Extraction Of Association Rules Research Articles

Cryptic Mining in Light of Artificial Intelligence

“The analysis of cryptic text is hard problem”, and there is no fixed algorithm for generating plain-text from cipher text. Human brains do this intelligently. The intelligent cryptic analysis process needs learning algorithms, co-operative effort of cryptanalyst and mechanism of knowledge based inference engine. This information of knowledge base will be useful for mining data(plain-text, key or cipher text plain-text relationships), classification of cipher text based on enciphering algorithms, key length or any other desirable parameters, clustering of cipher text based on similarity and extracting association rules for identifying weaknesses of cryptic algorithms. This categorization will be useful for placing given cipher text into a specific category or solving difficult level of cipher text-plain text conversion process. This paper elucidates cipher text-plain text process first than utilizes it to create a framework for AI-enabled-Cryptanalysis system. The process demonstrated in this paper attempts to analyze captured cipher from scratch. The system design elements presented in the paper gives all hints and guidelines for development of AI enabled Cryptic analysis tool.

Mining spatiotemporal association rules from spatiotemporal databases between two different fixed dates

Mining frequent itemsets from large spatiotemporal databases is a hard task due to the existence of hidden spatiotemporal relationships. The aim of our proposal is to look for spatiotemporal association rules that relate properties of reference objects like large towns with properties of other spatial task-relevant objects. The extracted patterns are different relationships relating the spatial objects during time periods. We propose a four-step approach; the core step is to extract the spatiotemporal relationships. The second and third steps are devoted respectively to frequent spatiotemporal itemsets generation and spatiotemporal association rules extraction. The fourth step is the refinement of the extracted rules. To prove the applicability of our method, we conduct experimentation on a spatiotemporal database describing the city of Tunis in the dates 1987 and 2001. On the basis of our proposed measures namely the spatial closeness relevance and the time subsequence, only interesting spatiotemporal association rules are retained.

Product failure pattern analysis from warranty data using association rule and Weibull regression analysis: A case study

The warranty data plays a crucial role in the improvement of the manufactured product. Association rule analysis is an efficient methodology for eliciting useful information from warranty data by defining the relationships between production data and failure data within warranty period. We extract association rules from warranty data of heavy duty diesel engine in order to find significant patterns of failures along with manufacturing information. We also used Weibull regression to identify influential factors that affect the variation in mean time between failures which are identified from extracted association rules. The results from the empirical study for manufacturing firm “D” provide information as to the areas in which improvements should be made. Moreover, the result for specific failure is able to suggest a solution to overcome short-sighted improvement representatively. This study expects to contribute quality improvement to manufacturing industry which is under coarse warranty data with enormous unrevealed information to draw meaningful information with ease.

Mining Fuzzy Association Rules Based on Parallel Particle Swarm Optimization Algorithm

The association rule extraction process often involves a large number of candidate item sets and multiple read operations on data sets. With the emergence of massive data, the sequential association rule extraction algorithm also suffers from large I/O overhead and insufficient memory. This paper presents a new multi-swarm parallel multi-mutation particle swarm optimization algorithm (MsP-MmPSO) to search several groups in parallel. Experimental results show that the MsP-MmPSO algorithm has an advantage in terms of execution time over traditional particle swarm optimization, especially when the amount or dimensions of the data increase. Experiments also verify that a good task allocation method can reduce the execution time of the parallel algorithm.

Haritalar Üzerinde Suç Verilerinin Görüntülenmesi ve Analizinin Sağlanması: Kocaeli İli Örneği

Nowadays, crime maps have been commonly used by different disciplines. The basic goal of using of crime mapping is to discover crime scenes and analyze them. Besides, it can be used for informing officers for local crime patterns, resource allocation decisions, evaluation analysis and crime forecast, and geographic profiling about ongoing crime series. In this study, we indicate police-judicial category crime data published in “Bizim Kocaeli” newspaper between 2011 and 2012 years on maps and develop a web-based application enabling user analysis related to these data. The user can realize spatial (e.g. finding an address), proximity (e.g. listing crimes in circle with a diameter of 300 meters in manner Kocaeli University-centralized), and network analysis (finding the route the nearest police station to a crime). Moreover, the user can extract association rules related to crimes via Appriori algorithm. This study contributes the peace and security of society

The Analysis of the Length of Studies in Higher Education based on Clustering and the Extraction of Association Rules

The length of studies of the students who “linger” in Higher Education has not been justified in many countries, and the Higher Education Institutes try to solve the problem using various methods. The problem of students who “linger” in their Departments beyond the six or seven years is seen as complex one, in the Greek Higher Education. Two main alternative methods have been discussed: Giving the students who “linger” a low priority for registration in the laboratory classes, and limiting the number of times of attending laboratory based courses. Eventually, according to the new legislation the Greek Higher Education Institutes must cut off access to the students who “linger” too long. This study focuses on this hard problem. Clustering techniques and the mining of Association rules are used. The results of clustering and the generation of the association rules are based on students’ questionnaires collected in the laboratory classes. Various interesting results and rules are extracted and discussed.

Association rule extraction from XML stream data for wireless sensor networks.

With the advances of wireless sensor networks, they yield massive volumes of disparate, dynamic and geographically-distributed and heterogeneous data. The data mining community has attempted to extract knowledge from the huge amount of data that they generate. However, previous mining work in WSNs has focused on supporting simple relational data structures, like one table per network, while there is a need for more complex data structures. This deficiency motivates XML, which is the current de facto format for the data exchange and modeling of a wide variety of data sources over the web, to be used in WSNs in order to encourage the interchangeability of heterogeneous types of sensors and systems. However, mining XML data for WSNs has two challenging issues: one is the endless data flow; and the other is the complex tree structure. In this paper, we present several new definitions and techniques related to association rule mining over XML data streams in WSNs. To the best of our knowledge, this work provides the first approach to mining XML stream data that generates frequent tree items without any redundancy.

Association Rules Mining Based on Adaptive Fuzzy Clustering Algorithm

Association rules extraction is one of the important goals of data mining and analyzing. Aiming at the problem that information lose caused by crisp partition of numerical attribute , in this article, we put forward a fuzzy association rules mining method based on fuzzy logic. First, we use c-means clustering to generate fuzzy partitions and eliminate redundant data, and then map the original data set into fuzzy interval, in the end, we extract the fuzzy association rules on the fuzzy data set as providing the basis for proper decision-making. Results show that this method can effectively improve the efficiency of data mining and the semantic visualization and credibility of association rules.

Web Recommendation Framework based on Association Rules Coverage to be Applied for Site Modification

This paper introduces a Web Recommendation Framework based on the usage history to be applied for Site Modification as one of the applications of Web Usage Mining (WUM) that is applicable for online business and marketing applications. The framework focuses on the three main interdependent tasks for performing WUM which are Preprocessing, Pattern Discovery and Pattern Analysis. In Preprocessing, we remove all irrelevant users’ requests from the web server log file leading to log reduction followed by users’ identification then sessions’ identification. We take into consideration the ambiguity found in some researches concerning the HTTP common methods. In Pattern Discovery, we extract Association Rules that can be used to relate pages that are most often referenced together in a single server session and may not be directly connected to one another via hyperlinks. In Pattern Analysis, we analyze the set of generated rules independent of the website’s topology to extract valid set of rules that achieves highest coverage for the dataset. Our experimental results confirmed that calculating association rules coverage in our case study can lead to the best rules to be provided as recommendations that can help Web designers to restructure their Web site, Web applications or even portals to better serve Web customers. General Terms Web Mining, Web Usage Mining

Prediction of high incidence of dengue in the Philippines.

BackgroundAccurate prediction of dengue incidence levels weeks in advance of an outbreak may reduce the morbidity and mortality associated with this neglected disease. Therefore, models were developed to predict high and low dengue incidence in order to provide timely forewarnings in the Philippines.MethodsModel inputs were chosen based on studies indicating variables that may impact dengue incidence. The method first uses Fuzzy Association Rule Mining techniques to extract association rules from these historical epidemiological, environmental, and socio-economic data, as well as climate data indicating future weather patterns. Selection criteria were used to choose a subset of these rules for a classifier, thereby generating a Prediction Model. The models predicted high or low incidence of dengue in a Philippines province four weeks in advance. The threshold between high and low was determined relative to historical incidence data.Principal FindingsModel accuracy is described by Positive Predictive Value (PPV), Negative Predictive Value (NPV), Sensitivity, and Specificity computed on test data not previously used to develop the model. Selecting a model using the F0.5 measure, which gives PPV more importance than Sensitivity, gave these results: PPV = 0.780, NPV = 0.938, Sensitivity = 0.547, Specificity = 0.978. Using the F3 measure, which gives Sensitivity more importance than PPV, the selected model had PPV = 0.778, NPV = 0.948, Sensitivity = 0.627, Specificity = 0.974. The decision as to which model has greater utility depends on how the predictions will be used in a particular situation.ConclusionsThis method builds prediction models for future dengue incidence in the Philippines and is capable of being modified for use in different situations; for diseases other than dengue; and for regions beyond the Philippines. The Philippines dengue prediction models predicted high or low incidence of dengue four weeks in advance of an outbreak with high accuracy, as measured by PPV, NPV, Sensitivity, and Specificity.

An effective association rule mining scheme using a new generic basis

Association rule mining among itemsets is a fundamental task and is of great importance in many data mining applications including attacks in network data, stock market, financial applications, bioinformatics to find genetic disorders, etc. However, association rule extraction from a reasonable-sized database produces a large number of rules. As a result, many of them are redundant to other rules, and they are practically useless. To overcome this issue, methods for mining non-redundant rules are essentially required. To address such problem, we initially propose a definition for redundancy in sense of minimal knowledge and then a compact representation of non-redundant association rules which we call as compact informative generic basis. We also provide an improved version of the existing DCI_CLOSED algorithm (DCI_PLUS) to find out the frequent closed itemsets (FCI) with their minimal representative generators in combination with BitTable which represents a compact database form in a single scan of the original database. We further introduce an algorithm for constructing the compact informative generic basis from the FCI and their generators in an efficient way. We finally present an inference mechanism in which all association rules can be generated without accessing the database. Experiments are performed on the proposed method. The experimental results show that the proposed method outperforms the other existing related methods.

A New Multiobjective Evolutionary Algorithm for Mining a Reduced Set of Interesting Positive and Negative Quantitative Association Rules

Most of the algorithms for mining quantitative association rules focus on positive dependencies without paying particular attention to negative dependencies. The latter may be worth taking into account, however, as they relate the presence of certain items to the absence of others. The algorithms used to extract such rules usually consider only one evaluation criterion in measuring the quality of generated rules. Recently, some researchers have framed the process of extracting association rules as a multiobjective problem, allowing us to jointly optimize several measures that can present different degrees of trade-off depending on the dataset used. In this paper, we propose MOPNAR, a new multiobjective evolutionary algorithm, in order to mine a reduced set of positive and negative quantitative association rules with low computational cost. To accomplish this, our proposal extends a recent multiobjective evolutionary algorithm based on decomposition to perform an evolutionary learning of the intervals of the attributes and a condition selection for each rule, while introducing an external population and a restarting process to store all the nondominated rules found and to improve the diversity of the rule set obtained. Moreover, this proposal maximizes three objectives-comprehensibility, interestingness, and performance-in order to obtain rules that are interesting, easy to understand, and provide good coverage of the dataset. The effectiveness of the proposed approach is validated over several real-world datasets.

Application of Data Mining Techniques to Predict Urinary Fistula Surgical Repair Outcome: The Case of Addis Ababa Fistula Hospital, Addis Ababa, Ethiopia

Background: Maternal outcomes are good in most countries of the developed world while the same is not true in many developing countries. The likelihood of the occurrence of incontinence after successful surgical repair makes predicting urinary fistula surgical repair outcome is important for decision making during treatment and follow up. Therefore, this research is aimed to apply data mining techniques to build a model that can assist in predicting surgical outcome of urinary fistula repair based on clinical assessments done just before surgical repair. Methods: The six-step hybrid knowledge discovery process model is used as a framework for the overall activities in the study. 15961 instances that have undergone urinary fistula repair in Addis Ababa Fistula Hospital are used for both predictive association rule extraction and predictive model building. Apriori algorithm is used to extract association rules while classification algorithms J48, PART, Naive Bayes and multinomial logistic regression are used to build predictive models. Support and confidence are used as interestingness measure for association rules while area under the WROC and ROC curve for each specific outcome is sequentially used to compare performances of models from the predictive algorithms. Results: Predictive association rules from Apriori have shown frequent co-occurrence of less severity of injury with cured outcome. The predictive model from PART-M2-C0.05-Q1 scheme has shown an area under WROC curve of 0.742. Area under the ROC curve for residual outcome (ROCResidual=0.822) from this algorithm is better than Naive Bayes and logistic, while the areas under the ROC curves for the other outcomes are greater than the model from J48. Conclusion: Predictive model is developed with the use of PART-M2-C0.05-Q1. The predictive association rules and predictive model built with the use of data mining techniques can assist in predicting urinary fistula surgical repair outcome. Therefore, it is better in detecting residual outcome than the logistic regression model.

Using data mining to analyse fashion consumers’ preferences from a cross-national perspective

The purpose of this study is twofold: (1) to cluster the respondents into three consumer groups – fashion innovator, fashion follower and laggard and (2) to extract association rules from the data set in order to understand consumers’ preferences. A data-mining method was employed to analyse considerable amount of data collected from four cities as well as to understand the complexity of the diffusion process of multiple apparel products. According to the results of the present study, style was not an important factor for the fashion leaders to purchase socks in Toronto, Hangzhou and Johor Bahru. In terms of t-shirts and evening dresses/suits, 53% and 51% of fashion laggards in China had shown their strong preferences for fit and comfort, respectively. Additionally, 60% of the fashion leaders in Canada had shown a strong preference for fit and style of t-shirts. Although this study is exploratory in nature, we believe that data mining has great potential for investigating fashion diffusion of innovativeness, and more replication of this type of research will be worthwhile and meaningful.

Web usage mining with evolutionary extraction of temporal fuzzy association rules

In Web usage mining, fuzzy association rules that have a temporal property can provide useful knowledge about when associations occur. However, there is a problem with traditional temporal fuzzy as...

Iндукцiя чисельних асоцiативних правил з врахуванням iндивiдуальної значущостi ознак

The problem of extracting of quantitative association rules is considered. Method for extraction of the quantitative association rules is proposed. The basic steps of the proposed method are fuzzyfication of the transactional database, determining the individual significance of features, the calculation of the thresholds of support and construction a base of quantitative association rules. The proposed method involves fuzzyfication of specified database transactions, and automatic partitioning of the ranges of values of features into intervals, takes into account the importance of individual features, uses criteria for the evaluation of indirect associations, which reduces the degree of user involvement in the process of mining association rules reduces the likelihood of extraction rules correctly describing these objects and processes. The use of a priori information about the importance of features in the developed method allows to reduce the search space and to reduce the number of extracted rules, and, accordingly, increase the levels of generalization and interpretability of the synthesized base of association rules.

Extraction of quantitative association rules considering significance of features

T he solution of the problem of automating the extraction of quantitative association rules in the diagnosis and recognition of images is considered in the paper, and some results of our research in this area are given. The main purpose of the study is developing a method for extracting quantitative association rules, considering the significance of features. The use of modern methods of searching association rules allows extracting new knowledge from large amounts of information. The issues of extracting the quantitative association rules are considered in the paper for identifying new knowledge when solving problems of diagnosing and recognizing of images. The proposed method allows extracting quantitative association rules from the transaction databases. We propose to use a priori information concerning the significance of features that reduces the search scope, the time of rules extraction, the number of extracted rules, and accordingly, increases the levels of generalization and interpretability of the synthesized base of association rules. The research results can be used by researchers who study and analyze complex objects, processes and systems in order to identify new knowledge, as well as in decision support systems in technical and medical diagnostics.

Web usage mining with evolutionary extraction of temporal fuzzy association rules

In Web usage mining, fuzzy association rules that have a temporal property can provide useful knowledge about when associations occur. However, there is a problem with traditional temporal fuzzy association rule mining algorithms. Some rules occur at the intersection of fuzzy sets’ boundaries where there is less support (lower membership), so the rules are lost. A genetic algorithm (GA)-based solution is described that uses the flexible nature of the 2-tuple linguistic representation to discover rules that occur at the intersection of fuzzy set boundaries. The GA-based approach is enhanced from previous work by including a graph representation and an improved fitness function. A comparison of the GA-based approach with a traditional approach on real-world Web log data discovered rules that were lost with the traditional approach. The GA-based approach is recommended as complementary to existing algorithms, because it discovers extra rules.

QAR-CIP-NSGA-II: A new multi-objective evolutionary algorithm to mine quantitative association rules

Some researchers have framed the extraction of association rules as a multi-objective problem, jointly optimizing several measures to obtain a set with more interesting and accurate rules. In this paper, we propose a new multi-objective evolutionary model which maximizes the comprehensibility, interestingness and performance of the objectives in order to mine a set of quantitative association rules with a good trade-off between interpretability and accuracy. To accomplish this, the model extends the well-known Multi-objective Evolutionary Algorithm Non-dominated Sorting Genetic Algorithm II to perform an evolutionary learning of the intervals of the attributes and a condition selection for each rule. Moreover, this proposal introduces an external population and a restarting process to the evolutionary model in order to store all the nondominated rules found and improve the diversity of the rule set obtained. The results obtained over real-world datasets demonstrate the effectiveness of the proposed approach.

An effective parallel approach for genetic-fuzzy data mining

Data mining is most commonly used in attempts to induce association rules from transaction data. In the past, we used the fuzzy and GA concepts to discover both useful fuzzy association rules and suitable membership functions from quantitative values. The evaluation for fitness values was, however, quite time-consuming. Due to dramatic increases in available computing power and concomitant decreases in computing costs over the last decade, learning or mining by applying parallel processing techniques has become a feasible way to overcome the slow-learning problem. In this paper, we thus propose a parallel genetic-fuzzy mining algorithm based on the master–slave architecture to extract both association rules and membership functions from quantitative transactions. The master processor uses a single population as a simple genetic algorithm does, and distributes the tasks of fitness evaluation to slave processors. The evolutionary processes, such as crossover, mutation and production are performed by the master processor. It is very natural and efficient to run the proposed algorithm on the master–slave architecture. The time complexities for both sequential and parallel genetic-fuzzy mining algorithms have also been analyzed, with results showing the good effect of the proposed one. When the number of generations is large, the speed-up can be nearly linear. The experimental results also show this point. Applying the master–slave parallel architecture to speed up the genetic-fuzzy data mining algorithm is thus a feasible way to overcome the low-speed fitness evaluation problem of the original algorithm.