22 August 2024 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
The electrocardiogram (ECG) has always served as a crucial biomedical examination for cardiac diseases monitoring and diagnosing. Typical ECG measurement requires attaching electrodes to the body, which is inconvenient for long-term monitoring. Recent wireless sensing maps wireless signals reflected from human chest into electrical activities of heart so as to reconstruct ECG contactlessly. While making great progress, we find existing works are effective only for healthy populations with normal ECG, but fall short when confronted with the most desired usage scenario: reconstructing ECG accurately for people with cardiac diseases such as atrial fibrillation, premature ventricular beat. To bridge the gap, we propose AirECG, which moves forward to reconstruct ECG for both healthy people and even cardiac patients with morbid ECG, i.e., irregular rhythm and anomalous ECG waveform, via contactless millimeter-wave sensing. To realize AirECG, we first custom-design a cross-domain diffusion model that can perform multiple iteration denoising inference, in contrast with the single-step generative models widely used in previous works. In this way, AirECG is able to identify and eliminate the distortion due to the unstable and irregular cardiac activities, so as to synthesize ECG even during abnormal beats. Furthermore, we enhance the determinacy of AirECG, i.e., to generate high-fidelity ECG, by designing a calibration guidance mechanism to combat the inherent randomness issue of the probabilistic diffusion model. Empirical evaluation demonstrates AirECG's ability of ECG synthesis with Pearson correlation coefficient (PCC) of 0.955 for normal beats. Especially for abnormal beats, the PCC still exhibits a strong correlation of 0.860, with 15.0%~21.1% improvement compared with state-of-the-art approaches.
6 March 2024 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Arrhythmia is a common problem of irregular heartbeats, which may lead to serious complications such as stroke and even mortality. Due to the paroxysmal nature of arrhythmia, its long-term monitoring and early detection in daily household scenarios, instead of depending on ECG examination only available during clinical visits, are of critical importance. While ambulatory ECG Holter and wearables like smartwatches have been used, they are still inconvenient and interfere with users' daily activities. In this paper, we bridge the gap by proposing mmArrhythmia, which employs low-cost mmWave radar to passively sense cardiac motions and detect arrhythmia, in an unobtrusive contact-less way. Different from previous mmWave cardiac sensing works focusing on healthy people, mmArrhythmia needs to distinguish the minute and transient abnormal cardiac activities of arrhythmia patients. To overcome the challenge, we custom-design an encoder-decoder model that can perform arrhythmia feature encoding, sampling and fusion over raw IQ sensing data directly, so as to discriminate normal heartbeat and arrhythmia. Furthermore, we enhance the robustness of mmArrhythmia by designing multichannel ensemble learning to solve the model bias problem caused by unbalanced arrhythmia data distribution. Empirical evaluation over 79,910 heartbeats demonstrates mmArrhythmia's ability of robust arrhythmia detection, with 97.32% accuracy, 98.63% specificity, and 92.30% sensitivity.
26 May 2025 in IEEE Internet of Things Journal
Heart rate variability (HRV) is an essential indicator of cardiovascular and nervous system function, with wide applications in health monitoring and disease management. Traditional contact-based methods like electrocardiograms (ECG) and photoplethysmography (PPG), while effective, face significant limitations in user experience, such as discomfort during prolonged use, and challenges in long-term, continuous monitoring. Meanwhile, contactless wireless sensing based on millimeter wave (mmWave) radar offers a promising alternative but is hindered by issues of directional sensing and noise interference. In this article, we propose mmWave Cardiac Gram (mmCG), a contactless HRV monitoring system. Specifically, it integrates a heartbeat spatial localization method for directional sensing, which significantly improves the SNR, and a dynamic peak search algorithm that leverages heartbeat temporal correlations to effectively mitigate the impact of artifacts. Experimental results show that mmCG achieves advanced performance, reducing the IBI error to 9.44 ms, a 51.29% improvement over existing methods. With its lightweight design and enhanced accuracy, mmCG offers a practical solution for daily HRV monitoring, with potential applications in stress management, personalized healthcare, and cardiovascular disease monitoring.
3 September 2025 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Olfaction, an essential human sense, has drawn significant attention for its sensitivity and environmental awareness, driving advancements in digital olfaction technologies. So far, the most widely used device in digital olfaction is the electronic nose, but direct contact with samples limits it applicability for widespread usage. In this paper, we bridge the gap by proposing Digital Olfactory Mucosa (DOM), which utilizes terahertz signals for contactless sensing and classifying odorant molecules by exploiting the molecular absorption properties of terahertz. Unlike recent wireless gas detecting works that focus on major molecules in the air, DOM specifically focuses on the rare odorant molecules in the air, usually less than 1ppm. To meet the challenge, we custom-design a unique signal processing model based on a hybrid neural network that can perform odorant feature sampling and fusion over time-domain and frequency-domain signals, so as to extract rare odorant molecular features. Furthermore, in order to better accommodate the diversity of odors, we design a dual granularity contrastive learning schema to optimize the spatial distribution of extracted olfactory features, which enhances the scalability of DOM. Evaluation on 25 odorant molecules within 10 odor clusters demonstrates DOM's ability to detect and classify odors, with 98.71% accuracy in odor cluster classification, and 98.66% in specific odor classification.
30 September 2026 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Arrhythmia poses a severe health risk, necessitating long-term monitoring to prevent complications like stroke. However, existing radar monitoring solutions fail to detect concurrent arrhythmias and lack clinical interpretability. In this paper, we bridge the gap by proposing READ (Radar Evidence-based Arrhythmia Diagnosis). Unlike previous “black-box” approaches, READ integrates mmWave radar with Large Language Models (LLMs) to deliver transparent, evidence-based diagnoses. However, training such a reasoning-capable model is hindered by the scarcity of mmWave datasets with detailed diagnostic annotations. To tackle this challenge, we first pretrain on large-scale ECG data to learn robust physiological patterns and then transfer this knowledge to radar domain using our proposed Cross-Physics Knowledge Distillation (CPKD) framework. Furthermore, we design a Morphological Grouping Tokenizer and a Morphology-Anchored Clinical Reasoning module, which parse raw signals into semantic tokens to guide step-by-step diagnostic inference. Empirical evaluation on a real-world dataset of 205 patients, collected in collaboration with medical institutions, demonstrates READ 's superior performance, achieving a 90.12% exact match ratio and a 0.9625 F 1 score. Our framework significantly outperforms state-of-the-art baselines while providing interpretable clinical reports.