检索结果-内蒙古大学图书馆

An Accurate Prediction of Coronary Heart Disease Using Ensemble Algorithms 1

An Accurate Prediction of Coronary Heart Disease Using Ensem...

1st IEEE International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics, AIKIIE 2023

作者： Joshi, Kambham Pratap Prasad, M Lakshmi Natchadalingam, R. Reddy, Pundru Chandra Shaker Mukherjee, Saptarshi Babu, G Charles Hyderabad Dundigal India Institute of Aeronautical Engineering Computer Science and Engineering Telangana Dundigal India R.L.Jalappa Institute of Technology CSE-Data Science Karnataka Bengaluru India School of Computer Science and Engineering Lovely Professional University Punjab Phagwara India Maulana Abul Kalam Azad University of Technology M. Tech-Bioinformatics West Bengal India Gokaraju Rangaraju Institute of Engineering and Technology Computing Science and Engineering Telangana Hyderabad India

ISBN: (纸本)9798350316469

Coronary Heart-disease (CHD) is one the foremost causes of death globally, making the accurate recognition of it vital. Machine-learning (ML) and deep-learning (DL) are two of the newest technologies being put to use in the healthcare industry. This paper uses a risk factor method to examine how CHD can be predicted. K-Nearest-Neighbors, Binary-Logistic Classification, and Naïve-Bayes are only few of the predictive methods that are measured by accuracy, recall, and receiver operating characteristic (ROC) curves for evaluation. Ensemble modeling strategies including bagging, boosting, and stacking are contrasted to these foundational classifiers. The efficacy of using ensemble approaches to enhance coronary heart disease prediction was investigated using a comparative analytical methodology. The 'Cardiovascular-Disease dataset,' which includes 80,000 records of patient data for CHD, is used to evaluate the modeling techniques. It is demonstrated that bagged models, on average, are more accurate than their non-bagged counterparts by the margin of 1.99 percentage points. The highest accuracy of all models was 76.5%, but the AUC for the boosted models was 0.78. Accuracy of 75.1% was achieved by the stacked model consisting of KNN, random-forest classifier, and SVM. In addition, data-analytic methods and K-Folds cross-validation were used to verify the tested models' performance. © 2023 IEEE.

关键词： Artificial intelligence CHD Ensemble techniques Heart-disease Hybrid modeling Machine-learning

来源：评论

学校读者我要写书评

暂无评论

MassSpecGym: A benchmark for the discovery and identification of molecules 38

MassSpecGym: A benchmark for the discovery and identificatio...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Bushuiev, Roman Bushuiev, Anton de Jonge, Niek F. Young, Adamo Kretschmer, Fleming Samusevich, Raman Heirman, Janne Wang, Fei Zhang, Luke Dührkop, Kai Ludwig, Marcus Haupt, Nils A. Kalia, Apurva Brungs, Corinna Schmid, Robin Greiner, Russell Wang, Bo Wishart, David S. Liu, Li-Ping Rousu, Juho Bittremieux, Wout Rost, Hannes Mak, Tytus D. Hassoun, Soha Huber, Florian van der Hooft, Justin J.J. Stravs, Michael A. Böcker, Sebastian Sivic, Josef Pluskal, Tomáš Institute of Organic Chemistry and Biochemistry The Czech Academy of Sciences Czech Republic Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Czech Republic Bioinformatics Group Wageningen University & Research Netherlands Department of Computer Science University of Toronto Canada Bioinformatics Institute for Computer Science Friedrich Schiller University Jena Germany Department of Computer Science University of Antwerp Belgium Department of computing science University of Alberta Canada Alberta Machine Intelligence Institute Canada Department of Molecular Genetics University of Toronto Canada Bright Giant GmbH Department of Computer Science Tufts University United States Department of Biological Sciences University of Alberta Canada Department of Computer Science Aalto University Finland Mass Spectrometry Data Center National Institute of Standards and Technology United States Department of Chemical and Biological Engineering Tufts University United States Centre for Digitalisation and Digitality University of Applied Sciences Düsseldorf Germany Department of Biochemistry University of Johannesburg South Africa Eawag Swiss Federal Institute of Aquatic Science and Technology Switzerland

The discovery and identification of molecules in biological and environmental samples is crucial for advancing biomedical and chemical sciences. Tandem mass spectrometry (MS/MS) is the leading technique for high-throughput elucidation of molecular structures. However, decoding a molecular structure from its mass spectrum is exceptionally challenging, even when performed by human experts. As a result, the vast majority of acquired MS/MS spectra remain uninterpreted, thereby limiting our understanding of the underlying (bio)chemical processes. Despite decades of progress in machine learning applications for predicting molecular structures from MS/MS spectra, the development of new methods is severely hindered by the lack of standard datasets and evaluation protocols. To address this problem, we propose MassSpecGym - the first comprehensive benchmark for the discovery and identification of molecules from MS/MS data. Our benchmark comprises the largest publicly available collection of high-quality labeled MS/MS spectra and defines three MS/MS annotation challenges: de novo molecular structure generation, molecule retrieval, and spectrum simulation. It includes new evaluation metrics and a generalization-demanding data split, therefore standardizing the MS/MS annotation tasks and rendering the problem accessible to the broad machine learning community. MassSpecGym is publicly available at https://***/pluskal-lab/MassSpecGym. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Eight Points Geometric Constraint for Stereo Matching

Eight Points Geometric Constraint for Stereo Matching

引用

International Conference on Systems and Informatics (ICSAI)

作者： Yuanbin Wang School of Data and Computer Science Xiamen Institute of Technology Xiamen China

Stereo point matching is a critical and fundamental problem in 3D vision. Numerous algorithms have been proposed to solve this problem. Since images obtained from 3D to 2D projection of a 3D scene lose depth information of the 3D scene, there is no numerical geometric invariant between stereo images. So, we do not have similar algorithms that use geometric invariants for point matching as in the case of 2D to 2D projective transformations. However, it is discovered that geometric constraints can be used to restrict the search space and eliminate faulty correspondences. In this paper we derive a new mathematical constraint relating eight corresponding points in stereo images. It is a simple formula consisting of coordinates of the eight points that compute to zero for the eight points to be in correspondence. This constraint can be used as a preliminary necessity testing step before other time-consuming methods to speed up the matching procedure.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IoT-Driven Image Recognition for Microplastic Analysis in Water Systems using Convolutional Neural Networks 2

IoT-Driven Image Recognition for Microplastic Analysis in Wa...

引用

2nd International Conference on computer, Communication and Control, IC4 2024

作者： Hasan, M D Ashfaqul Balasubadra, K. Vadivel, G. Arunfred, N. Ishwarya, M.V. Murugan, S. Malla Reddy Institute of Engineering and Technology Department of Computer Science and Engineering Telangana Hyderabad India R.M.D. Engineering College Kavaraipettai Department of Information Technology Tamil Nadu Chennai India University of Technology and Applied Science Department of Information Technology Dhofar Salalah Oman Srm Institute of Science and Technology Kattankulathur Faculty of Management Studies Tamil Nadu Chennai India Agni College of Technology Artificial Intelligence and Data Science Department Tamil Nadu Thazhambur India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350387933

Microplastic pollution in water systems is growing, requiring novel detection and analysis methods. This research presents an Internet of Things (IoT)-driven image identification system using Convolutional Neural Networks (CNNs) to detect and quantify microplastics in water samples. The suggested method is more scalable and responsive due to IoT real-time data capture and remote monitoring of water infrastructure. An innovative CNN architecture for image processing allows the system to accurately identify micro plastics. The CNN model is trained and validated using a large dataset of micro plastic-containing water samples. The trained model can recognize various sizes, shapes, and colors of micro plastics, making it responsive to different environmental situations. The IoT architecture also allows image recognition modules in dispersed sensor nodes to cover water systems. Extensive studies prove the system can analyze vast amounts of image data quickly and reliably. Edge computing also minimizes latency and improves micro plastic analysis system responsiveness. The suggested IoT-driven image recognition method for continuous micro plastic pollution monitoring and evaluation in water systems seems promising. Scalability, realtime capabilities, and accuracy make it useful for environmental monitoring agencies and academics trying to reduce microplastics' influence on aquatic ecosystems. This system advances IoT applications in environmental and pollution management. © 2024 IEEE.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Designing of Creator's Information Hub using Machine Learning 2

Designing of Creator's Information Hub using Machine Learnin...

引用

2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Gabhane, Diksha Gawande, Ujwalla Gaikwad, Sanjana Gajarlewar, Swati Bhawalkar, Rita Yeshwantrao Chavan College of Engineering Dept. of Computer Science & Design Nagpur India Yeshwantrao Chavan College of Engineering Dept. of Information Technology Nagpur India NCPharmacy Wanadongri Nagpur India G H Raisoni College of Engineering and Management Dept. of Cyber Security and Data Science Pune India

ISBN: (纸本)9798331528713

The proliferation of educational content on platforms like YouTube has transformed digital learning, yet it presents challenges in effective creation, dissemination, and impact assessment. This paper proposes a strategic initiative to collaborate with 6,000 active educational YouTubers to enhance global educational outreach. Central to this initiative is the compilation and analysis of a comprehensive dataset containing vital information about content creators and their audiences. Leveraging advanced machine learning algorithms, the analysis aims to identify collaboration opportunities, optimize engagement strategies, enhance content relevance and impact, facilitate knowledge sharing, and measure outcomes. The problem statement highlights fragmentation in educational content, lack of data-driven insights, and suboptimal collaboration opportunities. Addressing these challenges requires a structured approach to connect creators, leverage data analytics, and establish a collaborative ecosystem for enriching educational experiences worldwide. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Clustering-Based Negative Sampling Approaches for Protein-Protein Interaction Prediction 19th

Clustering-Based Negative Sampling Approaches for Protein-P...

引用

19th International Meeting on Computational Intelligence Methods for Bioinformatics and Biostatistics, CIBB 2024

作者： Kesemen, Zehra Karadeniz, İlknur Aydoğan, Reyhan Computer Science Özyeğin University Istanbul Turkey Artificial Intelligence and Data Engineering Özyeğin University Istanbul Turkey Interactive Intelligence Group Delft University of Technology Delft Netherlands

ISBN: (纸本)9783031897030

The lack of confirmed negative interactions poses a major challenge to the prediction of protein-protein interactions. The reliable selection of these negative samples within a dataset is crucial for a better understanding of the underlying patterns and dynamics. The random sampling method is the most widely used negative sampling method, where negative pairs are randomly selected from unlabelled samples (i.e., samples not experimentally confirmed as positive interactions). However, they tend to introduce inaccurately labelled negative samples, resulting in less reliable predictions, which may affect the efficiency of the learning process. Our study aims to assess the reliability of clustering-based negative sampling methods and highlight their fundamental differences from the widely used random sampling method. To achieve this goal, we propose a hierarchical clustering-based algorithm that uses different mechanisms to select negative instances from unlabelled instances. We investigated the effectiveness of our proposed approach compared to existing clustering-based negative sampling methods and random sampling on four different datasets. The results indicate that clustering-based methods surpass the commonly used random sampling method. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

Toward Intelligent Financial Advisors for Identifying Potential Clients:A Multitask Perspective

引用

Big data Mining and Analytics 2022年第1期5卷 64-78页

作者： Qixiang Shao Runlong Yu Hongke Zhao Chunli Liu Mengyi Zhang Hongmei Song Qi Liu Department of Anhui Province Key Laboratory of Big Data Analysis and Application(BDAA) School of Computer Science and TechnologyUniversity of Science and Technology of China Department of College of Management and Economics Tianjin University School of Management Hefei University of Technology Department of Information Technology China Merchants Bank

Intelligent Financial Advisors(IFAs)in online financial applications(apps)have brought new life to personal investment by providing appropriate and high-quality portfolios for *** real-world scenarios,identifying potential clients is a crucial issue for IFAs,i.e.,identifying users who are willing to purchase the ***,extracting useful information from various characteristics of users and further predicting their purchase inclination are ***,two critical problems encountered in real practice make this prediction task challenging,i.e.,sample selection bias and data *** this study,we formalize a potential conversion relationship,i.e.,user→activated user→client and decompose this relationship into three related ***,we propose a Multitask Feature Extraction Model(MFEM),which can leverage useful information contained in these related tasks and learn them jointly,thereby solving the two problems *** addition,we design a two-stage feature selection algorithm to select highly relevant user features efficiently and accurately from an incredibly huge number of user feature ***,we conduct extensive experiments on a real-world dataset provided by a famous fintech *** results clearly demonstrate the effectiveness of MFEM.

关键词： Intelligent Financial Advisor(IFA) potential client identification MultiTask Learning(MTL) feature selection

来源：评论

学校读者我要写书评

暂无评论

Cyber Physical Systems: Analyses, challenges and possible solutions

引用

Internet of Things and Cyber-Physical Systems 2021年第1期1卷 22-33页

作者： Tyagi, Amit Kumar Sreenath, N. Centre for Advanced Data Science Vellore Institute of Technology Tamilnadu Chennai600127 India School of Computer Science and Engineering Vellore Institute of Technology Tamilnadu Chennai600127 India Department of Computer Science and Engineering Puducherry Technological University Puducherry605014 India

It is becoming more difficult to protect the authentication of our data in today's world of smart living. On the one hand, we are able to live in smart homes and smart cities with ease. Even if we use the most complicated passwords, we can't be sure that the Internet of Things and the Internet of Everything are safe. One way to make sure people and things are safe is to use Multi-Factor Authentication. Also, a big and complicated system needs more efficient and robust solutions for real, and strong, security, so this is important. There are a lot of smart ways to solve problems today. For this reason, the internet of things is being used in every possible field or application. This new ecosystem, which is called Cyber Physical Systems, was built by IoTs. Cyber-Physical Systems use computing, communication, and control to make new technology or the next generation of engineered systems. In the last decade, there has been a lot of work done on cyber physical systems that we didn't expect. There have been a lot of threats, challenges, and important issues in the last decade. We have a big problem with the security of CPS because the basic blocks used to make them are very different. Even if we're talking about natural gas systems or transportation systems or other automated systems, they all have something to do with CPS, no matter what. These days, CPSs systems are used for energy, transportation, the environment, and health care, among other things. This article talks about a number of problems that need to be solved by researchers and scientists (working related to respective area, i.e., CPS). As a result, this article also talks about a partial survey of important research issues, and an overview of several research projects that have been done in the last decade by a number of different people to improve CPS. © 2021 The Authors

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Position: Insights from Survey Methodology can Improve Training data 41

Position: Insights from Survey Methodology can Improve Train...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Eckman, Stephanie Plank, Barbara Kreuter, Frauke Social Data Science Center University of Maryland College ParkMD United States LMU Munich Germany Computer Science Department IT University of Copenhagen Denmark LMU Munich Germany Institute for Statistics LMU Munich Germany Joint Program in Survey Methodology University of Maryland College ParkMD United States

Whether future AI models are fair, trustworthy, and aligned with the public's interests rests in part on our ability to collect accurate data about what we want the models to do. However, collecting high-quality data is difficult, and few AI/ML researchers are trained in data collection methods. Recent research in data-centric AI has show that higher quality training data leads to better performing models, making this the right moment to introduce AI/ML researchers to the field of survey methodology, the science of data collection. We summarize insights from the survey methodology literature and discuss how they can improve the quality of training and feedback data. We also suggest collaborative research ideas into how biases in data collection can be mitigated, making models more accurate and human-centric. Copyright 2024 by the author(s)

关键词： data collection

来源：评论

学校读者我要写书评

暂无评论

Enhancing Breast Cancer Diagnosis with Vision Transformers: A Novel Approach using MaskGuided Attention for Ultrasound Image Classification

Enhancing Breast Cancer Diagnosis with Vision Transformers: ...

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： Deena Sivakumar Anamika Kumari Divya Dharshini K Samiksha S Hemachandran M Department of Computer Science and Engineering Sri Ramachandra Institute of Higher Education and Research Chennai Department of Computer Science (AI & Data Analytics) Sri Ramachandra Institute of Higher Education and Research Chennai

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

Deep learning models, notably convolutional neural networks (CNNs), demonstrate great promise in medical image processing. Nonetheless, CNNs frequently encounter challenges in capture holistic context and long- range dependencies in high-resolution images, which are crucial for accurate medical diagnostics. A new state-of-the-art technique called Vision Transformers (ViTs) uses self-attention mechanisms for gathering global correlations between image patches, thereby addressing some of the inherent limitations of CNNs. This study investigates the application of ViTs for diagnosing breast cancer from ultrasound images of tumor. The findings suggest that ViTs not only achieve competitive accuracy in identifying breast cancer lesions but also offer superior interpretability through attention mechanism, which can aid clinicians in understanding model decisions. This paper highlights the potential of ViTs as a powerful tool in medical imaging, particularly for breast cancer diagnosis, and outlines future research directions for enhancing clinical applicability.

关键词： Deep learning computer vision Accuracy Attention mechanisms Ultrasonic imaging Transformers Breast cancer Convolutional neural networks Medical diagnosis Biomedical imaging

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：