Discovery Of Association Rules Research Articles

Discovery of the D-basis in binary tables based on hypergraph dualization

Discovery of (strong) association rules, or implications, is an important task in data management, and it finds application in artificial intelligence, data mining and the semantic web. We introduce a novel approach for the discovery of a specific set of implications, called the D-basis, that provides a representation for a reduced binary table, based on the structure of its Galois lattice. At the core of the method are the D-relation defined in a lattice theoretic framework and the hypergraph dualization algorithm that allows us to effectively produce the set of transversals for a given Sperner hypergraph. The latter algorithm, first developed by specialists from Rutgers Center for Operations Research, has already found numerous applications in solving optimization problems in data base theory, artificial intelligence and game theory. One application of the method is for analysis of gene expression data related to a particular phenotypic variable, and some initial testing is done for data provided by the University of Hawaii Cancer Center.

FIR: An Effective Scheme for Extracting Useful Metadata from Social Media.

Recently, the use of social media for health information exchange is expanding among patients, physicians, and other health care professionals. In medical areas, social media allows non-experts to access, interpret, and generate medical information for their own care and the care of others. Researchers paid much attention on social media in medical educations, patient-pharmacist communications, adverse drug reactions detection, impacts of social media on medicine and healthcare, and so on. However, relatively few papers discuss how to extract useful knowledge from a huge amount of textual comments in social media effectively. Therefore, this study aims to propose a Fuzzy adaptive resonance theory network based Information Retrieval (FIR) scheme by combining Fuzzy adaptive resonance theory (ART) network, Latent Semantic Indexing (LSI), and association rules (AR) discovery to extract knowledge from social media. In our FIR scheme, Fuzzy ART network firstly has been employed to segment comments. Next, for each customer segment, we use LSI technique to retrieve important keywords. Then, in order to make the extracted keywords understandable, association rules mining is presented to organize these extracted keywords to build metadata. These extracted useful voices of customers will be transformed into design needs by using Quality Function Deployment (QFD) for further decision making. Unlike conventional information retrieval techniques which acquire too many keywords to get key points, our FIR scheme can extract understandable metadata from social media.

Knowledge discovery and sequence-based prediction of pandemic influenza using an integrated classification and association rule mining (CBA) algorithm

Pandemic influenza is a major concern worldwide. Availability of advanced technologies and the nucleotide sequences of a large number of pandemic and non-pandemic influenza viruses in 2009 provide a great opportunity to investigate the underlying rules of pandemic induction through data mining tools. Here, for the first time, an integrated classification and association rule mining algorithm (CBA) was used to discover the rules underpinning alteration of non-pandemic sequences to pandemic ones. We hypothesized that the extracted rules can lead to the development of an efficient expert system for prediction of influenza pandemics. To this end, we used a large dataset containing 5373 HA (hemagglutinin) segments of the 2009 H1N1 pandemic and non-pandemic influenza sequences. The analysis was carried out for both nucleotide and protein sequences. We found a number of new rules which potentially present the undiscovered antigenic sites at influenza structure. At the nucleotide level, alteration of thymine (T) at position 260 was the key discriminating feature in distinguishing non-pandemic from pandemic sequences. At the protein level, rules including I233K, M334L were the differentiating features. CBA efficiently classifies pandemic and non-pandemic sequences with high accuracy at both the nucleotide and protein level. Finding hotspots in influenza sequences is a significant finding as they represent the regions with low antibody reactivity. We argue that the virus breaks host immunity response by mutation at these spots. Based on the discovered rules, we developed the software, “Prediction of Pandemic Influenza” for discrimination of pandemic from non-pandemic sequences. This study opens a new vista in discovery of association rules between mutation points during evolution of pandemic influenza.

A novel approach to adaptive relational association rule mining

The paper focuses on the adaptive relational association rule mining problem. Relational association rules represent a particular type of association rules which describe frequent relations that occur between the features characterizing the instances within a data set. We aim at re-mining an object set, previously mined, when the feature set characterizing the objects increases. An adaptive relational association rule method, based on the discovery of interesting relational association rules, is proposed. This method, called ARARM (Adaptive Relational Association Rule Mining) adapts the set of rules that was established by mining the data before the feature set changed, preserving the completeness. We aim to reach the result more efficiently than running the mining algorithm again from scratch on the feature-extended object set. Experiments testing the method's performance on several case studies are also reported. The obtained results highlight the efficiency of the ARARM method and confirm the potential of our proposal.

A new tree-based approach for evaluating rule antecedent constraint in confabulation based association rule mining

Confabulation-based Association Rule Mining (CARM) is an algorithm that is inspired by the thought process of human brain. It is an iterative method where, in each iteration, new rules are generated using a measure of cogency and constraints on the antecedents and consequents of the previous iteration. This cogency measure leads to a particular ability in dealing with rare items problem. Here, we aim to study CARM's antecedent constraint with respect to the ability of pruning uninteresting rules. Hence, a new Tree-based CARM (TCARM) algorithm is proposed which produces all rules using only cogency constraint on the consequents. In our experiments, the extracted rules of these two algorithms are compared with those of CFPGrowth using several measures such as precision, recall, support and cogency of rules. CFPGrowth is an approach that finds association rules using multiple minimum support and confidence, so the extracted rules of CFPGrowth support rare items and can be used for evaluating the extracted rules of CARM and TCARM. Our analysis based on the proposed TCARM and the extracted rules of CFPGrowth, on both synthetic and real datasets, show that CARM prunes uninteresting rules better than TCARM, which confirms that its antecedent constraint can help to control the number of extracted rules properly.

A probability-based incremental association rule discovery algorithm for record insertion and deletion

The maintenance of association rules for dynamic database is an important problem because the updates may not only invalidate some existing rules but also make other rules relevant. This paper is the extension work of probability-based incremental association rule discovery algorithm which can only handle new data insert into a dynamic database. Unlike the previous work, the proposed algorithm can efficiently handle in case of insertion as well as deletion simultaneously. Basically, the proposed algorithm maintains the support counts of frequent itemsets and promising frequent itemsets, i.e., infrequent itemsets that promise to be frequent in the future, in an original database. Promising frequent itemsets, which are obtained by using the principle of Bernoulli trials, can help to reduce a number of times to rescan the original database. The support counts of new candidate itemsets are approximated by using the principle of maximum possible value. The experimental results show that the execution time of the proposed algorithm is faster than that of Apriori, FUP2, EDUA, and pre-large algorithm.

Assembly system synthesis using association rule discovery

Assembly is the final process for product realization in which various parts, modules, and sub-assemblies are put together to build a product. Designing an assembly system typically involves many issues such as assembly equipment selection, assembly sequence planning, system layout, task assignments, and line balancing. Assembly system synthesis, specifically the choice of assembly resources/equipment, is examined in this paper. An association rule discovery model is employed to extract association relationships between existing and/or previous products and the systems used to assemble them. The extracted knowledge is used to synthesize assembly systems for new products that fall within the scope of their predecessors. The developed method is demonstrated using two examples from the automotive industry. System synthesis results that are consistent with the used assembly data instances are obtained in both examples. The presented systematic system synthesis method supports the utilization of existing legacy data in developing assembly systems for new product generations. This will lead to a significant reduction of time and effort needed to design assembly systems, particularly in applications that feature frequent design changes and updates, as in the automotive industry.

Obtaining optimal quality measures for quantitative association rules

There exist several works in the literature in which fitness functions based on a combination of weighted measures for the discovery of association rules have been proposed. Nevertheless, some differences in the measures used to assess the quality of association rules could be obtained according to the values of the weights of the measures included in the fitness function. Therefore, user׳s decision is very important in order to specify the weights of the measures involved in the optimization process. This paper presents a study of well-known quality measures with regard to the weights of the measures that appear in a fitness function. In particular, the fitness function of an existing evolutionary algorithm called QARGA has been considered with the purpose of suggesting the values that should be assigned to the weights, depending on the set of measures to be optimized. As initial step, several experiments have been carried out from 35 public datasets in order to show how the weights for confidence, support, amplitude and number of attributes measures included in the fitness function have an influence on different quality measures according to several minimum support thresholds. Second, statistical tests have been conducted for evaluating when the differences in measures of the rules obtained by QARGA are significative, and thus, to provide the best weights to be considered depending on the group of measures to be optimized. Finally, the results obtained when using the recommended weights for two real-world applications related to ozone and earthquakes are reported.

Using the interestingness measure lift to generate association rules

In this digital age, organizations have to deal with huge amounts of data, sometimes called Big Data. In recent years, the volume of data has increased substantially. Consequently, finding efficient and automated techniques for discovering useful patterns and relationships in the data becomes very important. In data mining, patterns and relationships can be represented in the form of association rules. Current techniques for discovering association rules rely on measures such as support for finding frequent patterns and confidence for finding association rules. A shortcoming of confidence is that it does not capture the correlation that exists between the left-hand side (LHS) and the right-hand side (RHS) of an association rule. On the other hand, the interestingness measure lift captures such as correlation in the sense that it tells us whether the LHS influences the RHS positively or negatively. Therefore, using Lift instead of confidence as a criteria for discovering association rules can be more effective. It also gives the user more choices in determining the kind of association rules to be discovered. This in turn helps to narrow down the search space and consequently, improves performance. In this paper, we describe a new approach for discovering association rules that is based on Lift and not based on confidence.

An efficient approach for mining association rules from high utility itemsets

Traditional association rule mining based on the support–confidence framework provides the objective measure of the rules that are of interest to users. However, it does not reflect the semantic measure among the items. The semantic measure of an itemset is characterized with utility values that are typically associated with transaction items, where a user will be interested to an itemset only if it satisfies a given utility constraint. In this paper, we first define the problem of finding association rules using utility-confidence framework, which is a generalization of the amount-confidence measure. Using this semantic concept of rules, we then propose a compressed representation for association rules having minimal antecedent and maximal consequent. This representation is generated with the help of high utility closed itemsets (HUCI) and their generators. We propose the algorithms to generate the utility based non-redundant association rules and methods for reconstructing all association rules. Furthermore, we describe the algorithms which generate high utility itemsets (HUI) and high utility closed itemsets with their generators. These proposed algorithms are implemented using both synthetic and real datasets. The results demonstrate better efficiency and effectiveness of the proposed HUCI-Miner algorithm compared to other well-known existing algorithms. In addition, the experimental results show better quality in the compressed representation of the entire rule set under the considered framework.

An integer programming model for discovering associations between manufacturing system capabilities and product features

Valuable implicit knowledge and patterns are accumulated over time in industrial databases at various stages of product development and production. An example of such hidden patterns would be the cutting tool which is typically used to produce a profiling feature in a given steel part. Discovering and interpreting such patterns would be useful in supporting and optimizing the operations and planning activities such as process planning and manufacturing systems synthesis. A novel knowledge discovery model is introduced to extract useful correlations between the manufacturing domain and design domain based on historical manufacturing data. An Integer Programming model is developed, for the first time, to extract association rules between sets of various product features and manufacturing capabilities used in their production. These associations identify the specific manufacturing system capabilities associated with (i.e. typically used for) the production of each product feature. The discovered knowledge is then used to synthesize the required manufacturing system capabilities for new products with new combinations of features. The proposed IP model was demonstrated using a case study of seven instances of machined parts and the corresponding milling machines used to produce them. The advantages of the proposed association rule discovery IP model were also demonstrated by comparing it with existing association rule discovery methods. The proposed model is simple and easy to implement and automate. Utilizing the proposed model in manufacturing system synthesis should greatly assist in speeding-up product development and manufacturing systems design and re-design.

The discovery of association rules in the rapid flow of data using a sliding chute window

Abstract. Window method based on the decline all set items are stored alphabetically in a tree. Each node in the tree represents a set of pens. In addition, an entry for each node keeps his collection of relevant data item. Cnt value reflects the current iteration of the model, blurred and tid specifies the number of the last transaction that contains the item has been set. Since the data distribution may change over the data flow, the sliding window method based on Only recently have shifted their attention to the data observed. Some data sets may be part of the data stream, but may be very new data entry and increasing data volume of data in another part of the same set of data with very low or even zero. For Fixing these algorithms have been introduced based on sliding windows that are turning their attention to the part of the data and the data prior to the most recent data not be exposed to fewer repetitions gradually so that the non-items become and the list of data that are evaluated in each window are deleted.

An Efficient Algorithm to Automated Discovery of Interesting Positive and Negative Association Rules

Association Rule mining is very efficient technique for finding strong relation between correlated data. The correlation of data gives meaning full extraction process. For the discovering frequent items and the mining of positive rules, a variety of algorithms are used such as Apriori algorithm and tree based algorithm. But these algorithms do not consider negation occurrence of the attribute in them and also these rules are not in infrequent form. The discovery of infrequent itemsets is far more difficult than their counterparts, that is, frequent itemsets. These problems include infrequent itemsets discovery and generation of interest negative association rules, and their huge number as compared with positive association rules. The interesting discovery of association rules is an important and active area within data mining research. In this paper, an efficient algorithm is proposed for discovering interesting positive and negative association rules from frequent and infrequent items. The experimental results show the usefulness and effectiveness of the proposed algorithm.

Feature Selection Based Hybrid Anomaly Intrusion Detection System Using K Means and RBF Kernel Function

In Information Security, intrusion detection is the act of detecting actions that attempt to compromise the security goals. One of the primary challenges to intrusion detection is the problem of misjudgment, misdetection and lack of real time response to the attack. Various data mining techniques as clustering, classification and association rule discovery are being used for intrusion detection. The proposed hybrid technique combines data mining approaches like K Means clustering algorithm and RBF kernel function of Support Vector Machine as a classification module. The main purpose of proposed technique is to decrease the number of attributes associated with each data point. So, the proposed technique can perform better in terms of Detection Rate and Accuracy when applied to KDDCUP’99 Data Set.

High performance framework for mining association rules from hierarchical data cubes

Online analytical processing OLAP is considered as a database prototype that gives a platform for the rich analysis of multidimensional data. A logical data structure known as the data cube often supports the OLAP. However, mining association rules from multidimensional data using OLAP techniques with data mining facilities is an issue of substantial complexity. In practice, the complexity is excited by the existence of dimension hierarchies that subdivide dimensions into aggregation layers of various granularity. Discovery of hierarchy-sensitive association rules can be very costly on large cubes. In this paper, we present an OLAP hierarchy-sensitive framework that supports the efficient and transparent manipulation of dimension hierarchies for extracting association rules from data cube. The experimental results show that, when compared to the alternatives, very slight overhead is required to handle streams of inter-dimensional association rules requests.

Fuzzy Association Rule Mining

The paper attempts to propose a fuzzy logic association algorithm to predict the risks involved in identifying diseases like breast cancer. Fuzzy logic algorithm is used to find association rules. The results of the study revealed that the prediction is better reliable than conventional methods.

Data Mining as Support for Customer Relationship Management: A Case Study

This article describes the data mining application to CRM - Customer Relationship Management. The article starts with an introduction showing the importance of the CRM strategy for the company, after it’s introduced the theoretical about CRM, Knowledge Discovery Database and its stages, with emphasis to the mining stage and concludes with presentation of a case study and the conclusions. For the case study it was developed a prototype of an information system of a bookstore, it was implemented, beyond the conventional functions, the association rules discovery algorithm. The implementation of the data mining technique allowed to the system supply support so that the user knows better the client, becoming possible the application of the strategy of CRM.

An evolutionary algorithm for the discovery of rare class association rules in learning management systems

Association rule mining, an important data mining technique, has been widely focused on the extraction of frequent patterns. Nevertheless, in some application domains it is interesting to discover patterns that do not frequently occur, even when they are strongly related. More specifically, this type of relation can be very appropriate in e-learning domains due to its intrinsic imbalanced nature. In these domains, the aim is to discover a small but interesting and useful set of rules that could barely be extracted by traditional algorithms founded in exhaustive search-based techniques. In this paper, we propose an evolutionary algorithm for mining rare class association rules when gathering student usage data from a Moodle system. We analyse how the use of different parameters of the algorithm determine the rule characteristics, and provides some illustrative examples of them to show their interpretability and usefulness in e-learning environments. We also compare our approach to other existing algorithms for mining both rare and frequent association rules. Finally, an analysis of the rules mined is presented, which allows information about students' unusual behaviour regarding the achievement of bad or good marks to be discovered.

A Novel Approach for Association Rule Mining using Pattern Generation

Data mining has become a process of significant interest in recent years due to explosive rate of the accumulation of data. It is used to discover potentially valuable implicit knowledge from the large transactional databases. Association rule mining is one of the well known techniques of data mining. It typically aims at discovering associations between attributes in the large databases. The first and the most influential traditional algorithm for association rule discovery is Apriori. Multiple scans of database, generation of large number of candidates item set and discovery of interesting rules are the main challenging issues for the improvement of Apriori algorithm. Therefore in order to decrease the multiple scanning of database, a new method of association rule mining using pattern generation is proposed in this paper. This method involves three steps. First, patterns are generated using items from the transaction database. Second, frequent item set is obtained using these patterns. Finally association rules are derived. The performance of this method is evaluated with the traditional Apriori algorithm. It shows that behavior of the proposed method is much more similar to Apriori algorithm with less memory space and reduction in multiple times scanning of database. Thus it is more efficient than the traditional Apriori algorithm.

Comparison of New Multilevel Association Rule Algorithm with MAFIA

Multilevel association rules provide the more precise and specific information. Apriori algorithm is an established algorithm for finding association rules. Fast Apriori implementation is modified to develop new algorithm for finding frequent item sets and mining multilevel association rules. MAFIA is another established algorithm for finding frequent item sets. In this paper, the performance of this new algorithm is analyzed and compared with MAFIA algorithm.