Search

Your search keyword '"Zhang, Yanping"' showing total 4,424 results
Start Over Author "Zhang, Yanping"
4,424 results on '"Zhang, Yanping"'

1. Why are hyperbolic neural networks effective? A study on hierarchical representation capability

Author

Tan, Shicheng, Zhao, Huanjing, Zhao, Shu, and Zhang, Yanping

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

Hyperbolic Neural Networks (HNNs), operating in hyperbolic space, have been widely applied in recent years, motivated by the existence of an optimal embedding in hyperbolic space that can preserve data hierarchical relationships (termed Hierarchical Representation Capability, HRC) more accurately than Euclidean space. However, there is no evidence to suggest that HNNs can achieve this theoretical optimal embedding, leading to much research being built on flawed motivations. In this paper, we propose a benchmark for evaluating HRC and conduct a comprehensive analysis of why HNNs are effective through large-scale experiments. Inspired by the analysis results, we propose several pre-training strategies to enhance HRC and improve the performance of downstream tasks, further validating the reliability of the analysis. Experiments show that HNNs cannot achieve the theoretical optimal embedding. The HRC is significantly affected by the optimization objectives and hierarchical structures, and enhancing HRC through pre-training strategies can significantly improve the performance of HNNs.

Published
2024

8. A Study of Green Supply Chain Finance Risk Contagion Measurement Based on SEIRS Model

Author

Chang, Dan, Zhang, Yanping, Guo, Yaotian, Barbosa-Povoa, Ana Paula, Editorial Board Member, de Almeida, Adiel Teixeira, Editorial Board Member, Gans, Noah, Editorial Board Member, Gupta, Jatinder N. D., Editorial Board Member, Heim, Gregory R., Editorial Board Member, Hua, Guowei, Editorial Board Member, Kimms, Alf, Editorial Board Member, Li, Xiang, Editorial Board Member, Masri, Hatem, Editorial Board Member, Nickel, Stefan, Editorial Board Member, Qiu, Robin, Editorial Board Member, Shankar, Ravi, Editorial Board Member, Slowiński, Roman, Editorial Board Member, Tang, Christopher S., Editorial Board Member, Wu, Yuzhe, Editorial Board Member, Zhu, Joe, Editorial Board Member, Zopounidis, Constantin, Editorial Board Member, Li, Menggang, editor, Guowei, Hua, editor, Huang, Anqiang, editor, Fu, Xiaowen, editor, and Chang, Dan, editor

Published
2024
Full Text
View/download PDF

9. A Novel Method for Fault Diagnosis of Motor Bearings via Chord Transformation Strategy

Author

Luo, Peien, Yin, Zhonggang, Zhang, Yanqing, Zhang, Yanping, Yuan, Dongsheng, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, Hu, Cungang, editor, and Cao, Wenping, editor

Published
2024
Full Text
View/download PDF

18. TMA: Temporal Motion Aggregation for Event-based Optical Flow

Author

Liu, Haotian, Chen, Guang, Qu, Sanqing, Zhang, Yanping, Li, Zhijun, Knoll, Alois, and Jiang, Changjun

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Event cameras have the ability to record continuous and detailed trajectories of objects with high temporal resolution, thereby providing intuitive motion cues for optical flow estimation. Nevertheless, most existing learning-based approaches for event optical flow estimation directly remould the paradigm of conventional images by representing the consecutive event stream as static frames, ignoring the inherent temporal continuity of event data. In this paper, we argue that temporal continuity is a vital element of event-based optical flow and propose a novel Temporal Motion Aggregation (TMA) approach to unlock its potential. Technically, TMA comprises three components: an event splitting strategy to incorporate intermediate motion information underlying the temporal context, a linear lookup strategy to align temporally fine-grained motion features and a novel motion pattern aggregation module to emphasize consistent patterns for motion feature enhancement. By incorporating temporally fine-grained motion information, TMA can derive better flow estimates than existing methods at early stages, which not only enables TMA to obtain more accurate final predictions, but also greatly reduces the demand for a number of refinements. Extensive experiments on DSEC-Flow and MVSEC datasets verify the effectiveness and superiority of our TMA. Remarkably, compared to E-RAFT, TMA achieves a 6\% improvement in accuracy and a 40\% reduction in inference time on DSEC-Flow. Code will be available at \url{https://github.com/ispc-lab/TMA}., Comment: Accepted by ICCV2023

Published
2023

19. Application Research of 'Internet+' Dialectical Behavior Therapy Intervention Mode in Adolescent Non-suicidal Self-injury Intervention

Author

ZHANG Yanping, YAN Fang, WANG Hailing, GUO Zhengjun, ZHAO Jingyuan, ZHAO Yujie

Subjects
adolescent, internet-based intervention, non-self-harm self-injury, dialectical behavior therapy, rehabilitation, random control, Medicine
Abstract

Background Adolescent non-suicidal self-injury has become an increasingly serious mental health problem, and its course is protracted, causing serious burdens to patients, families and society. Intervention of non-suicidal self-injury in adolescents requires a comprehensive intervention model, and the practice of online intervention management in China is still in its infancy. Objective To investigate the intervention effect of "Internet+" dialectical behavior therapy (DBT) on suicidal ideation, cognitive emotion regulation, and alleviation of depression in adolescent patients with non-suicidal self-injury. Methods A total of 120 adolescent patients with non-suicidal self-injury who were discharged from the Second Affiliated Hospital of Xinxiang Medical University from May 2021 to May 2022 were selected and randomly divided into the control group (n=60) and intervention group by randomized controlled single-blind method (n=60). The control group received drug intervention, telephone follow-up and psychological counseling, the intervention group implemented a one-year "Internet+" DBT training based on the control group, which was divided into 4 modules of mindfulness training, interpersonal effectiveness training, emotion regulation training and pain tolerance training. Before the intervention, 6 months and 12 months after the intervention, the Self-rating Idea of Suicide Scale (SIOSS), Chinese version of Cognitive Emotion Regulation Questionnaire, (CERQ-C) and Montgomery and Asberg Depression Rating Scale (MADRS) were used to evaluate the suicidal ideation, cognitive emotion regulation, and depression status of the two groups of patients. Repeated measures analysis of variance was used to compare the health status of the two groups at different time points. Results Finally, 57 cases in the control group and 55 cases in the intervention group completed the study. There was an interaction between group and time on SIOSS, CERQ-C, and MADRS scores (P0.001). The difference was statistically significant when comparing the self-blame, acceptance, and contemplation dimensions of the CERQ-C scores before and after intervention within the control group (P

Published
2024
Full Text
View/download PDF

24. Study on the waste activated sludge dewatering effect and mechanism conditioned by persulfate induced with iron-based sludge biochar

Author

ZHANG Jing, ZHANG Yanping, PEI Jiahua, JIA Xiaosai, LI Yibing, and LÜ Ning

Subjects
iron-based sludge biochar, persulfate, sludge dewatering, skeleton construction, extracellular polymer, Environmental technology. Sanitary engineering, TD1-1066
Abstract

In order to improve the dewatering performance of waste activated sludge，iron-based sludge biochar（Iron-SBC） activating persulfate（PDS） was used to treat sludge. The effects of PDS dosage，Iron-SBC dosage，reaction time，reaction temperature and initial pH on waste activated sludge dewatering efficiency were studied，and the mechanism was also analyzed. The results showed that when the temperature was 65 ℃，the dosage of PDS per unit TSS was 150 mg/g，the dosage of Iron-SBC per unit TSS was 350 mg/g，the initial pH was 6.68，after being conditioned by Iron-SBC/PDS for 20 minutes，the sludge capillary water absorption time，sludge specific resistance and sludge cake moisture content decreased to 8.4 s，5.4×1012 m/kg and 73.5%，respectively. The mechanism analysis indicated that oxidation reaction occurred during the process. The originally tight and flat sludge flocs and extracellular polymers were cracked and the bound water was released. The highly hydrophilic tightly bound extracellular polymeric substances（TB-EPS） in sludge were transformed into loosely bound extracellular polymeric substances（LB-EPS） and soluble extracellular polymeric substances（S-EPS），and the proteins which were unfavorable to sludge dewatering were oxidized and degraded. The decrease of TB-EPS and neutralization of positive iron ions increased the Zeta potential value. Iron-SBC with rigid structure reduced the compressibility coefficient of sludge cake. At the same time，under the flocculation of Fe3+，the fractal dimension of sludge became larger. Under the coupling action of “oxidation-skeleton construction”，the waste activated sludge deep dewatering was realized.

Published
2024
Full Text
View/download PDF

26. Coherence-Based Distributed Document Representation Learning for Scientific Documents

Author

Tan, Shicheng, Zhao, Shu, and Zhang, Yanping

Subjects
Computer Science - Computation and Language
Abstract

Distributed document representation is one of the basic problems in natural language processing. Currently distributed document representation methods mainly consider the context information of words or sentences. These methods do not take into account the coherence of the document as a whole, e.g., a relation between the paper title and abstract, headline and description, or adjacent bodies in the document. The coherence shows whether a document is meaningful, both logically and syntactically, especially in scientific documents (papers or patents, etc.). In this paper, we propose a coupled text pair embedding (CTPE) model to learn the representation of scientific documents, which maintains the coherence of the document with coupled text pairs formed by segmenting the document. First, we divide the document into two parts (e.g., title and abstract, etc) which construct a coupled text pair. Then, we adopt negative sampling to construct uncoupled text pairs whose two parts are from different documents. Finally, we train the model to judge whether the text pair is coupled or uncoupled and use the obtained embedding of coupled text pairs as the embedding of documents. We perform experiments on three datasets for one information retrieval task and two recommendation tasks. The experimental results verify the effectiveness of the proposed CTPE model.

Published
2022

28. Status of aquatic organisms resources and their environments in Yangtze River system (2017–2021)

Author

Yang, Haile, Shen, Li, He, Yongfeng, Tian, Huiwu, Gao, Lei, Wu, Jinming, Mei, Zhigang, Wei, Nian, Wang, Lin, Zhu, Tingbing, Hu, Feifei, Gong, Jinling, Du, Hongchun, Duan, Xinbin, Deng, Huatang, Wang, Daoqun, Zhu, Fengyue, Li, Yunfeng, Wu, Fan, Ru, Huijun, Zhang, Yan, Li, Junyi, Yang, Junlin, Zhou, Yuntao, Fang, Dongdong, Wang, Yinping, Lin, Danqing, Yang, Yanping, Li, Peijie, Liu, Silei, Yang, Jian, Zhuang, Ping, Wang, Sikai, Zhang, Tao, Yang, Gang, Yang, Wenbo, Yuan, Lilai, Cao, Kun, Xu, Shuo, Liu, Huiyuan, Liang, Zhiqiang, Wang, Chongrui, Li, Hong, Yuan, Xiping, Yang, Xin, Fu, Yilong, Zhang, Yanping, Zhang, Haixin, Tao, Zhiying, Wang, Sheng, Gao, Xiaoping, Jin, Binsong, Li, Kemao, Wang, Guojie, Jian, Shenglong, Li, Yingqin, Xue, Chenjiang, Lei, Chunyun, Xue, Shaowei, Sun, Yi, Zhu, Bin, Shao, Ke, Hu, Xingkun, Xiong, Meihua, Du, Jun, He, Bin, Yan, Tao, Huang, Yingying, Zou, Yuanchao, Xie, Biwen, Wang, Yongming, Li, Bin, Liu, Fei, Zhang, Yaoyao, Fan, Fei, Wang, Zhijian, Huang, Jing, Gu, Haoran, Ge, Hailong, Dan, Yan, Li, Yan, Wang, Shuqiao, Zhang, Chuang, Zhou, Lu, Wang, Xue, Zeng, Sheng, Xiang, Yan, He, Xugang, Qin, Jianhui, Xia, Chengxing, Hou, Jie, Shi, Yifu, Gao, Lifang, Zhu, Zhiqiang, Shen, Hongbao, Du, Yun, Duan, Xuejun, Xiong, Jiawu, Yang, Deguo, Liu, Shaoping, Ni, Zhaohui, Zhang, Hui, Liu, Kai, Zhao, Feng, Li, Yingren, Wang, Jianwei, and Wei, Qiwei

Published
2024
Full Text
View/download PDF

42. Robust Sentiment Analysis Model Based on Feature Representation in Uncertainty Domain

Author

CHEN Jie, LI Shuai, ZHAO Shu, ZHANG Yanping

Subjects
sentiment analysis, three-way decision, robustness, multi-granularity feature representation, feature fusion, Electronic computers. Computer science, QA75.5-76.95
Abstract

In the sentiment classification of text data, there are often some fuzzy data that are difficult to classify. Due to their uncertainty, these fuzzy data appear to be over fitted during model training, which affects the robustness of the model. The three-way decision theories divide the initial sample into deterministic domains and uncertain domains, and how to select appropriate features for representation in the uncertain domain where the fuzzy data is located for downstream tasks is the challenge of the three-way decision sentiment analysis models. To address this challenge, a robust sentiment analysis model (UFR-SA) based on feature representation of three-way decision uncertainty domains is proposed. Firstly, based on the three-way decision theory, the deterministic domain and the uncertain domain are divided. For fuzzy samples in the uncertain domain, heterogeneous sample point pairs are defined to construct hierarchical features. Secondly, a hierarchical feature fusion model is designed to incorporate the advantages of each granularity feature into a multi-layer perceptual network. Finally, a divide and conquer strategy is adopted for test samples in the deterministic domain and the uncertain domain. The deterministic domain data are represented by the original features, and the fuzzy data in the uncertain domain are represented by the fused robust features. Experimental results on SST-2, SST-5, and CR datasets show that UFR-SA effectively reduces the interference of fuzzy data on the model and outperforms the performance of state-of-the-art models.

Published
2023
Full Text
View/download PDF

43. GTM: Gray Temporal Model for Video Recognition

Author

Zhang, Yanping and Yu, Yongxin

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Data input modality plays an important role in video action recognition. Normally, there are three types of input: RGB, flow stream and compressed data. In this paper, we proposed a new input modality: gray stream. Specifically, taken the stacked consecutive 3 gray images as input, which is the same size of RGB, can not only skip the conversion process from video decoding data to RGB, but also improve the spatio-temporal modeling ability at zero computation and zero parameters. Meanwhile, we proposed a 1D Identity Channel-wise Spatio-temporal Convolution(1D-ICSC) which captures the temporal relationship at channel-feature level within a controllable computation budget(by parameters G & R). Finally, we confirm its effectiveness and efficiency on several action recognition benchmarks, such as Kinetics, Something-Something, HMDB-51 and UCF-101, and achieve impressive results.

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results