检索结果-内蒙古大学图书馆

A Web-Based Interface that Leverages Machine Learning to Assess an Individual’s Vulnerability to Brain Stroke

IEEE Access 2025年 13卷 87950-87964页

作者： Bhandari, Divyansh Agarwal, Arnav Reena Roy, R. Priyatharshini, Rajaram Cristian, Rodriguez Rivero Vellore Institute of Technology School of Electronics Engineering Tamil Nadu Chennai India Vellore Institute of Technology School of Computer Science and Engineering Tamil Nadu Chennai India Cardiff Metropolitan University Cardiff School of Technologies Centre for Engineering Research in Intelligent Sensors and SystemsComputer Science Wales United Kingdom Cardiff Metropolitan University Academic Associate Cardiff School of Technologies Cardiff United Kingdom Universitat Politècnica de Catalunya Industrial and ICT Systems Engineering Dept. of Mining Spain

Cerebral stroke is a major global health issue, contributing to high mortality and long-term disability. Early identification of individuals at high risk of stroke can significantly improve preventive care outcomes. We present a web-based stroke risk assessment tool that uniquely combines an accessible user interface with robust machine learning modeling. The proposed platform leverages a novel combination of SMOTE oversampling and logistic regression to address class imbalance in patient health records, improving the detection of stroke risk factors over existing methods. We compare a range of algorithms – including traditional classifiers and deep learning models – and report comprehensive performance metrics (accuracy, precision, recall, F1-score, and AUC-ROC) for each. Our best model (logistic regression with SMOTE and standard scaling) achieves 93.2% accuracy with a substantially higher F1-score for the stroke-positive class than other models, indicating improved sensitivity to stroke cases. To bridge the gap between complex predictive models and end-users, we deploy this model in an intuitive web interface (built with Streamlit) that non-technical individuals and healthcare providers can easily use. This interface requires no specialized knowledge, preserves user privacy by avoiding any data storage, and provides clear explanations of results. By offering a practical and transparent tool for stroke risk screening, our work advances health informatics with an emphasis on accessibility, interpretability, and early intervention. Potential applications range from personal health self-assessment to integration in clinical workflows for preventive care, ultimately aiming to improve public health outcomes through early detection and intervention in stroke. © 2013 IEEE.

关键词： Health insurance

来源：评论

学校读者我要写书评

暂无评论

Bias Evaluation and Mitigation in Retrieval-Augmented Medical Question-Answering systems

arXiv

引用

arXiv 2025年

作者： Ji, Yuelyu Zhang, Hang Wang, Yanshan Dept. of Information Science University of Pittsburgh PittsburghPA United States Intelligent Systems Program School of Computing and Information University of Pittsburgh PittsburghPA United States Dept. of Health Information Management University of Pittsburgh PA United States Clinical and Translational Science Institute University of Pittsburgh PittsburghPA United States University of Pittsburgh Medical Center PittsburghPA United States

Medical Question-Answering (QA) systems based on Retrieval-Augmented Generation (RAG) are promising for clinical decision support due to their capability to integrate external knowledge, thus reducing inaccuracies inherent in standalone large language models (LLMs). However, these systems may unintentionally propagate biases associated with sensitive demographic attributes like race, gender, and socioeconomic factors. This study systematically evaluates demographic biases within medical RAG pipelines across multiple QA benchmarks, including MedQA, MedMCQA, MMLU, and EquityMedQA. We quantify disparities in retrieval consistency and answer correctness by generating and analyzing queries sensitive to demographic variations. We further implement and compare several bias mitigation strategies—including Chain-of-Thought reasoning, Counterfactual filtering, Adversarial prompt refinement, and Majority Vote aggregation—to address identified biases. Experimental results reveal significant demographic disparities, highlighting that Majority Vote aggregation improves accuracy and fairness metrics. Our findings underscore the critical need for explicitly fairness-aware retrieval methods and prompt engineering strategies to develop truly equitable medical QA systems. © 2025, CC BY.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Modeling supports the implementation of urban greening as a response to the challenges of sustainable spatial planning

引用

Journal of Environmental Management 2025年 386卷 125648页

作者： Kim, Eun Sub Hyun, Jung Hee Kim, Na Yeon Heo, Su Jeong Kim, Da Seul Lee, Dong Kun Low-Carbon and Climate Impact Research Centre School of Energy and Environment City University of Hong Kong Tat Chee Ave Hong Kong Kowloon Tong China Systemic Risk and Resilience Research Group Advancing Systems Analysis International Institute for Applied Systems Analysis Austria Department of Landscape Architecture and Rural System Engineering Seoul National University Seoul08826 Korea Republic of Integrated Major in Smart City Global Convergence Program Seoul National University Seoul08826 Korea Republic of Forest Disaster & Environment Department National Institute of Forest Science Seoul Korea Republic of Interdisciplinary Program in Landscape Architecture Seoul National University Seoul08826 Korea Republic of Specialized Graduate School of Intelligent Eco-Science 4 Dept. of Landscape Architecture Seoul National University Seoul08826 Korea Republic of

Urban greening is critical for sustainable urban development, climate change mitigation, and biodiversity conservation. However, the effectiveness of urban greening varies depending on the specific goals (e.g., enhancing biodiversity, reducing urban heat, or both) and their spatial implementation. To address the spatial variability in the effectiveness of greening, we propose a spatial decision support model based on the non-dominated sorting genetic algorithm-II (NSGA-II). This model aims to optimize urban greening locations to maximize biomass density, mitigate urban heat stress, and improve landscape connectivity. Applied to Suwon City, South Korea, the model's effectiveness was evaluated against a business-as-usual (BAU) scenario across four scenarios: connectivity-based, biomass density-based, heat stress-based, and an integrated-based scenario. The integrated approach, balancing trade-offs between ecological benefits and implementation costs, outperformed the BAU scenario by 8.84 %. Despite highlighting a weaker correlation with heat stress mitigation, this outcome indicates significant improvements in biomass density and landscape connectivity. Our findings underscore the necessity of an integrated planning approach to urban greening, as it can contribute toward attaining urban development goals. Additionally, by proposing an app-based model for policymakers, our outputs should enable the reconciliation of multiple environmental objectives in urban landscapes. © 2025 Elsevier Ltd

关键词： Biotic

来源：评论

学校读者我要写书评

暂无评论

Extended abstract: BusTUC - A savant level intelligent bus oracle

Extended abstract: BusTUC - A savant level intelligent bus o...

引用

作者： Amble, Tore Division of Intelligent Systems Dept. of Computer and Information Science NTNU Norway

来源：评论

学校读者我要写书评

暂无评论

Speech Verification Based on Simplified Segmental Probability Model

引用

中国电子杂志（英文版） 2001年第2期10卷 175-178页

作者： JIA Bin ZHU Xiaoyan LUO Yupin HU Dongcheng Dept. of Automation Tsinghua University Beijing 100084 China State Key Laboratory of Intelligent Technology and Systems Dept. of Computer Science and TechnologyTsinghua University Beijing 100084 China

Today speech recognition is requested not only to decode utterances into transcriptions,but also to determine the reliabilities of the results,by Speech verification (SV) or Utterance Verification (UV). With conventional HMM, the measure of reliabilities can not be determined directly by the likelihoods of models. Whereas, Simplified Segmental Probability Model (SSPM), suggested in this paper,with its normalized likelihood, facilitates rendering SV and speech recognition at the same time and as a whole. SSPM also costs much less computation load than conventional HMM. In the paper, Integrated Anti-word Model (IAM) is suggested, which is used to advance the measure of SV likelihood of *** experiments show high performance and moderate computation with IAM.

关键词： Speech recognition Speech verification Segmental probability model Anti-word Hiden Markov model (HMM).

来源：评论

学校读者我要写书评

暂无评论

Information theory and classification error in probabilistic classifiers

引用

9th International Conference on Discovery science

作者： Perez, Aritz Larranaga, Pedro Inza, Inaki Intelligent Systems Group Computer Science and A.I Dept. University of the Basque Country Spain

ISBN: (纸本)3540464913

This work shows, using bivariate continuous artificial domains, the relation that seems to exist between some measures based on the information theory and the expected classification error. The relations that seem to be found in this work could be applied to the improvement of the classifiers which assign a posteriori probabilities to each class value. They also could be used in other tasks related to the supervised classification such as feature subset selection or discretization.

关键词： Classifiers

来源：评论

学校读者我要写书评

暂无评论

Merging Plans with Quantitative Temporal Constraints, Temporally Extended Actions, and Conditional Branches 5

Merging Plans with Quantitative Temporal Constraints, Tempor...

引用

5th International Conference on Artificial Intelligence Planning systems, AIPS 2000

作者： Tsamardinos, Ioannis Pollack, Martha E. Horty, John F. Intelligent Systems Program University of Pittsburgh United States Dept. of Computer Science and Intelligent Systems Program University of Pittsburgh United States Philosophy Department Inst. for Adv. Computer Studies University of Maryland United States

ISBN: (纸本)1577351118

We develop an algorithm for merging plans that are represented in a richly expressive language. Specifically, we are concerned with plans that have (i) quantitative temporal constraints, (ii) actions that are not instantaneous, but rather have temporal extent, and (iii) conditional branches. Given a set S of such plans, our algorithm finds a set of constraints that jointly ensure that the plans in S are mutually consistent, if such a set of constraints exists. The algorithm has three phases. In the first, it employs a new data structure, a conditional simple temporal network (CSTN), to identify conflicts between the plans. Next, it uses an approach developed by Yang (1997) to suggest a potential resolution of the identified conflicts. Finally, the CSTN is again used to check whether the proposed resolution observes all the temporal constraints. We have implemented our approach, and we present preliminary experimental evidence about domain factors that influence its performance. Copyright © 2000, AAAI (***). All rights reserved.

关键词： Merging

来源：评论

学校读者我要写书评

暂无评论

Experiments using an Adaptive Network-based Fuzzy Inference System (ANFIS) for the diagnosis of breast cancer

Experiments using an Adaptive Network-based Fuzzy Inference ...

引用

Smart Engineering System Design: Neural Networks, Fuzzy Logic, Evolutionary programming, Complex systems and Artificial Life - Proceedings of the Artificial Neural Networks in Engineering Conference

作者： Land Jr., Walker H. Lewis III, Harold W. Verheggen, Elizabeth A. Dept. of Computer Science Binghamton University Binghamton NY Center for Intelligent Systems Dept. of Systems Science Binghamton University Binghamton NY Dept. of Systems Science Binghamton University Binghamton NY

This paper describes a series of neural network experiments which contribute decision support information, aimed at reducing the misclassification rate of screening mammograms and improving recommendations regarding breast biopsy. Features were extracted from digitized film images, each with pathologically definite diagnosis, from a large public domain database. Decision trees were used to illicit separate approaches to classify different mammographic structures, which were then tuned for each structure as part of the fuzzy rule set in an Adaptive-Network-based Fuzzy Inference System (ANFIS). By comparing several neural network based computer-aided diagnosis (CAD) approaches for breast cancer classification as benign or malignant, our experiments indicate that separating discriminatory features into categories with predominant mammographic structures imparts substantial classification improvements of 50% to 151% at the clinically imperative levels of high sensitivity.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

INTERACTIVE DOMAIN ADAPTATION TECHNIQUE FOR THE CLASSIFICATION OF REMOTE SENSING IMAGES

INTERACTIVE DOMAIN ADAPTATION TECHNIQUE FOR THE CLASSIFICATI...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Persello, Claudio Dinuzzo, Francesco Max Planck Institute for Intelligent Systems Germany Dept. of Information Engineering and Computer Science University of Trento Italy

ISBN: (纸本)9781467311595

This paper presents a novel interactive domain-adaptation technique based on active learning for the classification of remote sensing (RS) images. The proposed method aims at adapting the supervised classifier trained on a given RS source image to make it suitable for classifying a different but related target image. The two images can be acquired in different locations and/or at different times, but present the same set of land-cover classes. The proposed approach iteratively selects the most informative samples of the target image to be labeled by the user and included in the training set, while the source-image samples are re-weighted or possibly removed from the training set on the basis of their disagreement with the target image classification problem. In this way, the consistent information available from the source image can be effectively exploited for the classification of a target image and for guiding the user in the selection of the new samples to be labeled, whereas the inconsistent information is automatically detected and removed. Experimental results on a Very High Resolution (VHR) multispectral dataset confirm the effectiveness of the proposed method.

关键词： Domain Adaptation Active Learning Image Classification Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

A sophisticated ad hoc cloud computing environment built by the migration of a server to facilitate distributed collaboration

A sophisticated ad hoc cloud computing environment built by ...

引用

26th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012

作者： Mori, Tatsuya Nakashima, Makoto Ito, Tetsuro Dept. Computer Science and Intelligent Systems Faculty of Engineering Oita University Oita-shi Japan

ISBN: (纸本)9780769546520

A sophisticated ad hoc cloud computing environment (SpACCE) providing calculation capacity of PCs is proposed to facilitate distributed collaboration. Distributed collaboration is now indispensable in daily work and mainly occurs ad hoc in offices and laboratories. However, computer resources in offices and laboratories are under-utilized, while conventional cloud computing environments composed of dedicated servers are not suited to flexibly deploying applications ad hoc. A SpACCE can be built according to the needs that occur at any given time on a set of personal, i.e., non-dedicated, PCs and dynamically migrate a server for application sharing to another PC. CollaboTray, an application-sharing system, indispensable to share any application without modification, is employed to realize the migration of a server. By migrating a server, the redundant calculation capacity of PCs used for individual work can be utilized to produce a sophisticated ad hoc cloud computing environment, where the response time of the application shared among the users is improved. The level of calculation capacity required to execute the migration of a server and the effectiveness of the migration were clarified by building a SpACCE in a university research room. © 2012 IEEE.

关键词： Cloud computing

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：