A deep learning approach with Bayesian optimization and ensemble classifiers for detecting denial of service attacks

Detecting malicious behavior is important for preventing security threats in a computer network. Denial of Service (DoS) is among the popular cyber attacks targeted at web sites of high‐profile organizations and can potentially have high economic and time costs. In this paper, several machine learning methods including ensemble models and autoencoder‐based deep learning classifiers are compared and tuned using Bayesian optimization. The autoencoder framework enables to extract new features by mapping the original input to a new space. The methods are trained and tested both for binary and multi‐class classification on Digiturk and Labris datasets, which were introduced recently for detecting various types of DDoS attacks. The best performing methods are found to be ensembles though deep learning classifiers achieved comparable level of accuracy.     

Energy‐efficient data transmission technique for wireless sensor networks based on DSC and virtual MIMO

In a wireless sensor network (WSN), the data transmission technique based on the cooperative multiple‐input multiple‐output (CMIMO) scheme reduces the energy consumption of sensor nodes quite effectively by utilizing the space‐time block coding scheme. However, in networks with high node density, the scheme is ineffective due to the high degree of correlated data. Therefore, to enhance the energy efficiency in high node density WSNs, we implemented the distributed source coding (DSC) with the virtual multiple‐input multiple‐output (MIMO) data transmission technique in the WSNs. The DSC‐MIMO first compresses redundant source data using the DSC and then sends it to a virtual MIMO link. The results reveal that, in the DSC‐MIMO scheme, energy consumption is lower than that in the CMIMO technique; it is also lower in the DSC single‐input single‐output (SISO) scheme, compared to that in the SISO technique at various code rates, compression rates, and training overhead factors. The results also indicate that the energy consumption per bit is directly proportional to the velocity and training overhead factor in all the energy saving schemes.     

Improved low energy adaptive clustering hierarchy and its optimum cluster head selection

ABSTRACT

Wireless sensor networks (WSNs) play a vital role in present-day world, which are being used in different types of applications and occupy an important part in networking domain. The main objective of WSNs is to sense and collect the information from a given area of interest and provide the gathered data to the sink. WSN comprises of number of sensor nodes with batteries of limited energy for communication and computational activities, which are not possible to recharge the batteries after their deployment in the region of interest. Therefore, saving battery energy and utilising the limited power to the optimum level for extending network lifetime became the main factor of WSN. Hence, optimum cluster head (CH) selection will make the network to support longer lifetime and balanced energy consumption during its lifetime. Our proposed protocol selects the optimum CH and found out to be more efficient than the existing low energy adaptive clustering hierarchy. The simulated output shows better network lifetime and in some other performance metric.     

基于深度卷积神经网络的自适应图像去雾算法

室外拍摄图像由于受雾气、雾霾、沙尘等大气颗粒杂质的影响呈现出图像灰白化,而现有的图像去雾算法存在过度依赖先验信息、透射率计算不精确的问题。针对上述问题,文中提出了一种基于深度卷积神经网络的自适应图像去雾算法。该算法基于大气散射模型实现了有雾图像的去雾,设计浅层提取、并行提取和深度融合共3个全卷积网络实现图像浅层特征与深层特征的融合,大幅提高了透射率图的准确性。去雾实验测试结果表明,文中所提出的算法对室外露天雾图具有良好的去雾效果,且去雾细节效果更加理想。     

蜂窝网络自组织研究及展望

自组织网络技术是提高蜂窝网络运行效率、降低运营成本的重要工具,已作为基本功能在4G标准化初始版本获得引入并得到不断发展。在复杂度更高的5G网络中实现网络自动化管理的需求将进一步增强。回顾了蜂窝网络自组织技术的基本概念、分类和主要用例,分析了主要研究方法;总结了学术界、标准化组织及研究机构的研究进展,重点介绍了基于机器学习的最新研究成果;调查了工程应用现状,分析了自组织网络面临的主要挑战,同时指出了新的研究方向。     

光纤网络断点数据提取方法研究

对光纤网络断点数据进行自动提取,是提升光纤网络安全性的有效方法,传统的光纤网络断点数据提取方法提取到的数据辨识度较低,无法在根本上提高网络安全性,为此提出一种基于遗传算法的光纤网络断点数据提取方法研究。通过构建光纤网络节点断点数据分布模型、断点数据特征信息采集、断点数据固定处理、断点数据提取优化四个阶段,实现光纤网络断点数据提取方法研究。仿真结果表明,采用该方法进行光纤网络断点数据提取的辨识度较高,对光纤网络断点数据固定能力较强,提高了光纤网络断点数据的提取能力。     

Neural Models for the Resonant Frequency of Electrically Thin and Thick Circular Microstrip Antennas and the Characteristic Parameters of Asymmetric Coplanar Waveguides Backed with a Conductor

Neural models for computing the resonant frequency of electrically thin and thick circular microstrip antennas, based on the multilayered perceptrons and the radial basis function networks, are presented. Five learning algorithms, delta-bar-delta, extended delta-bar-delta, quick-propagation, directed random search and genetic algorithms, are used to train the multilayered perceptrons. The radial basis function network is trained according to its learning strategy. The resonant frequency results of neural models are in very good agreement with the experimental results available in the literature. In this paper, the characteristic impedance and the effective permittivity of the asymmetric coplanar waveguide backed with a conductor are also computed by using only one neural model trained by the backpropagation with momentum and the extended delta-bar-delta algorithms. When the performances of neural models are compared with each other, the best results for test are obtained from the multilayered perceptrons trained by the extended delta-bar-delta algorithm.     

Bandwidth Adaptation Algorithms for Adaptive Multimedia Services in Mobile Cellular Networks

The fluctuation of available link bandwidth in mobilecellular networks motivates the study of adaptive multimediaservices, where the bandwidth of an ongoing multimedia call can bedynamically adjusted. We analyze the diverse objectives of theadaptive multimedia framework and propose two bandwidth adaptationalgorithms (BAAs) that can satisfy these objectives. The firstalgorithm, BAA-RA, takes into consideration revenue and``anti-adaptation' where anti-adaptation means that a user feelsuncomfortable whenever the bandwidth of the user's call ischanged. This algorithm achieves near-optimal total revenue withmuch less complexity compared to an optimal BAA. The secondalgorithm, BAA-RF, considers revenue and fairness, and aims at themaximum revenue generation while satisfying the fairnessconstraint defined herein. Comprehensive simulation experimentsshow that the difference of the total revenue of BAA-RA and thatof an optimal BAA is negligible. Also, numerical results revealthat there is a conflicting relationship between anti-adaptationand fairness.     

Energy-Efficient Broadcast and Multicast Trees in Wireless Networks

The wireless networking environment presents formidable challenges to the study of broadcasting and multicasting problems. In this paper we focus on the problem of multicast tree construction, and we introduce and evaluate algorithms for tree construction in infrastructureless, all-wireless applications. The performance metric used to evaluate broadcast and multicast trees is energy-efficiency. We develop the Broadcast Incremental Power (BIP) algorithm, and adapt it to multicast operation by introducing the Multicast Incremental Power (MIP) algorithm. These algorithms exploit the broadcast nature of the wireless communication environment, and address the need for energy-efficient operation. We demonstrate that our algorithms provide better performance than algorithms that have been developed for the link-based, wired environment.     

A Typology for Multi-Technology, Multi-Service Broadband Network Synthesis

Current technological possibilities for implementing multi-service networks include both single technology ATM or IP networks and multi-technology networks such as SONET-based or flat networks. However, regardless of the technology employed, the synthesis problem – to optimally route traffic and divide the network's transmission resources between its virtual links – remains of prime importance.In this paper, we review, compare, and classify the extensive recent literature concerning multi-service network synthesis methods. In order to do this, we propose a typology based on switching and control strategies and a general notation that reflects the layered nature of the network. Technology independent mathematical models describe the various, essentially different, approaches presently found in the literature.