltested datasets.
  arXiv  Detail & Related papers  (2021-01-19T03:08:03Z)
• Learning from Heterogeneous EEG Signals with Differentiable Channel Reordering [51.633889765162685]
  CHARM is a method for training a single neural network across inconsistent input channels. We perform experiments on four EEG classification datasets and demonstrate the efficacy of CHARM.
  arXiv  Detail & Related papers  (2020-10-21T12:32:34Z)
• Deep Phase Correlation for End-to-End Heterogeneous Sensor Measurements Matching [12.93459392278491]
  We present an end-to-end deep phase correlation network (DPCN) to match heterogeneous sensor measurements. The primary component is a differentiable correlation-based estimator that back-propagates the pose error to learnable feature extractors. With the interpretable modeling, the network is light-weighted and promising for better generalization.
  arXiv  Detail & Related papers  (2020-08-21T13:42:25Z)
• Data-Driven Symbol Detection via Model-Based Machine Learning [117.58188185409904]
  We review a data-driven framework to symbol detection design which combines machine learning (ML) and model-based algorithms. In this hybrid approach, well-known channel-model-based algorithms are augmented with ML-based algorithms to remove their channel-model-dependence. Our results demonstrate that these techniques can yield near-optimal performance of model-based algorithms without knowing the exact channel input-output statistical relationship.
  arXiv  Detail & Related papers  (2020-02-14T06:58:27Z)
• DeepSIC: Deep Soft Interference Cancellation for Multiuser MIMO Detection [98.43451011898212]
  In multiuser multiple-input multiple-output (MIMO) setups, where multiple symbols are simultaneously transmitted, accurate symbol detection is challenging. We propose a data-driven implementation of the iterative soft interference cancellation (SIC) algorithm which we refer to as DeepSIC. DeepSIC learns to carry out joint detection from a limited set of training samples without requiring the channel to be linear.
  arXiv  Detail & Related papers  (2020-02-08T18:31:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.