Author name cluster

Wenqi Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

EAAI Journal 2025 Journal Article

Weighted multi-source domain unsupervised adaptive network for rotating machinery fault diagnosis based on dual adversarial

Wenqi Wang
Zongzhen Zhang
Jinrui Wang
Baokun Han
Huaiqian Bao
Zhikang Fan
Rongkang Ge

Multi-domain adaptive methods are becoming a growing focus of fault diagnosis, which can provide enhanced data support for models using the feature information from various source domains. As a most commonly used method, unsupervised multi-domain adaptive methods (UMA) can eliminate the requirement for the label of the target domain samples. However, the neglect of contributions from different source domains to the target domain and insufficient utilization of diagnostic information from multiple source domains are the widely limitation of UMA. Therefore, a dual-adversarial weighted multi-source domain unsupervised adaptive network (DAWMUN) is proposed to utilize diagnostic information from multi-source domains and consider the contribution of different source domains. Firstly, the shared feature extractor and dual adversarial training with the domain adversarial modules between multi-source domains and source-target domains are used to enhance domain confusion between multi-source and target domains (MSTD). Secondly, based on Multiple Kernel Maximum Mean Discrepancy (MK-MMD), a novel weighting mechanism and the corresponding training framework are constructed to effectively reduce negative transfer. Finally, a novel weighted classifier is proposed to merge the outputs of multiple classifiers and synthesize the impact of each source domain. The performance of the DAWMUN is validated using a rotating machinery dataset across various transfer tasks under different rotational speed and load conditions. The experimental results demonstrate that the diagnostic accuracy using the proposed DAWMUN is superior to existing SSDA and MSDA methods, with the average accuracies of 98. 53 % and 98. 23 % across six tasks in two separate experimental setups. The comparison to the existing methods results that the DAWMUN still demonstrates superior performance with improvements of 2. 54 % and 2. 86 %, respectively.

Details DOI

JBHI Journal 2023 Journal Article

Geometry-Consistent Adversarial Registration Model for Unsupervised Multi-Modal Medical Image Registration

Yanxia Liu
Wenqi Wang
Yuhong Li
Haoyu Lai
Sijuan Huang
Xin Yang

Deformable multi-modal medical image registration aligns the anatomical structures of different modalities to the same coordinate system through a spatial transformation. Due to the difficulties of collecting ground-truth registration labels, existing methods often adopt the unsupervised multi-modal image registration setting. However, it is hard to design satisfactory metrics to measure the similarity of multi-modal images, which heavily limits the multi-modal registration performance. Moreover, due to the contrast difference of the same organ in multi-modal images, it is difficult to extract and fuse the representations of different modal images. To address the above issues, we propose a novel unsupervised multi-modal adversarial registration framework that takes advantage of image-to-image translation to translate the medical image from one modality to another. In this way, we are able to use the well-defined uni-modal metrics to better train the models. Inside our framework, we propose two improvements to promote accurate registration. First, to avoid the translation network learning spatial deformation, we propose a geometry-consistent training scheme to encourage the translation network to learn the modality mapping solely. Second, we propose a novel semi-shared multi-scale registration network that extracts features of multi-modal images effectively and predicts multi-scale registration fields in an coarse-to-fine manner to accurately register the large deformation area. Extensive experiments on brain and pelvic datasets demonstrate the superiority of the proposed method over existing methods, revealing our framework has great potential in clinical application.

Details DOI

AAAI Conference 2020 Conference Paper

Graph-Driven Generative Models for Heterogeneous Multi-Task Learning

Wenlin Wang
Hongteng Xu
Zhe Gan
Bai Li
Guoyin Wang
Liqun Chen
Qian Yang
Wenqi Wang

We propose a novel graph-driven generative model, that uniﬁes multiple heterogeneous learning tasks into the same framework. The proposed model is based on the fact that heterogeneous learning tasks, which correspond to different generative processes, often rely on data with a shared graph structure. Accordingly, our model combines a graph convolutional network (GCN) with multiple variational autoencoders, thus embedding the nodes of the graph (i. e. , samples for the tasks) in a uniform manner, while specializing their organization and usage to different tasks. With a focus on healthcare applications (tasks), including clinical topic modeling, procedure recommendation and admission-type prediction, we demonstrate that our method successfully leverages information across different tasks, boosting performance in all tasks and outperforming existing state-of-the-art approaches.

PDF Details