检索结果-南通市图书馆

Conceptualisation of Cyberattack prediction with deep learning

Cybersecurity 2018年第1期1卷 788-801页

作者： Ayei E.Ibor Florence A.oladeji olusoji B.okunoye obeten o.ekabua Department of Computer Science University of CalabarCalabarNigeria Department of Computer Sciences University of LagosLagosNigeria

The state of the cyberspace portends uncertainty for the future Internet and its accelerated number of *** paradigms add more concerns with big data collected through device sensors divulging large amounts of information,which can be used for targeted *** a plethora of extant approaches,models and algorithms have provided the basis for cyberattack predictions,there is the need to consider new models and algorithms,which are based on data representations other than task-specific *** learning,which is underpinned by representation learning,has found widespread relevance in computer vision,speech recognition,natural language processing,audio recognition,and drug ***,its non-linear information processing architecture can be adapted towards learning the different data representations of network traffic to classify benign and malicious network *** this paper,we model cyberattack prediction as a classification ***,the deep learning architecture was co-opted into a new model using rectified linear units(ReLU)as the activation function in the hidden layers of a deep feed forward neural *** approach achieves a greedy layer-by-layer learning process that best represents the features useful for predicting cyberattacks in a dataset of benign and malign *** underlying algorithm of the model also performs feature selection,dimensionality reduction,and clustering at the initial stage,to generate a set of input vectors called *** model is evaluated using CICIDS2017 and UNSW_NB15 datasets on a Python environment test *** obtained from experimentation show that our model demonstrates superior performance over similar models.

关键词： Cyberattacks Prediction Deep learning Python Dimensionality reduction

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Towards Release Planning Generic Model： Market-Driven Software Development Perspective

引用

通讯和计算机（中英文版） 2013年第4期10卷 443-450页

作者： Bassey Echeng Isong obeten obi ekabua Computer Science and Information Systems University of Venda Private Bag X5050 Thohoyandou 0950 South Africa Department of Computer Science North-West University Private Bag X2046Mmabatho 2735 South Africa

RP (release planning) is one of the most important issues involved in incremental software development. RP involves a complex task of selecting optimal sets of features to be assigned to a release taking into consideration all explicit and implicit objectives and constraints. However, the task is exacerbated by requirements dependencies since requirements are related to each other in a complex manner. Consequently, decisions made on one or many requirements affects other requirements in ways not even anticipated. This complex situation often directly affects various decisions and activities during development. Therefore, a good and effective software RP approach is crucial. Several software RP models have been proposed and validated in literature, but these models are not standard and not applicable in both strategic and operational levels. Each is known to addressing only few feature selection factors. This situation however makes it difficult to choose a model that suits a particular situation. This then calls for a generic RP model that combines all these factors in order to generate a good release plan for a product. Therefore, the objective of this paper is to propose a generic RP model based on EVoLVE* Model. In addition to the main contribution, the authors started by investigating RP and requirements dependencies challenges in MDSD (market-driven software development) environment.

关键词：软件开发一般模型市场导向最佳组合释放功能开发过程功能选择市场驱动

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Implementation of Efficient Burst Assembly Algorithm with Traffic Prediction

引用

Computer Technology and Application 2013年第3期4卷 153-161页

作者： Mmoloki MangwalaI Boyce Balekane Sigweni obeten obi ekabua Department of Computer Science North West University Private Bag X2046 Mmabatho 2735 South Africa

This paper reports on the implementation of efficient burst assembly algorithms and traffic prediction. The ultimate goal is to propose a new burst assembly algorithm which is based on time-burst length (hybrid) threshold with traffic prediction to reduce burst assembly delay in oBS (optical Burst Switching) networks. Research has shown that traffic always change from time to time, hence, any measure that is put in place should be able to adapt to such changes. With our implemented burst assembly algorithm, the traffic rate is predicted and the predicted rate is used to dynamically adjust the burst assembly length. This work further investigates the impact of the proposed algorithm on traffic self similarity.

关键词：交通预测算法组装流量预测突发长度光突发交换动态调整突发装配

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

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：