检索结果-内蒙古大学图书馆

Emerging Systems and Intelligent Computing (ESIC), International Conference on

作者： Mohini Parashar Arjun Rajput Rajesh Boghey Department of CSE TIT-Excellence Bhopal

ISBN: (数字)9798331522100

ISBN: (纸本)9798331522117

Focus of the paper is on predicting software defects (SD) based on Machine learning (ML) techniques which is a challenging research area because of unbalanced nature of data sets. In general, a set of design metrics is used for fault prediction and for identifying the fault-proneness in software and recent studies shows that ML techniques is being applied for defect prediction. However, some ML techniques cannot produce the needed results when dealing with unbalanced dataset and the results produced are not certainly inferred by the developers by observing these factors, we propose a unique approach for fault prediction which is based on feature selection technique which improves the overall performance by using attribute selection when predicting defects. The ML concentrates on the algorithms entirely centred on statistical methods and data mining techniques for classifying and predicting the defects and these statistical methods followed are quite similar to regression based methods which we used earlier to the ML. When more data is available, ML algorithms behave as dynamic algorithms to improve their performance significantly. The DT ML technique is providing good accuracy compared to other NB and SVM technique. In this model is simulated python language and calculated simulation parameter i.e. precision, recall and accuracy.

关键词： Support vector machines Measurement Accuracy Statistical analysis Heuristic algorithms software algorithms Machine learning Prediction algorithms software Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Information and software Support for the Multifactor Authentication Process using Biometric Data in Linux Kernel-Based Operating Systems

Information and Software Support for the Multifactor Authent...

引用

International Russian Smart Industry Conference (SmartIndustryCon)

作者： Alexander A. Zakharov Andrey M. Shabalin Roman V. Tikhonov Department of Smart City Technologies Information Security Tyumen State University Tyumen Russia Information Security Department Tyumen State University Tyumen Russia Department of information technology Akvatechnik Tyumen Russia

ISBN: (数字)9798331511241

ISBN: (纸本)9798331511258

The article substantiates the necessity of of implementing multifactor authentication based on user biometric data to enhance the security level of computer systems. Traditional methods such as password authentication are not always capable of providing the required level of protection for the account and user data. The authors analyze modern approaches to biometric authentication, identify the advantages of using them within multifactor systems, and address current issues related to the secure storage of biometric data. As a result of their research, they have developed a software architecture that uses the proposed mechanisms for integration in Linux kernel-based operating systems.

关键词： Biometrics software architecture Linux software algorithms Authentication Personal voice assistants Protection Open source software Secure storage Testing

来源：评论

学校读者我要写书评

暂无评论

Key Applications and Challenges of Virtual software Simulation Technology in Data Resource Searching Schemes

Key Applications and Challenges of Virtual Software Simulati...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： Jiao Yueyue Shandong Institute of Commerce and Technology Jinan Shandong China

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

With the continuous development of big data and complex software systems, virtual software simulation technology plays an increasingly important role in the fields of data resource search and security prevention applications. Inspired by this, this study first analyzes the basic principles of virtual software simulation technology, and proposes a new virtual simulation platform model by combining resource allocation strategy, search algorithm optimization and real-time interactivity, and conducts systematic extensibility research from the perspective of DDos detection. At the practical level, this study introduces a virtual simulation model based on the VERICUT platform to analyze the complex data search process and improve the modeling. The core methods of this research framework include the following three aspects: 1) Proposing a new collaborative management model for automated testing based on data flow; 2) Performing coverage testing of multi-dimensional data input and intermediate state parameterization at the practical level; 3) Proposing a new DDoS attack analysis and detection algorithm as an extension study. From the experimental results, it can be seen that in 50 sets of independent repeated tests, the DDos detection accuracy of the proposed algorithm is stable between 98% and 100%, with a small fluctuation rang. This shows the stability of the proposed model.

关键词： Analytical models Accuracy software algorithms Data models Stability analysis Real-time systems Security Resource management Optimization Testing

来源：评论

学校读者我要写书评

暂无评论

Efficient Load Balancing in software Defined Networks Using Unsupervised Meta-Reinforcement Learning

Efficient Load Balancing in Software Defined Networks Using ...

引用

Computational, Communication and Information Technology (ICCCIT), International Conference on

作者： Prerita Kulkarni Nitika Vats Doohan Department of Computer Science Medicaps University Indore India Department of Computer Science Sage University Indore India

ISBN: (数字)9798331512965

ISBN: (纸本)9798331512972

New technologies, such as cloud computing and big data, make traditional network management more difficult, while the network's user base continues to expand. Consequently, changes to the traditional network architecture are required. To address this issue and enhance network management compliance, a new idea called software-defined network (SDN) has been proposed. Due to limited network resources and to satisfy the criteria of quality of service, it is necessary to address numerous difficulties, one of which is load balancing (LB), which distributes data traffic among several resources to maximize their efficiency and reliability. The local information of a network is used to design LB in a typical network. Consequently, it is not very accurate. Still, software-defined network (SDN) controllers can see the network from anywhere in the world and make better LB. We provide a set of unsupervised meta- RL algorithms to build smart optimization architecture for SDN LB.

关键词： Uncertainty software algorithms Computer architecture Telecommunication traffic Load management Inference algorithms Reliability software defined networking Optimization Standards

来源：评论

学校读者我要写书评

暂无评论

Improving software Defects Detection: An In-Depth Analysis of Machine Learning Methods and Static Analysis Tools for Greater Accuracy

Improving Software Defects Detection: An In-Depth Analysis o...

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： Veer Bobade Chetan Puri Department of Artificial Intelligence and Machine Learning Faculty of Engineering And Technology DMIHER Wardha Maharashtra India Department of Computer Science and Engineering Faculty of Engineering And Technology DMIHER Wardha Maharashtra India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Enhancing software quality and reducing testing expenses requires better software fault detection. To guarantee the dependability and usability of software, software Defect Prediction (SDP) uses machine learning approaches to anticipate and address any problems early in the development cycle. Numerous machine learning techniques, such as Support Vector Machines (SVM), Random Forest (RF), Logistic Regression, Naïve Bayes, Multilayer Perceptron (MLP), Decision Stump, J48, Lazy IBK, and ZeroR, are thoroughly examined in this work. With an emphasis on feature selection as a crucial step in increasing prediction accuracy and lower computing costs, these approaches are assessed for their capacity to detect software flaws precisely. This research study demonstrates how these models may improve fault identification and prevention procedures using historical records from sources such as the PROMISE repository. The study highlights the best practices for machine learning-based software quality assurance, lowering expenses while guaranteeing superior results.

关键词： Support vector machines Accuracy Machine learning algorithms software algorithms Machine learning software quality Multilayer perceptrons Feature extraction Prediction algorithms Random forests

来源：评论

学校读者我要写书评

暂无评论

Development of Signal Detection and Recognition Algorithm Using software-Defined Radio

Development of Signal Detection and Recognition Algorithm Us...

引用

International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE)

作者： Anastasia O. Khodakova Yulia D. Naumova Sergey A. Chechenya Sergey V. Soldatkin Anton Y. Boev Konstantin V. Vorontsov Department of Formation and Processing of Radio Frequency Signals National Research University “MPEI” Moscow Russian Federation

ISBN: (数字)9798331531836

ISBN: (纸本)9798331531843

The article presents an analysis of the existing algorithms used in the implementation of a receiver of multi-position signals based on SDR technology. As a result, a comprehensive approach has been developed to solve the extended task of radio monitoring, which includes not only scanning the spectrum, detecting radio emissions, determining the type of modulation and the location of the source, but also decoding the data contained in the message. To implement the SDR-based algorithm, the GNU Radio program was used, which is convenient because it allows you to build circuits using software modules.

关键词： software algorithms Circuits Signal processing algorithms Receivers software Decoding Synchronization Monitoring Signal detection software radio

来源：评论

学校读者我要写书评

暂无评论

Runtime Embedded software Malfunction Detection Based on Profile Generation of Current-Level Pattern Matcher

Runtime Embedded Software Malfunction Detection Based on Pro...

引用

International Conference on Electronics, Information and Communications (ICEIC)

作者： Sanghoon Lee Daejin Park Software Disaster Research Center Kyungpook National University Daegu Korea School of Electronics Engineering Kyungpook National University Daegu Korea

ISBN: (数字)9798331510756

ISBN: (纸本)9798331510763

As the demand for high-performance embedded systems grows, the complexity of embedded software increases, potentially leading to software errors and system malfunctions. In this paper, we propose a system to monitor malfunctions caused by software errors by extracting the normal operating current patterns of a target embedded system (TES) in actual operation and comparing them with the real time current TES data. By using a monitoring embedded system (MES), the normal operating current patterns can be automatically generated, making it easy to promptly detect malfunctions in the exposed TES. When the MES detects a malfunction, it applies algorithms to efficiently recover the malfunctioning TES. The proposed system employs two algorithms when a malfunction in the TES is detected. First, upon detecting a malfunction, the MES resets TES to restore it to normal operation. If the malfunction persists after the reset, the MES controls the TES to completely halt operation. Second, if a malfunction is detected, it stabilizes the abnormal current state to the normal current state through a proportional integral derivation (PID) control. The TES typically consumes about 75 to 95 mA of current during normal operation. The MES applies a specific error detection rate of 20 %, considering any consumption above 114 mA a malfunction and using the algorithms to control it. The system has been verified to reset TES upon detecting a malfunction and to stabilize the operational current through PID control during abnormal current states.

关键词： Embedded systems PI control Runtime software algorithms Real-time systems PD control Protection Monitoring Pattern matching Embedded software

来源：评论

学校读者我要写书评

暂无评论

Continuous wavelet transform application in electromagnetic compatibility - algorithms and software realization

Continuous wavelet transform application in electromagnetic ...

引用

15th International Conference on software, Telecommunications and Computer Networks

作者： Wu, Wei Univ Missouri EMC Consortium Rolla MO 65401 USA

ISBN: (纸本)9789536114931

In this paper, a novel approach to detect electromagnetic interference from electronic equipment by means of continuous wavelet transform is presented. The algorithms of the proposed approach are given together with the software solutions. A case study is made to verify the effectiveness and correctness of this proposed approach and a "Workspace" concept is presented to interface analyzed data with the equipment under test, making the proposed solutions more feasible.

关键词： Continuous wavelet transforms Wavelet transforms Application software Electromagnetic compatibility software algorithms Frequency domain analysis Wavelet domain Electromagnetic interference Wavelet analysis Signal analysis

来源：评论

学校读者我要写书评

暂无评论

algorithms and software for LMI Problems in Control

引用

IEEE Control Systems 1997年第5期17卷 89-95页

作者： Vandenberghe, Lieven Balakrishnan, Venkataramanan Department of Electrical Engineering at the University of California Los Angeles CA 90095-1594 United States School of Electrical and Computer Engineering at Purdue University West Lafayette IN 47907-1285. United States

A number of important problems from system and control theory can be numerically solved by reformulating them as convex optimization problems with linear matrix inequality (LMI) constraints. While numerous articles have appeared cataloging applications of LMIs to control system analysis and design, there have been few publications in the control literature describing the numerical solution of these optimization problems. The purpose of this article is to provide an overview of the state of the art of numerical algorithms for LMI problems, and of the available software.

关键词： software algorithms Riccati equations Linear matrix inequalities Optimal control Linear feedback control systems Nonlinear control systems Control systems Application software Control system synthesis Control theory

来源：评论

学校读者我要写书评

暂无评论

Multiplicative Weights algorithms for Parallel Automated software Repair 35

Multiplicative Weights Algorithms for Parallel Automated Sof...

引用

35th IEEE International Parallel and Distributed Processing Symposium (IPDPS)

作者： Renzullo, Joseph Weimer, Westley Forrest, Stephanie Arizona State Univ Tempe AZ 85281 USA Univ Michigan Ann Arbor MI 48109 USA

ISBN: (纸本)9781665440660

Multiplicative Weights Update (MWU) algorithms are a form of online learning that is applied to multi-armed bandit problems. Such problems involve allocating a fixed number of trials among multiple options to maximize cumulative payoff. MWU is a popular and effective method for dynamically balancing the trade-off between exploring the value of new options and exploiting the information already gained. However, no clear strategy exists to help practitioners choose which of the several algorithmic designs within this family to deploy. In this paper, three variants of parallel MWU algorithms are considered: Two parallel variants that rely on global memory, and one variant that uses distributed memory. The three variants are first analyzed theoretically, and then their effectiveness is assessed empirically on the task of estimating distributions in the context of stochastic search for repairs to bugs in software. Earlier work on APR suffers from various inefficiencies, and the paper shows how to decompose the problem into two stages: one that is embarrassingly parallel and one that is amenable to MWU. We then model the cast of each MWU variant and derive the conditions under which it is likely to be preferred in practice. We find that all three MWU algorithms achieve accuracy above 90% but that there are significant differences in runtime and total cost. When 90% accuracy is sufficient and evaluating options is expensive, such as in our use case, we find that the algorithm that uses global memory and has high communication cast outperforms the other two. We analyze the reasons for this surprising result.

关键词： Distributed processing Runtime Heuristic algorithms software algorithms Computer bugs Stochastic processes Maintenance engineering

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：