Search

With the immense growth of services offered by Internet, the requirement of broadband connectivity has increased significantly in past few years. Organizations and individuals are relying heavily on the internet for their daily communication needs. Consequently, networks have become more prone to different types of network attacks. Intrusion Detection Systems (IDS) offer a method to protect networks against many such attacks. Numerous IDS have been proposed in literature, which employ different techniques to identify attack patterns as well as abrupt changes in network traffic flows. Anomaly detection is a type of Intrusion Detection corresponding to a suite of techniques that can be used to identify novel or "zero-day" attacks against computers and network infrastructure. Different Anomaly-based Intrusion Detection Systems (ADS) work on different principles e.g., a few take into account the packet headers only, where as others operate on payload as well as packet headers. In this paper we evaluate six different ADS; three of them work on packet header only, while remaining three works on both header and payload. We aim to provide a conclusive comparison of these ADS (header only or both header and payload) in terms of accuracy, complexity and detection delay to highlight factors that must be considered while designing IDS in future. The comparison is performed using two real-world labeled datasets to enable cross-reference for future research in this field. In the end of this paper we will conclude that anomaly detectors which work on both header and payload perform better than those ADS which consider only header for intrusion detection. [ABSTRACT FROM AUTHOR]

Recent years have witnessed intense research in the general area of Multi-Classifier systems (MCS), but this has rarely incorporated any utilisation of weightless neural systems(WNS) as the combiner of an MCS ensemble. This paper explores the application of weightless networks within the multi-classifier environment by introducing an intelligent multiclassifier system using a WNS called the Enhanced Probabilistic Convergent Neural Networks (EPCN). The paper explores the use of EPCN by illustrating its major features, such as the specification of disjoint or overlapping input subset to the MCS, and the inherently parallel nature of the design. Within the proposed system, the number of base classifiers per MCS could be specified manually or automatically. . The proposed MCS is problem-domain independent and, our investigation is performed on handwritten characters. The proposed MCS is adaptive, its combiner is capable of extracting absolute or weighted classification decision(output) from base classifier. Diversity is increased in the base classifier by injecting randomness into the system parameters. Two types of EPCN classifiers are proposed, fix-PCN and rand-PCN. These PCNs are independent and orthogonal. One uses a fixed method of forming connectivity while the other uses random method of forming connectivity. In order to verify the performance of the recognition system, tests were performed, off-line, on benchmark datasets of unconstrained handwritten numerals. Experimental results suggest that MCS outperforms single EPCN in classification of handwritten characters. [ABSTRACT FROM AUTHOR]

The current research from the field of economic sciences uses the neural and neuro-fuzzy networks procedures as an alternative to classical methods. This paper deals with neuro-fuzzy classifiers and presents a new neuro-fuzzy classifier which considers the example dependent costs in the inductive construction of classifiers. [ABSTRACT FROM AUTHOR]

Network coding is a novel technique that includes many applications in realistic networking era. Through network coding, intermediary nodes might send out packets that are combinations of incoming information. The basic theme behind network coding is the summation of incoming information traffic through simple XOR. There are many profits of network coding: improved throughput, less number of transmissions, better network management, less BER, minimum delay, less resource consumptions. In this paper we will prove how network coding improves and achieves the Qos of any network. We also discuss the Implementation aspects of network coding like how it may implemented on current infrastructure networks, we also discuss the theoretical and practical results on network coding for improving quality of service parameters using four basic approaches of network coding, Optimal, Deterministic, Random and Heuristic approach. [ABSTRACT FROM AUTHOR]

Pose problem is a big challenge for applying face recognition technology under real world conditions. In this paper, appearance based approach was proposed to recognize face across front and non-frontal view images by reconstructing frontal view features. Statistical learning method based on sample images is applied to find transformation matrix which encapsulated general knowledge of pose transition in feature subspace, therefore, different view feature vectors constituted linear equations and transformation matrix can be solved from the equations by least square (LS) approach. Experimental results on popular FERET and CMU databases showed that the proposed method could cope with the head rotation roughly within half profile view. Compared with model based approaches, this method is not dependent on heavy computation and has merit of easy implementing in live conditions. [ABSTRACT FROM AUTHOR]

Clustering is grouping of patterns according to similarity or distance in different perspectives. Various data representations, similarity measurements and organization manners are led to several classes of clustering methods. In this paper a new combinatorial method is proposed that iteratively uses another clustering method such as Rival Penalized Competitive Learning (RPCL) or K-Means as the core of clustering system. Moreover, some novel auxiliary techniques are suggested to increase the clustering performance. The proposed method has been compared with well known clustering methods such as K-Means, its improvement, ISODATA and DSRPCL2. The new combinatorial technique can detect the drawbacks of core clustering method and improve its efficiency. Our method is applied on some standard multi-class datasets. After clustering, labels of grouped samples in each cluster are compared with their real class labels to show the accuracy of clustering. [ABSTRACT FROM AUTHOR]

In our paper, we are utilizing the cellular wireless network with high reliability using fixed relay nodes. The size and scope of wireless networks continue to grow with more clients or users, and introduction of innumerable devices and sensors at homes and businesses. These, in conjunction with short and dynamic flow of information, is adding to the spatiotemporal complexity of the network topology and dynamics requiring self organization. [ABSTRACT FROM AUTHOR]

This paper discusses the potential of Particle Swarm Optimisation (PSO) for inducing Bayesian Networks (BNs). Specifically, we detail two methods which adopt the search and score approach to BN learning. The two algorithms are similar in that they both use PSO as the search algorithm, and the K2 metric to score the resulting network. The difference lies in the way networks are constructed. The CONstruct And Repair (CONAR) algorithm generates structures, validates, and repairs if required, and the REstricted STructure (REST) algorithm, only permits valid structures to be developed. Initial experiments indicate that these approaches produce promising results when compared to other BN learning strategies. [ABSTRACT FROM AUTHOR]

Application Service Maintenance (ASM) projects mainly use Activity-Based software estimation methodology compared to Function Point or Lines of Code Estimation methodologist[1]. This is due to the nature of execution of ASM Projects differ with nature of execution of development projects. Activity based estimation methodology breaks estimation at each sub activities level of software Development Life Cycle(SDLC) using work break down structure. Prediction of effort for each micro level activities of SDLC is really challenging one. Regression Analysis has been done for the data collected for some Enhancements of ASM projects. This paper explains how to predict the estimation for each micro level activities of SDLC by statistical analysis using Regression Approach. [ABSTRACT FROM AUTHOR]