Constructing a Fuzzy Network Intrusion Classifier Based on Differential Evolution and Harmonic Search

I. A. Hodashinsky, M. A. Mech 

Department of Complex Information Security Tomsk State University of Control Systems and Radioelectronics (TUSUR), Tomsk, Russia 

ABSTRACT

 This paper presents a method for constructing intrusion detection systems based on efficient fuzzy rulebased classifiers. The design process of a fuzzy rule-based classifier from a given input-output data set can be presented as a feature selection and parameter optimization problem. For parameter optimization of fuzzy classifiers, the differential evolution is used, while the binary harmonic search algorithm is used for selection of relevant features. The performance of the designed classifiers is evaluated using the KDD Cup 1999 intrusion detection dataset. The optimal classifier is selected based on the Akaike information criterion. The optimal intrusion detection system has a 1.21% type I error and a 0.39% type II error. A comparative study with other methods was accomplished. The results obtained showed the adequacy of the proposed method. 

KEYWORDS

 Intrusion detection; fuzzy classifier; differential evolution; feature selection; binary harmonic search; Akaike information criterion

More Details: 

Lightweight Cryptography for Distributed PKI Based MANETS

N Chaitanya Kumar, Abdul Basit, Priyadarshi Singh, and V. Ch. Venkaiah 

School of Computer and Information Sciences, University of Hyderabad, Hyderabad-500046, India 

Abstract.

Because of lack of infrastructure and Central Authority(CA), secure communication is a challenging job in MANETs. A lightweight security solution is needed in MANET to balance its nodes resource tightness and mobility feature. The role of CA should be decentralized in MANET because the network is managed by the nodes themselves without any fixed infrastructure and centralized authority. In this paper, we created a distributed PUblic Key Infrastructure (PKI) using Shamir secret sharing mechanism which allows the nodes of the MANET to have a share of its private key. The traditional PKI protocols require centralized authority and heavy computing power to manage public and private keys, thus making them not suitable for MANETs. To establish a secure communication for the MANET nodes, we proposed a lightweight crypto protocol which requires limited resources, making it suitable for MANETs. 

Keywords: 

Secret sharing, Lightweight Cryptography, Public key cryptography, MANETS

More Details:

A System for Visualization of Big Attributed Hierarchical Graphs

Victor N. Kasyanov, Timur A. Zolotuhin

 Institute of Informatics Systems, Novosibirsk State University Novosibirsk, Russia  

ABSTRACT 

Information visualization is a process of transformation of large and complex abstract forms of information into the visual forms, strengthening cognitive abilities of users and allowing them to take the most optimal decisions. A graph is an abstract structure that is widely used to model complex information for its visualization. In the paper, we consider a system aimed at supporting of visualization of big amounts of complex information on the base of attributed hierarchical graphs. 

KEYWORDS

 Attributed Hierarchical Graphs; Big Graphs; Information Visualization; Visualization Systems  

More Details:

Performance Evaluation of Blowfish Algorithm on Supercomputer IMAN1

Mahmoud Rajallah Asassfeh1 , Mohammad Qatawneh1 and Feras Mohamed ALAzzeh2

 1Department of Computer Science-King Abdullah II School for information technology, University of Jordan, Amman-Jordan, 2Department of computer information systems, Alzaytoonah University of Jordan, Amman-Jordan.

 ABSTRACT 

Cryptographic applications are becoming increasingly more important in today’s world of data exchange, big volumes of data need to be transferred safely from one location to another at high speed. In this paper, the parallel implementation of blowfish cryptography algorithm is evaluated and compared in terms of running time, speed up and parallel efficiency. The parallel implementation of blowfish is implemented using message passing interface (MPI) library, and the results have been conducted using IMAN1 Supercomputer. The experimental results show that the runtime of blowfish algorithm is decreased as the number of processors is increased. Moreover, when the number of processors is 2, 4, and 8, parallel efficiency achieves up to 99%, 98%, and 66%, respectively. 

KEYWORDS 

Blowfish; Encryption; MPI; Supercomputer

More Details : 

Task Allocation and Path Planning for Network of Autonomous Underwater Vehicles

Bychkov Igor, Kenzin Maksim and Maksimkin Nikolay 

Matrosov Institute for System Dynamics and Control Theory, Siberian Branch of the Russian Academy of Science, Irkutsk, Russia

ABSTRACT 

Cooperative multi-objective missions for connected heterogeneous groups of autonomous underwater vehicles are highly complex operations and it is an important and challenging problem to effectively route these vehicles in the dynamic environment under given communication constraints. We propose a solution for the task allocation and path planning problems based on the evolutionary algorithms that allows one to obtain feasible group routes ensuring well-timed accomplishment of all objectives.

KEYWORDS

 autonomous underwater vehicle; mission planning; heterogeneous group routing; evolutionary algorithm

More Details :  

Improvements in Routing Algorithms to Enhance Lifetime of Wireless Sensor Networks

D. Naga Ravikiran1 and C.G. Dethe2 

1Research Scholar, ECE Department, Priyadarshini Institute of Engineering and Technology (PIET), Nagpur, Maharashtra. 

2Director, UGC-Human Resource Development Centre, RTM Nagpur University, Nagpur, India.

ABSTRACT: 

Wireless sensor network (WSN) brings a new paradigm of real-time embedded systems with limited computation, communication, memory, and energy resources that are being used fora huge range of applications. Clustering in WSNs is an effective way to minimize the energy consumption of sensor nodes. In this paper improvements in various parameters are compared for three different routing algorithms. First, it is started with Low Energy Adaptive Cluster Hierarchy (LEACH)which is a famed clustering mechanism that elects a CH based on the probability model. Then, work describes a Fuzzy logic system initiated CH selection algorithm for LEACH. Then Artificial Bee Colony (ABC)which is an optimisation protocol owes its inspiration to the exploration behaviour of honey bees. In this study ABC optimization algorithm is proposed for fuzzy rule selection. Then, the results of the three routing algorithms are compared with respect to various parameters.

 KEYWORDS 

Wireless Sensor Network (WSN), LEACH, Clustering, Artificial Bee Colony (ABC), Fuzzy logic system.

More Details : 

The Development and Study of the Methods and Algorithms for the Classification of Data Flows of Cloud Applications in the Network of the Virtual Data Center

Irina Bolodurina1 and Denis Parfenov2 

1Department of Applied Mathematics Orenburg State University Orenburg, Russia 

2 Faculty of Distance Learning Technologies Orenburg State University Orenburg, Russia  

ABSTRACT 

This paper represents the results of the research, which have allowed us to develop a hybrid approach to the processing, classification, and control of traffic routes. The approach enables to identify traffic flows in the virtual data center in real-time systems. Our solution is based on the methods of data mining and machine learning, which enable to classify traffic more accurately according to more criteria and parameters. As a practical result, the paper represents the algorithmic solution of the classification of the traffic flows of cloud applications and services embodied in a module for the controller of the software-defined network. This solution enables to increase the efficiency of handling user requests to cloud applications and reduce the response time, which has a positive effect on the quality of service in the network of the virtual data center. 

KEYWORDS 

Cloud applications; software-defined network; traffic flows; virtual data center; data mining; machine learning  

More Details: 

Path Splitting for Virtual Network Embedding in Elastic Optical Networks

Path Splitting for Virtual Network Embedding in Elastic Optical Networks

Badr Oulad Nassar and Takuji Tachibana Graduate School of Engineering, University of Fukui, Fukui City, Japan 

ABSTRACT

 In elastic optical networks, a wavelength is divided into frequency slots (FS) and optical signals are switched at multiple FS intervals. On the other hand, network virtualization manages network resources by efficiently mapping virtual nodes and links to physical ones (virtual network embedding). In this paper, we propose a dynamic virtual network embedding algorithm to decrease the rejection rate of virtual optical network requests. We define four schemes for node mapping. For link mapping, the primary path, which is the shortest path between the mapped nodes, is computed. If there are no available FSs, path splitting is performed and FSs are assigned at links in primary and alternatives paths. By simulation, we evaluate the effectiveness of path splitting for NSFNET and ARPA2. Numerical results show that path splitting is effective in decreasing the rejection rate. Finally, LLNL scheme, which considers both node and link resources, has the smallest rejection rate. 

KEYWORDS

Path Splitting, Virtual Optical Network, Virtual Network Embedding, Elastic Optical Network

More Details :