Xuedong Tian

Dr. Xuedong Tian

Hebei University, Baoding, Hebei, China
orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
5 January 2021 in IEEE Access
Verified
Journal Article
Open access
XTXuedong Tian
Xuedong Tian
JWJiameng Wang
Jiameng Wang
When retrieving scientific documents with mathematical expressions as the main content, both mathematical expressions and their contextual text features require consideration. However, mathematical expressions are different from texts in terms of grammar and semantics. Thus, integrating the above features and realizing scientific document retrieval is difficult. In this study, a retrieval method of scientific documents based on HFS (Hesitation Fuzzy Sets) and BERT (Bidirectional Encoder Representations from Transformer) is proposed. This method is realized through utilizing the advantages of HFS in multi-attribute decision making and BERT in context-dependent similarity calculation. By analyzing mathematical expressions and calculating the membership degree of symbolic multi-attributes, the similarity of mathematical expressions can be obtained, which can improve the accuracy of mathematical expression recall. With the extraction of the text of the expression context, BERT is used to calculate the context similarity. Then, the recalled technical documents are sorted according to the similarity of context, and the final retrieval result can be obtained. Experiments were carried out on 10,372 Chinese and 11,770 English scientific documents in the NTCIR extended data set. The average value of MAP_ $k (k=10)$ for the recall results of scientific documents was 74.13%. The average $n$ DCG ( $n=10$ ) for the ranking of scientific documents was 86.04%.

21 August 2022 in Electronics
Verified
Journal Article
Open access
PDF file
DZDan Zhao
Dan Zhao
XTXuedong Tian
Xuedong Tian
The easy availability and usability of photo-editing tools have increased the number of forgery attacks, primarily splicing attacks, thereby increasing cybercrimes. Because of an existing image-splicing tamper-detection algorithm based on deep learning with high model complexity and weak robustness, a multiscale fusion lightweight model for image-splicing tamper detection is proposed. For the above problems and to improve MobileNetV2, the structural block of the classification part of the original network structure was removed, the stride of the sixth largest structural block of the network was changed to 1, the dilated convolution was used instead of downsampling, and the features extracted from the second and third large structural blocks in the network were downsampled with maximal pooling; then, the constraint on the backbone network was increased by jumping connections. Combined with the pyramid pooling module, the acquired feature layers were divided into regions of different sizes for average pooling; then, all feature layers were fused. The experimental results show that it had a low number of parameters and required a small amount of computation, achieving 91.0% and 96.4% precision on CASIA and COLUMB, respectively, and 83.2% and 88.1% F-measure on CASIA and COLUMB, respectively.

27 January 2022 in Computational Intelligence and Neuroscience
Verified
Journal Article
Open access
PDF file
CLChun Li
Chun Li
YWYu Wen
Yu Wen
QSQingxuan Shi
Qingxuan Shi
FYFang Yang
Fang Yang
HMHongyan Ma
Hongyan Ma
XTXuedong Tian
Xuedong Tian
To solve the problem of low detection accuracy due to the loss of detailed information when extracting pavement crack features in traditional U-shaped networks, a pavement crack detection method based on multiscale attention and hesitant fuzzy set (HFS) is proposed. First, the encoding-decoding structure is used to construct a pavement crack segmentation network, ResNeXt50 is used to extract features in the encoding stage, and a multiscale feature fusion module (MFF) is designed to obtain multiscale context information. Second, in the decoding stage, a high-efficiency dual attention module (EDA) is used to enhance the ability of capturing details of the cracks while suppressing background noise. Finally, the membership degree of the crack is calculated based on the advantages of the HFS in multiattribute decision-making to obtain the similarity of the crack, and the binary image after segmentation is judged by the hesitation fuzzy measure. The experiment was conducted on the public road crack dataset Crack500. In terms of segmentation performance, the evaluation indexes Intersection over Union (IoU), Precision, and Dice coefficients of the proposed network reached 55.56%, 74.26%, and 67.43%, respectively; in terms of classification performance, for transversal and longitudinal cracks, the classification accuracy was 84% ± 0.5%, while the block and the alligator were both 78% ± 0.5%. The experimental results prove that the crack details detected by the proposed method are more abundant, and the image detection effect of complex topological structures and small cracks are better.

3 August 2022 in Electronics
Verified
Journal Article
Open access
PDF file
HYHaixin Yang
Haixin Yang
BTBingjie Tian
Bingjie Tian
XTXuedong Tian
Xuedong Tian
Few-shot text classification aims to recognize new classes with only a few labeled text instances. Previous studies mainly utilized text semantic features to model the instance-level relation among partial samples. However, the single relation information makes it difficult for many models to address complicated natural language tasks. In this paper, we propose a novel hesitant fuzzy graph neural network (HFGNN) model that explores the multi-attribute relations between samples. We combine HFGNN with the Prototypical Network to achieve few-shot text classification. In HFGNN, multiple relations between texts, including instance-level and distribution-level relations, are discovered through dual graph neural networks and fused by hesitant fuzzy set (HFS) theory. In addition, we design a linear function that maps the fused relations to a more reasonable range in HFGNN. The final relations are used to aggregate the information of neighbor instance nodes in the graph to construct more discriminative instance features. Experimental results demonstrate that the classification accuracy of the HFGNN-based Prototypical Network (HFGNN-Proto) on the ARSC, FewRel 5-way 5-shot, and FewRel 10-way 5-shot datasets reaches 88.36%, 94.45%, and 89.40%, respectively, exceeding existing state-of-the-art few-shot learning methods.

4 August 2020 in IEEE Access
Verified
Journal Article
Open access
XTXuedong Tian
Xuedong Tian
TSTengying Sun
Tengying Sun
YQYanmei Qi
Yanmei Qi
To address the low segmentation accuracy caused by the rich glyph styles of ancient Chinese characters and the complex layout of ancient Chinese books, which affects the retrieval and recognition results, an algorithm for the layout image analysis of ancient Chinese books and Chinese character image segmentation is proposed. The initial segmentation results were obtained through the projection method of the layout of ancient Chinese books, and the connected component analysis of the above results was carried out to determine the rough divided blocks of under-segmentation and over-segmentation. Considering under-segmentation of adhesive Chinese characters, the improved K-means clustering method was used to segment adhesive blocks to obtain single-character images. To address the over-segmentation of character components separation, a method based on interval-valued hesitant fuzzy set is proposed. This method analyzed the features of the connected component in the block, characterized the over-segmentation connected component. The hesitant fuzzy distances between other connected components and the standard merge evaluation interval number were calculated in sequence. The connected component with the smallest distance was preferentially merged with the over-segmentation connected component until no over-segmentation connected component remained in the block. The experimental segmentation accuracy was 89.94%.

1 January 2017
Verified
Conference Paper
Open access
PDF file
XTXuedong Tian
Xuedong Tian
Full text search engines widely used today still have no math searching function, which brings inconvenience for people finding their scientific documents with mathematical query words. It is necessary to research and develop the theory and technology of mathematical expression retrieval. This paper proposed an index model of mathematical expressions for realizing math retrieval through analyzing the characteristics of formulae. Firstly, the FDS data was obtained from the formulae expressed in LaTeX description with recursive analysis. Then, the index features including the level and location features of operators were extracted from the FDS data of formulae. Finally, the extracted features were used to construct a feature vector for dividing formulae into several classes and the math index was constructed for the classes respectively. The experiment was carried out on 134199 formulae and the result shows its effectiveness for improving the efficiency of mathematical expression retrieval.