Ch. Aswani Kumar

Short Communication: Concept lattice reduction using fuzzy K-Means clustering

During the design of concept lattices, complexity plays a major role in computing all the concepts from the huge incidence matrix. Hence for reducing the size of the lattice, methods based on matrix decompositions like SVD are available in the literature. However, SVD computation is known to have large time and memory requirements. In this paper, we propose a new method based on Fuzzy K-Means clustering for reducing the size of the concept lattices. We demonstrate the implementation of proposed method on two application areas: information retrieval and information visualization.

FUZZY CLUSTERING-BASED FORMAL CONCEPT ANALYSIS FOR ASSOCIATION RULES MINING

Formal Concept Analysis (FCA), in which data is represented as a formal context, offers a framework for Association Rules Mining (ARM) by handling functional dependencies in the data. However, with the size of the formal context, the number of rules grows exponentially. In this article, we apply Fuzzy K-Means clustering on the data set to reduce the formal context and FCA on the reduced data set for mining association rules. With experiments on two real-world healthcare data sets, we offer the evidence for performance of FKM-based FCA in mining association rules.

Bipolar fuzzy graph representation of concept lattice

Formal Concept Analysis (FCA) is a mathematical framework for knowledge processing tasks. FCA has been successfully incorporated into fuzzy setting and its extension (interval-valued fuzzy set) for handling vagueness and impreciseness in data. However, the analysis in such settings is restricted to unipolar space. Recently, some applications of bipolar information are shown in bipolar fuzzy graph, lattice theory as well as in FCA. The adequate analysis of bipolar information using FCA requires incorporation of bipolar fuzzy set and an appropriate lattice structure. For this purpose, we propose an algorithm for generating the bipolar fuzzy formal concepts, a method for ( α , β ) -cut of bipolar fuzzy formal context and its implications with illustrative examples.

MINING ASSOCIATIONS IN HEALTH CARE DATA USING FORMAL CONCEPT ANALYSIS AND SINGULAR VALUE DECOMPOSITION

In recent times Formal Concept Analysis (FCA), in which the data is represented as a formal context, has gained popularity for Association Rules Mining (ARM). Application of ARM in health care datasets is challenging and a highly rewarding problem. However, datasets in the medical domain are of high dimension. As the dimensionality of dataset increases, size of the formal context as well as complexity of FCA based ARM also increases. To handle the problem of high dimensionality and mine the associations, we propose to apply Singular Value Decomposition (SVD) on the dataset to reduce the dimensionality and apply FCA on the reduced dataset for ARM. To demonstrate the proposed method, experiments are conducted on Tuberculosis (TB) and Hypertension (HP) datasets. Results indicate that with fewer concepts, SVD based FCA has achieved the performance of FCA on TB data and performed better than FCA on HP data.

An analysis of supervised tree based classifiers for intrusion detection system

Due to increase in intrusion incidents over internet, many network intrusion detection systems are developed to prevent network attacks. Data mining, pattern recognition and classification methods are used to classify network events as a normal or anomalous one. This paper is aimed at evaluating different tree based classification algorithms that classify network events in intrusion detection systems. Experiments are conducted on NSL-KDD 99 dataset. Dimensionality of the attribute of the dataset is reduced. The results show that RandomTree model holds the highest degree of accuracy and reduced false alarm rate. RandomTree model is evaluated with other leading intrusion detection models to determine its better predictive accuracy.

Intrusion detection model using fusion of PCA and optimized SVM

Intrusion detection systems (IDS) play a major role in detecting the attacks that occur in the computer or networks. Anomaly intrusion detection models detect new attacks by observing the deviation from profile. However there are many problems in the traditional IDS such as high false alarm rate, low detection capability against new network attacks and insufficient analysis capacity. The use of machine learning for intrusion models automatically increases the performance with an improved experience. This paper proposes a novel method of integrating principal component analysis (PCA) and support vector machine (SVM) by optimizing the kernel parameters using automatic parameter selection technique. This technique reduces the training and testing time to identify intrusions thereby improving the accuracy. The proposed method was tested on KDD data set. The datasets were carefully divided into training and testing considering the minority attacks such as U2R and R2L to be present in the testing set to identify the occurrence of unknown attack. The results indicate that the proposed method is successful in identifying intrusions. The experimental results show that the classification accuracy of the proposed method outperforms other classification techniques using SVM as the classifier and other dimensionality reduction or feature selection techniques. Minimum resources are consumed as the classifier input requires reduced feature set and thereby minimizing training and testing overhead time.

Designing role-based access control using formal concept analysis

Role-based access control (RBAC) is one of the most popular and widely deployed access control model. The objective of this paper is to design an RBAC using formal concept analysis, which is based on mathematical lattice and order theory. For this purpose, we derive a dyadic formal context from the triadic security context that represents role-based access permission and perform attribute exploration from formal concept analysis. We demonstrate the proposed method on a health care ad hoc network. The analysis indicates that the proposed method follows the RBAC constraints: static separation of duties and role hierarchy. Copyright

A Method for Reduction of Fuzzy Relation in Fuzzy Formal Context

Recently, fuzzy set theory in Formal Concept Analysis (FCA) has become an effective tool for knowledge representation and discovery. In this paper we present a method, for reducing the fuzzy relation for a given fuzzy context. The proposed method provides an alternative approach towards reducing the knowledge in the formal context in contrast to existing object, attribute and formal context reduction. Through this method, fuzzy relation can be projected with regards to both objects and attributes and provides two projected fuzzy formal contexts. From these two contexts, we can generate the fuzzy concepts and visualize them in a lattice structure.

Interval-valued fuzzy graph representation of concept lattice

Formal Concept Analysis (FCA) with fuzzy setting has been successfully applied by researchers for data analysis and representation. Reducing the number of fuzzy formal concepts and their lattice structure are addressed as a major issues. In this study, we try to link between interval-valued fuzzy graph and fuzzy concept lattice to overcome from the issue. We show that proposed method reduces the number of fuzzy formal concepts and their lattice structure while preserving specialized and generalized concepts. Proposed link will be useful for the researcher in data analysis and processing.

Simulation and analysis of RTS/CTS DoS attack variants in 802.11 networks

Denial-of-Service attacks (DoS) have become a widespread problem on the Internet. These attacks are easy to execute. Low rate attacks are relatively new variants of DoS attacks. Low rate DoS attacks are difficult to detect since attacker sends attack stream with low volume and the countermeasures used to handle the high rate DoS attacks are not suitable for these types of attacks. RTS/CTS attack is one type of Low rate DoS attack. In this paper, we analyze RTS/CTS attack which exploits the medium reservation mechanism of 802.11 networks through duration field. We propose variants of RTS/CTS attacks in wireless networks. We simulate the attacks behaviour in ns2 simulation environment to demonstrate the attack feasibility as well as potential negative impact of these attacks on 802.11 based networks. We have created an application that has the capability to create test bed environment for the attacks, perform RTS/CTS attacks and generate suitable graphs to analyze the attacks behaviour. We also briefly discuss possible ways of detecting and mitigating such Low rate DoS attacks in wireless networks.