检索结果-内蒙古大学图书馆

Federated learning: Applications, challenges and future directions

International Journal of Hybrid Intelligent systems 2022年第1-2期18卷 19-35页

作者： Bharati, Subrato Mondal, M. Rubaiyat Hossain Podder, Prajoy Prasath, V.B. Surya Institute of Information and Communication Technology Bangladesh University of Engineering and Technology Dhaka Bangladesh Division of Biomedical Informatics Cincinnati Children's Hospital Medical Center Cincinnati OH United States Department of Pediatrics University of Cincinnati College of Medicine Cincinnati OH United States Department of Biomedical Informatics College of Medicine University of Cincinnati Cincinnati OH United States Department of Electrical Engineering and Computer Science University of Cincinnati Cincinnati OH United States

Federated learning (FL) refers to a system in which a central aggregator coordinates the efforts of several clients to solve the issues of machine learning. This setting allows the training data to be dispersed in order to protect the privacy of each device. This paper provides an overview of federated learning systems, with a focus on healthcare. FL is reviewed in terms of its frameworks, architectures and applications. It is shown here that FL solves the preceding issues with a shared global deep learning (DL) model via a central aggregator server. Inspired by the rapid growth of FL research, this paper examines recent developments and provides a comprehensive list of unresolved issues. Several privacy methods including secure multiparty computation, homomorphic encryption, differential privacy and stochastic gradient descent are described in the context of FL. Moreover, a review is provided for different classes of FL such as horizontal and vertical FL and federated transfer learning. FL has applications in wireless communication, service recommendation, intelligent medical diagnosis system and healthcare, which we review in this paper. We also present a comprehensive review of existing FL challenges for example privacy protection, communication cost, systems heterogeneity, unreliable model upload, followed by future research directions. © 2022 - IOS Press. All rights reserved.

关键词： Artificial intelligence computing methodologies federated learning healthcare machine learning privacy protection

来源：评论

学校读者我要写书评

暂无评论

MBEEC: A bio-inspired routing protocol with multihop between cluster-heads for energy saving in WSN 11

MBEEC: A bio-inspired routing protocol with multihop between...

引用

11th International Wireless Communications and Mobile Computing Conference, IWCMC 2015

作者： Martins, Francisco Leonardo Jales Celestino Junior, Joaquim Da Silva Rego, Antoniel Neto, Jose Henrique Brandao Dos Santos, Andre Patel, Ahmed State University of Ceara Jazan University Jazan Saudi Arabia Computer Network Department Computer Science and Information System College Jazan University Jazan Saudi Arabia School of Computing and Information Systems Faculty of Science Engineering and Computing Kingston University Kingston upon ThamesKT1 2EE United Kingdom

ISBN: (纸本)9781479953448

This paper presents a Multihop Routing Algorithm for Wireless Sensor Networks (MBEEC) based on the Dijkstra Algorithm. An important challenge in wireless sensor networks is to balance the energy consumption. The Bio-Inspired Algorithm for Energy Efficient Routing for Continuous Data Dissemination Networks Wireless Sensor (BEE-C) can provide important savings on energy consumption but does not provide routing calculations that ensures a long lived topology. Lifetime is an extremely important factor in a Wireless Sensor Network, because of the difficulty of maintenance, limited battery, memory and processing that sensors have. MBEEC inherits the properties of BEE-C but uses Dijkstra Algorithm for calculating the routes. To ensure the longer lifetime of the network, MBEEC addresses a multihop algorithm in terms of consumption in a matter more energy efficient than BEE-C using Dijkstra to calculate routes, thus balancing the entire network. © 2015 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Mild Cognitive Impairment Detection through Efficient Magnetic Resonance Image Analysis

引用

computers, Materials & Continua 2024年第8期80卷 2081-2098页

作者： Atif Mehmood Zhonglong Zheng Rizwan Khan Ahmad Al Smadi Farah Shahid Shahid Iqbal Mutasem K.Alsmadi Yazeed Yasin Ghadi Syed Aziz Shah Mostafa M.Ibrahim Department of Computer Science and Technology Zhejiang Normal UniversityJinhua321002China Zhejiang Institute of Photoelectronics&Zhejiang Institute for Advanced Light Source Zhejiang Normal UniversityJinhua321004China Department of Data Science and Artificial Intelligence Zarqa UniversityZarqa13100Jordan School of Chemical and Environmental Engineering College of ChemistryChemical Engineering andMaterials ScienceSoochow UniversitySuzhou215123China Department of Management Information Systems College of Applied Studies and Community ServiceImam Abdulrahman Bin Faisal UniversityDammam32244Saudi Arabia Department of Computer Science Al Ain UniversityAbu Dhabi999041United Arab Emirates Department of Electrical Engineering Faculty of EngineeringMinia UniversityMinia61519Egypt Healthcare Technology and Innovation Theme Faculty Research Centre for Intelligent HealthcareCoventry UniversityCoventryCV48BWUK

Neuroimaging has emerged over the last few decades as a crucial tool in diagnosing Alzheimer’s disease(AD).Mild cognitive impairment(MCI)is a condition that falls between the spectrum of normal cognitive function and ***,previous studies have mainly used handcrafted features to classify MCI,AD,and normal control(NC)*** paper focuses on using gray matter(GM)scans obtained through magnetic resonance imaging(MRI)for the diagnosis of individuals with MCI,AD,and *** improve classification performance,we developed two transfer learning strategies with data augmentation(i.e.,shear range,rotation,zoom range,channel shift).The first approach is a deep Siamese network(DSN),and the second approach involves using a cross-domain strategy with customized *** performed experiments on the Alzheimer’s Disease Neuroimaging Initiative(ADNI)dataset to evaluate the performance of our proposed *** experimental results demonstrate superior performance in classifying the three binary classification tasks:NC ***,NC ***,and MCI ***,we achieved a classification accuracy of 97.68%,94.25%,and 92.18%for the three cases,*** study proposes two transfer learning strategies with data augmentation to accurately diagnose MCI,AD,and normal control individuals using GM *** findings provide promising results for future research and clinical applications in the early detection and diagnosis of AD.

关键词： Alzheimer’s disease mild cognitive impairment normal control transfer learning classification augmentation

来源：评论

学校读者我要写书评

暂无评论

#Walangpasok on Twitter: Natural language processing as a method for analyzing tweets on class suspensions in the Philippines 12

#Walangpasok on Twitter: Natural language processing as a me...

引用

12th International Conference on Knowledge and Smart Technology, KST 2020

作者： Ancheta, Jeffrey Rosario Gorro, Ken D. Uy, Mark Anthony D. De la Salle University Departamento Ng Filipino Manila Philippines University of San Carlos Political Science Department Cebu City Philippines College of Computer Studies and Systems University of the East-Manila Manila Philippines

ISBN: (纸本)9781728144665

In this study, we aim to prove that natural language processing (NLP) can be used as a method for analyzing qualitative data like tweets. To validate this, we examine various topics emerging from tweets about class suspensions in the Philippines using #walangpasok (no classes). By utilizing three NLP techniques, we presented various topics. Using Latent Dirichlet Allocation (LDA), the study identified the following: (1) information dissemination and public announcements from government offices, and (2) sentiments of students. Through Word2Vec, we generated (1) monitoring and dissemination of alerts and warnings, (2) local government accountability, and (3) sentiments of Twitter users. An intrinsic evaluation was conducted for word2vec model using cosine similarity. The word-groups have an average cosine similarity of 0.997811. Lastly, the topics that emerged using K-means are (1) weather advisory, (2) class suspension announcements, (3) role of local government, and (4) users' sentiments and outlook towards a situation. The number of clusters generated by the k-means clustering algorithm was decided based on the silhouette score of 0.0153423865462. It turns out that the study provided the same results using NLP techniques. We also performed open coding to analyze the data manually and to ensure that the obtained results using the techniques are accurate. Thus, the use of NLP as a method of qualitative data analysis can be considered reliable and may be recommended to use in other qualitative research, particularly in the field of social sciences. © 2020 IEEE.

关键词： Information dissemination

来源：评论

学校读者我要写书评

暂无评论

ICT for flood risk management strategies a GIS-based MCDA (M) approach

ICT for flood risk management strategies a GIS-based MCDA (M...

引用

IST-Africa

作者： Avelino Mondlane Karin Hansson Oliver Popov Eduardo Mondlane University Centre for Informatics Maputo Mozambique Department of Computer and Systems Science Stockholm University Stockholm Sweden

This paper discusses the application of Analytic Hierarchy (AHP) on Geographic Information System (GIS) based Multcriteria Decision Analysis (Making) MCDA (M) for flood risk management strategies at the Limpopo River Basin in Mozambique. An analytical process is carried out based on GIS Decision Support System (DSS) taking into account the role of ICT and interest of both the decision makers and different stakeholders namely the householders and economic agents, within the basin. The study aims to provide the different stakeholders and decision makers with a decision tool and it focuses on the Mozambican section Limpopo River Basin as part of the national strategies to mitigate the exposure to both floods and droughts that cyclically affect the region.

关键词： Analytic hierarchy process Geographic information systems Floods Rivers Risk management Decision support systems

来源：评论

学校读者我要写书评

暂无评论

A framework like a tool for specify motivating collaborative learning participatory simulations

A framework like a tool for specify motivating collaborative...

引用

11th International Conference on computer Supported Cooperative Work in Design, CSCWD 2007

作者： Zurita, Gustavo Baloian, Nelson Baytelman, Felipe Farias, Antonio Antunes, Pedro Universidad de Chile Information Systems Department Business School Santiago Chile Universidad de Chile Computer Science Departments Engineering School Santiago Chile Department of Informatics Faculty of Sciences University of Lisboa Bloco C6 Campo Grande 1700 Lisboa Portugal

ISBN: (纸本)1424409632

Several research efforts suggest that collaborative participatory simulations improve teaching and learning, increasing motivation inside the classroom. Currently, it has been mainly applied with students of primary and secondary educational levels, leaving higher level students aside. This paper presents a framework for implementing Participatory Simulations, where social interactions and motivational effects are the main facilitators. An instance of this framework was implemented for business school undergraduate students. Its implementation is simple, lightweight, fully based on pen-based, and designed to work with handhelds over an ad-hoc wireless network. ©2007 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

RETRACTED ARTICLE: Diagnosing breast cancer with an improved artificial immune recognition system

引用

Soft Computing 2015年第10期20卷 4069-4084页

作者： Saybani, Mahmoud Reza Wah, Teh Ying Aghabozorgi, Saeed Reza Shamshirband, Shahaboddin Mat Kiah, Miss Laiha Balas, Valentina Emilia Department of Information Systems Faculty of Computer Science and Information Technology University of Malaya Kula Lumpur Malaysia Department of Computer Networks Markaz-e Elmi Karbordi Bandar Abbas 1 University of Applied Science Bandar Abbas Iran Department of Computer System and Technology Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia Department of Automation and Applied Informatics Aurel Vlaicu University of Arad Arad Romania

Breast cancer is the top cancer in women worldwide. Scientists are looking for early detection strategies which remain the cornerstone of breast cancer control. Consequently, there is a need to develop an expert system that helps medical professionals to accurately diagnose this disease. Artificial immune recognition system (AIRS) has been used successfully for diagnosing various diseases. However, little effort has been undertaken to improve its classification accuracy. To increase the classification accuracy, this study introduces a new hybrid system that incorporates support vector machine, fuzzy logic, and real tournament selection mechanism into AIRS. The Wisconsin Breast Cancer data set was used as the benchmark data set; it is available through the machine learning repository of the University of California at Irvine. The classification performance was measured through tenfold cross-validation, student’s t test, sensitivity and specificity. With an accuracy of 100 %, the proposed method was able to classify breast cancer dataset successfully.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of integrated curricula for AD and BS degree programs in IT area

Development of integrated curricula for AD and BS degree pro...

引用

Frontiers in Education (FIE) Conference

作者： V. Uskov A. Saad S. Geonetta Department of Computer Science and Information Systems Bradley University Peoria IL Georgia Institute of Technology Computer Engineering – GTREP Savannah GA Midstate College Computer and Information Systems Peoria IL

In today's economy, one of the biggest competitive advantages is an information technology (IT) knowledge force. The National science Foundation Advanced Technological Education project # DUE-9950029 (NSF ATE project) is aimed to help increase the pool of highly skilled and well-trained IT technicians and technologists in the USA. It addresses the severe national shortage for such workers that is projected to persist well into the 21/sup st/ Century. The project serves both traditional and returning students. It aims to provide a 2+2+2 seamless transition for students from their junior year in high school, through an Associate Degree (AD) at the community college level or at university, to a Bachelor of science (BS) degree in IT. The NSF ATE project's team and faculty of more than 15 collaborating educational institutions created a draft of the IT integrated curricula and IT courseware-a model that can be readily adopted by other K=16 US educational institutions.

关键词： Educational institutions Educational technology Information systems Educational programs Courseware computer science education Information technology Guidelines Machinery systems engineering education

来源：评论

学校读者我要写书评

暂无评论

An Affinity Propagation Approach for Entity Clustering with Spark 2020

An Affinity Propagation Approach for Entity Clustering with ...

引用

5th International Conference on Intelligent Information Technology, ICIIT 2020

作者： Tran, Phuc Quang Trieu, Ngoan Thanh Luong, Huong Hoang Tran, Nghi C. Huynh, Hiep Xuan Department of Foreign Languages and Informatics People's Police College III Cantho Viet Nam College of Information and Communication Technology Can Tho University Cantho Viet Nam Department of Information Technology FPT University Cantho Viet Nam College of Electrical Engineering and Computer Science National Central University Taoyuan Taiwan

ISBN: (纸本)9781450376594

With the dramatically increasing amount of electronic data, the automatic detection and extraction of information in the text is the first step for all other data analysis activities. Clustering entities is the important methods for discovering knowledge and extracting appropriate data applied in several applications. The clustering methods often need to pre-determine the number of clusters and the initial centers thus the problem of "initial staring conditions" usually occurs. In this paper we propose a new approach that overcome this problem for clustering entities without pre-defining the number of clusters with the Affinity Propagation algorithm. The algorithm is built on the Spark platform for speed up the clustering process. The experiments are conducted on different characteristics datasets. © 2020 ACM.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Exploring Online Programming-Related Information Seeking Behaviors via Discussion Forums

Exploring Online Programming-Related Information Seeking Beh...

引用

International Conference on Advanced Learning Technologies (ICALT)

作者： Yihan Lu I-Han Hsiao Qi Li Informatics & Decision Systems Engineering Arizona State University USA Department of Computer Science Northern Kentucky University USA

ISBN: (纸本)9781467390422

In this work, we studied how programming novices explore and search on online discussion forums. We collected novices' intentions and search logs. The results indicated that novices had significant different behavior patterns compare to experienced learners, and they indeed require specific assistant in generating search queries, and filtering helpful information among the search result. This work also suggests directions to assist future learners in seeking programming information in online environment.

关键词： Programming profession Discussion forums Search problems Education Problem-solving History

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：