检索结果-内蒙古大学图书馆

Impact of COVID-19 research: a study on predicting influential scholarly documents using machine learning and a domain-independent knowledge graph

引用

JOURNAL OF BIOMEDICAL SEMANTICS 2023年第1期14卷 18页

作者： Rabby, Gollam D'Souza, Jennifer Oelen, Allard Dvorackova, Lucie Svatek, Vojtech Auer, Soeren Leibniz Univ Hannover L3S Res Ctr Hannover Germany Prague Univ Econ & Business Dept Informat & Knowledge Engn Nam Winstona Churchilla 1938-4 Prague 12000 Czech Republic Leibniz Informat Ctr Sci & Technol Hannover Germany Prague Univ Econ & Business Dept Econometr Prague Czech Republic

Multiple studies have investigated bibliometric features and uncategorized scholarly documents for the influential scholarly document prediction task. In this paper, we describe our work that attempts to go beyond bibliometric metadata to predict influential scholarly documents. Furthermore, this work also examines the influential scholarly document prediction task over categorized scholarly documents. We also introduce a new approach to enhance the document representation method with a domain-independent knowledge graph to find the influential scholarly document using categorized scholarly content. As the input collection, we use the WHO corpus with scholarly documents on the theme of COVID-19. This study examines different document representation methods for machine learning, including TF-IDF, BOW, and embedding-based language models (BERT). The TF-IDF document representation method works better than others. From various machine learning methods tested, logistic regression outperformed the other for scholarly document category classification, and the random forest algorithm obtained the best results for influential scholarly document prediction, with the help of a domain-independent knowledge graph, specifically DBpedia, to enhance the document representation method for predicting influential scholarly documents with categorical scholarly content. In this case, our study combines state-of-the-art machine learning methods with the BOW document representation method. We also enhance the BOW document representation with the direct type (RDF type) and unqualified relation from DBpedia. From this experiment, we did not find any impact of the enhanced document representation for the scholarly document category classification. We found an effect in the influential scholarly document prediction with categorical data.

关键词： Influential scholarly document prediction machine learning algorithms Text mining COVID-19 World health organization Domain-independent knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Multifaceted Applications of Federated learning: Beyond Neural Networks 2nd

Multifaceted Applications of Federated Learning: Beyond Neur...

引用

2nd European Symposium on Artificial Intelligence in Manufacturing-ESAIM

作者： Legler, Tatjana Hegiste, Vinit Ruskowski, Martin Univ Kaiserslautern Landau RPTU Chair Machine Tools & Control Syst D-67663 Kaiserslautern Germany German Res Ctr Artificial Intelligence DFKI Innovat Factory Syst D-67663 Kaiserslautern Germany

ISBN: (纸本)9783031864919;9783031864896;9783031864889

The advent of Federated learning (FL) has brought about a revolutionary change in the field of machine learning, enabling the decentralised training of models across a multitude of devices while simultaneously maintaining the confidentiality of the data. In contrast to conventional centralized methodologies, FL maintains the localisation of data, with only model updates being shared. This methodology enhances model generalisation and stability without compromising data sovereignty. A variety of machine learning techniques, including support vector machines (SVMs) and decision trees, can be effectively utilised within the context of FL frameworks. SVMs offer efficient solutions for classification tasks with minimal computational overhead, while decision trees provide interpretable models for both classification and regression. This paper explores the application of these methods in FL settings, highlighting their advantages and potential use cases in diverse industries, particularly in manufacturing. Furthermore, it discusses the integration of reinforcement learning with FL, emphasising its potential for enhancing intelligent and adaptable decentralised systems.

关键词： Federated learning machine learning algorithms Privacy-preserving Techniques

来源：评论

学校读者我要写书评

暂无评论

Prediction of Breast Cancer using Traditional and Ensemble Technique: A machine learning Approach

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2023年第6期14卷 867-875页

作者： Islam, Tamanna Akhi, Amatul Bushra Akter, Farzana Hasan, Md. Najmul Lata, Munira Akter Daffodil Int Univ Dept Comp Sci Engn Dhaka Bangladesh Bangabandhu Sheikh Mujibur Rahman Digital Univ Dept IoT & Robot Engn Dhaka Bangladesh Bangabandhu Sheikh Mujibur Rahman Digital Univ Dept Educ Technol Dhaka Bangladesh

Breast cancer is a prevalent and potentially lifethreatening disease that affects millions of individuals worldwide. Early detection plays a crucial role in improving patient outcomes and increasing the chances of survival. In recent years, machine learning (ML) techniques have gained significant attention in the field of breast cancer detection and diagnosis due to their ability to analyze large and complex datasets, extract meaningful patterns, and facilitate accurate classification. This research focuses on leveraging ML algorithms and models to enhance breast cancer detection and provide more reliable diagnostic results in the real world. Two datasets from Kaggle have been used in this study and Decision tree (DT), Random (KNN) etc. are applied to identify potential breast cancer cases. On the first dataset, A, the test's accuracy using Logistic Regression, SVM, and Grid SearchCV was 95.614%, however in dataset B, the accuracy of Logistic Regression and Decision Tree increased to 99.270%. The accuracy of Boosting Decision Tree was 99.270% when compared to other algorithms. To defend the performances, various ensemble models are used. To assign the optimal parameters to each classifier, a hyper-parameter tweaking method is used. The experimental study examined the findings of recent studies and discovered that LRBO performed best, with the highest level of accuracy for predicting breast cancer being 95.614%.

关键词： Breast cancer prediction machine learning algorithms ensemble models voting stacking

来源：评论

学校读者我要写书评

暂无评论

Design of machine learning based Decoding algorithms for Codes on Graph

Design of Machine learning based Decoding Algorithms for Cod...

引用

Silchar Subsection Conference (SILCON), IEEE

作者： Joyal Sunny Ameenudeen P E Renjith H Kumar Dept of ECE Rajiv Gandhi Institute of Technology Kottayam Kerala India Dept of ECE College of Engineering Trivandrum Kerala India

ISBN: (纸本)9781665471015

In a communication system, it is more challenging to receive a signal at the receiver than it is to transmit one. The receiver’s task and complexity are larger than the transmitter’s because the received signal must travel over a channel where it will be attenuated and distorted. Communication over unstable noisy channels is made possible by channel coding. Channel encoding is done at the transmitter in the baseband domain and at the receiver, it can be effectively retrieved by using a variety of techniques. This study discusses Belief Propagation (BP) and the Min sum technique for decoding the LDPC encoded codewords using Tanner graphs. We also examine a method to decode the encoded data in a communication system, where the decoding algorithm at the receiver is recast as a machine learning process. So a receiver designed using deep learning techniques can always adapt to the changes in the channel optimization techniques and thus reduce the overall computational complexity.

关键词： Training Wireless communication machine learning algorithms Transmitters Receivers Data models Parity check codes

来源：评论

学校读者我要写书评

暂无评论

Numerical investigations on the deposition characteristics of lunar dust in the human bronchial airways

引用

Particuology 2025年第2期97卷 25-38页

作者： Hao Jing Yuan Xue Bin Wu Yixiao Wang Zhaojun Xi Xinguang Cui School of Aerospace Engineering Huazhong University of Science and TechnologyWuhan430074China China Astronaut Research and Training Center BeijingChina China-EU Institute for Clean and Renewable Energy Huazhong University of Science and TechnologyWuhanChina

Although it is widely acknowledged that lunar dust (LD) is toxic to the human health, its deposition characteristics in the bronchial airways remain unknown, which is significantly important to understand its toxicity. Therefore, this study employs computational fluid dynamics and machine learning algorithm methods to address this issue considering the difficulty of conducting the experiments of LD deposition. The major results are: (1) the deposition efficiencies (DE) of micrometer-sized LD in the terminal bronchioles vary significantly depending on the human body posture, with a notable difference of DE up to 29% between standing and lying flat postures;(2) LD deposition in various bronchial regions shows differences under activity intensities, with higher DE in segmental bronchi and terminal bronchioles under intense and lower intensive activities, respectively;(3) In predicting DE of LD, machine learning algorithms outperform fitting functions, achieving higher precision and smaller errors, reducing the root mean square error by approximately 60%–80%. These results indicate that LD deposition characteristics in the bronchial airways under lunar environment are also influenced by the combined factors of particle size, activity intensity, and body posture.

关键词： Deposition of lunar dust Bronchial airways Computational fluid dynamics machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A Review of Data-Driven Approaches with Emphasis on machine learning Base Intrusion Detection algorithms

A Review of Data-Driven Approaches with Emphasis on Machine ...

引用

Information Technology for Education and Development (ITED)

作者： Maryam Abdullahi Musa Abdulsalam Ya'u Gital Kabiru Musa Ibrahim Haruna Chiroma Mustapha Lawal Abdulrahman Ibrahim Muhammad Umar Department of Mathematical Science Abubakar Tafawa Balewa University Bauchi Nigeria Department of Management Information Technology Abubakar Tafawa Balewa University Bauchi Nigeria Department University of Hafr Al Batin Saudi Arabia

The importance of the internet across the globe cannot be over-emphasized as such network security is essential to curb future attack occurrences. Cyber-attacks like DDoS and Ransomware yielded a lot of damage to connected devices by endangering and accessing them, notwithstanding these damages are air marked to be on the rise. To overcome these issues, machine learning has been used in different computing aspects such as cyber–Intrusion Detection. Recently, deep learning, extreme learning, and deep extreme learning networks have superseded machine learning in this context due to their iterative hidden layers that can manipulate complex features of cyber intrusion data. Hence, this research surveys the application of data-driven intelligent algorithms for cyber security attack detection in comparison to conventional machine learning techniques. The review focuses on the performance evaluation of several state-of-the-art intelligent algorithms and provides research gaps and future 2trends in the context of Data Security Attacks and Cyber Intrusion Detection.

关键词： Performance evaluation Deep learning machine learning algorithms Data security Education Intrusion detection Network security

来源：评论

学校读者我要写书评

暂无评论

Sex estimation from long bones: a machine learning approach

引用

INTERNATIONAL JOURNAL OF LEGAL MEDICINE 2023年第6期137卷 1887-1895页

作者： Knecht, Siam Santos, Frederic Ardagna, Yann Alunni, Veronique Adalian, Pascal Nogueira, Luisa Aix Marseille Univ CNRS EFS ADES F-13007 Marseille France Univ Cote Azur Inst Univ Anthropol Med Legale Fac Med 28 Ave Valombrose F-06107 Nice 2 France Univ Bordeaux CNRS MCC UMR 5199PACEA Batiment B8AAllee Geoffroy St HilaireCS 50023 F-33615 Pessac France CNRS UMR 7264 CEPAM 24 Ave Diables Bleus F-06300 Nice France

Sex estimation from skeletal remains is one of the crucial issues in forensic anthropology. Long bones can be a valid alternative to skeletal remains for sex estimation when more dimorphic bones are absent or degraded, preventing any estimation from the first intention methods. The purpose of this study was to generate and compare classification models for sex estimation based on combined measurement of long bones using machine learning classifiers. Eighteen measurements from four long bones (radius, humerus, femur, and tibia) were taken from a total of 2141 individuals. Five machine learning methods were employed to predict the sex: a linear discriminant analysis (LDA), penalized logistic regression (PLR), random forest (RF), support vector machine (SVM), and artificial neural network (ANN). The different classification algorithms using all bones generated highly accuracy models with cross-validation, ranging from 90 to 92% on the validation sample. The classification with isolated bones ranked between 83.3 and 90.3% on the validation sample. In both cases, random forest stands out with the highest accuracy and seems to be the best model for our investigation. This study upholds the value of combined long bones for sex estimation and provides models that can be applied with high accuracy to different populations.

关键词： Forensic anthropology Sexual dimorphism Sex prediction Long bones Statistical models machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Detecting Credit Card Theft with Various machine learning Methods 5th

Detecting Credit Card Theft with Various Machine Learning Me...

引用

5th International Conference on Data Science, machine learning and Applications

作者： Sravani, G. Regulwar, Ganesh B. Sairam, G. Nikitha, M. Sowmya, Ch. Kethireddy, Bhaskerreddy Vardhaman Coll Engn Dept Informat Technol Hyderabad India

ISBN: (纸本)9789819780334;9789819780310;9789819780303

Financial organisations and customers share a common fear about credit card fraud. Credit card fraud generally happens when the card was stolen for any of the unauthorized purposes or even when the fraudster uses the credit card information for his use. As a solution to this problem, machine learning algorithms have been developed to quickly identify and assist with fraudulent transactions. We want to use machine literacy styles to produce a model for detecting credit card fraud in this design. The design must be completed by obtaining sale data from the credit card firm, pre-processing the data to eliminate missing values and unnecessary data, and choosing crucial attributes to train the machine literacy model. The model will be trained with a range of machine learning methods, including logistic regression, SVM. Among the performance metrics that will be used to judge the model's effectiveness are perfection, recall, and best position. By altering the model's characteristics and parameters, performance will be improved as well.

关键词： Credit card fraud fraudulent transactions machine learning algorithms Precision

来源：评论

学校读者我要写书评

暂无评论

A comparative paradigm of sequential mediation models of influencers' credibility using PLS-SEM with machine learning

引用

JOURNAL OF MARKETING ANALYTICS 2025年 1-36页

作者： Sharkasi, Nora Rezakhah, Saeid Agag, Gomaa Tokyo Int Univ Inst Int Strategy Higashi Ikebukuro 4-42-31 Toshima Tokyo 1700013 Japan Amirkabir Univ Technol Fac Math & Comp Sci 424 Hafez Ave Tehran 15875 Iran Nottingham Business Sch Dept Mkt 50 Shakespeare St Nottingham NG1 4FQ England Oxford Business Coll SK Res Oxford England

Companies employ social media influencers SMIs due to the compelling evidence of their advertising effectiveness. However, for optimal selection of SMIs, more research is needed to assess and compare the effect of different types of factors as in product-related or audience-related in SMIs advertising. To do so, we investigate the effect of source influence SI of SMIs on the intention to purchase I2P through the sequential mediation of parasocial relationships PSR with audience benign envy BE (audience-related) and PSR with brand-influencer fit BIF (product-related). Two independent samples (N = 411;N = 355) are used to perform: (i) PLS-SEM analysis to obtain the model's predictive power, and (ii) classification-based machine learning ML to evaluate the model's accuracy. A comparative paradigm is proposed based on within-study and between-studies comparative analyses. Both samples indicate a high role of trustworthiness and expertise in forming SI. Comparative mediation analysis and predictive accuracy scores show that BE as an audience-related feature, plays a more vital role in affecting/predicting the followers' I2P compared to the brand-related feature, BIF. The results of comparative analysis contribute to the knowledge of SMIs' credibility and provide a better understanding of SMIs' selection strategies for marketing practitioners and researchers.

关键词： Brand-influencer fit Benign envy Source influence Parasocial relationships Intention to purchase machine learning algorithms Classification PLS-SEM Sequential mediation Comparative analysis

来源：评论

学校读者我要写书评

暂无评论

Liver Disease Prediction and Classification using machine learning Techniques

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2023年第2期14卷 871-878页

作者： Tokala, Srilatha Hajarathaiah, Koduru Gunda, Sai Ram Praneeth Botla, Srinivasrao Nalluri, Lakshmikanth Nagamanohar, Pathipati Anamalamudi, Satish Enduri, Murali Krishna SRM Univ AP Dept Comp Sci & Engn Amaravati India

Recently liver diseases are becoming most lethal disorder in a number of countries. The count of patients with liver disorder has been going up because of alcohol intake, breathing of harmful gases, and consumption of food which is spoiled and drugs. Liver patient data sets are being studied for the purpose of developing classification models to predict liver disorder. This data set was used to implement prediction and classification algorithms which in turn reduces the workload on doctors. In this work, we proposed apply machine learning algorithms to check the entire patient's liver disorder. Chronic liver disorder is defined as a liver disorder that lasts for at least six months. As a result, we will use the percentage of patients who contract the disease as both positive and negative information We are processing Liver disease percentages with classifiers, and the results are displayed as a confusion matrix. We proposed several classification schemes that can effectively improve classification performance when a training data set is available. Then, using a machine learning classifier, good and bad values are classified. Thus, the outputs of the proposed classification model show accuracy in predicting the result.

关键词： machine learning algorithms classification model classifier liver disease

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：