Search papers, labs, and topics across Lattice.
This study addresses the challenge of performance degradation in millimeter-wave human activity recognition due to changes in user orientation by developing a physics-guided simulator that generates orientation-diverse training data from single-orientation motion. A dual-attention network is employed to extract robust representations from dual-link Doppler spectrograms, while an adversarial transfer learning mechanism aligns feature distributions with minimal unlabeled target-domain samples. The proposed S2M-Sense platform achieves an average structural similarity index of 0.84 and recognition accuracy of 95% after transfer learning, significantly outperforming existing cross-domain sensing methods.
Achieving 95% recognition accuracy in human activity recognition with just 16 unlabeled samples highlights a breakthrough in sim-to-real transfer learning for wireless sensing.
Millimeter-wave human activity recognition suffers significant performance degradation when the user's orientation changes relative to the sensing system, yet collecting labeled multi-orientation data is labor-intensive and costly. To eliminate the need for exhaustive multi-orientation measured data, we develop a physics-guided simulator that synthesizes orientation-diverse wireless training data from single-orientation motion. Specifically, to suppress orientation-induced feature variations, we propose a dual-attention network that extracts activity-discriminative and orientation-robust representations from dual-link Doppler spectrograms. To bridge the simulation-to-reality gap, we introduce an adversarial unsupervised transfer learning mechanism that aligns feature distributions using only a small number of unlabeled target-domain samples. The S2M-Sense platform shows high fidelity in reproducing real-world signatures, validated against 60.48 GHz mmWave measured data with an average structural similarity index measure (SSIM) of 0.84 between simulated and measured Doppler spectrograms across all 4 activities and 4 orientations. Experimental results show that S2M-Sense achieves 88.33% recognition accuracy using only the dual-link multi-orientation simulated dataset, which improves to 95% after simulation-to-reality transfer learning with as few as 16 unlabeled measured samples. Both cases with and without transfer learning outperform state-of-the-art cross-domain sensing methods.
