Number Of Frequent Itemsets Research Articles

Construction of Innovative Working Mode of College Counselors Based on Data Mining Technology

Data mining technology can analyze and mine university management data, provide more data support for university management, and play an important role in optimizing teaching quality, but these technologies are rarely applied to the work of university counselors. Based on this, this paper studies the construction and research of college counselors’ innovative work mode based on data mining technology. Based on the simple analysis of the impact of big data on the traditional working mode of counselors, this paper introduces the application of data mining commonly used in colleges and universities and puts forward the existing shortcomings. The innovative working mode of college counselors is designed. In the analysis of students’ daily behavior, the advantages of cluster analysis and support vector machine are used to analyze students’ consumption behavior. The Apriori algorithm is applied to the student achievement early warning management to improve the Apriori algorithm. Simulation results show that the proposed algorithm can shorten the running time, reduce the number of frequent item sets, and improve the classification accuracy.

Reference itemsets: useful itemsets to approximate the representation of frequent itemsets

Deriving frequent itemsets from databases is an important research issue in data mining. The number of frequent itemsets may be unusually large when a low minimum support threshold is given. As such, the design of a compact representation to compress and describe them is an interesting topic. In the past, most related research on compact representation focused on frequent closed itemsets and frequent maximal itemsets. The former is a lossless compact technology that can totally recover all frequent itemsets and their frequencies. Contrarily, the latter may lose some information regarding frequent itemsets, because it reserves frequent itemsets only and is unable to identify their frequency. In this paper, we propose a new compact representation that lies between closed itemsets and maximal itemsets. It can reserve all frequent itemsets and identify their approximate frequency. In addition, an efficient algorithm that corresponds to this new concept is designed to find related key information in databases. Finally, a series of experiments are conducted to show the effectiveness of compact representation and the performance of the proposed algorithm.

RANWAR: rank-based weighted association rule mining from gene expression and methylation data.

Ranking of association rules is currently an interesting topic in data mining and bioinformatics. The huge number of evolved rules of items (or, genes) by association rule mining (ARM) algorithms makes confusion to the decision maker. In this article, we propose a weighted rule-mining technique (say, RANWAR or rank-based weighted association rule-mining) to rank the rules using two novel rule-interestingness measures, viz., rank-based weighted condensed support (wcs) and weighted condensed confidence (wcc) measures to bypass the problem. These measures are basically depended on the rank of items (genes). Using the rank, we assign weight to each item. RANWAR generates much less number of frequent itemsets than the state-of-the-art association rule mining algorithms. Thus, it saves time of execution of the algorithm. We run RANWAR on gene expression and methylation datasets. The genes of the top rules are biologically validated by Gene Ontologies (GOs) and KEGG pathway analyses. Many top ranked rules extracted from RANWAR that hold poor ranks in traditional Apriori, are highly biologically significant to the related diseases. Finally, the top rules evolved from RANWAR, that are not in Apriori, are reported.

An Optimized Apriori Algorithm Based on Sparse Matrix for Intrusion Detection

The original Apriori algorithm is widely used in the intrusion detection field, but it may consume incredible computing resources in the process of handling network packets. We propose our optimized-Apriori algorithm which can greatly improves the algorithm efficiency by means of reducing the data storage space and the number of frequent item sets. We take full advantage of the characteristics of sparse matrix to save storage space and shorten the running time. The experimental results show that our optimized-Apriori algorithm can make a larger progress in saving the storage space of network data to be processed, even shortening nearly half of the data mining time in the process of intrusion detection.

An Efficient and Accurate Discovery of Frequent Patterns Using Improved WARM to Handle Large Web Log Data

In the booming era of Internet, web search is inevitable to everyone. In web search, mining frequent pattern is a challenging one, particularly when handling tera byte size databases. Finding solution for these issues have primarily started attracting the key researchers. Due to high the demand in finding the best search methods, it is very important and interesting to predict the user's next request. The number of frequent item sets and the database scanning time should be reduced for fast generating frequent pattern mining. It fulfills user's accurate need in a magic of time and offers a customized navigation. Association Rule mining plays key role in discovering associated web pages and many researchers are using Apriori algorithm with binary representation in this area. But it does not provide best solution for finding navigation order of web pages. To overcome this, weighted Apriori was introduced. But still, it is difficult to produce most favorable results especially in large databases. In the effort of finding best solution, the authors have proposed a novel approach which combines weighted Apriori and dynamic programming. The conducted experiments so far, shows' better tracking of maintaining navigation order and gives the confidence of making the best possible results. The proposed approach enriches the web site effectiveness, raises the knowledge in surfing, ensures prediction accuracies and achieves less complexity in computing with very large databases.

Application of Incremental Mining and Apriori Algorithm on Library Transactional Database

Data mining is used to extract hidden, predictive information from large databases, which can be used for predicting future trends and allowing businesses to make knowledge- driven decisions [1].In this paper we explain how Apriori algorithm can be applied on the university’s library transactional database in order to find out the frequent book items and generate rules on these book items so as to predict the book borrowing behavior of the students. It then explains how incremental mining when incorporated by adding five more transactions to the original set of ten transactions changes the number of frequent item-sets and association rules generated by the algorithm.

A Bitmap Approach for Closed and Maximal Frequent Itemset Mining

Association Rule Mining (ARM) plays a fundamental role in many data mining tasks that attempt to find interesting patterns from databases, such as correlations, sequences, episodes, classifiers, clusters, etc. Frequent Itemset Mining (FIM) is one of the essential parts of ARM which is an active research area and a large number of algorithms have been developed. FIM algorithms may be depth-first or breadth-first approach. Most depth-first based approaches do not effectively address the cost of database projections. Consequently, their performance gets degraded severely as the total number of frequent itemsets in a database increases significantly. To solve this problem, a three - strategy adaptive algorithm, Bitmap Itemset Support Counting (BISC) with the closed and maximal frequent itemset is presented in this paper. The core strategy of the proposed algorithm is the usage of the closed and maximal frequent itemset detection which could be able to find least number of association rules. The proposed approach is compared with the conventional approach to evaluate the performance and accuracy. The experimental results show that the proposed approach outperforms the existing approach. Keywords: Data Mining Algorithms; Bitmap; Frequent Itemset Mining; Association Rule Mining.

The Association Rules Updating Algorithm Based on Reverse Search

This paper analyzed the existing association rules update algorithm IUA, found out that when the decision makers gave priority attention to the situation of maximum frequent itemsets, this algorithm cannot lower the cost of the database traversal to quickly access to the largest number of frequent itemsets. For the lack of the algorithm, an algorithm which is based on reverse search approach to update association rules is presented. The updating algorithm based on reverse search first generated all frequent itemsets of new itemsets. Then, it spliced the new largest frequent itemsets and original largest frequent itemsets for trimming, get the updated maximal frequent itemsets. This algorithm not only reduces the traversal times in the process of association rules updating, but also realized the priority access to the largest operation of frequent itemsets.

Krimp: mining itemsets that compress

One of the major problems in pattern mining is the explosion of the number of results. Tight constraints reveal only common knowledge, while loose constraints lead to an explosion in the number of returned patterns. This is caused by large groups of patterns essentially describing the same set of transactions. In this paper we approach this problem using the MDL principle: the best set of patterns is that set that compresses the database best. For this task we introduce the Krimp algorithm. Experimental evaluation shows that typically only hundreds of itemsets are returned; a dramatic reduction, up to seven orders of magnitude, in the number of frequent item sets. These selections, called code tables, are of high quality. This is shown with compression ratios, swap-randomisation, and the accuracies of the code table-based Krimp classifier, all obtained on a wide range of datasets. Further, we extensively evaluate the heuristic choices made in the design of the algorithm.

EstMax: Tracing Maximal Frequent Item Sets Instantly over Online Transactional Data Streams

Frequent item set mining is one of the most challenging issues for descriptive data mining. In general, its resulting set tends to produce a large number of frequent item sets. To represent them in a more compact notation, closed or maximal frequent item sets are often used but finding such item sets over online transactional data streams is not easy due to the requirements of a data stream. For this purpose, this paper proposes a method of tracing the set of MFIs instantly over an online data stream. The method, namely estMax, maintains the set of frequent item sets by a prefix tree and extracts all MFIs without any additional superset/subset checking mechanism. Upon processing a new transaction, those frequent item sets that are matched maximally by the transaction are newly marked in their corresponding nodes of the prefix tree as candidates for MFIs. At the same time, if any subset of a newly marked item set has been already marked as a candidate MFI by a previous transaction, it is cleared as well. By employing this additional step, it is possible to extract the set of MFIs at any moment. The performance of the estMax method is comparatively analyzed by a series of experiments to identify its various characteristics.

MINING ESSENTIAL RULES USING FREQUENT CLOSED ITEMSETS LATTICE

In traditional mining of association rules, finding all association rules from databases that satisfy minSup and minConf faces with some problems in case of the number of frequent itemsets is large. Thus, it is necessary to have a suitable method for mining fewer rules but they still embrace all rules of traditional mining method. One of the approaches that is the mining method of essential rules: it only keeps the rule that its left hand side is minimal and its right side is maximal (follow in parent-child relationship). In this paper, we propose a new algorithm for mining the essential rules from the frequent closed itemsets lattice to reduce the time of mining rules. We use the parent-child relationship in lattice to reduce the cost of considering parent-child relationship and lead to reduce the time of mining rules.

A framework for incremental generation of closed itemsets

Association rule mining from a transaction database (TDB) requires the detection of frequently occurring patterns, called frequent itemsets ( FIs), whereby the number of FIs may be potentially huge. Recent approaches for FI mining use the closed itemset paradigm to limit the mining effort to a subset of the entire FI family, the frequent closed itemsets ( FCIs). We show here how FCIs can be mined incrementally yet efficiently whenever a new transaction is added to a database whose mining results are available. Our approach for mining FIs in dynamic databases relies on recent results about lattice incremental restructuring and lattice construction. The fundamentals of the incremental FCI mining task are discussed and its reduction to the problem of lattice update, via the CI family, is made explicit. The related structural results underlie two algorithms for updating the set of FCIs of a given TDB upon the insertion of a new transaction. A straightforward method searches for necessary completions throughout the entire CI family, whereas a second method exploits lattice properties to limit the search to CIs which share at least one item with the new transaction. Efficient implementations of the parsimonious method is discussed in the paper together with a set of results from a preliminary study of the method's practical performances.

Dataless Transitions Between Concise Representations of Frequent Patterns

For many data mining problems in order to solve them it is required to discover frequent patterns. Frequent itemsets are useful e.g. in the discovery of association and episode rules, sequential patterns and clusters. Nevertheless, the number of frequent itemsets is usually huge. Therefore, a number of lossless representations of frequent itemsets have recently been proposed. Two of such representations, namely the closed itemsets and the generators representation, are of particular interest as they can efficiently be applied for the discovery of most interesting non-redundant association and episode rules. On the other hand, it has been proved experimentally that other representations of frequent patterns happen to be more concise and more quickly extractable than these two representations even by several orders of magnitude. Hence, such concise representations seem to be an interesting alternative for materializing and reusing the knowledge of frequent patterns. The problem however arises, how to transform the intermediate representations into the desired ones efficiently and preferably without accessing the database. This article tackles this problem. As a result of investigating the properties of representations of frequent patterns, we offer a set of efficient algorithms for dataless transitioning between them.

Parametric Algorithms for Mining Share Frequent Itemsets

Itemset share, the fraction of some numerical total contributed by items when they occur in itemsets, has been proposed as a measure of the importance of itemsets in association rule mining. The IAB and CAC algorithms are able to find share frequent itemsets that have infrequent subsets. These algorithms perform well, but they do not always find all possible share frequent itemsets. In this paper, we describe the incorporation of a threshold factor into these algorithms. The threshold factor can be used to increase the number of frequent itemsets found at a cost of an increase in the number of infrequent itemsets examined. The modified algorithms are tested on a large commercial database. Their behavior is examined using principles of classifier evaluation from machine learning.