检索结果-内蒙古大学图书馆

International Conference on Data science and Advanced Analytics (DSAA)

作者： Youxingzhu Deng Yipeng Zhou Gang Liu Jessie Hui Wang Yu Shui College of Computer Science and Software Engineering Shenzhen University Shenzhen China School of Computing Faculty of Science and Engineering Macquarie University Sydney Australia Institute for Network Sciences and Cyberspace Tsinghua University Peking China School of Computer Science University of Technology Sydney Sydney Australia

Federated learning (FL) is an emerging paradigm using a parameter server (PS) to coordinate multiple decentralized clients for training a common model without exposing their raw data. Despite its amazing capability in preserving data privacy, FL confronts two significant challenges that have not been sufficiently addressed by existing works, which are: 1) heterogeneous data distributed on clients given that the PS cannot alter data locations. 2) limited computation resources of FL clients who may conduct model training with mobile devices. To tackle these challenges, we propose a novel federated one-shot transferring of intermediate features (FedOTF) algorithm. More specifically, FedOTF consists of two stages: feature extraction and model reconstruction. To overcome challenge 1, clients in stage 1 only collaboratively train a small model in a federated manner, with the objective to extract features. In stage 2, intermediate features (generated by the small model trained by stage 1) are transferred from clients to the PS so that a large model can be trained to overcome challenge 2. In addition, the design of FedOTF is robust, which can flexibly diminish the number of communication rounds of stage 1 when network capacity is limited, and reduce the amount of exposed features when privacy is concerned. To verify the superiority of FedOTF, we conduct comprehensive experiments with real datasets. The experiment results demonstrate that FedOTF can significantly improve the model utility of FL because a better model can be finally obtained by the PS without incurring heavy computational load on clients. Besides, we conduct robustness evaluation of FedOTF which can achieve stable performance when varying network capacity and privacy requirement.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scarce Resource Allocations That Rely On Machine Learning Should Be Randomized

arXiv

引用

arXiv 2024年

作者： Jain, Shomik Creel, Kathleen Wilson, Ashia Institute for Data Systems and Society MIT United States Department of Philosophy & Religion Khoury College of Computer Sciences Northeastern University United States Department of Electrical Engineering and Computer Science MIT United States

Contrary to traditional deterministic notions of algorithmic fairness, this paper argues that fairly allocating scarce resources using machine learning often requires randomness. We address why, when, and how to randomize by proposing stochastic procedures that more adequately account for all of the claims that individuals have to allocations of social goods or opportunities. © 2024, CC BY.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Cross Contrasting Feature Perturbation for Domain Generalization

Cross Contrasting Feature Perturbation for Domain Generaliza...

引用

International Conference on computer Vision (ICCV)

作者： Chenming Li Daoan Zhang Wenjian Huang Jianguo Zhang Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Peng Cheng Laboratory Shenzhen China

Domain generalization (DG) aims to learn a robust model from source domains that generalize well on unseen target domains. Recent studies focus on generating novel domain samples or features to diversify distributions complementary to source domains. Yet, these approaches can hardly deal with the restriction that the samples synthesized from various domains can cause semantic distortion. In this paper, we propose an online one-stage Cross Contrasting Feature Perturbation (CCFP) framework to simulate domain shift by generating perturbed features in the latent space while regularizing the model prediction against domain shift. Different from the previous fixed synthesizing strategy, we design modules with learnable feature perturbations and semantic consistency constraints. In contrast to prior work, our method does not use any generative-based models or domain labels. We conduct extensive experiments on a standard DomainBed benchmark with a strict evaluation protocol for a fair comparison. Comprehensive experiments show that our method outperforms the previous state-of-the-art, and quantitative analyses illustrate that our approach can alleviate the domain shift problem in out-of-distribution (OOD) scenarios. https://***/hackmebroo/CCFP

关键词：

来源：评论

学校读者我要写书评

暂无评论

Solving the Many to Many Grouped Task Allocation Problem via E-CARGO

Solving the Many to Many Grouped Task Allocation Problem via...

引用

IEEE International Conference on Networking, Sensing and Control

作者： Mozhdeh Noroozi Rasoolabadi Haibin Zhu Chun Wang Institute for Information Systems Engineering Concordia University Montreal Canada Department of Computer Science and Mathematics Nipissing University North Bay Canada

The task allocation between team members of each organization's departments is a crucial project management activity that needs adequate attention to improve organizational efficiency. If a related decision is not made properly, it may immediately cause problems with coordination and communication, task delays, and increased costs. Tasks are usually grouped and then these groups are assigned to the agents. Moreover, it is important to consider the difficulty level of the tasks and the member’s ability. The task allocation process becomes increasingly complex when administrators strive to maintain the balance between the workload of allocated task groups and the agents' capabilities. The E-CARGO (Environments - Classes, Agents, Roles, Groups, and Objects) model, created for the purpose of Role-Based Collaboration (RBC), has been effectively utilized to address the given problem. In this paper, a novel approach is presented to formalize the Grouped Task Allocation Problem (GTAP) employing an extended Group Multirole Assignment with Conflicting Roles problem (GMRACR), which is a sub-model of E-CARGO. In this paper, a role negotiation method is introduced, which is based on GMRACR. It employs a partitioning clustering algorithm along with the Analytic Hierarchy Process (AHP) to evaluate the difficulty level of tasks and the abilities of agents, respectively. This formalization of GTAP facilitates the identification of a solution using the IBM ILOG CPLEX optimization package (CPLEX). The proposed method helps decision-makers with a framework to successfully assign balanced grouped tasks. Through simulation experiments on a real-world problem, the efficacy of the suggested approach is substantiated. Experimental results reveal the practicality of the solutions recommended in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hash Tag-Based Sentiment Analysis Using A Deep Learning Approach

Hash Tag-Based Sentiment Analysis Using A Deep Learning Appr...

引用

International Conference on Advanced Computing and Communication systems (ICACCS)

作者： R. Venkatesan M. Sangeetha S. Nivedha M. Selvakumar K.S. Chandru P. Parthasarathi Department of Information Technology Bannari Amman Institute of Technology Erode India Department of Information Technology K S Rangasamy College of Technology Namakkal India Dept. of Computer Science & Engineering Hindusthan College of Engg and Technology Coimbatore India Dept. Computer Science & Business Systems Bannari Amman Institute of Technology Erode India Dept. Computer Science and Engineering Bannari Amman Institute of Technology Erode India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384376

Social commerce uses a variety of social networking sites like Facebook, Instagram, Twitter, Pinterest, and business Whatsapp as a platform to promote products and services. Since advertising, a product, or service in s-comm will reach as high as a possible number of users on networking sites. Ads will spread virally by sharing among friends and friends of friends. So that wider reachability is possible and shortly will get the customer for our business. The success of an s-comm campaign is measured by the degree to which consumers interact with the sellers through review comments, likes, and shares between friends. Customer behavior analysis is needed for s-comm marketing because social commerce can significantly boost economic growth. The sentiment analysis of customer recommendations was investigated using a dataset of women's s-comm apparel hashtags and reviews. So for such reviews are experimented with different machine learning algorithms (Decision tree, SVM, Random Forest, KNN, Naïve Bayes and LSTM). These models handled the common English reviews and compared the metrics (Accuracy, Sensitivity and Specificity) with one another. Instead of working with individual model, this paper introduces a novel hybrid approach that integrates CNN and Ada Boost LSTM algorithms to provide better results in sentiment analysis when compared to other machine learning algorithms mentioned above. While considering the hash tag with common review comments the hybrid system is out performed. The comparison analysis is done for performance matrices namely accuracy of 98%, specificity of 98.1%, and sensitivity of 98.1%. In the s-commerce transaction industry, this hybrid approach will help to create a deeper understanding of consumer sentiment analysis and psychologically attract clients.

关键词： Deep learning Sentiment analysis Analytical models Accuracy Sensitivity Machine learning algorithms Reviews Social networking (online) Biological system modeling Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Radiomics Analysis for Prostate Cancer Detection Harnessing Machine and Deep Learning Models 22

Large-Scale Radiomics Analysis for Prostate Cancer Detection...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Mylona, Eugenia Zaridis, Dimitrios I. Kalantzopoulos, Charalampos N. Pezoulas, Vasileios C. Tachos, Nikolaos S. Matsopoulos, George K. Regge, Daniele Papanikolaou, Nikolaos Tsiknakis, Manolis Marias, Kostas Fotiadis, Dimitrios I. Biomedical Research Institute Forth IoanninaGR 45110 Greece University of Ioannina Unit of Medical Technology Intelligent Information Systems Greece School of Electrical & Computer Engineering National Technical University of Athens Biomedical Engineering Laboratory Athens15780 Greece Candiolo Cancer Institute FPO-IRCCS Department of Radiology Strada Provinciale Candiolo Turin10060 Italy Champalimaud Foundation Computational Clinical Imaging Group Portugal Institute of Computer Science Forth Computational Biomedicine Laboratory HeraklionGR 70013 Greece Hellenic Mediterranean University Department of Electrical and Computer Engineering HeraklionGR 71004 Greece

ISBN: (纸本)9798331520526

Prostate cancer (PCa) is the second most common cancer in men, making early detection crucial for effective treatment. This study explores the efficacy of machine learning (ML) and deep learning (DL) models in detecting PCa lesions using radiomics features derived from multiparametric MRI data. Leveraging a dataset of 7621 retrospective and 2132 prospective cases from 12 clinical centers across Europe, we compared the performance of various ML (LASSO, Random Forest, SVM, XGBoost) and DL models (CNN, MLP, Transformer, CNN&MLP). Radiomic features were extracted and refined through a robust feature selection process. Models' performance was evaluated through nested cross-validation (CV) and externally. The CNN&MLP model achieved the highest ROC AUC (0.86) and PR AUC (0.90) in CV, while LASSO showed consistent generalization in external validation. Our findings indicate that DL models excel in high-dimensional data analysis but face challenges in generalizing to external datasets, highlighting the importance of external validation for clinical applicability. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Career Track Based Capstone Course Design for Information systems Curriculum

Career Track Based Capstone Course Design for Information Sy...

引用

IEEE Education engineering (EDUCON)

作者： Swapna Gottipati Kyong Jin Shim Subhajit Datta School of Computing and Information Systems Singapore Management University Singapore Department of Computer Science and Engineering Heritage Institute of Technology Kolkata India

ISBN: (数字)9798350399431

ISBN: (纸本)9798350399448

The aim of technical education is to design a career-based curriculum that imparts a set of skills to students and enable them to contribute to a nation's economic progress. With their multifarious uses, information systems (IS) lie at the heart of modern economies. IS curricula offer several tracks for students to pursue career paths based on their interests and opportunities. To offer students an opportunity to apply the knowledge they glean from classroom instructions on real-world problems, capstone projects are essential elements in most, if not all, IS programs. As IS programs increasingly offer a wider range of career paths for students, the design and delivery of such capstone projects present a set of unique challenges. In this paper, we examine the set of challenges and share our experience from designing and delivering a career track-based capstone course for the first time at a large university. Feedback from students and faculty supervisors indicates that the course was able to meet its learning objectives to a notable extent and offered important pointers to future improvements in the course design.

关键词： Heart Economics engineering profession Stakeholders engineering education Information systems

来源：评论

学校读者我要写书评

暂无评论

CONCENTRATION IN GOSSIP OPINION DYNAMICS OVER RANDOM GRAPHS

arXiv

引用

arXiv 2023年

作者： Xing, Yu Johansson, Karl H. Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology and Digital Futures Stockholm Sweden

We study concentration inequalities in gossip opinion dynamics over random graphs. In the model, a network is generated from a random graph model with independent edges, and agents interact pairwise randomly over the network. During the process, regular agents average neighbors’ opinions and then update, whereas stubborn agents do not change opinions. To approximate the original process, we introduce a gossip model over an expected graph, obtained by averaging all possible networks generated from the random graph model. Using concentration inequalities, we derive high-probability bounds for the distance between the expected final opinion vectors over the random graph and over the expected graph. Leveraging matrix perturbation results, we show how such concentration can help study the effect of network structure on the expected final opinions in two cases: (i) When the influence of stubborn agents is large, the expected final opinions polarize and are close to stubborn agents’ opinions. (ii) When the influence of stubborn agents is small, the expected final opinions are close to each other. With the help of concentration inequalities for Markov chains, we obtain high-probability bounds for the distance between time-averaged opinions and the expected final opinions over the expected graph. In simulation, we validate the theoretical findings, and study a gossip model over a stochastic block model that has community structure. © 2023, CC BY.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Studying the impact of the user subscription times in different cloud configurations 33

Studying the impact of the user subscription times in differ...

引用

33rd International Conference on software engineering and Knowledge engineering, SEKE 2021

作者： de la Cruz, Hernán-Indibil Cambronero, María-Emilia Valero, Valentín Cañizares, Pablo C. Bernal, Adrián Núñez, Alberto Albacete Research Institute of Informatics Computer Science Department Universidad de Castilla-La Mancha Spain Computer Science Department Autonomous University of Madrid Spain Software Systems and Computation Department Complutense University of Madrid Spain

ISBN: (纸本)1891706527

In this paper, we model cloud systems and the user interactions with the cloud provider using the UML2Cloud profile. In general, users request virtual machines according to their needs, but they can also subscribe to the cloud provider and wait to be notified when the requested resources are not available. In this case, users indicate a maximum subscription time, so once this time elapses without being notified, users leave the system unattended. In this paper, then, we present an exhaustive research study to measure how the user subscription times affect the overall system responsiveness. In this study, three different cloud configurations are analyzed. Each cloud processes several workloads, which are generated using two distribution functions for the user arrivals, namely a normal and a cyclic normal distribution. The purpose of this study is to find out the inflection point for the waiting time of the users, from which the cloud responsiveness and its performance do not improve. The obtained information is therefore useful for the cloud provider to improve the configuration of the cloud. © 2021 Knowledge systems institute Graduate School. All rights reserved.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Mobile Healthcare: Societal Impact, Workforce Adaptation, and Enhanced Predictive Modeling for Diabetes Risk Assessment

AI-Driven Mobile Healthcare: Societal Impact, Workforce Adap...

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： Shreyas Rajendra Hole Vinothkumar Kolluru Ranita Gangul Sagar Kolekar Advaitha Naidu Chintakunta Sudeep Mungara Computer Science & Engineering (AI& ML) Dayananda Sagar University Bangalore India Department of data Science Stevens Institute of Technology Hoboken NJ U.S.A. Computer Science & Engineering Delaware State University Bangalore India Department of Civil Engineering Symbiosis Institute of Technology (SIT) Symbiosis International (Deemed University) Pune India Department of Computer Science University of North Carolina at Charlotte Charlotte NC U.S.A. Masters in Information Systems Stevens Institute of Technology Hoboken NJ U.S.A.

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

With advancements in artificial intelligence, it is natural for the health industry to focus on IOT devices. AI could promote a paradigm shift in how doctors and patients interact through immediate updates, predictive features, and remote access. The focus of this study is the outreach and employment aspects revolving around AI-enabled health care, with special attention to mHealth solutions. We searched through published data and came across 112 relevant studies identifying keywords such as accessibility, empowerment, and workforce. One of the most interesting findings was the fact that AI targeting mobile applications has the possibility of increasing access to health services by approximately 60 percent for rural areas, as well as increasing the patient cooperative rate by approximately 45%, where a predictive health tracking device has been utilized. We proposed two new measures: the Physical Activity and Nutrition Index (PANI) and Health Status Index (HSI), allowing for better diabetes risk predictions with a 0.82 AUC-ROC and better generalizability than traditional baselines, with an improvement of 12%. When identifying the best available ML models, including Logistic Regression, Random Forest, XGBoost, LightGBM, and Bayesian Neural Networks, we found that the hybrid Random Forest + Linear SVC model had the best performance with recall and accuracy of 0.77 and 0.72, respectively. The ability of the model to demonstrate both interpretability and specificity was evident. It was also observed that synthetic data augmentation (SMOTE) increased the recall for minority class predictions by 18% but did not reduce specificity.

关键词： Adaptation models Uncertainty Neural networks Medical services Predictive models Diabetes Bayes methods Risk management Indexes Random forests

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：