XSXuefeng Song

Xuefeng Song

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xuefeng Song has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A domain adversarial network for small-sample obstructive sleep apnea detection using a single-lead piezoelectric sensor

    by Xuefeng Song, Xiaoxin Lan, Tianyuan Hou, Hongyan Liu, Yuhang Wang, Junye Tong, Siqi Jia, Haibo Yuan, Yi Xin

    Objective. In recent years, increasing attention to sleep health has accelerated development of wearable devices for home monitoring. Two critical challenges remain: providing an unobtrusive sensing solution suitable for long-term deployment, and designing algorithms that generalize across diverse users and acoustic environments when annotated data are limited. Approach. We develop a single-lead bone-conduction monitoring system and a distribution-aware detection model. The wearable system uses a piezoelectric sensor at the lateral throat to capture tracheal vibrations for continuous overnight monitoring, which improves user comfort relative to multi-lead polysomnography (PSG). For robust event recognition, we propose the convolutional memory adaptive prototypic network (CMAP), which combines convolutional–recurrent feature extraction with domain-adversarial training and a prototypical constraint to learn domain-invariant representations under limited labels. We evaluated our solution with a cohort of 95 participants undergoing simultaneous PSG and wearable monitoring. Main results. For snore and breath sound event detection during sleep, the model attained precision of 0.90 and recall of 0.93. The estimated Apnea–Hypopnea Index (AHI) from our system correlated strongly with PSG-derived AHI (Pearson r = 0.94, p < 0.001). The model achieved 83.2% accuracy in four-class severity classification across healthy, mild, moderate and severe obstructive sleep apnea (OSA). Significance. These results indicate that a single-sensor, distribution-aware approach can provide a reliable acoustic surrogate for AHI and clinically relevant severity classification. The proposed wearable and CMAP model offer a practical, comfortable, and cost-effective solution for early clinical triaging, scalable home-based OSA screening and longitudinal monitoring with low user burden.


  • All-Solid Ultralow Noise Electric Field Sensor Based on the Sol Adhesion Method for Telluric and Marine Electrode Field Detection

    by Yuhang Wang, Rui Li, Xuefeng Song, Junye Tong, Tianyuan Hou, Yi Xin, Yuan Wang

    The sol adhesion method prepared an all-solid ultralow noise electric field sensor. Compared with the sintering method, electrolysis method, and ball milling method, the content of Ag (silver) and AgCl (silver chloride) stays at a high-level amount, the mixture is more uniform and there are no impurities introduced in the fabrication process. Some experiments were designed to characterize the basic properties and electrochemical characteristics of the electrode. Scanning electron microscope (SEM) shows the produced Ag/AgCl (silver and silver chloride) has small particle sizes and a large contact area. The potential drifts of electrodes are less than $15~\mu $ V. The self-potential is less than $80~\mu $ V. Self-noise of the electrode is 1.99 nV/ $\surd $ Hz@1 Hz. Meanwhile, the electrode responds well to electric field signals from 0.1 Hz to 3 kHz and can detect small amplitude signals to 2 mV without distortion. The electrode has the advantages of low impedance, low noise, high sensitivity, and high stability. The self-potential test showed the Ag/AgCl electrodes spent less than 20 min to reach stability is at least three times faster than that of Cu, Ag, Pb/PbCl, and stainless-steel electrodes. Stability potential and range drift are at least 98% and 93% lower than that of other electrodes. In the telluric test, the signal amplitude is at least four times of Ag and Pb/PbCl electrodes. In the marine test, the signal amplitude value is 4 mV level with the noise amplitude value is 0.06 mV level. It shows the good performance of the electrodes. This study is of great significance in accurately measuring marine and telluric electric fields.


  • High-Temperature Resistance BiScO₃–PbTiO₃ Nanofiber Overpressure Sensor for Free-Field Shock Waves Testing

    by Junye Tong, Tianyuan Hou, Yuhang Wang, Xuefeng Song, Meng Cui, Yi Xin, Tingting Lin

    In the process of developing energetic materials, it is necessary to evaluate the explosive power of energetic materials, especially the destructive effect of shock waves. Overpressure measurement is an important method to evaluate the power of shock waves. This article proposes an overpressure sensor based on BiScO3–PbTiO3 (BSPT) piezoelectric ceramic nanofibers (NFs). The BSPT NF sensor has the characteristics of high-temperature and high-pressure impact resistance and can be used for shock wave measurement. Experimental results show that the BSPT NF sensor has high-temperature stability; the sensitivity remains above 5.4 V/N at 60 °C–220 °C, and its sensitivity is still higher than 3.7 V/N at 240 °C. In addition, the BSPT NFs overpressure sensor has excellent overload resistance, measuring up to 65 kPa of overpressure without any damage when the trinitrotoluene (TNT) equivalent is 9.6 kg and the sensor is 4 m away from the explosion center. The results indicate that the BSPT NFs overpressure sensor has great application potential in the field of explosion testing.


  • A vital sign signal noise suppression method for wearable piezoelectric devices

    by Yi Xin, Hongyan Liu, Tianyuan Hou, Xuefeng Song, Junye Tong, Meng Cui, Meina Li, Jingjie Zhai

    This paper tackles the problem of noise suppression during vital sign signal monitoring. Physiological signal monitoring is a significant and promising medical monitoring method, and wearable medical monitoring devices based on piezoelectric polymer sensors are a trending way for their advantages of being flexible in the shape, portable to use, and comfortable to wear. However, this raises the question that the measured signal contains much more noise components. To avoid the following shortcoming of low signal to noise ratio (SNR), a noise suppression method based on improved wavelet threshold and empirical mode decomposition combined with singular value decomposition (SVD) screening the intrinsic mode function (IMF) components is proposed. A wavelet transform is first used under the combination of hard and soft thresholds to focus the target range in the low-frequency region where the energy of the physiological signal is concentrated. Then, a complete ensemble empirical mode decomposition is used to decompose the signal effectively, which can resist the influence of random noises. Meanwhile, a SVD decomposition procedure was used to filter out the lower correlated IMF components to retain the validity of the original signal. We verified the effectiveness of the proposed method through simulated and measured experiments as well as the advantages and disadvantages of the algorithm compared with other physiological signal denoising algorithms through SNR filtering results, power spectrum distribution, and other perspectives. The results proved that the proposed method could effectively remove more detailed noise and improve the SNR of the signal efficiently, which is more conducive to the demand for auxiliary medical diagnosis in the future.


  • All Solid-State Electrode With Low Contact Resistance and Low Polarization for Measuring the Electrical Properties of Rocks

    by Yi Xin, Yuhang Wang, Xuefeng Song, Junye Tong, Tianyuan Hou, Hongyan Liu, Meng Cui

    Accurate measurement of rock electrical properties plays a crucial role in resource exploration and geological exploration. But there are kinds of problems with traditional rock measuring electrodes including high contact resistance, high electrode polarization, low stability and so on. To solve these problems, we designed and fabricated an all solid-state electrode with low contact resistance, low polarizability and high stability. The electrode consists of silver (Ag) and silver chloride (AgCl). To reduce the contact resistance between the electrode and rocks, the electrode was fabricated by powder sintering and repressing, and a scanning electron microscope (SEM) showed that the surface of the electrodes was multi-holes and coarse which is beneficial to reduce contact resistance. In addition, the Ag and AgCl mixture was prepared in the polyvinyl pyrrolidone (PVP) gel, which reduced the particle size of the AgCl and led to a low polarization degree of the electrode. An experimental system for evaluation and characterization was designed to measure the basic characteristics, stability, contact resistance and polarization of the electrodes, which are essential features and will affect the accuracy of electrical measurement. And the copper (Cu) electrode is the reference electrode. The results showed that the maximum resistance of the electrode pair is lower than 0.13 Ω. Through the measurements of core samples with different moisture content, contact resistances are lower than the Cu electrodes by at least 74%, and the accuracy of resistivity measurement is increased by more than 25%. The polarization degree of the electrode is reduced by more than 65%. After multiple measurements, the electrodes still maintain great performance and the uncertainty in measurement keeps at a low level. These characteristics will improve the measuring accuracy of the core electrical properties remarkably. Therefore, this research will promote the study of petrophysical and the exploration of mineral resources.