Fuzzy Data Mining Research Articles

Fuzzy data mining: a literature survey and classification framework

Despite the tremendous application of data mining in business areas and simultaneous development in the area of fuzzy systems, both the technologies have never been able to prove worth in combination. The development in the application of fuzzy data mining is rapidly increasing and exhaustive literature survey in the field of fuzzy data mining has not been done in the past which prompted us to find and classify the existing literature in fuzzy data mining which will pave the way for further quality research in fuzzy data mining. The authors classified the available literature on three broad categories on the basis of data mining techniques which are applicable. The further classification is done on the basis on application areas where fuzzy data mining has found its worth.

Finding Pareto-front Membership Functions in Fuzzy Data Mining

Abstract Transactions with quantitative values are commonly seen in real-world applications. Fuzzy mining algorithms have thus been developed recently to induce linguistic knowledge from quantitative databases. In fuzzy data mining, the membership functions have a critical influence on the final mining results. How to effectively decide the membership functions in fuzzy data mining thus becomes very important. In the past, we proposed a fuzzy mining approach based on the Multi-Objective Genetic Algorithm (MOGA) to find the Pareto front of the desired membership functions. In this paper, we adopt a more sophisticated multi-objective approach, the SPEA2, to find the appropriate sets of membership functions for fuzzy data mining. Two objective functions are used to find the Pareto front. The first one is the suitability of membership functions and the second one is the total number of large 1-itemsets derived. Experimental comparisons of the proposed and the previous approaches are also made to show the effe...

A decision making process application for the slurry production in ceramics via fuzzy cluster and data mining

To increase productivity, companies are in search of techniques that enable them to make faster and more effective decisions. Data mining and fuzzy clustering algorithms can serve for this purpose. This paper models the decision making process of a ceramics production company using a fuzzy clustering algorithm and data mining. Factors that affect the quality of slurry are measured over time. Using this data, a fuzzy clustering algorithm assigns the degrees of memberships of the slurry for the different quality clusters. An expert can decide on acceptance or rejection of slurry based on calculated degrees of memberships. In addition, by using data mining techniques we generated some rules that provide the optimum conditions for acceptance of the slurry.

Data Mining Approaches for Geo-Spatial Big Data

The availability of a vast amount of heterogeneous information from a variety of sources ranging from satellite imagery to the Internet has been termed as the problem of Big Data. Currently there is a great emphasis on the huge amount of geophysical data that has a spatial basis or spatial aspects. To effectively utilize such volumes of data, data mining techniques are needed to manage discovery from such volumes of data. An important consideration for this sort of data mining is to extend techniques to manage the inherent uncertainty involved in such spatial data. In this paper the authors first provide overviews of uncertainty representations based on fuzzy, intuitionistic, and rough sets theory and data mining techniques. To illustrate the issues they focus on the application of the discovery of association rules in approaches for vague spatial data. The extensions of association rule extraction for uncertain data as represented by rough and fuzzy sets are described. Finally an example of rule extraction for both fuzzy and rough set types of uncertainty representations is given

Fuzzy data mining for time-series data

Time series analysis has always been an important and interesting research field due to its frequent appearance in different applications. In the past, many approaches based on regression, neural networks and other mathematical models were proposed to analyze the time series. In this paper, we attempt to use the data mining technique to analyze time series. Many previous studies on data mining have focused on handling binary-valued data. Time series data, however, are usually quantitative values. We thus extend our previous fuzzy mining approach for handling time-series data to find linguistic association rules. The proposed approach first uses a sliding window to generate continues subsequences from a given time series and then analyzes the fuzzy itemsets from these subsequences. Appropriate post-processing is then performed to remove redundant patterns. Experiments are also made to show the performance of the proposed mining algorithm. Since the final results are represented by linguistic rules, they will be friendlier to human than quantitative representation.

Tracking Controller Design for Nonlinear Dynamic Systems via Fuzzy Association Rule Reduction

One of the conventional significant criteria to be considered in real-time control applications is the computational complication of the controllers. The major weakness of fuzzy data mining is that after applying fuzzy data mining on the quantitative data, the number of extracted fuzzy association rules is very enormous. When many connection rules are obtained, the value of them will be reduced. This paper presents structures and a systematical progress method for two degree of freedom fuzzy controllers with nonhomogenous dynamics with respect to the two input channels. In this paper, singular value decomposition (SVD)-based complexity reduction technique and a reduced modified fuzzy logic controller (MFLC) are proposed. We introduce an approach to reduce and summarize the extracted fuzzy association rules after fuzzy data mining. Matlab/Simulink software is used to simulate the mathematical model of the Gun Turret-Barrel dynamic system. Different controllers are applied to the system. A comparison is introduced among the system performances under the control of each of FLC, a reduced FLC (in the number of membership functions and rules by using SVD method), and a reduced MFLC (reduction in the number of rules and modification in the shape of the membership functions by observing the system performance). The analysis points out that the proposed MFLC can ensure better control system performance with respect to the reference input in comparison with other controllers.

A multi-level ant-colony mining algorithm for membership functions

Fuzzy data mining is used to extract fuzzy knowledge from linguistic or quantitative data. It is an extension of traditional data mining and the derived knowledge is relatively meaningful to human beings. In the past, we proposed a mining algorithm to find suitable membership functions for fuzzy association rules based on ant colony systems. In that approach, precision was limited by the use of binary bits to encode the membership functions. This paper elaborates on the original approach to increase the accuracy of results by adding multi-level processing. A multi-level ant colony framework is thus designed and an algorithm based on the structure is proposed to achieve the purpose. The proposed approach first transforms the fuzzy mining problem into a multi-stage graph, with each route representing a possible set of membership functions. The new approach then extends the previous one, using multi-level processing to solve the problem in which the maximum quantities of item values in the transactions may be large. The membership functions derived in a given level will be refined in the subsequent level. The final membership functions in the last level are then outputted to the rule-mining phase to find fuzzy association rules. Experiments are also performed to show the performance of the proposed approach. The experimental results show that the proposed multi-level ant colony systems mining approach can obtain improved results.

Fuzzy data mining for segmentation and profiling

The paper presents fuzzy data mining for churn behavior analysis in telecom. Fuzzy data mining is used to identify the clusters in the given large dataset using the modified single pass fuzzy clustering algorithm. Subsequently, fuzzy rule induction is used to reveal variables that provide maximal separation between churners and non-churners in different clusters. This study provides evidence against extra resources for handling large data. The preliminary results are encouraging. The quality of clusters and rules derived for classification are almost identical on both the proposed approach and the original Fuzzy C-Means algorithm.

Distributed and Scalable Intrusion Detection System Based on Agents and Intelligent Techniques

The Internet explosion and the increase in crucial web applications such as ebanking and e-commerce, make essential the need for network security tools. One of such tools is an Intrusion detection system which can be classified based on detection approachs as being signature-based or anomaly-based. Even though intrusion detection systems are well defined, their cooperation with each other to detect attacks needs to be addressed. Consequently, a new architecture that allows them to cooperate in detecting attacks is proposed. The architecture uses Software Agents to provide scalability and distributability. It works in two modes: learning and detection. During learning mode, it generates a profile for each individual system using a fuzzy data mining algorithm. During detection mode, each system uses the FuzzyJess to match network traffic against its profile. The architecture was tested against a standard data set produced by MIT's Lincoln Laboratory and the primary results show its efficiency and capability to detect attacks. Finally, two new methods, the memory-window and memoryless-window, were developed for extracting useful parameters from raw packets. The parameters are used as detection metrics.

Intelligent phishing detection system for e-banking using fuzzy data mining

Detecting and identifying any phishing websites in real-time, particularly for e-banking, is really a complex and dynamic problem involving many factors and criteria. Because of the subjective considerations and the ambiguities involved in the detection, fuzzy data mining techniques can be an effective tool in assessing and identifying phishing websites for e-banking since it offers a more natural way of dealing with quality factors rather than exact values. In this paper, we present novel approach to overcome the ‘fuzziness’ in the e-banking phishing website assessment and propose an intelligent resilient and effective model for detecting e-banking phishing websites. The proposed model is based on fuzzy logic combined with data mining algorithms to characterize the e-banking phishing website factors and to investigate its techniques by classifying the phishing types and defining six e-banking phishing website attack criteria’s with a layer structure. Our experimental results showed the significance and importance of the e-banking phishing website criteria (URL & Domain Identity) represented by layer one and the various influence of the phishing characteristic on the final e-banking phishing website rate.

MINING SIMPLIFIED FUZZY IF-THEN RULES FOR PATTERN CLASSIFICATION

A fuzzy if-then rule whose consequent part is a real number is referred to as a simplified fuzzy rule. Simplified fuzzy if-then rules have been widely used in function approximation problems due to no complicated defuzzification is required. The proposed simplified fuzzy rule-based classification system, whose number of output is equal to the number of different classes, approximates an unknown mapping from input to desired output for each discriminant function. Not only a fuzzy data mining method is proposed to find simplified fuzzy if-then rules from training data, but also the genetic algorithm is employed to determine some user-specified parameters. To evaluate the classification performance of the proposed method, computer simulations are performed on some well-known datasets, showing that the generalization ability of the proposed method is comparable to the other fuzzy or nonfuzzy methods.

An ACS-based framework for fuzzy data mining

Data mining is often used to find out interesting and meaningful patterns from huge databases. It may generate different kinds of knowledge such as classification rules, clusters, association rules, and among others. A lot of researches have been proposed about data mining and most of them focused on mining from binary-valued data. Fuzzy data mining was thus proposed to discover fuzzy knowledge from linguistic or quantitative data. Recently, ant colony systems (ACS) have been successfully applied to optimization problems. However, few works have been done on applying ACS to fuzzy data mining. This thesis thus attempts to propose an ACS-based framework for fuzzy data mining. In the framework, the membership functions are first encoded into binary-bits and then fed into the ACS to search for the optimal set of membership functions. The problem is then transformed into a multi-stage graph, with each route representing a possible set of membership functions. When the termination condition is reached, the best membership function set (with the highest fitness value) can then be used to mine fuzzy association rules from a database. At last, experiments are made to make a comparison with other approaches and show the performance of the proposed framework.

An improved approach to find membership functions and multiple minimum supports in fuzzy data mining

Fuzzy mining approaches have recently been discussed for deriving fuzzy knowledge. Since items may have their own characteristics, different minimum supports and membership functions may be specified for different items. In the past, we proposed a genetic-fuzzy data-mining algorithm for extracting minimum supports and membership functions for items from quantitative transactions. In that paper, minimum supports and membership functions of all items are encoded in a chromosome such that it may be not easy to converge. In this paper, an enhanced approach is proposed, which processes the items in a divide-and-conquer strategy. The approach is called divide-and-conquer genetic-fuzzy mining algorithm for items with Multiple Minimum Supports (DGFMMS), and is designed for finding minimum supports, membership functions, and fuzzy association rules. Possible solutions are evaluated by their requirement satisfaction divided by their suitability of derived membership functions. The proposed GA framework maintains multiple populations, each for one item’s minimum support and membership functions. The final best minimum supports and membership functions in all the populations are then gathered together to be used for mining fuzzy association rules. Experimental results also show the effectiveness of the proposed approach.

Using fuzzy data mining to evaluate survey data from olive grove cultivation

User knowledge about cultivation and soils is relevant in developing countries, given the lack of any other kind of information, and in developed countries where it may contribute to the sustainable and operational planning for farm production systems. But user data show a high degree of inaccuracy and uncertainty; hence the appropriate treatment of this kind of data in order to obtain potentially useful information requires suitable storage and processing techniques, such as fuzzy relational database and fuzzy data mining techniques. The user data were obtained from a survey with 126 variables carried out on 210 olive grove farms in the Province of Granada (southern Spain). A set of 34 variables were selected following a cleaning process, and 1420 fuzzy association rules relating handling, soil, or environment with olive fruit production (kg ha −1), % of oil in olive fruit or acidity of fruit on tree (olive oil quality), were obtained. Several of these rules can be considered as user evaluation rules (UER) because they show a clear association between the corresponding variables. It is demonstrated that the greatest influence of the variables for handling, soil and environment on the production and the quality of the olive oil, arises when those variables limit or reduce the production or quality. Some UER are corroborated with the knowledge regarding olive cultivation found in the bibliography. Some others contradict the knowledge and others reveal relationships not described previously. Because of this, the proposed working method can be considered as mostly exploratory. The final objective of this work is to help decision-making in the field of olive cultivation in Andalusia. However, the working method described in this paper is applicable to other geographical areas and to other kinds of crops.

Inferring Gene Regulatory Networks From Expression Data by Discovering Fuzzy Dependency Relationships

For one to infer the structures of a gene regulatory network (GRN), it is important to identify, for each gene in the GRN, which other genes can affect its expression and how they can affect it. For this purpose, many algorithms have been developed to generate hypotheses about the presence or absence of interactions between genes. These algorithms, however, cannot be used to determine if a gene activates or inhibits another. To obtain such information to better infer GRN structures, we propose a fuzzy data mining technique here. By transforming quantitative expression values into linguistic terms, it defines a measure of fuzzy dependency among genes. Using such a measure, the technique is able to discover interesting fuzzy dependency relationships in noisy, high dimensional time series expression data so that it can not only determine if a gene is dependent on another but also if a gene is supposed to be activated or inhibited. In addition, the technique can also predict how a gene in an unseen sample (i.e., expression data that are not in the original database) would be affected by other genes in it and this makes statistical verification of the reliability of the discovered gene interactions easier. For evaluation, the proposed technique has been tested using real expression data and experimental results show that the use of fuzzy-logic based technique in gene expression data analysis can be quite effective.

Fuzzy Data Mining and Genetic Algorithms Applied to Intrusion Detection

Fuzzy Data Mining and Genetic Algorithms Applied to Intrusion Detection

SIMPLE FUZZY GRID PARTITION FOR MINING MULTIPLE-LEVEL FUZZY SEQUENTIAL PATTERNS

Fuzzy sequential patterns are discovered by finding intertransaction fuzzy patterns among data items at a single level. In this paper, a fuzzy data mining method for finding fuzzy sequential patterns at multiple levels of abstraction is developed. Actually, a new method is proposed to mine multiple level fuzzy sequential patterns, using fuzzy partition by a simple fuzzy grid, among data items at a concept hierarchy. The proposed method is composed of two phases: one to find frequent level crossing fuzzy 1-sequences, and the other to generate multiple level fuzzy sequential patterns by analyzing the temporal relation between those frequent fuzzy 1-sequences. A numerical example along with a mining process is used to illustrate the usefulness of the proposed method.

Intelligent Fril/SQL interrogator

The intelligent Fril/SQL interrogator is an object-oriented and knowledge-based support query system, which is implemented by the set of logic objects linking one another. These logic objects integrate SQL query, support logic programming language—Fril and Fril query together by processing them in sequence in slots of each logic object. This approach therefore takes advantage of both object-oriented system and a logic programming-based system. Fuzzy logic data mining and a machine learning tool kit built in the intelligent interrogator can automatically provide a knowledge base or rules to assist a human to analyze huge data sets or create intelligent controllers. Alternatively, users can write or edit the knowledge base or rules according to their requirements, so that the intelligent interrogator is also a support logic programming environment where users can write and run various Fril programs through these logic objects. © 2007 Wiley Periodicals, Inc. Int J Int Syst 22: 279–302, 2007.

A framework for an adaptive anomaly detection system with fuzzy data mining

In this paper, we present an adaptive anomaly detection framework that is applicable to network-based intrusion detection. Our framework employs fuzzy cluster algorithm to detect anomalies in an online, adaptive fashion without a priori knowledge of the underlying data. We evaluate our method by performing experiments over network records from the KDD CUP99 data set.

Mining Frequent Fuzzy Grids in Dynamic Databases with Weighted Transactions and Weighted Items

Incremental mining algorithms that derive the latest mining output by making use of previous mining results are attractive to business organisations. In this paper, a fuzzy data mining algorithm for incremental mining of frequent fuzzy grids from quantitative dynamic databases is proposed. It extends the traditional association rule problem by allowing a weight to be associated with each item in a transaction and with each transaction in a database to reflect the interest/intensity of items and transactions. It uses the information about fuzzy grids that are already mined from original database and avoids start-from-scratch process. In addition, we deal with "weights-of-significance" which are automatically regulated as the incremental databases are evolved and implant themselves in the original database. We maintain "hopeful fuzzy grids" and "frequent fuzzy grids" and our algorithm changes the status of the grids which have been discovered earlier so that they reflect the pattern drift in the updated quantitative databases. Our heuristic approach avoids maintaining many "hopeful fuzzy grids" at the initial level. The algorithm is illustrated with one numerical example and demonstration of experimental results are also incorporated.