XMXiao Ma

Xiao Ma

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Xiao Ma has a total of 28 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    PPG-IDR: Leveraging User Identity for Robust Cross-user PPG Sensing via Disentangled Representations

    by Hung Manh Pham, Xiao Ma, Changshuo Hu, Xiaoyu Xu, Thivya Kandappu, Yuezhong Wu, Tarek Abdelzaher, Archan Misra, Dong Ma

    Photoplethysmography (PPG) is widely used in non-invasive health monitoring applications such as heart rate and blood pressure estimation. Despite deep learning substantially advancing PPG sensing accuracy, models trained on a population often struggle with cross-user generalization , exhibiting significant performance degradation when applied to unseen individuals. Building on the evidence that PPG signals encode biometric traits for user authentication, we hypothesize that these identity-specific features are a primary confounding noise of poor cross-user generalization. To validate this hypothesis and address the issue, we propose PPG-IDR (Identity Disentangled Representations), a framework designed to disentangle medical physiological features from identity-specific information. PPG-IDR utilizes a dual-branch design to partition the feature space, employing adversarial and orthogonality constraints to suppress identity leakage, alongside a self-supervised objective to refine medical representations. We evaluated PPG-IDR using multiple datasets across six downstream tasks, and the results demonstrate that PPG-IDR consistently outperforms strong baselines in unseen-user scenarios. These findings highlight the importance of identity disentanglement for scalable and robust cross-user PPG sensing.

  • Open Access

    PPG-Sport: A Dataset for Reliable Heart Rate Monitoring from Wrist PPG Under Dynamic Sports Conditions

    by Changshuo Hu, Hung Manh Pham, Yiming Zhang, Guanru Yan, Xiao Ma, Yuezhong Wu, Thivya Kandappu, Archan Misra, Dong Ma

    Photoplethysmography (PPG) has become a cornerstone of physiological sensing in wearable devices, enabling non-invasive monitoring of heart rate and related biomarkers. However, its reliability deteriorates sharply under dynamic, high-intensity, or non-periodic motions such as those in sports, where existing datasets fail to capture realistic wrist dynamics. To address this gap, we introduce PPG-Sport, the first large-scale dataset designed for heart rate monitoring from wrist-worn PPG under real sports conditions. The PPG-Sport dataset includes synchronized PPG, inertial measurement unit (IMU), and electrocardiography (ECG) recordings from both wrists of 30 participants across six representative activities: stationary, walking, running, badminton, table tennis, and basketball, amounting to 48 hours of multimodal data. PPG-Sport uniquely captures three critical properties absent in prior datasets: (1) non-periodicity, reflecting irregular and broadband motion patterns; (2) high intensity, with frequent, large-magnitude accelerations; and (3) bilateral asymmetry, caused by distinct functional roles of the dominant and non-dominant hands during sports. We further establish a deep-learning-based benchmark that combines both temporal and spectral representations of PPG and IMU signals to evaluate heart rate estimation performance. Experimental results show that models trained only on conventional periodic activities fail drastically in sports scenarios. Although incorporating sports data mitigates the degradation, significant errors remain. These findings highlight PPG-Sport as an essential and challenging benchmark for developing motion-robust physiological sensing algorithms during sports activities. Dataset and benchmark code are available at: https://github.com/LaserHu/PPG-Sport.

  • Toward Diverse Tiny-Model Selection for Microcontrollers

    by Xiao Ma, Shengfeng He, Hezhe Qiao, Dong Ma

    Enabling efficient and accurate deep neural network (DNN) inference on microcontrollers is challenging due to their constrained on-chip resources. Existing approaches mainly focus on compressing larger models, often compromising model accuracy as a trade-off. In this paper, we rethink the problem from the inverse perspective by directly constructing small/weak models, then enhancing their accuracy. Thus, we propose DiTMoS, a novel DNN training and inference framework featuring a selector-classifiers architecture, where the selector routes each input sample to the appropriate classifier for classification. DiTMoS is built on a key insight: a combination of weak models can exhibit high diversity and the union of them can significantly raise the upper bound of overall accuracy. To approach the upper bound, DiTMoS introduces three strategies including diverse training data splitting to enhance the classifiers’ diversity, adversarial selector-classifiers training to ensure synergistic interactions thereby maximizing their complementarity, and heterogeneous feature aggregation to improve the capacity of classifiers. We further design a network slicing technique to eliminate the extra memory consumption incurred by feature aggregation. We deploy DiTMoS on the Nucleo STM32F767ZI board and evaluate its performance across three time-series datasets for human activity recognition, keyword spotting, and emotion recognition tasks. The experimental results show that: (a) DiTMoS improves accuracy by up to 13.4% compared to the best baseline; (b) network slicing successfully eliminates the memory overhead introduced by feature aggregation, with only a minimal increase in latency.


  • Open Access

    LR-Auth: Towards Practical Implementation of Implicit User Authentication on Earbuds

    by Changshuo Hu, Xiao Ma, Xinger Huang, Yiran Shen, Dong Ma

    The increasing use of earbuds in applications like immersive entertainment and health monitoring necessitates effective implicit user authentication systems to preserve the privacy of sensitive data and provide personalized experiences. Existing approaches, which leverage physiological cues (e.g., jawbone structure) and behavioral cues (e.g., gait), face challenges such as limited usability, high delay and energy overhead, and significant computational demands, rendering them impractical for resource-constrained earbuds. To address these issues, we present LR-Auth, a lightweight, user-friendly implicit authentication system designed for various earbud usage scenarios. LR-Auth utilizes the modulation of sound frequencies by the user's unique occluded ear canal, generating user-specific templates through linear correlations between two audio streams instead of complex machine-learning models. Our prototype, evaluated with 30 subjects under diverse conditions, demonstrates over 99% balanced accuracy with five 100 ms audio segments, even in noisy environments and during music playback. LR-Auth significantly reduces system overhead, achieving a 20 × to 404 × decrease in latency and a 24 × to 410 × decrease in energy consumption compared to existing methods. These results highlight LR-Auth's potential for accurate, robust, and efficient user authentication on resource-constrained earbuds.


  • Multi-UAV Cooperative Search Method based on Multi-group ant Colony Algorithm

    by Yike Gao, Chenhao Wei, Xiao Ma, Bofeng Chang, Zhiyuan Liu, Ye Wu

    Multi-UAV cooperative flight also plays an important role in artificial intelligence. When multi-UAVs search for targets in cooperative missions, it is particularly important that all UAVs can work together effectively to improve the search efficiency and reduce the search risk. Firstly, this paper expounds the research background and significance of Multi-UAV cooperative target search. This article by using ant colony algorithm, the search problem of single UAV flying target is solved, and then the search problem of Multi-UAV flying target is solved by using multi-group ant colony algorithm. Finally, the effectiveness of the Multi-UAV cooperative search method improved by multi-group ant colony algorithm is proved by simulation and comparative analysis.

  • A Calibration Method of Inner Bore Profile Detecting on Electromagnetic Railgun

    by Xiao Ma, Ronggang Cao, Yu Zhou, Xueyi Hu, Fadong Li

    When the electromagnetic rail gun accelerates the armature, the rail is in a harsh condition of high temperature, high pressure and powerful current which will cause a series of grooving phenomenon. In order to detect the inner bore profile, we developed a measuring device using laser triangulation method and basically realized the measurement of the inner bore profile measurement. However, except for the translation and deflection errors, we found that the actual measurement cross-section would be rotated due to the unsteady movement compared with the ideal section. In addition, the previous calibration needs a high-resolution image sensor to get deflection information, it means high cost. In this paper, we analyzed the 3 kinds of deviations and provide a method to calibrate the rotation error using a calibration block. An improved calibration system was designed in low cost and experiment verified the feasibility of the calibration method. The calibration system can be divided into 3 parts, the outside global laser light provides a constant central position, a distance detecting device with a cone laser generator and an inside calibration block. After experiment, the calibration method was effective and the deviation of the profile can be corrected.