检索结果-内蒙古大学图书馆

A System to automate the development of anomaly-based network intrusion detection model

Journal of Physics: Conference Series 2021年第1期2089卷

作者： B Padmaja K Sai Sravan E Krishna Rao Patro G Chandra Sekhar Associate Professor Department of Computer Science and Engineering Institute of Aeronautical Engineering Hyderabad India Student Department of Computer Science and Engineering Institute of Aeronautical Engineering Hyderabad India Assistant Professor Department of Computer Science and Engineering Institute of Aeronautical Engineering Hyderabad India

Cyber security is the major concern in today's world. Over the past couple of decades, the internet has grown to such an extent that almost every individual living on this planet has the access to the internet today. This can be viewed as one of the major achievements in the human race, but on the flip side of the coin, this gave rise to a lot of security issues for every individual or the company that is accessing the web through the internet. Hackers have become active and are always monitoring the networks to grab every possible opportunity to attack a system and make the best fortune out of its vulnerabilities. To safeguard people's and organization's privacy in this cyberspace, different network intrusion detection systems have been developed to detect the hacker's presence in the networks. These systems fall under signature based and anomaly based intrusion detection systems. This paper deals with using anomaly based intrusion detection technique to develop an automation system to both train and test supervised machine learning models, which is developed to classify real time network traffic as to whether it is malicious or not. Currently the best models by considering both detection success rate and the false positives rate are Artificial Neural Networks(ANN) followed by Support Vector Machines(SVM). In this paper, it is verified that Artificial Neural Network (ANN) based machine learning with wrapper feature selection outperforms support vector machine (SVM) technique while classifying network traffic as harmful or harmless. Initially to evaluate the performance of the system, NSL-KDD dataset is used to train and test the SVM and ANN models and finally classify real time network traffic using these models. This system can be used to carry out model building automatically on the new datasets and also for classifying the behaviour of the provided dataset without having to code.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IMPROVED RESOURCE MANAGEMENT AND UTILIZATION BASED ON A FOG-CLOUD COMPUTING SYSTEM WITH IOT INCORPORATED WITH CLASSIFIER SYSTEMS

引用

Microprocessors and Microsystems 2021年

作者： M. Buvana K. Loheswaran Karanam Madhavi Sivakumar Ponnusamy Aradhana Behura R. Jayavadivel Assistant Professor Department of Computer Science and Engineering PSNA College of Engineering and Technology Dindigul India Associate Professor Department of Computer Science and Engineering CMR College of Engineering &Technology Kandlakoya Medchal Road Hyderabad - 501 401 Telangana India Professor Computer Science and Engineering Department Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad 500090 Telangana state India Associate Professor Department of Computer Science and Engineering SRM Institute of Science &Technology Delhi NCR Campus Modinagar Ghaziabad Uttar Pradesh-201204 India Assistant Professor Department of Computer Science and Engineering GITA Engineering College Road Badaraghunathpur Janla Bhubaneswar Odisha-752054 India Associate Professor Department Computer Science and Engineering Vivekanandha College of Engineering for Women Tiruchengode Namakkal Tamilnadu-– 637205 India

With the rapid rise of computing devices-linked networks, the Internet of Things (IoT) has increased proportionally and speedily. After that, the size of the data generated and significantly increased computational effort. A solution for a very large workload is cloud computing significantly slowed and continues to be a problem in a distributed computer network. Addressing the workload at the network edge can enchase time feedback, and delaying the data load management task imposes performance constraints from the power source to the edge of the network, which does not support only limited battery power. Therefore, the workload must be distributed equally to the clouds and across the network. This document presents the XCS Classification System (LCS), by XCS and BCM-XCS, to ensure energy consumption at the end of the project which decreases the workloads of the processing time. Our test outcome showed the dominance of BCM-XCS XCS according to standard methods. A distributed method of allocating responsibility for reducing the processing time between node cloud and fog. In addition to the significant benefits of handling fluctuating turnaround times, the proposed procedures can simultaneously decrease 42% response times utilizing an average consumption of energy in the grid edge. With the propounded method, rechargeable batteries are used on the edge of the grid also can load approximately 18% more than the best method of the prior art.

关键词： Learning classification systems (LCS) Extended Classification System (XCS) Internet of Things (IoT) fog computing best classifier memory (BCM)

来源：评论

学校读者我要写书评

暂无评论

Detect the Replication Attack on Wireless sensor network by Using Intrusion Detection System

引用

Journal of Physics: Conference Series 2021年第1期1717卷

作者： P. Manju Bala S. Usharani V. Abarna Associate Professor Department of Computer Science and Engineering IFET College of Engineering Villupuram. UG Scholar Department of Computer Science and Engineering IFET College of Engineering Villupuram.

Remote sensor systems are conveyed in dense regions wherever the sensor nodes are physically seized by intruders. As several nodes take care of the entire group area, the captured nodes are repeated. To rectify this attack, a response was provided. Be that as it may, because of the absence of improvements in the device size, these structures have low efficiency to recognize the clone hubs quickly. In order to quickly locate the clone hubs, an expansion calculation is generated in this paper with the improved LEACH called NI-LEACH convention which is utilized to limit the group by taking the vitality of every hub and the minimum range of clusters. In addition to this protocol, an IDS (Intrusion Detection System) calculation is designed and generated by doling out screen hubs in the remote sensor organization to identify replication assaults. Reenactment findings show that in remote sensor networks the new calculation is straightforward and powerful to implement. With a high probability proportion, a harmful centre can be reliably detected and established and ideal throughput can also be achieved all the *** limit of the method is expanded definitely byconsuming this calculation against the clone hub assault byintruders.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Survey for Dependent on Neuro Fuzzy Algorithm for Framework ID

引用

Journal of Physics: Conference Series 2021年第1期1717卷

作者： S. Umadevi B.V.K. Namratha Associate Professor Department of Computer Science and Engineering IFET College of Engineering Villupuram. UG Scholar Department of Computer Science and Engineering IFET College of Engineering Villupuram.

This article focuses on hybrid neuro-fuzzy techniques, its advantages and disadvantages. The techniques of fuzzy logic and neural networks are commonly used for artificial intelligence. At the point when they are utilized in a joined manner, they are called Neuro-Fuzzy Systems. In the Neuro-Fuzzy Systems fuzzy sets and fuzzy rules are adjusted using input output patterns. The Neuro-fuzzy systems are implemented by different authors in different models. The Neuro-Fuzzy frameworks have the accompanying attributes: quick learning, versatility on-line, to modify itself with the point of getting the little worldwide blunder conceivable and little computational multifaceted nature. The obtaining of information, the pre-handling of information and preparing information are additionally significant for the achievement of the use of the neuro-fuzzy models

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative evaluation of performance and scalability of convolutional neural network implementations on a multisystem HPC architecture

引用

Journal of Physics: Conference Series 2021年第1期2062卷

作者： Sunil Pandey Naresh Kumar Nagwani Shrish Verma Research Scholar Dept of Computer Science and Engineering NIT Raipur India Associate Professor Dept of Computer Science and Engineering NIT Raipur India Professor Dept of Electronics and Communications Engineering NIT Raipur India

The convolutional neural network training algorithm has been implemented for a central processing unit based high performance multisystem architecture machine. The multisystem or the multicomputer is a parallel machine model which is essentially an abstraction of distributed memory parallel machines. In actual practice, this model corresponds to high performance computing clusters. The proposed implementation of the convolutional neural network training algorithm is based on modeling the convolutional neural network as a computational pipeline. The various functions or tasks of the convolutional neural network pipeline have been mapped onto the multiple nodes of a central processing unit based high performance computing cluster for task parallelism. The pipeline implementation provides a first level performance gain through pipeline parallelism. Further performance gains are obtained by distributing the convolutional neural network training onto the different nodes of the compute cluster. The two gains are multiplicative. In this work, the authors have carried out a comparative evaluation of the computational performance and scalability of this pipeline implementation of the convolutional neural network training with a distributed neural network software program which is based on conventional multi-model training and makes use of a centralized server. The dataset considered for this work is the North Eastern University's hot rolled steel strip surface defects imaging dataset. In both the cases, the convolutional neural networks have been trained to classify the different defects on hot rolled steel strips on the basis of the input image. One hundred images corresponding to each class of defects have been used for the training in order to keep the training times manageable. The hyperparameters of both the convolutional neural networks were kept identical and the programs were run on the same computational cluster to enable fair comparison. Both the convolutional neur

关键词：

来源：评论

学校读者我要写书评

暂无评论

Aspects of programming for implementation of convolutional neural networks on multisystem HPC architectures

引用

Journal of Physics: Conference Series 2021年第1期2062卷

The training of deep learning convolutional neural networks is extremely compute intensive and takes long times for completion, on all except small datasets. This is a major limitation inhibiting the widespread adoption of convolutional neural networks in real world applications despite their better image classification performance in comparison with other techniques. Multidirectional research and development efforts are therefore being pursued with the objective of boosting the computational performance of convolutional neural networks. Development of parallel and scalable deep learning convolutional neural network implementations for multisystem high performance computing architectures is important in this background. Prior analysis based on computational experiments indicates that a combination of pipeline and task parallelism results in significant convolutional neural network performance gains of up to 18 times. This paper discusses the aspects which are important from the perspective of implementation of parallel and scalable convolutional neural networks on central processing unit based multisystem high performance computing architectures including computational pipelines, convolutional neural networks, convolutional neural network pipelines, multisystem high performance computing architectures and parallel programming models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Preface

引用

Journal of computer science & Technology 2021年第5期36卷 961-962页

作者： Chao Li Yun Liang Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai Tenured Associate Professor School of Electronics Engineering and Computer Science Peking UniversityBeijing

It is our great pleasure to welcome you to the 14th Advanced Parallel Processing Technology(APPT 2021),the flagship conference of the China computer Federation Technical Committee on computer Architecture(CCF TCARCH)!

关键词： computer welcome Preface

来源：评论

学校读者我要写书评

暂无评论

Built-in translation on Web Messenger

引用

Journal of Physics: Conference Series 2021年第1期1911卷

作者： U Karthikeyan A Ajit Surya S Bhargav P Bhargav Associate Professor Under Graduate Students Department of Computer Science and Engineering Rajalakshmi Engineering College Chennai-602105 INDIA

The paper aims at providing the users with a web messenger application that translates messages sent by sender to the receiver. The translation is provided by Google Translate API. This helps in having a seamless conversation experience. Any language that is supported by Google Translate can be sent and received by the users. It is planned to provide transfer of graphic files as well as other file types. Interestingly, this method of communication is the most popular form. Encryption and Decryption is provided by employing AES Algorithm function set. The encryption and decryption make it safe for communication by protecting the conversation from outside threats. In order to have a conversation between two people normally in their own preferred language, they have to rely on using Google Translate solely by copying the message text and finding the translation. This web application we have proposed combats that problem by providing simultaneous translation of text messages to the user's preferred language. Languages that can be translated are the same as what Google Translate provides. ISO 639-1 language codes are used as language code by the sending entity to send the data to the receiving entity. Accuracy have been identified as same as what Google Translate provides, above 60%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine learning approach for detection of keratoconus

引用

IOP Conference Series: Materials science and engineering 2021年第1期1055卷

作者： S Shanthi K Nirmaladevi M Pyingkodi K Dharanesh T Gowthaman B Harsavardan Associate Professor Department of Computer Science and Engineering Kongu Engineering College Erode India Assistant Professor Department of Computer Applications Kongu Engineering College Erode India UG Student Department of Computer Science and Engineering Kongu Engineering College Erode India

Keratoconus is a progressive eye disease and it should be detected in early stage, to avert probable refractive surgery that could develop ecstasies. In this the authors proposes a new computer aided diagnosis model based on Support Vector Machine (SVM) learning to detect the early stage of keratoconus using the available topographic, pachymetric and aberrometry parameters of patients with keratoconus, subclinical keratoconus and normal corneas. The proposed SVM produces 91.8% accuracy with 94.2% sensitivity, 97.5% specificity for classification of early keratoconus from normal; 100% accuracy with 100%, 100% of sensitivity and specificity respectively for classification of early keratoconus from subclinical keratoconus.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Supplemental educational program to heighten the impact of research - an opportunity for OA imaging

引用

Osteoarthritis imaging 2023年第2期3卷 100155页

作者： Deborah Burstein Rudolph Mitchell Emery Brown Martha L Gray Associate Professor Department of Radiology Beth Israel Deaconess Medical Center Harvard Medical School 330 Brookline Avenue Boston MA USA. Associate Director for Research and Evaluation in the Teaching + Learning Lab Massachusetts Institute of Technology Cambridge MA USA. Edward Hood Taplin Professor of Computational Neuroscience and Health Sciences and Technology Department of Brain and Cognitive Sciences and Institute for Medical Engineering and Science Massachusetts Institute of Technology Cambridge MA USA. J.W. Kieckefer Professor of Medical and Electrical Engineering Department of Electrical Engineering and Computer Science and Institute for Medical Engineering and Science Massachusetts Institute of Technology Cambridge MA USA.

Objective:To develop and evaluate a supplementary educational program ("IMPACT") centered on enabling participants to consider specifically and articulate explicitly the best path for and potential impact of their research. Design:Participants (trainees) and faculty mentors were from all areas of biomedical research. The group worked longitudinally in small, rotating groups, through a process of developing a written statement ("Impact Statement"), an overview ("Impact Storyline") and an oral presentation ("Impact Case") of their work. Results:One hundred and eighty-seven Fellows enrolled in the program. Of the 179 (96%) Fellows who completed the program, 159 (89%) responded to a post-program survey; 94% indicated that IMPACT was a significant learning experience, 89% indicated that they were more able to identify the long-term potential of their research, 95% felt more able to talk about their work to diverse audiences. Conclusion:This voluntary educational program was appreciated by the participants and led to increased confidence in their ability to drive their science towards a clear impact and communicating that potential to others. This type of program may aid in redirecting some of the efforts and resources of imaging in OA from the large focus on technical developments to more direct biological and clinical questions which might be resolved with current technology.

关键词： Communication Diversity Impact Research

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：