Xiaofei Yang

Xiaofei Yang

Auto-generated profile, based on publicly available information

Xiaofei Yang

Huazhong University of Science and Technology

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 June 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
YQYijie Qin
Yijie Qin
KLKeyan Li
Keyan Li
WZWenting Zhang
Wenting Zhang
YPYang Pan
Yang Pan
JCJun Chen
Jun Chen
XYXiaofei Yang
Xiaofei Yang
Active magnetic detection is an effective method for detecting metal targets. Its practical application is confirmed in many previous studies, and its advantages over passive detection have been widely recognized. Most importantly, it can detect weak magnetic or nonmagnetic metal targets, unlike traditional magnetic detection. However, the secondary magnetic field generated by the eddy current on the target excited by the active emission primary magnetic field is always weak, and it has a fast attenuation in space. The target signal measured by the sensor is typically several orders of magnitude smaller than the background interference, which makes it challenging to extract the target signal during detection. This study mitigates these challenges by constructing the secondary magnetic field characteristic of the target from the perspective of signal energy. A set of 13 orthonormal basis functions (OBFs) are further derived to linearly describe this characteristic, which improves the signal-to-noise ratio (SNR) of the signal. The main contribution of this study is the proposal of an eddy current magnetic field OBF (ECMF-OBF) method to effectively characterize the secondary magnetic field of magnetic targets in active magnetic detection. The SNR is considerably improved by the proposed method, and this is independent of the target magnetic moment orientation. Our experiment is performed in different environments, including indoors, lake, and sea, to verify the method’s performance. Therefore, it has excellent value in the practical application of active magnetic detection.

27 June 2024 in IEEE Sensors Journal
Verified
Journal Article
Closed access
ZCZijie Chen
Zijie Chen
MLMiao Linliang
Miao Linliang
XYXiaofei Yang
Xiaofei Yang
JOJun Ouyang
Jun Ouyang
A Siamese neural network architecture is introduced to enhance the stability and generalization of deep neural networks for magnetic anomaly detection. Grounded in signal disparity contrastive learning, this study addresses the statistical disparity in signals from various regions and times. Within the proposed architecture, two identical one-dimensional convolutional neural networks with shared parameters are used as feature extractors for obtaining the embedding of paired input signals in the target space. Decision networks are then formulated to measure the discrepancies between these embeddings, shedding light on the differences between the original signals. A base signal family is crafted for detection using multiple noisy signals that are spatially and temporally aligned with the evaluated signal. The difference between the measured signal and those in the base family is computed. A voting mechanism subsequently determines if the assessed signal is a magnetic anomaly. Numerous semi-realistic datasets are employed for network training. The results indicate that the proposed network surpasses several existing networks in robustness with regard to detection area, time, and signal parameter variations and also has excellent detection capability and temperature in the face of measured magnetic anomaly signals. Notably, with changes in test parameters, the network only requires the background noise signal as the base, maintaining high detection performance without retraining.

1 March 2022 in AIP Advances
Verified
Journal Article
Open access
PDF file
YQYijie Qin
Yijie Qin
MLMaobin Li
Maobin Li
KLKeyan Li
Keyan Li
YPYang Pan
Yang Pan
XYXiaofei Yang
Xiaofei Yang
JOJun Ouyang
Jun Ouyang
Magnetic anomaly detection (MAD) is an effective method to detect the existence and localization of magnetic targets. Magnetic signal processing technology can extract target signals from complex background noise. However, traditional magnetic signal processing methods cannot greatly improve the signal-to-noise ratio (SNR) while also restoring information concerning the target. This is because the main existing method to calculate a target’s magnetic moment requires a pure target signal. Our research regarding the full magnetic gradient orthonormal basis function (FMG-OBF) addresses the problem of low SNRs for the target magnetic anomaly (TMA) signal. However, this method can only detect the presence of the target and cannot obtain the magnetic moment characteristics of the target. Benefiting from the FMG tensor, which contains large amounts of spatial magnetic field information, this paper is devoted to characterizing TMA in different orientations from the signal energy point of view. We analyze the influences of the target magnetic moment’s variation on the energy components of the TMA signal in various orientations, and further propose a target magnetic moment orientation estimation method. Compared with the traditional signal processing method, the proposed method can estimate the magnetic moment orientation of the target while greatly improving the SNR. Therefore, this method has significant application potential for the classification and identification of weak TMA signals in MAD.

29 July 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YQYijie Qin
Yijie Qin
MLMiao Linliang
Miao Linliang
HQHailin Qiu
Hailin Qiu
ZCZijie Chen
Zijie Chen
HKHaorui Ke
Haorui Ke
JOJun Ouyang
Jun Ouyang
Magnetic anomaly detection (MAD) plays a critical role in both geophysical exploration and environmental monitoring. Despite advancements, traditional MAD methods often struggle with low signal-to-noise ratios (SNR) and complex background noise, limiting their effectiveness. This study introduces a novel magnetic anomaly signal Restormer (MASR) approach, significantly outperforming existing signal restoration techniques in the MAD field regarding accuracy and reliability. Leveraging the unconventional computing power of magnetic tunnel junctions (MTJs), we propose an integrated measurement-computation system designed to implement the MASR method efficiently. Our system demonstrates superior detection performance and marks a departure from conventional von Neumann architectures, offering enhanced computational efficiency and energy savings. By integrating nanodevice-enabled artificial intelligence (AI) directly with signal measurement, our approach minimizes reliance on external processing units and data transmission, ensuring rapid, real-time MAD processing. This system is particularly suited to address the challenges of low SNR and harsh working conditions prevalent in geoscience data analysis. Experimental results obtained from real-world oceanic deployments validate the superiority of the MASR method and the integrated system in achieving high-fidelity magnetic anomaly signal restoration under challenging conditions. This research not only advances the field of MAD but also paves the way for future developments in energy-efficient, compact, and high-performance real-time remote sensing systems, laying the groundwork for broader applications of nanotechnology-enabled AI in autonomous and efficient remote sensing systems.

19 January 2017 in Applied Physics Express
Verified
Journal Article
Closed access
PZPeng Zhou
Peng Zhou
CYChao Yang
Chao Yang
JLJunyu Li Li
Junyu Li Li
XLXiangli Liu
Xiangli Liu
ZMZhiheng Mei
Zhiheng Mei
TZTianjin Zhang
Tianjin Zhang

1 October 2016 in Brain Research Bulletin
Verified
Journal Article
Closed access
ALAi-Ling Li
Ai-Ling Li
XYXiaofei Yang
Xiaofei Yang
J.-C. ChiaoJ.-C. Chiao
J.-C. Chiao
YPYuan Bo Peng
Yuan Bo Peng