Jingzehua Xu

Mr. Jingzehua Xu


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
30 March 2024 in Micromachines
Verified
Journal Article
Open access
PDF file
CRcui rubiao
cui rubiao
JXJingzehua Xu
Jingzehua Xu
BHBotao Huang
Botao Huang
化徐化坤 徐
化坤 徐
MPMiao Peng
Miao Peng
Huiliang CaoHuiliang Cao
Huiliang Cao
MEMS accelerometers are significantly impacted by temperature and noise, leading to a considerable compromise in their accuracy. In response to this challenge, we propose a parallel denoising and temperature compensation fusion algorithm for MEMS accelerometers based on RLMD-SE-TFPF and GRU-attention. Firstly, we utilize robust local mean decomposition (RLMD) to decompose the output signal of the accelerometer into a series of product function (PF) signals and a residual signal. Secondly, we employ sample entropy (SE) to classify the decomposed signals, categorizing them into noise segments, mixed segments, and temperature drift segments. Next, we utilize the time-frequency peak filtering (TFPF) algorithm with varying window lengths to separately denoise the noise and mixed signal segments, enabling subsequent signal reconstruction and training. Considering the strong inertia of the temperature signal, we innovatively introduce the accelerometer’s output time series as the model input when training the temperature compensation model. We incorporate gated recurrent unit (GRU) and attention modules, proposing a novel GRU-MLP-attention model (GMAN) architecture. Simulation experiments demonstrate the effectiveness of our proposed fusion algorithm. After processing the accelerometer output signal through the RLMD-SE-TFPF denoising algorithm and the GMAN temperature drift compensation model, the acceleration random walk is reduced by 96.11%, with values of 0.23032 g/h/Hz for the original accelerometer output signal and 0.00895695 g/h/Hz for the processed signal.

16 November 2023 in Sensors
Verified
Journal Article
Open access
PDF file
ZZzekai Zhang
zekai Zhang
SSShaoyang Song
Shaoyang Song
JXJingzehua Xu
Jingzehua Xu
ZWZiyuan Wang
Ziyuan Wang
XHXiangwang Hou
Xiangwang Hou
YRYong Ren
Yong Ren
The space–air–ground integrated network (SAGIN) represents a pivotal component within the realm of next-generation mobile communication technologies, owing to its established reliability and adaptable coverage capabilities. Central to the advancement of SAGIN is propagation channel research due to its critical role in aiding network system design and resource deployment. Nevertheless, real-world propagation channel research faces challenges in data collection, deployment, and testing. Consequently, this paper designs a comprehensive simulation framework tailored to facilitate SAGIN propagation channel research. The framework integrates the open source QuaDRiGa platform and the self-developed satellite channel simulation platform to simulate communication channels across diverse scenarios, and also integrates data processing, intelligent identification, algorithm optimization modules in a modular way to process the simulated data. We also provide a case study of scenario identification, in which typical channel features are extracted based on channel impulse response (CIR) data, and recognition models based on different artificial intelligence algorithms are constructed and compared.

13 October 2025 in arXiv
Verified
Preprint
Open access
PDF file
ZWZixi Wang
Zixi Wang
YCYushe Cao
Yushe Cao
YHYubo Huang
Yubo Huang
JWJinzhu Wei
Jinzhu Wei
JXJingzehua Xu
Jingzehua Xu
XLXin Lai
Xin Lai
In this paper, we propose a new method called Self-Training with Dynamic Weighting (STDW), which aims to enhance robustness in Gradual Domain Adaptation (GDA) by addressing the challenge of smooth knowledge migration from the source to the target domain. Traditional GDA methods mitigate domain shift through intermediate domains and self-training but often suffer from inefficient knowledge migration or incomplete intermediate data. Our approach introduces a dynamic weighting mechanism that adaptively balances the loss contributions of the source and target domains during training. Specifically, we design an optimization framework governed by a time-varying hyperparameter $\varrho$ (progressing from 0 to 1), which controls the strength of domain-specific learning and ensures stable adaptation. The method leverages self-training to generate pseudo-labels and optimizes a weighted objective function for iterative model updates, maintaining robustness across intermediate domains. Experiments on rotated MNIST, color-shifted MNIST, portrait datasets, and the Cover Type dataset demonstrate that STDW outperforms existing baselines. Ablation studies further validate the critical role of $\varrho$'s dynamic scheduling in achieving progressive adaptation, confirming its effectiveness in reducing domain bias and improving generalization. This work provides both theoretical insights and a practical framework for robust gradual domain adaptation, with potential applications in dynamic real-world scenarios. The code is available at https://github.com/Dramwig/STDW.