检索结果-内蒙古大学图书馆

2023 IEEE Global Conference on Information Technologies and Communications, GCITC 2023

作者： Pandey, Trilok Nath Navya Kala, S.V. Amrutha, S. Dash, Bibhuti Bhusan Patra, Sudhansu Shekhar Vellore Institute of Technology School of Computer Science and Engineering Chennai India Kiit Deemed to Be University School of Computer Applications Bhubaneswar India

ISBN: (纸本)9798350308167

The intent of customer segmentation is primarily to aid institutions to custom-make their marketing techniques and methods to suit the specific requirements of every consumer group. As this helps to solve the segregating of the groups of customers for banks efficiently and helps provide more custom-made services for customers of each group better, applying the customer segmentation for banking data can provide many insights that can be beneficial to banks as well as their customers. This increases the effectiveness of customer interaction and can maximize selling opportunities. It makes marketers more efficient in terms of time, money, and other resources. © 2023 IEEE.

关键词： Customer segmentation Gaussian mixture model clustering hierarchical agglomerative clustering hyper parameter tuning k-modes

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Multi-Source Domains Adaptation with Locally Topological Persevering

Unsupervised Multi-Source Domains Adaptation with Locally To...

引用

2023 China Automation Congress, CAC 2023

作者： Chen, Zhifeng Wang, Lvda Li, Ying Ying, Shihui College of Science Shanghai University Department of Mathematics China Beijing Institute of Computer Technology and Applications China College of Computer Engineering and Science Shanghai University China

ISBN: (纸本)9798350303759

Most existing unsupervised domain adaptation (UDA) methods primarily focus on single-source and single-target domain scenarios, referred to as single-source unsupervised domain adaptation. However, in practical applications, it is often possible to collect labeled data from multiple distinct source domains, which not only differ from the target domain but also exhibit dissimilarities among themselves. As a result, the concept of multi-source unsupervised domain adaptation has emerged. While mainstream UDA techniques aim to align features between two domains, addressing domain shift solely through feature alignment might prove inadequate, potentially undermining the inherent structure of the data. To mitigate this risk, this paper introduces a method called Locally Topology Preserving Multi-Source Unsupervised Domain Adaptation (LTP- MDA). By performing clustering on both source and target data, distinct clusters are formed. During the domain-adaptive feature transformation, this method ensures the preservation of the structural integrity of these clusters throughout the transformation. Additionally, due to the possibility of misclassification during the clustering process, we leverage consistency weights derived from genuine labels in the source domain and pseudo-labels in the target domain to guide the clustering process. Experimental results demonstrate the remarkable performance of our approach across various cross-domain adaptation tasks. We extensively evaluate our method on three benchmark datasets, validating its effectiveness and robustness. © 2023 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Fraud Detection in Bitcoin Transactions: An AI Approach

Deep Learning for Fraud Detection in Bitcoin Transactions: A...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Shravan, M. Ajitha, E. Arnone, Gioia Renu, Nekkanti Tiwari, Mohit Chouhan, Kuldeep Sr University School of Business Telangana Warangal India St. Joseph's Institute of Technology Computer Science and Engineering India Vrije Universiteit Brussel Department of Private and Economic Law Bruxelles Belgium Department of Computer Science and Engineering Duvvada India Bharati Vidyapeeth's College of Engineering Department of Computer Science and Engineering Delhi Delhi India Sharda University Sharda School of Engineering and Technology Department of Computer Science and Applications Greater Noida201310 India

ISBN: (纸本)9798331508685

This research looks into how deep learning methods can be used to find fake Bitcoin transfers. It's mostly about the unique problems and chances that come with trading in cryptocurrencies and blockchain. Deep learning models are used to look at transaction trends and find oddities that could be signs of fraud. This is because Bitcoin's open structure makes it harder to use traditional methods of fraud detection. We offer a structure that connects CNNs (convolutional neural networks) and RNNs (recurrent neural networks) so that strange patterns can be found in big sets of blockchain transactions. An AI-driven method aims to improve detection accuracy while lowering false positives by taking on scammers' complicated and always-changing strategies. Experienced researchers have shown that the model is good at finding strange things, which means it can be used to safely stop theft in Bitcoin networks in real time. It looks like deep learning could make digital money safer and give us data that can be used in bigger blockchain-based money systems. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Reliability via Subsystem Structures of Arrangement Graph Networks

引用

IEEE Transactions on Reliability 2024年第1期73卷 279-289页

作者： Huang, Yanze Lin, Limei Xu, Li Hsieh, Sun-Yuan Fujian University of Technology Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fuzhou350118 China Fujian Normal University College of Computer and Cyber Security Key Laboratory of Network Security and Cryptology Fuzhou350117 China National Cheng Kung University Department of Computer Science and Information Engineering Tainan701 Taiwan

With the rapid growth of the number of processors in a multiprocessor system, faulty processors occur in it with a probability that rises quickly. The probability of a subsystem with an appropriate size being fault-free in a definite time interval is a significant and practical measure of the reliability for a multiprocessor system, which characterizes the functionality of a multiprocessor system well. Motivated by the study of subgraph reliability, as well as the attractive structure and fault tolerance properties of (n, k)-arrangement graph A n, k, we focus on the subgraph reliability for A n, k under the probabilistic fault model in this article. First, we investigate intersections of no more than four subgraphs in A n, k, and classify all the intersecting modes. Second, we focus on the probability P(q, A n, k n-1, k-1) with which at least one (n-1, k-1)-subarrangement graph is fault-free in A n, k, when given a uniform probability q with which a single vertex is fault-free, and we establish the P(q, A n, kn-1, k-1) by adopting the principle of inclusion-exclusion under the probabilistic fault model. Finally, we study the probabilistic fault model involving a nonuniform probability with which a single vertex is fault-free, and we prove that the P(q, A n, kn-1, k-1) under both models is very close to the asymptotic value by both theoretical arguments and experimental results. © 1963-2012 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Alzheimer's Disease Classification using Capsule Network 4

Alzheimer's Disease Classification using Capsule Network

引用

4th International Conference on Expert Clouds and applications, ICOECA 2024

作者： Pattanayak, Binod Kumar Mansingh, Padmini Pati, Bibudhendu Dash, Bibhuti Bhusan Gourisaria, Mahendra Kumar Patra, Sudhansu Shekhar ITER SOA Deemed to be University Department of Computer Science and Engineering Bhubaneswar India Rama Devi Women's University Department of Computer Science Bhubaneswar India School of Computer Applications KIIT Deemed to be University Bhubaneswar India School of Computer Engineering KIIT Deemed to be University Bhubaneswar India

ISBN: (纸本)9798350385793

The most prevalent type of dementia is Alzheimer's disease, which impairs thinking, memory, and communication abilities. Better patient treatment is made possible with early disease identification. To detect and predict Alzheimer's disease through the analysis of Magnetic Resonance Images (MRIs), deep learning and big data analytics have recently been created. To improve the classification of Alzheimer's disease patients, this work utilizes capsule network. A critical evaluation is carried out on patients with Alzheimer's disease to improve stage-specific classification. Specifically, the study analyses various methods for performing abnormality identification in brain MRI images and pinpoint the shortcomings of those methods. Thus, it is possible to close the research gaps and enhance the shortcomings of different approaches to produce more accurate and superior results. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis of Important Facts between Heart Disease Features using Machine Learning Classifiers 14

Analysis of Important Facts between Heart Disease Features u...

引用

14th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023

作者： Pal, Gyanendra Kumar Gangwar, Sanjeev Department of Computer Science & Engineering VBS Purvanchal University Jaunpur India Department of Computer Applications VBS Purvanchal University Jaunpur India

The heart disease is very dangerous disease so diagnosis expert cannot easily manage the effects of risk factors. Machine learning algorithms provide way to predict complex problem in dataset. In this paper, we have simplified dataset by two different features selection methods as Lasso Regression and Random Forest. The Lasso algorithm easily reduces the weak features and prepared strong important collection of features. The Random Forest randomly selects the important features and reduces dataset complexity. In this experiment, we have used Random Forest as predictor algorithm and test dataset model on different K-Fold cross validation as K=2, 4, 6, &. 10., and analyzed simplify dataset by Lasso and Random Forest. Finally, we find Random Forest perform better on dataset which is simplified by Random Forest features selection method. In our experimental results, the proposed Random Forest model performs excellent works in terms of accuracy and ROC. The Random Forest approach with Random Forest features selection calculated classification accuracy as 99% and ROC values calculated 93% on 10-fold cross validation. © Grenze Scientific Society, 2023.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Empowering Dynamic Scheduling in IoT Networks through Collaborative Policy Learning via Federated Reinforcement Techniques 2

Empowering Dynamic Scheduling in IoT Networks through Collab...

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Thirunavukkarasu, M. Thaiyalnayaki, S. Jose, Naduvathezhath Nessariose Maheshwari, S. Pavithra, B. Malathi, G. Department of Computer Science & Applications S.A College of Arts & Science India Department of Computer Science Rabiammal Ahamed Maideen College for Women India Denken Solutions India Department of Information Technology Sri Sai Ranganathan Engineering College India Department of Computer science and Engineering Sri Sai Ranganathan Engineering College India Department of Computer Science and Engineering Sri Sai Ram Institute of Technology Chennai India

ISBN: (纸本)9798350383867

In the burgeoning landscape of Internet of Things (IoT) networks, efficient management of resources is paramount for ensuring optimal performance and resource utilization. Dynamic scheduling, particularly in the context of cloud-edge-terminal IoT networks, presents a significant challenge due to the diverse and dynamic nature of connected devices and their varying computational requirements. Traditional centralized approaches to scheduling may prove inadequate in such dynamic environments, necessitating the exploration of novel techniques. This project proposes a pioneering approach to address the dynamic scheduling challenges in IoT networks by leveraging collaborative policy learning through federated reinforcement techniques. The proposed framework harnesses the power of federated learning, a decentralized machine learning paradigm, to collectively train policies for dynamic scheduling tasks across distributed edge and terminal devices while preserving data privacy and security. Key components of the proposed framework include a collaborative learning architecture that orchestrates the exchange of policy updates among edge and terminal devices, enabling them to adaptively refine their scheduling policies based on local observations and feedback. Reinforcement learning serves as the underlying mechanism for policy optimization, allowing devices to learn and adapt to evolving network conditions and user demands over time. By decentralizing the learning process and leveraging the collective intelligence of edge and terminal devices, the proposed framework offers several advantages. These include improved scalability, reduced communication overhead, and enhanced resilience to network failures. Furthermore, the federated approach ensures data privacy and regulatory compliance by keeping sensitive information localized to individual devices. To evaluate the effectiveness of the proposed framework, comprehensive simulations and real-world experiments will be conducted u

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain Technology: Reshaping Telemedicine and Telehealth Services for Emergency Management

Blockchain Technology: Reshaping Telemedicine and Telehealth...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Singh, Neelam Mittal, Varsha Rawat, Vandana Kumar, Priyansh Graphic Era Deemed to Be University Dept. of Computer Science and Engineering Uttrakhand Dehradun India Graphic Era Deemed to Be University Dept. of Computer Applications Uttrakhand Dehradun India

ISBN: (纸本)9798331508685

Both consumers and healthcare providers have benefited greatly from the quick development of software-based technology. The dominance of blockchains is impending as the medical care sector moves quickly towards digitization and customization. The development of blockchain provided answers to several problems that had long plagued the healthcare sector. However, not only in healthcare due to its capabilities, blockchain technology has found great success in a variety of industrial fields. The important factors propelling the growth of the healthcare blockchain market are the rise in data breaches, privacy concerns, fake pharmaceuticals, and provided answers to numerous problems that had long plagued the healthcare sector. Although telemedicine had been developing for a while, the covid-19 epidemic gave it the necessary kick. In order to facilitate social isolation, the pandemic made it necessary to expand virtual healthcare and distant therapy. Over the past year, the telemedicine market has experienced rapid expansion. In the current study, the adaptation issues and prospective prospects for blockchain technology in the telehealth and telemedicine sectors are *** on a systematic review, we have determined the existing state of the use of blockchain technology in a number of healthcare-related areas, the ideal state that would be achieved, the research gap regarding the usage of blockchain technology in a number of healthcare-related application areas, as well as a number of potential research agendas for future studies. © 2025 IEEE.

关键词： Telemedicine

来源：评论

学校读者我要写书评

暂无评论

An Approach for Enhancing Data Storage Capacity in Quick Response Code using Zip Compression Technique

An Approach for Enhancing Data Storage Capacity in Quick Res...

引用

2023 International Conference on Artificial Intelligence and Smart Communication, AISC 2023

作者： Bhardwaj, Cheshtaa Garg, Hitendra G.L Bajaj Group of Institutions Department of Computer Science and Engineering Mathura India Gla University Department of Computer Engineering and Applications Mathura India

ISBN: (纸本)9798350322309

A 2-D matrix barcode known as Quick Response Code stores data in four distinct encoding modes. Nowadays, it can be found on almost every product, billboard, digital transaction, and so on because of its growing popularity. It is now so user- and mobile-friendly that users can seamlessly transit from offline to online environments. It is used to store the information, allowing people to interact in real world using Smartphone and also as an information sharing medium. The primary objective of this work is to use ZIP compression to improve QR code data storage. This paper will provide a brief explanation of how QR code data storage capacity is enhanced by ZIP compression. As ZIP compression is a lossless compression technique, the result demonstrates how more data can be stored in QR codes of different sizes without losing any information in the form of compressed data. Additionally, after scanning the QR code, the compressed data is decompressed to retrieve the original data. © 2023 IEEE.

关键词： Data compression

来源：评论

学校读者我要写书评

暂无评论

An Imperial Analysis of Large Language Models for Automated Tweet Sentiment Prediction

An Imperial Analysis of Large Language Models for Automated ...

引用

2023 International Conference on Sustainable Communication Networks and Application, ICSCNA 2023

作者： Akhouri, Shivam Ajbani, Vidhi Lakshminarayanan, Ritika Pandey, Trilok Nath Nigam, Meher Shrishti Patra, Sudhansu Shekhar Vellore Institute of Technology School of Computer Science and Engineering Chennai India Kiit Deemed to Be University School of Computer Applications Bhubaneswar India

ISBN: (纸本)9798350313987

Company' s brand perception majorly depends on customer experience and the reviews which follow that. A customer is capable of influencing many more people just on the basis of reviews given by him/her. Google released Pathways Language Model (PaLM) which is a major advancement in Artificial Intelligence (AI). It has been trained with the Pathways System, which allows it to generalize tasks in various domains. In this work, a trustworthy platform is provided for the examination of millions of people's continually moving and changing perspectives. Twitter data is captured, and effective sentiment and data analysis is used to generate trustworthy and helpful info graphics reflecting public opinion. Product sales, stock returns, election outcomes, and other commercial and social events may all be predicted and explained using the information found in tweets. Brands, product manufacturers, and other companies may utilise the information derived from data analysis to better understand their brand image, expand their market share by targeting the relevant demographics at the right moments, and enhance their offerings in terms of both quality and customer service. © 2023 IEEE.

关键词： Attention Units Data visualization Masks Sentiment Analysis Tokenization

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：