检索结果-内蒙古大学图书馆

Electrical, Energy, and Artificial Intelligence (EICEEAI), International engineering Conference on

作者： Alireza Kazemi Reza Boostani Mahmoud Odeh Mohammad Rasmi AL-Mousa Mathematics Department Faculty of Science Shiraz University Shiraz Fars Iran CSE&IT Dept. Electrical and Computer Engineering School Shiraz University Shiraz Fars Iran Department of Management Information System Zarqa University Jordan Department of Cyber Security Faculty of Information Technology Zarqa University Zarqa Jordan

Support Vector Machine (SVM) is originally a binary large-margin classifier emerged from the concept of structural risk minimization. Multiple solutions such as one-versus-one and one-versus-all have been proposed for creating multi-class SVM using elementary binary SVMs. Also multiple solutions have been proposed for SVM model selection, adjusting margin-parameter C and the Gaussian kernel variance. Here, an improved classifier named SVM-SVM is proposed for multi-class problems which increases accuracy and decreases dependency to margin-parameter selection. SVM-SVM adopts two K-class one-vs-one SVMs in a cascaded two-layer structure. In the first layer, input features are fed to one-vs-one SVM with non-linear kernels. We introduce this layer as a large-margin non-linear feature transform that maps input feature space to a discriminative K*(K-1)/2 dimensional space. To assess our hierarchical classifier, some datasets from the UCI repository are evaluated. Standard one-vs-one SVM and one-vs-one fuzzy SVM are used as reference classifiers in experiments. Results show significant improvements of our proposed method in terms of test accuracy and robustness to the model (margin and kernel) parameters in comparison with the reference classifiers. Our observations suggest that a multi-layer (deep) SVM structures can gain the same benefits as is seen in the deep neural nets (DNNs).

关键词： Support vector machines Electric potential Statistical learning Neural networks Transforms Nonhomogeneous media Robustness

来源：评论

学校读者我要写书评

暂无评论

PDA Construction via Union of Cartesian Product Cache Configurations for Coded Caching

arXiv

引用

arXiv 2025年

作者： Wang, Jinyu Cheng, Minquan Wan, Kai Caire, Giuseppe Key Lab of Education Blockchain and Intelligent Technology Ministry of Education China Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin541004 China School of Mathematics and Statistics Guangxi Normal University Guilin541004 China School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan430074 China Electrical Engineering and Computer Science Department Technische Universität Berlin Berlin10587 Germany

Caching is an efficient technique to reduce peak traffic by storing popular content in local caches. Placement delivery array (PDA) proposed by Yan et al. is a combinatorial structure to design coded caching schemes with uncoded placement and one-shot linear delivery. By taking the m-fold Cartesian product of a small base PDA, Wang et al. constructed a big PDA while maintaining the memory ratio and transmission load unchanged, which achieves linear growth in both the number of users and coded caching gain. In order to achieve exponential growth in both the number of users and coded caching gain, in this paper we propose a PDA construction by taking the union operation of the cache configurations from the m-fold Cartesian product of a base PDA. The resulting PDA leads to a coded caching scheme with subpacketization increasing sub-exponentially with the number of users while keeping the load constant for fixed memory ratio. By applying the proposed construction to existing base PDAs, three new coded caching schemes are obtained, which cover some existing schemes as special cases and can achieve lower load with simultaneously lower subpacketization for some memory ratios. Copyright © 2025, The Authors. All rights reserved.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

Privacy engineering in the Wild: Understanding the Practitioners’ Mindset, Organisational Aspects, and Current Practices

arXiv

引用

arXiv 2022年

作者： Iwaya, Leonardo Horn Ali Babar, Muhammad Rashid, Awais Centre for Research on Engineering Software Technologies The University of Adelaide AdelaideSA5005 Australia Australia research group Department of Mathematics and Computer Science Karlstad University Sweden Bristol Cyber Security Group Department of Computer Science University of Bristol United Kingdom REPHRAIN: National Research Centre on Privacy Harm Reduction and Adversarial Influence Online United Kingdom

Privacy engineering, as an emerging field of research and practice, comprises the technical capabilities and management processes needed to implement, deploy, and operate privacy features and controls in working systems. For that, software practitioners and other stakeholders in software companies need to work cooperatively toward building privacy-preserving businesses and engineering solutions. Significant research has been done to understand the software practitioners’ perceptions of information privacy, but more emphasis should be given to the uptake of concrete privacy engineering components. This research delves into the software practitioners’ perspectives and mindset, organisational aspects, and current practices on privacy and its engineering processes. A total of 30 practitioners from nine countries and backgrounds were interviewed, sharing their experiences and voicing their opinions on a broad range of privacy topics. The thematic analysis methodology was adopted to code the interview data qualitatively and construct a rich and nuanced thematic framework. As a result, we identified three critical interconnected themes that compose our thematic framework for privacy engineering "in the wild": (1) personal privacy mindset and stance, categorised into practitioners’ privacy knowledge, attitudes and behaviours;(2) organisational privacy aspects, such as decision-power and positive and negative examples of privacy climate;and, (3) privacy engineering practices, such as procedures and controls concretely used in the industry. Among the main findings, this study provides many insights about the state-of-the-practice of privacy engineering, pointing to a positive influence of privacy laws (e.g., EU General Data Protection Regulation) on practitioners’ behaviours and organisations’ cultures. Aspects such as organisational privacy culture and climate were also confirmed to have a powerful influence on the practitioners’ privacy behaviours. A conducive environment f

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Traffic engineering in Dynamic Hybrid Segment Routing Networks

引用

computers, Materials & Continua 2021年第7期68卷 655-670页

作者： Yingya Guo Kai Huang Cheng Hu Jiangyuan Yao Siyu Zhou College of Mathematics and Computer Science Fuzhou UniversityFuzhou350000China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou UniversityFuzhou350000China Key Laboratory of Spatial Data Mining&Information Sharing Ministry of EducationFuzhou350003China School of Information Science and Technology Guangdong University of Foreign StudiesGuangzhou510006China School of Computer Science and Cyberspace Security Hainan UniversityHaiKou570228China Tandon School of Engineering New York UniversityNew York10012USA Department of Computing Hong Kong Polytechnic UniversityHong Hom999077Hong Kong

The emergence of Segment Routing(SR)provides a novel routing paradigm that uses a routing technique called source packet *** SR architecture,the paths that the packets choose to route on are indicated at the ingress *** with shortest-path-based routing in traditional distributed routing protocols,SR can realize a flexible routing by implementing an arbitrary flow splitting at the ingress *** the advantages of SR,it may be difficult to update the existing IP network to a full SR deployed network,for economical and technical *** partial of the traditional IP network to the SR network,thus forming a hybrid SR network,is a preferable *** the traffic is dynamically changing in a daily time,in this paper,we propose a Weight Adjustment algorithm WASAR to optimize routing in a dynamic hybrid SR *** algorithm can be divided into three steps:firstly,representative Traffic Matrices(TMs)and the expected TM are obtained from the historical TMs through ultrascalable spectral clustering ***,given the network topology,the initial network weight setting and the expected TM,we can realize the link weight optimization and SR node deployment optimization through a Deep Reinforcement Learning(DRL)***,we optimize the flow splitting ratios of SR nodes in a centralized online manner under dynamic traffic demands,in order to improve the network *** the evaluation,we exploit historical TMs to test the performance of the obtained routing configuration in *** extensive experimental results validate that our proposed WASAR algorithm has superior performance in reducing Maximum Link Utilization(MLU)under the dynamic traffic.

关键词： Traffic engineering routing optimization segment routing deep reinforcement learning ultra-scalable spectral clustering

来源：评论

学校读者我要写书评

暂无评论

An access control scheme in IoT-enabled Smart-Grid systems using blockchain and PUF

引用

Internet of Things (Netherlands) 2023年 22卷

作者： Zahoor, Amina Mahmood, Khalid Shamshad, Salman Saleem, Muhammad Asad Ayub, Muhammad Faizan Conti, Mauro Das, Ashok Kumar Department of Computer Science COMSATS University Islamabad Sahiwal Campus 57000 Pakistan Graduate School of Intelligent Data Science National Yunlin University of Science and Technology Yunlin 64002 Taiwan Department of Software Engineering The University of Lahore Lahore 54590 Pakistan Department of Computer Science University of Sahiwal Sahiwal 57000 Pakistan Department of Mathematics University of Padua Padua 35131 Italy Center for Security Theory and Algorithmic Research International Institute of Information Technology Hyderabad 500 032 India

IoT-enabled Smart Grid (IoT-SG) is an emerging paradigm that enables the bi-direction communication of IoT devices and hardware to efficiently collect and transmit the consumer's information over the Internet. However, the underlying open communication network and resource-constrained capabilities of devices invite manifold challenges and threats in terms of security and privacy. To alleviate such issues, we designed a private blockchain-based access control protocol for IoT-SG using Physically Unclonable Function (PUF). Our protocol allows the Service Provider (SP) and smart meters to transfer the data in an efficient and secure manner. The participating SPs form the Peer-to-Peer (P2P) network, and each peer node is responsible for securely creating the blocks from the gathered data. Thereafter, all the peer nodes employ a voting-based consensus mechanism to verify and add the recently created block into the blockchain network. We have rigorously validated the security of our protocol under the Random or Real (RoR) model. The testbed results and security feature analysis show that our protocol is more efficient than competing ones while it also provides significant security properties. © 2023 Elsevier B.V.

关键词： Authentication Blockchain Internet of Things (IoT) Key agreement security Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Detection of Liver Disease Using Machine Learning Approach

Detection of Liver Disease Using Machine Learning Approach

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Pravin Ramdas Kshirsagar Dhoma Harshavardhan Reddy Mallika Dhingra Dharmesh Dhabliya Ankur Gupta Department of Artificial Intelligence G H Raisoni College of Engineering Nagpur Maharashtra India Trainee Security Analyst JunoClinic Davman Technology Services Private Limited Mumbai Maharashtra India Department of Mathematics and Statistics Manipal University Jaipur Jaipur Rajasthan India Department of Information Technology Vishwakarma Institute of Information Technology Pune Maharashtra India Department of Computer Science and Engineering Vaish College of Engineering Rohtak Haryana India

For more effective therapy, it’s critical to get an early diagnosis of liver illness. Due to the disease’s modest symptoms, it is a very difficult challenge for medical experts to forecast the disease in its early stages. Frequently, the symptoms show up only when it’s too late. This study uses machine learning techniques to enhance the detection of liver illness in an effort to solve this problem. The major goal of this study is to distinguish between liver patients and healthy people using classification algorithms. The prevalence of liver illness has been rising globally in the twenty-first century. According to the most recent survey data, the death rate from liver disease has increased by almost 2 million per year globally. 3.5% of deaths globally are caused by liver disease generally. As one of the most fatal diseases, chronic liver disease can be readily cured with early diagnosis and therapy. The lifespan of a patient with Chronic Liver Disease (CLD) would increase due to the rapid development of artificial intelligence (AI), including various machine learning algorithms like SVM, K-mean clustering, KNN, Random forest, Logistic regression, etc. The foundation of this research is the use of machine learning algorithms to predict liver disease. Pre-processing, feature extraction, and classification are just a few of the stages that go into predicting liver disease. In this study, a hybrid classification system is suggested for predicting liver illness.

关键词： Support vector machines Performance evaluation Machine learning algorithms Liver diseases Medical treatment Artificial neural networks Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Efficient Public Integrity Auditing for Cloud Storage Against Malicious Auditors 16th

Blockchain-Based Efficient Public Integrity Auditing for Clo...

引用

16th International Conference on Information security and Cryptology, Inscrypt 2020

作者： Li, Shanshan Xu, Chunxiang Zhang, Yuan Yang, Anjia Wen, Xinsheng Chen, Kefei School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China College of Cyber Security Jinan University Guangzhou China Department of Mathematics Hangzhou Normal University Hangzhou China Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Ministry of Industry and Information Technology Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (纸本)9783030718510

Public integrity auditing enables a user to delegate a third-party auditor (TPA) to periodically audit the integrity of the outsourced data. Whereas, the security of public auditing schemes relies on the trustworthiness of TPA: once TPA misbehaves, the data integrity auditing would be invalidated. In this paper, we propose a blockchain-based efficient public integrity auditing scheme to resist misbehaved TPA, where the user is required to check the behaviors of TPA in a much longer period compared with that of the data integrity auditing performed by TPA. To free users from heavy computation costs during the checking, our scheme uses two key techniques. We first design a smart contract to (1) enable TPA to record each auditing entry (which records the information about each auditing task) into the blockchain and (2) ensure the validity of each recorded entry. Then, we propose an auditing record chain built on the Ethereum blockchain to link all auditing entries corresponding to the same data in the chronological order. By doing so, the user only needs to check the last auditing entry generated by TPA to verify the trustworthiness of TPA (i.e., whether TPA has correctly performed the prescribed auditing tasks). Compared with existing schemes, where the user has to check multiple entries one by one, our scheme achieves the same security guarantee with constant and low costs in terms of communication and computation. © 2021, Springer Nature Switzerland AG.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

A Review on Application of Deep Learning in Natural Language Processing

A Review on Application of Deep Learning in Natural Language...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

Natural Language Processing (NLP) is a developing method utilized in building different sorts of Artificial Intelligence (AI) that is available in today’s time. More intellectual applications will tend to be a primary goal for ongoing and upcoming research. The requirement and desire for data-driven strategies for automatic semantic analysis have risen as a result of recent improvements in processing capacity as well as the accessibility of enormous several linguistic records. A boom in the applications throughout the previous several years of deep learning approaches has advanced the area of natural language processing. This review offers a succinct summary of deep learning architectures and techniques as well as a basic introduction to the area. Our goal is to develop a theoretical study of numerous sectors where NLP may have a significant impact and completely alter the situation with its automated approaches. Everyone is interested in investing in it since it is a hot issue. An in-depth investigation of NLP and its field is used to create these applications. Natural language processing (NLP) trends and its constituent parts are covered in the introduction to this article before it discusses applications for NLP, its emergence, and related issues.

关键词： Deep learning computer science Semantics Linguistics Market research Natural language processing Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Review on Comparative study of 4G, 5G and 6G Networks

A Review on Comparative study of 4G, 5G and 6G Networks

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Pravin Ramdas Kshirsagar Dhoma Harshavardhan Reddy Mallika Dhingra Dharmesh Dhabliya Ankur Gupta Department of Artificial Intelligence G H Raisoni College of Engineering Nagpur Maharashtra India Trainee Security Analyst JunoClinic Davman Technology Services Pvt. Ltd Mumbai Maharashtra India Department of Mathematics and Statistics Manipal University Jaipur Jaipur Rajasthan India Department of Information Technology Vishwakarma Institute of Information Technology Pune Maharashtra India Department of Computer Science and Engineering Vaish College of Engineering Rohtak Haryana India

In the previous several years, wireless telecommunications technology has seen a significant change. The term “generation” in the context of wireless communication typically describes to a shift in the essential characteristics of the assistance being offered, such as transmission technologies, bit rates, frequency bands, channel frequency bandwidth, and data transfer capacity. One of the most active technological fields that is expanding too quickly is the wireless age. There is a need to implement such technologies that can be integrated and adjusted in order to produce a more advanced and unified system because there are numerous superior technologies available. In this work, we provide a summary of several wireless telecommunications technologies, in particular, 4G, 5G, and 6G Networks, and a detailed comparison between them.

关键词： Wireless communication 6G mobile communication Satellites 5G mobile communication Web and internet services Market research Telecommunications

来源：评论

学校读者我要写书评

暂无评论

Efficient Privacy-Preserving ML for IoT: Cluster-Based Split Federated Learning Scheme for Non-IID Data

Efficient Privacy-Preserving ML for IoT: Cluster-Based Split...

引用

Cyber security in Networking Conference (CSNet)

作者： Mohamad Arafeh Mohamad Wazzeh Hakima Ould-Slimane Chamseddine Talhi Azzam Mourad Hadi Otrok Department of Software and IT engineering Ecole de Technologie Superieure (ETS) Montreal Canada Department of Mathematics and Computer Science Universite de Quebec a Trois-Rivieres (UQTR) Canada Division of Science New York University Abu Dhabi UAE Department of CSM Cyber Security Systems and Applied AI Research Center Lebanese American University Beirut Lebanon Department of EECS Center of Cyber-Physical Systems (C2PS) Khalifa University Abu Dhabi UAE

This paper proposes a scheme addressing the challenges of integrating privacy-preserving distributed machine learning in the Internet of Things (IoT) context while improving the efficiency of the learning process and accelerating the convergence of the model. Specifically, it addresses the presence of non-independent and identically distributed (Non-IID) data and device heterogeneity, which occurs during parallel training and are common characteristics of IoT environments. In this context, SplitFed is a privacy-preserving technique that combines Federated Learning (FL) and Split Learning (SL) to enable fast and privacy-preserving model training on IoT devices. Through parallelism, FL allows fast and parallel model training. Furthermore, SL enables weak devices to train models through model splitting. However, SplitFed suffers from the increasing convergence time due to the FL parallelism introducing Non-IID and stragglers issues. In this paper, we aim to address the aforementioned problems by proposing a clustering parallelization scheme. As such, similar clients are combined based on their weight divergence and considered a single FL unit addressing the Non-IID problem. Moreover, to improve time efficiency and overcome the stragglers' presence, we offer a second clustering stage that separates clients by efficiency and uses FedAsync for model aggregation.

关键词：

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：