检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Santcroos, Mark A. Kosters, Walter A. Lefter, Mihai Laros, Jeroen F.J. Vis, Jonathan K. Department of Human Genetics Leiden University Medical Center Netherlands Department of Clinical Genetics Leiden University Medical Center Netherlands Leiden Institute of Advanced Computer Science Leiden University Netherlands Netherlands

Motivation: Accurate variant descriptions are of paramount importance in the field of genetics. The domain is confronted with increasingly complex variants, making it more challenging to generate proper variant descriptions. Results: We present a graph based on all minimal alignments that is a complete representation of a variant and we provide three complementary extraction methods to derive variant descriptions from this graph. Our experiments show that our method in comparison with dbSNP results in identical HGVS descriptions for simple variants and more meaningful descriptions for complex variants. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sociotechnical AI Governance: Challenges and Opportunities for HCI

Sociotechnical AI Governance: Challenges and Opportunities f...

引用

2025 CHI Conference on human Factors in Computing Systems, CHI EA 2025

作者： Kevin Feng, K.J. Pang, Rock Yuren Kuo, Tzu-Sheng Winecoff, Amy Tseng, Emily Widder, David Gray Suresh, Harini Reinecke, Katharina Zhang, Amy X. University of Washington SeattleWA United States Paul G. Allen School of Computer Science & Engineering University of Washington SeattleWA United States Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA United States Center for Democracy & Technology WashingtonDC United States Microsoft Research New YorkNY United States Cornell Tech New YorkNY United States Brown University ProvidenceRI United States

ISBN: (纸本)9798400713958

Rapid advancements in and adoption of frontier AI systems have amplified the need for AI governance measures across the public sector, academia, and industry. Prior work in technical AI governance has proposed agendas for governing technical components in AI development, such as data, models, and compute. However, recent calls for more sociotechnical approaches recognize the critical role of social infrastructures surrounding technical ones in shaping governance decisions and efforts. While scholars and practitioners have advocated for sociotechnical AI governance, concrete research directions in this area are only beginning to emerge. This workshop aims to gather the expertise of researchers in HCI and adjacent disciplines to chart promising paths forward for sociotechnical AI governance. To make problems in this area more tangible, we outline four core governance challenges for contributions: anticipating high-priority risks to address with governance, identifying where to focus governance efforts and who should lead those efforts, designing appropriate interventions and tools to implement governance actions in practice, and evaluating the effectiveness of these interventions and tools in context. Through papers, panel discussions, keynotes, and collaborative drafting of a research agenda, this workshop will build community and empower actionable efforts to tackle AI governance through a sociotechnical lens. © 2025 Copyright held by the owner/author(s).

关键词： AI governance human-AI interaction responsible AI sociotechnical methods

来源：评论

学校读者我要写书评

暂无评论

Enhancing ESG Reporting Analysis: Leveraging GPT and Resampling Methods for Improved Multi-Label Classification

Enhancing ESG Reporting Analysis: Leveraging GPT and Resampl...

引用

Electronic Communications, Internet of Things and Big Data (ICEIB), International Conference on

作者： Jun-Wei Wu Lydia Hsiao-Mei Lin Richard Tzong-Han Tsai Department of Computer Science and Information Engineering National Central University Taoyuan Taiwan Department of Interaction Design National Taipei University of Technology Taipei Taiwan Center for GIS Research Center for Humanities and Social Sciences Academia Sinica Taipei Taiwan

ISBN: (数字)9798350360721

ISBN: (纸本)9798350360738

ESG reporting, covering environmental, social, and governance aspects, is a crucial resource for investors, companies, and governments to understand a company's value. However, the sheer volume of data and information in the reports makes it difficult to retrieve specific information on ESG. ESG-BERT models are developed to categorize the content of ESG reports based on the relevant field. However, the accurate prediction of multiple classifications is difficult due to unevenly distributed labels. To address this problem, we used a self-made assistant based on GPT to label the data and then resampling technology to adjust the balance of the data set. After the data set was balanced, we adjusted to ESG-BERT to improve its multi-label classification accuracy. We evaluated multiple resampling methods and determined the most suitable strategy for classifying ESG report content. Thus, the accuracy of ESG content analysis was improved through more refined model adjustment and preprocessing methods. The results indicated that balancing the data for improved classification ensures fairness and objectivity in distributing content for ESG reports with multiple labels.

关键词： Analytical models Accuracy Government Training data Companies Big Data Data models

来源：评论

学校读者我要写书评

暂无评论

CL-MIL: Multi-Instance Learning on Whole-Slide Images with Self-Supervised Contrastive Learning

CL-MIL: Multi-Instance Learning on Whole-Slide Images with S...

引用

International Conference on computer and Communications (ICCC)

作者： Pengfei Xiu Dongying Liu Sheng Wang Hongliang Wang Wei Wang Shun Li Shenyang Institute of Computing Technology Chinese Academy of Science Shenyang China University of Chinese Academy of Sciences Beijing China Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Department of Gastroenterology Shengjing Hospital of China Medical University Shenyang China School of Computer Science and Engineering Northeastern University Shenyang China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

Histopathological examination of tissue slides is considered the gold standard for clinical cancer diagnosis. However, it heavily relies on pathologists' subjective judgment and involves substantial workload. Existing convolutional neural network (CNN)-based whole slide image (WSI) diagnostic methods suffer from high annotation costs and complex data acquisition processes. Therefore, this study proposes a weakly supervised multiple instance learning method based on self-supervised contrastive learning (CL-MIL) for WSI classification. By integrating self-supervised contrastive learning strategies, leveraging data augmentation through H&E stain separation, and introducing causal intervention via backdoor adjustment to mitigate dataset bias, our approach significantly enhances feature representation and classification performance in pathological images. Experimental results on the Camelyon16 and TCGA lung cancer datasets demonstrate that our method outperforms other comparable WSI classification models across various evaluation metrics, achieving higher diagnostic efficiency and accuracy. Additionally, our method exhibits good interpretability, enabling precise localization of pathological regions and providing robust technical support for clinical applications.

关键词： Measurement Location awareness Pathology Accuracy Weak supervision Lung cancer Contrastive learning Feature extraction Standards Image classification

来源：评论

学校读者我要写书评

暂无评论

CL-MIL: Multi-Instance Learning on Whole-Slide Images with Self-Supervised Contrastive Learning 10

CL-MIL: Multi-Instance Learning on Whole-Slide Images with S...

引用

10th International Conference on computer and Communications, ICCC 2024

作者： Xiu, Pengfei Liu, Dongying Wang, Sheng Wang, Hongliang Wang, Wei Li, Shun Shenyang Institute of Computing Technology Chinese Academy of Science Shenyang China University of Chinese Academy of Sciences Beijing China Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Shengjing Hospital of China Medical University Department of Gastroenterology Shenyang China School of Computer Science and Engineering Northeastern University Shenyang China

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition from Eye Movements Using Multi-way Autoregressive Model

Emotion Recognition from Eye Movements Using Multi-way Autor...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Tian-Fang Ma Xuan-Hao Liu Wei-Long Zheng Bao-Liang Lu Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

The application of physiological signals in emotion recognition is a popular research topic in human-computer interactions. Eye movement, as an important physiological signal, plays an essential role in medicine, psychology, cognitive science, and other scientific research fields. Previous studies have successfully identified human emotions by combining various eye-related measurements, selecting features, and utilizing machine learning techniques. However, the exploration of eye movement signals in emotion recognition remains insufficient. In this study, we utilize eye tracking heatmap and eye movement trajectory data for emotion recognition for the first time. Based on the two types of eye movement data, we develop a multi-way autoregressive model capable of processing multi-view eye movement data. Compared to traditional deep learning baseline models, our model better adapts to the structure of eye movement data and significantly improves the classification performance. Furthermore, we integrate heatmap and trajectory data with commonly used eye-related measurement features, which further enhance the performance of emotion recognition beyond previous methods.

关键词： Heating systems Emotion recognition Adaptation models Accuracy Psychology Gaze tracking Biomedical measurement Data models Physiology Trajectory

来源：评论

学校读者我要写书评

暂无评论

Dietary carbohydrate intake and risk of type 2 diabetes:a 16-year prospective cohort study

引用

science China(Life sciences) 2025年第4期68卷 1149-1157页

作者： Lu Gan Yi Yang Bin Zhao Kai Yu Kehua Guo Fang Fang Zhiguang Zhou Demetrius Albanes Jiaqi Huang National Clinical Research Center for Metabolic Diseases Metabolic Syndrome Research CenterKey Laboratory of Diabetes ImmunologyMinistry of Educationand Department of Metabolism and EndocrinologyThe Second Xiangya Hospital of Central South UniversityCSU-Sinocare Research Center for Nutrition and Metabolic HealthXiangya School of Public HealthCentral South UniversityFurong LaboratoryChangsha410011China Division of Cancer Epidemiology and Genetics National Cancer InstituteNIHDepartment of Health and Human ServicesBethesdaMD20892USA School of Computer Science and Engineering Central South UniversityChangsha410083China Institute of Environmental Medicine Karolinska InstituteStockholm17177Sweden National Clinical Research Center for Metabolic Diseases Key Laboratory of Diabetes ImmunologyMinistry of Educationand Department of Metabolism and EndocrinologyThe Second Xiangya Hospital of Central South UniversityChangsha410011China

Despite considerable research underscoring the importance of carbohydrate intake in relation to the risk of type 2 diabetes(T2D),a comprehensive assessment of this relationship is currently *** aimed to examine the associations of various types and food sources of dietary carbohydrate intake with the risk of T2D,to evaluate potential effect modification by other factors,including genetic susceptibility,and to explore the potential mediators for such *** present study included 161,872 participants of the UK Biobank who were free of prevalent cancer,cardiovascular disease,or diabetes,and had at least one validated 24-h dietary recall *** age-stratified Cox proportional hazard regression models were applied to estimate hazard ratios(HRs)and 95%confidence intervals(CI)for the associations of various types and food sources of dietary carbohydrate intake with risk of *** a median follow-up of 13.6 years,4,176 incident cases of T2D were *** the multivariable-adjusted models,a greater intake of fiber,carbohydrates from whole grains,and carbohydrates from non-starchy vegetables was significantly associated with a lower risk of T2D(highest *** quantile,HR[95%CI]=0.70[0.62–0.79],0.74[0.67–0.82],and 0.83[0.75–0.92],respectively,all P for trend<0.005).In contrast,a higher intake of starch and carbohydrate from starchy vegetables was associated with an increased risk of T2D(highest *** quantile,HR[95%CI]=1.31[1.16–1.48]and 1.19[1.09–1.31],respectively,both P for trend<0.005).Replacing one serving of refined grains or starchy vegetables with an equal amount of whole grains or non-starchy vegetables was associated with 4%to 10%lower risk of T2D(all P values<0.001).The observed associations were generally similar across population subgroups,including individuals with different genetic susceptibility to *** analyses of the inverse association between T2D risk and isocaloric substitution of carbohy

关键词： dietary carbohydrate type 2 diabetes prospective cohort study UK Biobank

来源：评论

学校读者我要写书评

暂无评论

The Crafts+Fabrication Workshop: Engaging Students with Intangible Cultural Heritage-Oriented Creative Design 22

The Crafts+Fabrication Workshop: Engaging Students with Inta...

引用

2022 ACM Designing Interactive Systems Conference: Digital Wellbeing, DIS 2022

作者： Lu, Zhicong Tan, Peng Ji, Yi Ma, Xiaojuan Department Of Computer Science City University Of Hong Kong China Center For Human-Engaged Computing Kochi University Of Technology Japan Guangdong University Of Technology China Hong Kong University Of Science And Technology Hong Kong

ISBN: (纸本)9781450393584

Engaging local communities is essential to safeguarding intangible cultural heritage (ICH). To better encourage the participation of local communities, especially younger generations, e.g., students, ICH experience and education workshops are widely adopted by academia, museums, governments, and non-profit organizations. The expected outcomes of these workshops, such as archives, documents, and even creative design solutions, can benefit the promotion and preservation of ICH. However, because of the steep learning curve of using traditional ICH tools and the lack of interactions between students and ICH practitioners, many ICH workshops currently fail to engage students in learning ICH-related knowledge, developing empathy with ICH, or designing novel artifacts with ICH elements. To bridge this gap, we designed a workshop, which integrated ICH in China, digital fabrication, creative technology, and making, to engage Chinese students with ICH and creative design. We conducted empirical studies to collect feedback from students (N = 30) and ICH professionals (N=6). The application of digital fabrication tools successfully piqued students' interest in ICH and enabled them to create interactive ICH artifacts through quick prototyping. However, the ICH professionals pointed out several issues of using digital fabrication, especially regarding tacit knowledge, use of traditional tools, and cultural authenticity. We discuss the importance of these factors in students' acquisition of ICH knowledge and ICH-oriented design, and provide implications for future ICH design workshops. © 2022 ACM.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Minion: A Technology Probe for Resolving Value Conflicts through Expert-Driven and User-Driven Strategies in AI Companion Applications

arXiv

引用

arXiv 2024年

作者： Fan, Xianzhe Xiao, Qing Zhou, Xuhui Su, Yuran Lu, Zhicong Sap, Maarten Shen, Hong Tsinghua University Beijing China Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA United States Department of Computer Science City University of Hong Kong Hong Kong SAR China Language Technologies Institute Carnegie Mellon University PittsburghPA United States

AI companions based on large language models can role-play and converse very naturally. When value conflicts arise between the AI companion and the user, it may offend or upset the user. Yet, little research has examined such conflicts. We first conducted a formative study that analyzed 151 user complaints about conflicts with AI companions, providing design implications for our study. Based on these, we created Minion, a technology probe to help users resolve human-AI value conflicts. Minion applies a user-empowerment intervention method that provides suggestions by combining expert-driven and user-driven conflict resolution strategies. We conducted a technology probe study, creating 40 value conflict scenarios on *** and Talkie. 22 participants completed 274 tasks and successfully resolved conflicts 94.16% of the time. We summarize user responses, preferences, and needs in resolving value conflicts, and propose design implications to reduce conflicts and empower users to resolve them more effectively. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LEARNING WHAT TO DO BY SIMULATING THE PAST 9

LEARNING WHAT TO DO BY SIMULATING THE PAST

引用

9th International Conference on Learning Representations, ICLR 2021

作者： Lindner, David Shah, Rohin Abbeel, Pieter Dragan, Anca Department of Computer Science ETH Zurich Switzerland Center for Human-Compatible AI UC Berkeley United States

Since reward functions are hard to specify, recent work has focused on learning policies from human feedback. However, such approaches are impeded by the expense of acquiring such feedback. Recent work proposed that agents have access to a source of information that is effectively free: in any environment that humans have acted in, the state will already be optimized for human preferences, and thus an agent can extract information about what humans want from the state (Shah et al., 2019). Such learning is possible in principle, but requires simulating all possible past trajectories that could have led to the observed state. This is feasible in gridworlds, but how do we scale it to complex tasks? In this work, we show that by combining a learned feature encoder with learned inverse models, we can enable agents to simulate human actions backwards in time to infer what they must have done. The resulting algorithm is able to reproduce a specific skill in MuJoCo environments given a single state sampled from the optimal policy for that skill. © 2021 ICLR 2021 - 9th International Conference on Learning Representations. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：