XiaoHan Zhang

Dr. XiaoHan Zhang

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
11 November 2024 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
CWChenze Wang
Chenze Wang
HWHan Wang
Han Wang
XZXiaoHan Zhang
XiaoHan Zhang
QLQing Liu
Qing Liu
MLMin Liu
Min Liu
GXGaowei Xu
Gaowei Xu
Industrial time series prediction (ITSP) is critical to the predictive maintenance system of modern industry. However, time-varying conditions and complex industrial processes cause the distribution drift of industrial time series, raising the difficulty of prediction. This article proposes an ITSP model considering distribution information, namely MDEformer. First, the multivariate dynamic embedding (MDE) is designed to provide the property of the channel-binding dynamic distribution awareness. Specifically, a dynamic mode transition and selection module is adopted to exploit dynamic distribution features of time series, and the bidirectional dynamic residual connection integrates dynamic distribution information into embedding vectors to filter distribution change interference. Then, the vanilla Transformer encoder is used to achieve multivariate prediction. Finally, a generative pretraining and fine-tuning strategy is used to enhance the generalization ability in real production scenarios. Extensive results on a real-world zinc smelting dataset illustrate the superiority of MDEformer.

23 December 2025 in Information Fusion
Verified
Journal Article
Closed access
XZXiaoHan Zhang
XiaoHan Zhang
HWHan Wang
Han Wang
CWChenze Wang
Chenze Wang
GXGaowei Xu
Gaowei Xu
MLMin Liu
Min Liu
LCLiu Chuang
Liu Chuang

20 November 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
CYChangjiang Yin
Changjiang Yin
JLJunqi Luo
Junqi Luo
QYQin Ye
Qin Ye
XZXiaoHan Zhang
XiaoHan Zhang
Cross-view geo-localization aims to retrieve images of the same location captured from different viewpoints. Recent deep learning methods have improved this task. However, most rely on full model fine-tuning, which demands large memory and storage due to extensive parameters. To address this limitation, we propose AdaptGeo, a parameter-efficient framework that adapts frozen vision foundation model through lightweight transformer-based adapter. The adapter employs multi-head attention to learn viewpoint-invariant representations, effectively bridging the domain gap between drone and satellite imagery. The framework is further enhanced by a multi-objective learning strategy that integrates contrastive learning with location-specific supervision. A frozen backbone also allows feature pre-extraction, reducing training and inference cost. Experiments on University-1652 and SUES-200 datasets demonstrate competitive performance. Compared to traditional full model fine-tuning approaches, our method reduces trainable parameters by over 87%. The proposed approach provides an efficient solution for adapting visual foundation models to cross-view geo-localization.

12 June 2026 in Sensors
Verified
Journal Article
Open access
PDF file
XLXIAO LAI
XIAO LAI
XZXiaoHan Zhang
XiaoHan Zhang
ZXZiqi Xie
Ziqi Xie
MLMin Liu
Min Liu
Currently, data-driven fault diagnosis methods have achieved remarkable progress. However, in industrial scenarios, acquiring a sufficient amount of fault data poses a challenge, thereby leading to the issue of imbalanced data in intelligent fault diagnosis. Furthermore, manual recording and instrument measurement errors will introduce label noise, which significantly impacts diagnosis performance. To address these problems, this paper proposes a safe-domain generative adversarial network with Swin Transformer (SDGAN-ST). A safe domain selection method is utilized to eliminate noisy samples and construct a pure dataset that poses no risk to the GAN training process. Consequently, GAN can generate high-quality minority samples to rebalance the original dataset. Additionally, the Swin Transformer is employed as a classifier to capture global information for each fault sample, thereby achieving high diagnostic accuracy. Experiments on the CWRU dataset and a real-world oxygen compressor bearing dataset demonstrate the effectiveness of the proposed method. On the CWRU dataset, SDGAN-ST achieves accuracies of 98.88%, 97.63%, and 97.50% under imbalance ratios of 1:10, 1:20, and 1:30, respectively. On the real-world dataset, SDGAN-ST achieves 100% accuracy under all three imbalance ratios. Additional experiments under noise ratios of 20%, 30%, and 40% show that SDGAN-ST maintains stable diagnostic performance and is more robust to label noise than ordinary WGAN-GP-based methods.

2 September 2026 in Journal of Manufacturing Systems
Verified
Journal Article
Closed access
XZXiaoHan Zhang
XiaoHan Zhang
GXGaowei Xu
Gaowei Xu
CWChenze Wang
Chenze Wang
HWHan Wang
Han Wang
MSMingzhe She
Mingzhe She
MLMin Liu
Min Liu