Search

Your search keyword '"Wang, Xiaoqin"' showing total 3,229 results
Start Over Author "Wang, Xiaoqin"
3,229 results on '"Wang, Xiaoqin"'

1. AI-Enhanced Cognitive Behavioral Therapy: Deep Learning and Large Language Models for Extracting Cognitive Pathways from Social Media Texts

Author

Jiang, Meng, Yu, Yi Jing, Zhao, Qing, Li, Jianqiang, Song, Changwei, Qi, Hongzhi, Zhai, Wei, Luo, Dan, Wang, Xiaoqin, Fu, Guanghui, and Yang, Bing Xiang

Subjects
Computer Science - Computation and Language, Computer Science - Machine Learning
Abstract

Cognitive Behavioral Therapy (CBT) is an effective technique for addressing the irrational thoughts stemming from mental illnesses, but it necessitates precise identification of cognitive pathways to be successfully implemented in patient care. In current society, individuals frequently express negative emotions on social media on specific topics, often exhibiting cognitive distortions, including suicidal behaviors in extreme cases. Yet, there is a notable absence of methodologies for analyzing cognitive pathways that could aid psychotherapists in conducting effective interventions online. In this study, we gathered data from social media and established the task of extracting cognitive pathways, annotating the data based on a cognitive theoretical framework. We initially categorized the task of extracting cognitive pathways as a hierarchical text classification with four main categories and nineteen subcategories. Following this, we structured a text summarization task to help psychotherapists quickly grasp the essential information. Our experiments evaluate the performance of deep learning and large language models (LLMs) on these tasks. The results demonstrate that our deep learning method achieved a micro-F1 score of 62.34% in the hierarchical text classification task. Meanwhile, in the text summarization task, GPT-4 attained a Rouge-1 score of 54.92 and a Rouge-2 score of 30.86, surpassing the experimental deep learning model's performance. However, it may suffer from an issue of hallucination. We have made all models and codes publicly available to support further research in this field.

Published
2024

6. Identifying Barriers and Enablers to Attending Diabetic Retinopathy Screening in Immigrants to Canada From Ethnocultural Minority Groups: Protocol for a Qualitative Descriptive Study

Author

Dogba, Maman Joyce, Brent, Michael H, Bach, Catherine, Asad, Sarah, Grimshaw, Jeremy, Ivers, Noah, Légaré, France, Witteman, Holly O, Squires, Janet, Wang, Xiaoqin, Sutakovic, Olivera, Zettl, Mary, Drescher, Olivia, van Allen, Zack, McCleary, Nicola, Tremblay, Marie-Claude, Linklater, Stefanie, and Presseau, Justin

Subjects
Medicine, Computer applications to medicine. Medical informatics, R858-859.7
Abstract

BackgroundImmigrants to Canada belonging to ethnocultural minority groups are at increased risk of developing diabetes and complications, including diabetic retinopathy, and they are also less likely to be screened and treated. Improved attendance to retinopathy screening (eye tests) has the potential to reduce permanent complications, including blindness. ObjectiveThis study aims to identify the barriers and enablers of attending diabetic retinopathy screening among ethnocultural minority immigrants living with diabetes in Quebec and Ontario, Canada, to inform the development of a behavior change intervention to improve diabetic retinopathy screening attendance. MethodsThe research question draws on the needs of patients and clinicians. Using an integrated knowledge translation approach, the research team includes clinicians, researchers, and patient partners who will contribute throughout the study to developing and reviewing materials and procedures, helping to recruit participants, and disseminating findings. Using a convenience snowball strategy, we will recruit participants from three target groups: South Asian and Chinese people, and French-speaking people of African descent. To better facilitate reaching these groups and support participant recruitment, we will partner with community organizations and clinics serving our target populations in Ontario and Quebec. Data will be collected using semistructured interviews, using topic guides developed in English and translated into French, Mandarin, Hindi, and Urdu, and conducted in those languages. Data collection and analysis will be structured according to the Theoretical Domains Framework (TDF), which synthesizes predominant theories of behavior change into 14 domains covering key modifiable factors that may operate as barriers or enablers to attending eye screening. We will use directed content analysis to code barriers and enablers to TDF domains, then thematic analysis to define key themes within domains. ResultsThis study was approved for funding in December 2017, and the research ethics board approved the conduct of the study as of January 13, 2018. Data collection then began in April 2018. As of August 28, 2018, we have recruited 22 participants, and analysis is ongoing, with results expected to be published in 2020. ConclusionsFindings from this study will inform the codevelopment of theory-informed, culturally- and linguistically-tailored interventions to support patients in attending retinopathy screening. International Registered Report Identifier (IRRID)DERR1-10.2196/15109

Published
2020
Full Text
View/download PDF

11. Frontal cortex activity during the production of diverse social communication calls in marmoset monkeys.

Author

Zhao, Lingyun and Wang, Xiaoqin

Subjects
Animals, Humans, Male, Callithrix, Vocalization, Animal, Frontal Lobe, Social Behavior, Speech
Abstract

Vocal communication is essential for social behaviors in humans and non-human primates. While the frontal cortex is crucial to human speech production, its role in vocal production in non-human primates has long been questioned. It is unclear whether activities in the frontal cortex represent diverse vocal signals used in non-human primate communication. Here we studied single neuron activities and local field potentials (LFP) in the frontal cortex of male marmoset monkeys while the animal engaged in vocal exchanges with conspecifics in a social environment. We found that both single neuron activities and LFP were modulated by the production of each of the four major call types. Moreover, neural activities showed distinct patterns for different call types and theta-band LFP oscillations showed phase-locking to the phrases of twitter calls, suggesting a neural representation of vocalization features. Our results suggest important functions of the marmoset frontal cortex in supporting the production of diverse vocalizations in communication.

Published
2023

12. Analysis of the microecological mechanism of diabetic kidney disease based on the theory of 'gut–kidney axis': A systematic review

Author

Huang Lili, Wu Wenjing, and Wang Xiaoqin

Subjects
diabetic kidney disease, intestinal microbiota, metabolite, “gut–kidney axis”, Biology (General), QH301-705.5
Abstract

Diabetic kidney disease (DKD) is one of the main microvascular complications of diabetes mellitus, as well as the leading cause of end-stage renal disease. Intestinal microbiota has emerged as a crucial regulator of its occurrence and development. Dysbiosis of the intestinal microbiota can disrupt the intestinal mucosal barrier, abnormal immunological response, reduction in short-chain fatty acid metabolites, and elevation of uremic toxins, all closely related to the occurrence and development of DKD. However, the underlying mechanisms of how intestinal microbiota and its metabolites influence the onset and progression of DKD has not been fully elucidated. In the current review, we will try to summarize the microecological mechanism of DKD by focusing on three aspects: the intestinal microbiota and its associated metabolites, and the “gut–kidney axis,” and try to summarize therapies targeted at managing the intestinal microbiota, expecting to provide theoretical basis for the subsequent study of the relationship between intestinal homeostasis and DKD, and will open an emerging perspective and orientation for DKD treatment.

Published
2024
Full Text
View/download PDF

13. STING activation in TET2-mutated hematopoietic stem/progenitor cells contributes to the increased self-renewal and neoplastic transformation

Author

Xie, Jiaying, Sheng, Mengyao, Rong, Shaoqin, Zhou, Dan, Wang, Chao, Wu, Wanling, Huang, Jingru, Sun, Yue, Wang, Yin, Chen, Pingyue, Wu, Yushuang, Wang, Yuanxian, Wang, Lan, Zhou, Bo O., Huang, Xinxin, Walsh, Colum P., Bohlander, Stefan K., Huang, Jian, Wang, Xiaoqin, Xu, Guo-Liang, Gao, Hai, and Shi, Yuheng

Published
2023
Full Text
View/download PDF

15. Binary Representation via Jointly Personalized Sparse Hashing

Author

Wang, Xiaoqin, Chen, Chen, Lan, Rushi, Liu, Licheng, Liu, Zhenbing, Zhou, Huiyu, and Luo, Xiaonan

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Unsupervised hashing has attracted much attention for binary representation learning due to the requirement of economical storage and efficiency of binary codes. It aims to encode high-dimensional features in the Hamming space with similarity preservation between instances. However, most existing methods learn hash functions in manifold-based approaches. Those methods capture the local geometric structures (i.e., pairwise relationships) of data, and lack satisfactory performance in dealing with real-world scenarios that produce similar features (e.g. color and shape) with different semantic information. To address this challenge, in this work, we propose an effective unsupervised method, namely Jointly Personalized Sparse Hashing (JPSH), for binary representation learning. To be specific, firstly, we propose a novel personalized hashing module, i.e., Personalized Sparse Hashing (PSH). Different personalized subspaces are constructed to reflect category-specific attributes for different clusters, adaptively mapping instances within the same cluster to the same Hamming space. In addition, we deploy sparse constraints for different personalized subspaces to select important features. We also collect the strengths of the other clusters to build the PSH module with avoiding over-fitting. Then, to simultaneously preserve semantic and pairwise similarities in our JPSH, we incorporate the PSH and manifold-based hash learning into the seamless formulation. As such, JPSH not only distinguishes the instances from different clusters, but also preserves local neighborhood structures within the cluster. Finally, an alternating optimization algorithm is adopted to iteratively capture analytical solutions of the JPSH model. Extensive experiments on four benchmark datasets verify that the JPSH outperforms several hashing algorithms on the similarity search task.

Published
2022

16. Modeling the Impact of Intrinsic Coding Interest on STEM Career Interest: Evidence from Senior High School Students in Two Large Chinese Cities

Author

Jiang, Haozhe, Chugh, Ritesh, Turnbull, Darren, Wang, Xiaoqin, and Chen, Suting

Abstract

The problem motivating this study is the urgent need to explore the antecedents of STEM career interest and the growing importance of coding in STEM careers, coupled with the unclear relationship between intrinsic coding interest and STEM career interest. To narrow the research gap, this study explores the direct and indirect effects of intrinsic coding interest on STEM career interest. As a quantitative cross-sectional survey research, 669 students from three senior high schools in two large Chinese cities were investigated. Applying a structural equation modeling approach, the research instrument was validated and the research hypotheses were tested. The findings articulate the direct influence of intrinsic coding interest, coding self-efficacy and perceptions of coders on STEM career interest, and detect the mediating roles of coding self-efficacy and perceptions of coders between intrinsic coding interest and STEM career interest. This study affirms a new theoretical model with strong predictive power, accounting for 64% of the variance in STEM career interest. This study contributes theoretically and practically to the limited literature on coding-related antecedents of STEM career interest.

Published
2023
Full Text
View/download PDF

18. Rethinking Classifier and Adversarial Attack

Author

Yang, Youhuan, Sun, Lei, Dai, Leyu, Guo, Song, Mao, Xiuqing, Wang, Xiaoqin, and Xu, Bayi

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Cryptography and Security
Abstract

Various defense models have been proposed to resist adversarial attack algorithms, but existing adversarial robustness evaluation methods always overestimate the adversarial robustness of these models (i.e., not approaching the lower bound of robustness). To solve this problem, this paper uses the proposed decouple space method to divide the classifier into two parts: non-linear and linear. Then, this paper defines the representation vector of the original example (and its space, i.e., the representation space) and uses the iterative optimization of Absolute Classification Boundaries Initialization (ACBI) to obtain a better attack starting point. Particularly, this paper applies ACBI to nearly 50 widely-used defense models (including 8 architectures). Experimental results show that ACBI achieves lower robust accuracy in all cases.

Published
2022

19. CE-based white-box adversarial attacks will not work using super-fitting

Author

Yang, Youhuan, Sun, Lei, Dai, Leyu, Guo, Song, Mao, Xiuqing, Wang, Xiaoqin, and Xu, Bayi

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Cryptography and Security
Abstract

Deep neural networks are widely used in various fields because of their powerful performance. However, recent studies have shown that deep learning models are vulnerable to adversarial attacks, i.e., adding a slight perturbation to the input will make the model obtain wrong results. This is especially dangerous for some systems with high-security requirements, so this paper proposes a new defense method by using the model super-fitting state to improve the model's adversarial robustness (i.e., the accuracy under adversarial attacks). This paper mathematically proves the effectiveness of super-fitting and enables the model to reach this state quickly by minimizing unrelated category scores (MUCS). Theoretically, super-fitting can resist any existing (even future) CE-based white-box adversarial attacks. In addition, this paper uses a variety of powerful attack algorithms to evaluate the adversarial robustness of super-fitting, and the proposed method is compared with nearly 50 defense models from recent conferences. The experimental results show that the super-fitting method in this paper can make the trained model obtain the highest adversarial robustness.

Published
2022

26. Improving social justice in observational studies: protocol for the development of a global and Indigenous STROBE-equity reporting guideline

Author

Funnell, Sarah, Jull, Janet, Mbuagbaw, Lawrence, Welch, Vivian, Dewidar, Omar, Wang, Xiaoqin, Lesperance, Miranda, Ghogomu, Elizabeth, Rizvi, Anita, Akl, Elie A., Avey, Marc T., Antequera, Alba, Bhutta, Zulfiqar A., Chamberlain, Catherine, Craig, Peter, Cuervo, Luis Gabriel, Dicko, Alassane, Ellingwood, Holly, Feng, Cindy, Francis, Damian, Greer-Smith, Regina, Hardy, Billie-Jo, Harwood, Matire, Hatcher-Roberts, Janet, Horsley, Tanya, Juando-Prats, Clara, Kasonde, Mwenya, Kennedy, Michelle, Kredo, Tamara, Krentel, Alison, Kristjansson, Elizabeth, Langer, Laurenz, Little, Julian, Loder, Elizabeth, Magwood, Olivia, Mahande, Michael Johnson, Melendez-Torres, G. J., Moore, Ainsley, Niba, Loveline Lum, Nicholls, Stuart G., Nkangu, Miriam Nguilefem, Lawson, Daeria O., Obuku, Ekwaro, Okwen, Patrick, Pantoja, Tomas, Petkovic, Jennifer, Petticrew, Mark, Pottie, Kevin, Rader, Tamara, Ramke, Jacqueline, Riddle, Alison, Shamseer, Larissa, Sharp, Melissa, Shea, Bev, Tanuseputro, Peter, Tugwell, Peter, Tufte, Janice, Von Elm, Erik, Waddington, Hugh Sharma, Wang, Harry, Weeks, Laura, Wells, George, White, Howard, Wiysonge, Charles Shey, Wolfenden, Luke, and Young, Taryn

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results