cs.LGNov 13, 2026

HeteroWear: Sensor-Aware Self-Supervised Learning for Heterogeneous Wearable Activity Recognition

Authors: Yasaman Mohammadpour, Pouya Shaeri

Organizations: School of Computing and Augmented Intelligence, Arizona State University, Tempe, Arizona, USA

Abstract

Self-supervised learning for wearable sensing is usually confined to a single dataset or device family, leaving open whether representations transfer across heterogeneous sensor configurations and whether gains come from pretraining rather than architecture or richer sensor input. We present HeteroWear, a sensor-aware self-supervised framework pretrained on an eight-dataset wearable corpus (173 subjects, 358,261 windows) spanning inertial and physiological signals across body locations, devices, and sampling rates. HeteroWear separates within-sensor temporal modeling from cross-sensor relational modeling using sensor-context embeddings, temporal and cross-sensor Transformers, and latent cross-attention fusion. Training combines structured sensor dropout, cross-configuration consistency, and per-axis masked sensor modeling; missing sensors are omitted rather than reconstructed. Under leave-one-dataset-out pretraining and subject-disjoint evaluation on PAMAP2, WISDM, HHAR, HARTH, and UCI-HAR, HeteroWear improves mean macro-F1 from 0.688 to 0.724 over the identical architecture trained from scratch, with the largest gain on HHAR (0.823 versus 0.741), and achieves the highest macro-F1 on four of five benchmarks relative to single-accelerometer supervised baselines. Held-out-device evaluation yields a mean +0.066 macro-F1 improvement. Under 50% test-time channel removal, HeteroWear retains 73.8% of full-channel performance versus 64.1% for the same architecture trained from scratch without sensor dropout. Ablations show that structured sensor dropout primarily drives robustness, while cross-configuration consistency and sensor-context encoding contribute to transfer.

Figures & tables

Explore similar work

May 8, 2026

BenchHAR: Benchmarking Self-Supervised Learning for Generalizable Sensor-based Activity Recognition

Human Activity Recognition (HAR) from wearable sensors supports broad healthcare and behavior science applications. However, data heterogeneity and the scarcity of labeled data limit its real-world generalization. Recent advances in self-supervised learning (SSL) in vision and language domains have shown strong capability for learning generalizable representations from unlabeled data. Yet, few studies have systematically compared the generalization performance of SSL methods or explored how to adapt them for generalizable HAR. To address these gaps, we present BenchHAR, a unified framework for evaluating the generalization capability of SSL methods for sensor-based HAR on unseen target distributions. BenchHAR curates a large-scale dataset (~258K samples) and evaluates eight representative SSL methods across 12 encoder-classifier architectures. Our results reveal that existing SSL methods struggle to achieve satisfactory generalization performance. We find that: (1) For HAR models, the hybrid paradigm (combining reconstruction and contrastive pretraining) achieves the best overall performance. The CNN encoder exhibits the strongest ability to learn generalizable representations, while more expressive classifier architectures further improve generalization. (2) For data scale, increasing the amount of pretraining data from downstream activity classes consistently improves generalization, while adding more labeled data yields limited gains. Interestingly, incorporating unlabeled data from non-downstream activity classes does not improve generalization. (3) Sensor data collected from custom-grade devices generalizes better than that from research-grade devices, and data from limb transfers more effectively to trunk positions. BenchHAR provides a unified benchmark and actionable insights for generalizable sensor-based HAR systems. Our code is available at https://github.com/saiketa/HAR-Bench.
Oct 14, 2026

W-JEPA: Wavelet Joint-Embedding Predictive Architecture for Wearable Activity Recognition

A major challenge in wearable device activity recognition is the heterogeneity across datasets in sensor placement, channel count, sampling rate and subjects. Moreover, the motion patterns that distinguish activities often appear as subtle, scale-specific variations within otherwise similar waveforms. As a result, raw signals are often ambiguous, and models trained on them tend to rely on cues specific to a particular sensor setup or participant, which limits both cross-dataset transfer and generalization to unseen participants. Addressing this requires representations that preserve such activity-relevant, scale-specific variation. We introduce W-JEPA, a self-supervised framework that exploits the multiscale structure of inertial motion and leverages a joint-embedding predictive architecture, by organizing windows into a fixed grid of wavelet tokens indexed by scale, sensor axis, and time. These wavelet tokens help expose activity-specific detail within broadly similar raw signals, and serve as the units of masked latent prediction. W-JEPA predicts masked token representations supplied by an exponential-moving-average (EMA) target encoder. Because recovering a masked token requires relating motion at one scale and axis to motion at other scales and axes, the model learns the cross-scale, cross-axis structure of human movement. Across six wearable activity benchmarks, W-JEPA outperforms state-of-the-art methods under random-window splits and remains the strongest when subjects are held out, improving average macro-F1 by 8.7 percentage points over the strongest published baseline. These results indicate that physically grounded multiscale tokenization, combined together with latent predictive learning, provides a promising foundation for transferable representations of heterogeneous wearable inertial data.
Mar 11, 2026

Bio-Inspired Self-Supervised Learning for Wrist-worn Accelerometer Data

Wearable accelerometers enable large-scale health monitoring, yet learning robust human-activity representations has been constrained by scarce labeled data. While self-supervised learning offers a remedy, existing methods treat sensor streams as unstructured time series, overlooking the underlying biological structure of human movement, a factor we argue is critical for effective Human Activity Recognition (HAR). We introduce a novel tokenization strategy grounded in the submovement theory of motor control, which posits that continuous wrist motion is composed of elementary basis functions called submovements. We define our token as the movement segment, a computationally tractable unit of motion composed of a finite sequence of submovements. By pretraining a Transformer encoder via masked reconstruction of these tokens, we shift the learning focus from local waveform morphology to high-level structural and temporal organization. Pretrained on the NHANES corpus (approximately 28k hours; 11k participants), our representations outperform strong wearable SSL baselines across six subject-disjoint HAR benchmarks. Code and pretrained weights are available at https://prithvitarale.github.io/biopm-site/.