检索结果-南通市图书馆

Quantum Inspired Differential Evolution with Explainable Artificial Intelligence-Based COVID-19 Detection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer systems Science & Engineering 2023年第7期46卷 209-224页

作者： Abdullah M.Basahel Mohammad Yamin Department of Management Information Systems Faculty of Economics and AdministrationKing Abdulaziz UniversityJeddah21589Saudi Arabia

Recent advancements in the Internet of Things(Io),5G networks,and cloud computing(CC)have led to the development of Human-centric IoT(HIoT)applications that transform human physical monitoring based on machine monitoring.The HIoT systems find use in several applications such as smart cities,healthcare,transportation,etc.Besides,the HIoT system and explainable artificial intelligence(XAI)tools can be deployed in the healthcare sector for effective decision-making.The COVID-19 pandemic has become a global health issue that necessitates automated and effective diagnostic tools to detect the disease at the initial stage.This article presents a new quantum-inspired differential evolution with explainable artificial intelligence based COVID-19 Detection and Classification(QIDEXAI-CDC)model for HIoT systems.The QIDEXAI-CDC model aims to identify the occurrence of COVID-19 using the XAI tools on HIoT systems.The QIDEXAI-CDC model primarily uses bilateral filtering(BF)as a preprocessing tool to eradicate the noise.In addition,RetinaNet is applied for the generation of useful feature vectors from radiological images.For COVID-19 detection and classification,quantum-inspired differential evolution(QIDE)with kernel extreme learning machine(KELM)model is utilized.The utilization of the QIDE algorithm helps to appropriately choose the weight and bias values of the KELM model.In order to report the enhanced COVID-19 detection outcomes of the QIDEXAI-CDC model,a wide range of simulations was carried out.Extensive comparative studies reported the supremacy of the QIDEXAI-CDC model over the recent approaches.

关键词： Human-centric IoT quantum computing explainable artificial intelligence healthcare COVID-19 diagnosis

Enhancing Network Intrusion Detection Model Using Machine Learning Algorithms

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第4期67卷 979-990页

作者： Nancy Awadallah Awad department of Computer and information systems Sadat Academy for Management SciencesCairo11742Egypt

After the digital revolution,large quantities of data have been generated with time through various networks.The networks have made the process of data analysis very difficult by detecting attacks using suitable techniques.While Intrusion Detection systems(IDSs)secure resources against threats,they still face challenges in improving detection accuracy,reducing false alarm rates,and detecting the unknown ones.This paper presents a framework to integrate data mining classification algorithms and association rules to implement network intrusion detection.Several experiments have been performed and evaluated to assess various machine learning classifiers based on the KDD99 intrusion dataset.Our study focuses on several data mining algorithms such as;naïve Bayes,decision trees,support vector machines,decision tables,k-nearest neighbor algorithms,and artificial neural networks.Moreover,this paper is concerned with the association process in creating attack rules to identify those in the network audit data,by utilizing a KDD99 dataset anomaly detection.The focus is on false negative and false positive performance metrics to enhance the detection rate of the intrusion detection system.The implemented experiments compare the results of each algorithm and demonstrate that the decision tree is the most powerful algorithm as it has the highest accuracy(0.992)and the lowest false positive rate(0.009).

关键词： Intrusion detection association rule data mining algorithms KDD99

Analyzing market performance via social media: a case study of a banking industry crisis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(information Sciences) 2014年第5期57卷 33-50页

作者： JIANG CuiQing LIANG Kun CHEN Hsinchun DING Yong School of management Hefei University of Technology Department of Management Information Systems The University of Arizona

Analyzing market performance via social media has attracted a great deal of attention in the finance and machine-learning disciplines.However,the vast majority of research does not consider the enormous influence a crisis has on social media that further affects the relationship between social media and the stock market.This article aims to address these challenges by proposing a multistage dynamic analysis framework.In this framework,we use an authorship analysis technique and topic model method to identify stakeholder groups and topics related to a special firm.We analyze the activities of stakeholder groups and topics in different periods of a crisis to evaluate the crisis’s influence on various social media parameters.Then,we construct a stock regression model in each stage of crisis to analyze the relationships of changes among stakeholder groups/topics and stock behavior during a crisis.Finally,we discuss some interesting and significant results,which show that a crisis affects social media discussion topics and that different stakeholder groups/topics have distinct effects on stock market predictions during each stage of a crisis.

关键词： social media market performance stakeholder theory authorship analysis technique topic model

Efficient Training of Multi-Layer Neural Networks to Achieve Faster Validation

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computer systems Science & Engineering 2021年第3期36卷 435-450页

作者： Adel Saad Assiri management information systems department College of BusinessKing Khalid UniversityAbhaSaudi Arabia

Artificial neural networks(ANNs)are one of the hottest topics in computer science and artificial intelligence due to their potential and advantages in analyzing real-world problems in various disciplines,including but not limited to physics,biology,chemistry,and engineering.However,ANNs lack several key characteristics of biological neural networks,such as sparsity,scale-freeness,and small-worldness.The concept of sparse and scale-free neural networks has been introduced to fill this gap.Network sparsity is implemented by removing weak weights between neurons during the learning process and replacing them with random weights.When the network is initialized,the neural network is fully connected,which means the number of weights is four times the number of neurons.In this study,considering that a biological neural network has some degree of initial sparsity,we design an ANN with a prescribed level of initial sparsity.The neural network is tested on handwritten digits,Arabic characters,CIFAR-10,and Reuters newswire topics.Simulations show that it is possible to reduce the number of weights by up to 50%without losing prediction accuracy.Moreover,in both cases,the testing time is dramatically reduced compared with fully connected ANNs.

关键词： Sparsity weak weights multi-layer neural network NN training with initial sparsity

Analysis and design of a smart card based authentication protocol

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Zhejiang University-Science C(Computers and Electronics) 2013年第12期14卷 909-917页

作者： Kuo-Hui YEH Kuo-Yu TSAI Jia-Li HOU department of information management National Dong Hwa University Department of Management Information Systems Hwa Hsia Institute of Technology

Numerous smart card based authentication protocols have been proposed to provide strong system security and robust individual privacy for communication between parties these days. Nevertheless, most of them do not provide formal analysis proof, and the security robustness is doubtful. Chang and Cheng(2011) proposed an efficient remote authentication protocol with smart cards and claimed that their proposed protocol could support secure communication in a multi-server environment. Unfortunately, there are opportunities for security enhancement in current schemes. In this paper, we identify the major weakness, i.e., session key disclosure, of a recently published protocol. We consequently propose a novel authentication scheme for a multi-server environment and give formal analysis proofs for security guarantees.

关键词：身份验证协议智能卡设计安全通信认证协议多服务器安全保障个人隐私

Efficient and secure three-party authenticated key exchange protocol for mobile environments

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Zhejiang University-Science C(Computers and Electronics) 2013年第5期14卷 347-355页

作者： Chih-ho CHOU Kuo-yu TSAI Tzong-chen WU Kuo-hui YEH department of information management National Taiwan University of Science and Technology Department of Management Information Systems Hwa Hsia Institute of Technology department of information management National Dong Hwa University

Yang and Chang (2009) proposed a three-party authenticated key exchange protocol for securing communications in mobile-commerce environments. Their protocol reduces computation and communication costs by employing elliptic curve cryptosystems. However, Tan (2010) pointed out that Yang and Chang (2009)'s protocol cannot withstand impersonation and parallel attacks, and further proposed an enhanced protocol to resist these attacks. This paper demonstrates that Tan (2010)'s approach still suffers from impersonation attacks, and presents an efficient and secure three-party authenticated key exchange protocol to overcome shown weaknesses.

关键词： Three-party Key exchange Authentication Mobile environments

Anomaly Classification Using Genetic Algorithm-Based Random Forest Modelfor Network Attack Detection

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第1期66卷 767-778页

作者： Adel Assiri management information systems department College of BusinessKing Khalid UniversityAbha61421Saudi Arabia

Anomaly classification based on network traffic features is an important task to monitor and detect network intrusion attacks.Network-based intrusion detection systems(NIDSs)using machine learning(ML)methods are effective tools for protecting network infrastructures and services from unpredictable and unseen attacks.Among several ML methods,random forest(RF)is a robust method that can be used in ML-based network intrusion detection solutions.However,the minimum number of instances for each split and the number of trees in the forest are two key parameters of RF that can affect classification accuracy.Therefore,optimal parameter selection is a real problem in RF-based anomaly classification of intrusion detection systems.In this paper,we propose to use the genetic algorithm(GA)for selecting the appropriate values of these two parameters,optimizing the RF classifier and improving the classification accuracy of normal and abnormal network traffics.To validate the proposed GA-based RF model,a number of experiments is conducted on two public datasets and evaluated using a set of performance evaluation measures.In these experiments,the accuracy result is compared with the accuracies of baseline ML classifiers in the recent works.Experimental results reveal that the proposed model can avert the uncertainty in selection the values of RF’s parameters,improving the accuracy of anomaly classification in NIDSs without incurring excessive time.

关键词： Network-based intrusion detection system(NIDS) random forest classifier genetic algorithm KDD99 UNSW-NB15

Recent Developments in Authentication Schemes Used in Machine-Type Communication Devices in Machine-to-Machine Communication: Issues and Challenges

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第4期79卷 93-115页

作者： Shafi Ullah Sibghat Ullah Bazai Mohammad Imran Qazi Mudassar Ilyas Abid Mehmood Muhammad Asim Saleem Muhmmad Aasim Rafique Arsalan Haider Ilyas Khan Sajid Iqbal Yonis Gulzar Kauser Hameed department of Computer Engineering Balochistan University of Information TechnologyEngineering and Management SciencesQuetta87300Pakistan department of information Technology Balochistan University of Information TechnologyEngineeringand Management SciencesQuetta87300Pakistan department of information systems College of Computer Sciences and Information TechnologyKing Faisal UniversityHofuf in Al-Ahsa31982Saudi Arabia Department of Management Information Systems College of Business AdministrationKing Faisal UniversityHofuf in Al-Ahsa31982Saudi Arabia department of Software Engineering College of ComputingRiphah International UniversityFaisalabad44000Pakistan department of Electrical Engineering Balochistan University of information Technology Engineeringand Management SciencesQuetta87300Pakistan department of Mathematics College of Science Al-ZulfiMajmaah UniversityAl-Majmaah11952Saudi Arabia

Machine-to-machine (M2M) communication plays a fundamental role in autonomous IoT (Internet of Things)-based infrastructure, a vital part of the fourth industrial revolution. Machine-type communication devices(MTCDs) regularly share extensive data without human intervention while making all types of decisions. Thesedecisions may involve controlling sensitive ventilation systems maintaining uniform temperature, live heartbeatmonitoring, and several different alert systems. Many of these devices simultaneously share data to form anautomated system. The data shared between machine-type communication devices (MTCDs) is prone to risk dueto limited computational power, internal memory, and energy capacity. Therefore, securing the data and devicesbecomes challenging due to factors such as dynamic operational environments, remoteness, harsh conditions,and areas where human physical access is difficult. One of the crucial parts of securing MTCDs and data isauthentication, where each devicemust be verified before data transmission. SeveralM2Mauthentication schemeshave been proposed in the literature, however, the literature lacks a comprehensive overview of current M2Mauthentication techniques and the challenges associated with them. To utilize a suitable authentication schemefor specific scenarios, it is important to understand the challenges associated with it. Therefore, this article fillsthis gap by reviewing the state-of-the-art research on authentication schemes in MTCDs specifically concerningapplication categories, security provisions, and performance efficiency.

关键词： Authentication cyber security internet of things machine-type communication devices machine-to-machine communication

A decision support model for supplier portfolio selection in the retail industry

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of management Analytics 2021年第3期8卷 486-501页

作者： Stanislaus Solomon William A.Ellegood Gertrude Pannirselvam Jason Riley management and Marketing department Southern Illinois University EdwardsvilleEdwardsvilleILUSA management Marketingand Information Systems DepartmentSam Houston State UniversityHuntsvilleTXUSA

In this paper we propose and test a staged knapsack model to create a supplier portfolio for retailers.The first two stages in the model use judgement criteria related to supplier characteristics and supplier fit,gathered from managers to create a portfolio that optimizes supplier rank and fit scores.In the third stage we optimize cost by considering landed costs for each supplier in the portfolio to arrive at the final set of suppliers.The results indicate that the criteria used,and the staged refinement of the supplier pool resulted in a better fit than just considering the landed costs of the final pool of suppliers without rank and fit score constraints.The proposed method will enable purchasing managers to strategically create a supplier portfolio that will suit the retailer’s needs more effectively.

关键词： supplier selection retail decision support supplier portfolio knapsack problem