检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhang, Xiatan Zheng, Sisi Shum, Hubert P.H. Zhang, Haozheng Song, Nan Song, Mingkang Jia, Hongxiao Beijing Key Laboratory of Mental Disorders National Clinical Research Center for Mental Disorders National Center for Mental Disorders Beijing Anding Hospital Capital Medical University Beijing China Advanced Innovation Center for Human Brain Protection Beijing Anding Hospital Capital Medical University Beijing China Department of Computer Science Durham University Durham United Kingdom

Resting-state fMRI (rs-fMRI) functional connectivity (FC) analysis provides valuable insights into the relationships between different brain regions and their potential implications for neurological or psychiatric disorders. However, specific design efforts to predict treatment response from rs-fMRI remain limited due to difficulties in understanding the current brain state and the underlying mechanisms driving the observed patterns, which limited the clinical application of rs-fMRI. To overcome that, we propose a graph learning framework that captures comprehensive features by integrating both correlation and distance-based similarity measures under a contrastive loss. This approach results in a more expressive framework that captures brain dynamic features at different scales and enables more accurate prediction of treatment response. Our experiments on the chronic pain and depersonalization disorder datasets demonstrate that our proposed method outperforms current methods in different scenarios. To the best of our knowledge, we are the first to explore the integration of distance-based and correlation-based neural similarity into graph learning for treatment response prediction. © 2023, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Optimizing Heart Disease Prediction Models through SMOTE: Addressing Data Imbalance

Optimizing Heart Disease Prediction Models through SMOTE: Ad...

引用

Emerging Smart Technologies and Applications (eSmarTA), International Conference on

作者： Waheeb Baddah Hamzah Ali Qasem Ayman Alsabry Rana Saleh Al Gawani Wafa Mohammed Alzuraiqi F. E. Hanash Azal University for Human Development International University of Technology Twintech Sana’a Yemen International University of Technology Twintech 21 September University of Medical and Applied Sciences Sana’a Yemen Department of Computer Science International University of Technology Twintech Sana’a Yemen Lebanese International University Sana’a Yemen Emirates International University International University of Technology Twintech Sana’a Yemen

ISBN: (数字)9798350354133

ISBN: (纸本)9798350354140

The problem of data imbalance poses a significant challenge in the field of medical diagnostics, particularly in heart disease prediction using machine learning models. This study investigates the application of the Synthetic Minority Over-sampling Technique (SMOTE) to address this imbalance and improve the predictive accuracy of heart disease models. Through a rigorous methodology involving data collection, preprocessing, and the evaluation of 21 machine learning models, the study compares the performance of models trained on both original and SMOTE-balanced datasets. The findings indicate that models trained on SMOTE-balanced datasets showed statistically significant improvements in precision, F1-score, and often recall, with varied impacts on accuracy depending on the dataset. Key performance metrics such as accuracy, precision, recall, and F1-score are analyzed using t-tests to assess the statistical significance of improvements offered by SMOTE. Notably, the enhancements were particularly evident in precision and F1-score across the Cleveland and Statlog heart disease datasets, demonstrating SMOTE's ability to enhance model performance effectively. This study aims to demonstrate the potential of SMOTE in enhancing model performance, thus contributing to more effective and reliable heart disease diagnostics.

关键词： Heart Measurement Accuracy Machine learning Predictive models Data collection Data models

来源：评论

学校读者我要写书评

暂无评论

Accelerating Sustainability through Leveraging Machine Learning to Analyze CSR Spending in the Indian Automobile Industry

Accelerating Sustainability through Leveraging Machine Learn...

引用

International Conference on Circuit, Power and Computing Technologies (ICCPCT)

作者： Kottala Sri Yogi Dankan Gowda V Anwesha Pati Ved Srinivas Santosh Aghav Ibrahim Abdullah Department of Operations Symbiosis Institute of Business Management Hyderabad Symbiosis International University Pune India Department of Electronics and Communication Engineering BMS Institute of Technology and Management Bangalore Karnataka Symbiosis Institute of Business Management Hyderabad India Department of Human Resources Thiagarajar School of Management Madurai Tamil Nadu India Symbiosis Law School Hyderabad Symbiosis International (Deemed University) Pune India Department of Computer Science Al-Turath University College Baghdad Iraq

ISBN: (数字)9798350372816

ISBN: (纸本)9798350372823

This paper uses machine learning to assess Corporate Social Responsibility spending trends on the Indian automobile sector between 2016 and 2021. Simply put, the aim of the research is to recognize trends and patterns in sustainability expenditures. More specifically, the study examines how businesses allocate money across the three important aspects of the sustainability report: People, Planet, and Profit Purcell, 2020. The research is based on a largely industry-based database obtained from public companies’ records. The use of advanced statistical techniques, such as machine learning and random forest modeling, enables one to examine the impact of financial allocations on sustainability achievements. Increments in CSR spending are related to enhanced company sustainability performance in terms of correlation outcomes. The paper also recognizes areas where cost cuts have the best returns, as well as shortfalls in the existing CSR approach, offering a strategy for possible development’s.

关键词： Profitability Companies Market research Automobiles Synchronization Resource management Sustainable development

来源：评论

学校读者我要写书评

暂无评论

An ecologically valid examination of event-based and time-based prospective memory using immersive virtual reality: The influence of attention, memory, and executive function processes on real-world prospective memory.

TechRxiv

引用

TechRxiv 2021年

作者： Kourtesis, Panagiotis MacPherson, Sarah E. Human Cognitive Neuroscience Department of Psychology University of Edinburgh Edinburgh United Kingdom Department of Psychology University of Edinburgh Edinburgh United Kingdom Lab of Experimental Psychology Suor Orsola Benincasa University of Naples Naples Italy Interdepartmental Centre for Planning and Research "Scienza Nuova" Suor Orsola Benincasa University of Naples Naples Italy National Research Institute of Computer Science and Automation INRIA Rennes France Univ Rennes Rennes France gResearch Institute of Computer Science and Random Systems IRISA Rennes France French National Centre for Scientific Research CNRS Rennes France Department of Psychology University of Edinburgh 7 George Square EdinburghEH8 9JZ United Kingdom

Studies on prospective memory (PM) predominantly assess either event- or time-based PM by implementing non-ecological laboratory-based tasks. The results deriving from these paradigms have provided findings that are discrepant with ecologically valid research paradigms that converge on the complexity and cognitive demands of everyday tasks. The Virtual Reality Everyday Assessment Lab (VR-EAL), an immersive virtual reality (VR) neuropsychological battery with enhanced ecological validity, was implemented to assess everyday event- and time-based PM, as well as the influence of other cognitive functions on everyday PM functioning. The results demonstrated the importance of delayed recognition, planning, and visuospatial attention on everyday PM. Delayed recognition and planning ability were found to be central in event- and time-based PM respectively. In order of importance, delayed recognition, visuospatial attention speed, and planning ability were found to be involved in event-based PM functioning. Comparably, planning, visuospatial attention accuracy, delayed recognition, and multitasking/task-shifting ability were found to be involved in time-based PM functioning. These findings further suggest the importance of ecological validity in the study of PM, which may be achieved using immersive VR paradigms. © 2021, CC BY.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

VICE: variational interpretable concept embeddings 22

VICE: variational interpretable concept embeddings

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Lukas Muttenthaler Charles Y. Zheng Patrick McClure Robert A. Vandermeulen Martin N. Hebart Francisco Pereira Machine Learning Group Technische Universität Berlin Berlin Institute for the Foundations of Learning and Data (BIFOLD) Berlin Germany Machine Learning Team FMRI Facility National Institute of Mental Health Bethesda MD Department of Computer Science Naval Postgraduate School Monterey CA Vision and Computational Cognition Group MPI for Human Cognitive and Brain Sciences Leipzig Germany

ISBN: (纸本)9781713871088

A central goal in the cognitive sciences is the development of numerical models for mental representations of object concepts. This paper introduces Variational Interpretable Concept Embeddings (VICE), an approximate Bayesian method for embedding object concepts in a vector space using data collected from humans in a triplet odd-one-out task. VICE uses variational inference to obtain sparse, non-negative representations of object concepts with uncertainty estimates for the embedding values. These estimates are used to automatically select the dimensions that best explain the data. We derive a PAC learning bound for VICE that can be used to estimate generalization performance or determine a sufficient sample size for experimental design. VICE rivals or outperforms its predecessor, SPoSE, at predicting human behavior in the triplet odd-one-out task. Furthermore, VICE's object representations are more reproducible and consistent across random initializations, highlighting the unique advantage of using VICE for deriving interpretable embeddings from human behavior.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Development of a Food Image Database for Food Identification

SSRN

引用

SSRN 2023年

作者： Lin, Luotao He, Jiangpeng Cowan, Alexandra E. Qin, Yue Zhu, Fengqing Delp, Edward J. Eicher-Miller, Heather A. Department of Nutrition Science College of Health and Human Sciences Purdue University West LafayetteIN47906 United States Elmore Family School of Electrical and Computer Engineering College of Engineering Purdue University West LafayetteIN47906 United States Institute for Advancing Health through Agriculture Texas A&M AgriLife Research College StationTX77845 United States

New imaging technologies to identify food can reduce the reporting burden of participants but heavily rely on quality of the food image databases to which they are linked to accurately identify food images. The objective of this study was to develop methods to create a food image database based on the most commonly consumed U.S. foods and those contributing most to energy. The objective included using a systematic classification structure for foods based on the standardized United States department of Agriculture (USDA) What We Eat in America (WWEIA) food classification system that can ultimately be used to link food images to a nutrition composition database, the USDA Food and Nutrient Database for Dietary Studies (FNDDS). The food image database was built using images mined from the web that were fitted with bounding boxes;identified, annotated, and then organized according to classification aligning with USDA WWEIA. The images were classified by food category and subcategory and then assigned a corresponding USDA food code within USDA's FNDDS in order to systematically organize the food images and facilitate a linkage to nutrient composition. The resulting food image database can be used in food identification and dietary assessment. © 2023, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Improving AlphaFLOW for Efficient Protein Ensembles Generation

arXiv

引用

arXiv 2024年

作者： Li, Shaoning Li, Mingyu Wang, Yusong He, Xinheng Zheng, Nanning Zhang, Jian Heng, Pheng Ann Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Medicinal Chemistry and Bioinformatics Center Shanghai Jiao Tong University School of Medicine China National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University China Shanghai Institute of Materia Medica Chinese Academy of Sciences China

Investigating conformational landscapes of proteins is a crucial way to understand their biological functions and properties. AlphaFLOW stands out as a sequence-conditioned generative model that introduces flexibility into structure prediction models by fine-tuning AlphaFold under the flow-matching framework. Despite the advantages of efficient sampling afforded by flow-matching, AlphaFLOW still requires multiple runs of AlphaFold to finally generate one single conformation. Due to the heavy consumption of AlphaFold, its applicability is limited in sampling larger set of protein ensembles or the longer chains within a constrained timeframe. In this work, we propose a feature-conditioned generative model called AlphaFLOW-Lit to realize efficient protein ensembles generation. In contrast to the full fine-tuning on the entire structure, we focus solely on the light-weight structure module to reconstruct the conformation. AlphaFLOW-Lit performs on-par with AlphaFLOW and surpasses its distilled version without pretraining, all while achieving a significant sampling acceleration of around 47 times. The advancement in efficiency showcases the potential of AlphaFLOW-Lit in enabling faster and more scalable generation of protein ensembles. © 2024, CC BY.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Explaining GPT-4's Schema of Depression Using Machine Behavior Analysis

arXiv

引用

arXiv 2024年

作者： Ganesan, Adithya V. Varadarajan, Vasudha Lal, Yash Kumar Eijsbroek, Veerle C. Kjell, Katarina Kjell, Oscar N.E. Dhanasekaran, Tanuja Stade, Elizabeth C. Eichstaedt, Johannes C. Boyd, Ryan L. Schwartz, H. Andrew Flek, Lucie Department of Computer Science Stony Brook University United States Department of Psychology Lund University Sweden United States Department of Psychology Stanford University United States Institute for Human-Centered AI Stanford University United States Department of Psychology School of Behavioral and Brain Sciences The University of Texas Dallas United States Bonn-Aachen International Center for Information Technology University of Bonn Germany The Lamarr Institute for Machine Learning and Artificial Intelligence Germany

Use of large language models such as ChatGPT (GPT-4) for mental health support has grown rapidly, emerging as a promising route to assess and help people with mood disorders, like depression. However, we have a limited understanding of GPT-4's schema of mental disorders, that is, how it internally associates and interprets symptoms. In this work, we leveraged contemporary measurement theory to decode how GPT-4 interrelates depressive symptoms to inform both clinical utility and theoretical understanding. We found GPT-4's assessment of depression: (a) had high overall convergent validity (r = 0.71 with self-report on 955 samples, and r = 0.81 with experts judgments on 209 samples);(b) had moderately high internal consistency (symptom inter-correlates r = .23 to .78) that largely aligned with literature and self-report except that GPT-4;(c) underemphasized suicidality's - and overemphasized psychomotor's - relationship with other symptoms, and (d) had symptom inference patterns that suggest nuanced hypotheses (e.g. sleep and fatigue are influenced by most other symptoms while feelings of worthlessness/guilt is mostly influenced by depressed mood). © 2024, CC BY-SA.

关键词： Measurement theory

来源：评论

学校读者我要写书评

暂无评论

Theories behind UX research and how they are used in practice

Theories behind UX research and how they are used in practic...

引用

30th ACM Conference on human Factors in Computing Systems, CHI 2012

作者： Obrist, Marianna Roto, Virpi Law, Effie Lai-Chong Väänänen-Vainio-Mattila, Kaisa Vermeeren, Arnold Buie, Elizabeth Culture Lab. School of Computing Science Newcastle University Newcastle Upon Tyne NE1 7RU United Kingdom Aalto University P.O.Box 31000 00076 Aalto Finland University of Leicester Department of Computer Science LE1 7RH Leicester United Kingdom Tampere University of Technology Unit of Human-Centered Tech. P.O.Box 589 FI-33101 Tampere Finland Delft University of Technology Fac. of Ind. Design Engineering Landbergstraat 15 NL 2628 CE Delft Netherlands Luminanze Consulting LLC 2909 Collins Avenue Silver Spring MD 20902 United States

ISBN: (纸本)9781450310161

At CHI2011 we organized a SIG session asking the question "What theoretical roots do we build on, if any, in UX research?" Overall, 122 single items from about 70 participants were collected, which corroborates the relevance of and interest in this topic. Whilst the theoretical foundations for UX research are not yet established, those responses can serve as candidate resources for setting the theoretical directions. A primary conclusion from the SIG discussion is that the CHI community needs theories in UX research and practice. A major contribution of the workshop will be to clarify the applicability and transferability of different theories, theoretical foundations, concepts in informing UX design and evaluation in both research and practice. In particular we will look into theories that have already been applied in practice. © 2012 Authors.

关键词： human engineering

来源：评论

学校读者我要写书评

暂无评论

Deep learning based subdivision approach for large scale macromolecules structure recovery from electron cryo tomograms

arXiv

引用

arXiv 2017年

作者： Xu, Min Chai, Xiaoqi Muthakana, Hariank Liang, Xiaodan Yang, Ge Zeev-Ben-Mordehai, Tzviya Xing, Eric Computational Biology Department Carnegie Mellon University Pittsburgh15213 United States Biomedical Engineering Department Carnegie Mellon University Pittsburgh15213 United States Computer Science Department Carnegie Mellon University Pittsburgh15213 United States Machine Learning Department Carnegie Mellon University Pittsburgh15213 United States Division of Structural Biology Wellcome Trust Centre for Human Genetics University of Oxford OxfordOX3 7BN United Kingdom

Motivation: Cellular Electron CryoTomography (CECT) enables 3D visualization of cellular organization at near-native state and in sub-molecular resolution, making it a powerful tool for analyzing structures of macromolecular complexes and their spatial organizations inside single cells. However, high degree of structural complexity together with practical imaging limitations make the systematic de novo discovery of structures within cells challenging. It would likely require averaging and classifying millions of subtomograms potentially containing hundreds of highly heterogeneous structural classes. Although it is no longer difficult to acquire CECT data containing such amount of subtomograms due to advances in data acquisition automation, existing computational approaches have very limited scalability or discrimination ability, making them incapable of processing such amount of data. Results: To complement existing approaches, in this paper we propose a new approach for subdividing subtomograms into smaller but relatively homogeneous subsets. The structures in these subsets can then be separately recovered using existing computation intensive methods. Our approach is based on supervised structural feature extraction using deep learning, in combination with unsupervised clustering and reference-free classification. Our experiments show that, compared to existing unsupervised rotation invariant feature and pose-normalization based approaches, our new approach achieves significant improvements in both discrimination ability and scalability. More importantly, our new approach is able to discover new structural classes and recover structures that do not exist in training data. Copyright © 2017, The Authors. All rights reserved.

关键词： Data acquisition

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：