Support Threshold Research Articles

An Efficient Rigorous Approach for Identifying Statistically Significant Frequent Itemsets

As advances in technology allow for the collection, storage, and analysis of vast amounts of data, the task of screening and assessing the significance of discovered patterns is becoming a major challenge in data mining applications. In this work, we address significance in the context of frequent itemset mining. Specifically, we develop a novel methodology to identify a meaningful support threshold s * for a dataset, such that the number of itemsets with support at least s * represents a substantial deviation from what would be expected in a random dataset with the same number of transactions and the same individual item frequencies. These itemsets can then be flagged as statistically significant with a small false discovery rate. We present extensive experimental results to substantiate the effectiveness of our methodology.

Single-pass incremental and interactive mining for weighted frequent patterns

Weighted frequent pattern (WFP) mining is more practical than frequent pattern mining because it can consider different semantic significance (weight) of the items. For this reason, WFP mining becomes an important research issue in data mining and knowledge discovery. However, existing algorithms cannot be applied for incremental and interactive WFP mining and also for stream data mining because they are based on a static database and require multiple database scans. In this paper, we present two novel tree structures IWFPTWA (Incremental WFP tree based on weight ascending order) and IWFPTFD (Incremental WFP tree based on frequency descending order), and two new algorithms IWFPWA and IWFPFD for incremental and interactive WFP mining using a single database scan. They are effective for incremental and interactive mining to utilize the current tree structure and to use the previous mining results when a database is updated or a minimum support threshold is changed. IWFPWA gets advantage in candidate pattern generation by obtaining the highest weighted item in the bottom of IWFPTWA. IWFPFD ensures that any non-candidate item cannot appear before candidate items in any branch of IWFPTFD and thus speeds up the prefix tree and conditional tree creation time during mining operation. IWFPTFD also achieves the highly compact incremental tree to save memory space. To our knowledge, this is the first research work to perform single-pass incremental and interactive mining for weighted frequent patterns. Extensive performance analyses show that our tree structures and algorithms are very efficient and scalable for single-pass incremental and interactive WFP mining.

An enhanced pre-FUFP algorithm for incremental mining of association rules

Several algorithms have been developed for association rule mining which has now become an interesting field of research in the knowledge discovery domain. Discovery of association rules from large and incremental databases is one of the toughest tasks in data mining. Researchers have been motivated to design innovative and incremental algorithm for association rules mining because the quantity of data available in the real life databases are increasing at a tremendous rate. In this paper, we propose an efficient incremental mining algorithm, called enhanced pre-FUFP algorithm which extends the pre-large item set algorithm further by including the recency concept. The main aim of our proposed approach is to efficiently handle the items that are included recently in the updated database based on adaptive support threshold. At first, the FP-tree is constructed for the old database and then the transactions of incremental database are processed one at a time. After that, the association rules are mined from the updated FP-tree by incorporating an adaptive support. Experiments are performed on extensive real life datasets to compare the performance of our proposed approach with that of the pre-FUFP algorithm. The comparison results show the superiority of our enhanced pre-FUFP algorithm over other existing incremental algorithms.

Multi-level sequence mining based on gsp

Mining sequential patterns is an important problem in the field of data mining and many algorithms and optimization techniques have been published to deal with that problem. The GSP algorithm, which is one of them, can be used for mining sequential patterns with some additional constraints. In this paper, we propose a new algorithm for mining multi-level sequential patterns based on GSP. The idea is that if a more general item appears in a pattern, the pattern has higher or at least the same support as the one containing the corresponding specific item. However, too generalized sequence patterns are not important for user. In our algorithm generalization uses a selective method based on information content of patterns. This allows us to mine more patterns with the same minimal support threshold and to reveal new potentially useful patterns.

MIS-Tree Algorithm for Mining Association Rules with Multiple Minimum Supports

Mining association rules with multiple minimum supports are an important generalization of the association-rule-mining problem. Instead of setting a single minimum support threshold for all items, they allow users to specify multiple minimum supports to reflect the natures of the items, and an Apriori-based algorithm, named MSapriori, is widely used to mine all frequent itemsets. In this paper the FP-tree-like structures, MIS-tree is widely used to store the crucial information about frequent patterns. The benefit of MIS-tree is it avoids rescanning and finds the different frequent itemsets.

Class Association Rule Pada Metode Associative Classification

Frequent patterns (itemsets) discovery is an important problem in associative classification rule mining. Differents approaches have been proposed such as the Apriori-like, Frequent Pattern (FP)-growth, and Transaction Data Location (Tid)-list Intersection algorithm. This paper focuses on surveying and comparing the state of the art associative classification techniques with regards to the rule generation phase of associative classification algorithms. This phase includes frequent itemsets discovery and rules mining/extracting methods to generate the set of class association rules (CARs). There are some techniques proposed to improve the rule generation method. A technique by utilizing the concepts of discriminative power of itemsets can reduce the size of frequent itemset. It can prune the useless frequent itemsets. The closed frequent itemset concept can be utilized to compress the rules to be compact rules. This technique may reduce the size of generated rules. Other technique is in determining the support threshold value of the itemset. Specifying not single but multiple support threshold values with regard to the class label frequencies can give more appropriate support threshold value. This technique may generate more accurate rules. Alternative technique to generate rule is utilizing the vertical layout to represent dataset. This method is very effective because it only needs one scan over dataset, compare with other techniques that need multiple scan over dataset. However, one problem with these approaches is that the initial set of tid-lists may be too large to fit into main memory. It requires more sophisticated techniques to compress the tid-lists.

Transfusion Practice of Packed Red Blood Cells to Low Birth Weight Preterm Neonates in a Level-3 Neonatal Unit

Background: 65% of low-birth-weight (LBW) infants admitted to the neonatal intensive care unit (NICU) receive multiple transfusions mainly of packed red blood cells (PRBCs), supposedly steered by evidence-based guidelines. In addition to the absolute haemoglobin (Hb) level, transfusion depends on such factors as oxygen requirements, ventilation, and erythrocyte regenerative activity.Aim: Audit transfusion practice of PRBCs to infants with birth weight of ≤ 1500 grams in the Homerton Hospital NICU.Method: Retrospective analysis of the transfusion practice of RBCs in infants with birth weight of ≤ 1500 grams.Results: The higher incidence of transfusion events was in the 27-to-30 weeks' group. Transfusions were given to 47% of babies on mechanical ventilation, 22.5% on nCPAP, 12.5% self-ventilating in O2 (SVIO2), and 18% in air.The median values of Hb were higher in the MV group (128 [practice] vs 120 [guidelines] g/l), versus 103, 94, and 79 g/l in each of the other groups respectively. The median FiO2 trigger for transfusing babies on MV was 30%, but 27% for those on nCPAP, and 35% for those who are spontaneously breathing in O2.43% of babies were transfused beyond the neonatal period, followed by those transfused during the first week (18%). Numbers of transfusions per baby ranged from one in ∽29%), to > 11 in ∽10% of patients.Conclusions: We are still transfusing at higher Hb, ventilator support, and FiO2 thresholds stated by the guidelines. Clinical approach taking “symptoms” and reticulocyte count into consideration is not usually followed when deciding for PRBCs transfusions.

A Novel Efficient Classification Algorithm Based on Class Association Rules

A novel classification algorithm based on class association rules is proposed in this paper. Firstly, the algorithm mines frequent items and rules only in one phase. Then, the algorithm ranks rules that pass the support and confidence thresholds using a global sorting method according to a series of parameters, including confidence, support, antecedent cardinality, class distribution frequency, item row order and rule antecedent length. Classifier building is based on rule items that do not overlap in the training phase and rule items that each training instance is covered by only a single rule. Experimental results on the 8 datasets from UCI ML Repository show that the proposed algorithm is highly competitive when compared with the C4.5,CBA,CMAR and CPAR algorithms in terms of classification accuracy and efficiency. This algorithm can offer an available associative classification technique for data mining.

Data Stream Frequent Closed Item Sets Mining Based on Fast Sliding Window

According to the mobility and continuity of the flow of data streams，this paper presents an algorithm called NSWR to mine the frequent item sets from a fast sliding window over data streams and it meets people’s needs of getting the frequent item sets over data that recently arrive. NWSR, using an effective bit-sequence representation of items based on the data stream sliding window, helps to store data; to support different support threshold value inquiry through hash-table-based frequent closed item sets results query method; to offer screening method based on the classification of closed item sets for reducing the number of item sets that need closure judgments, effectively reducing the computational complexity. Experiments show that the algorithm has better time and space efficiency.

Mining top- k regular-frequent itemsets using database partitioning and support estimation

Temporal regularity of itemset appearance can be regarded as an important criterion for measuring the interestingness of itemsets in several applications. A frequent itemset can be said to be regular-frequent in a database if it appears at a regular period. Therefore, the problem of mining a complete set of regular-frequent itemsets requires the specification of a support and a regularity threshold. However, in practice, it is often difficult for users to provide an appropriate support threshold. In addition, the use of a support threshold tends to produce a large number of regular-frequent itemsets and it might be better to ask for the number of desired results. We thus propose an efficient algorithm for mining top- k regular- frequent itemsets without setting a support threshold. Based on database partitioning and support estimation techniques, the proposed algorithm also uses a best-first search strategy with only one database scan. We then compare our algorithm with the state-of-the-art algorithms for mining top- k regular-frequent itemsets. Our experimental studies on both synthetic and real data show that our proposal achieves high performance for small and large values of k.

CMRules: Mining sequential rules common to several sequences

Sequential rule mining is an important data mining task used in a wide range of applications. However, current algorithms for discovering sequential rules common to several sequences use very restrictive definitions of sequential rules, which make them unable to recognize that similar rules can describe a same phenomenon. This can have many undesirable effects such as (1) similar rules that are rated differently, (2) rules that are not found because they are considered uninteresting when taken individually, (3) and rules that are too specific, which makes them less likely to be used for making predictions. In this paper, we address these problems by proposing a more general form of sequential rules such that items in the antecedent and in the consequent of each rule are unordered. We propose an algorithm named CMRules for mining this form of rules. The algorithm proceeds by first finding association rules to prune the search space for items that occur jointly in many sequences. Then it eliminates association rules that do not meet the minimum confidence and support thresholds according to the sequential ordering. We evaluate the performance of CMRules in three different ways. First, we provide an analysis of its time complexity. Second, we compare its performance (in terms of execution time, memory usage and scalability) with an adaptation of an algorithm from the literature that we name CMDeo. For this comparison, we use three real-life public datasets, which have different characteristics and represent three kinds of data. In many cases, results show that CMRules is faster and has a better scalability for low support thresholds than CMDeo. Lastly, we report a successful application of the algorithm in a tutoring agent.

A Learning Theory Framework for Association Rules and Sequential Events

We present a framework and generalization analysis for the use of association rules in the setting of supervised learning. We are specifically interested in a sequential event prediction problem where data are revealed one by one, and the goal is to determine what will next be revealed. In the context of this problem, algorithms based on association rules have a distinct advantage over classical statistical and machine learning methods; however, to our knowledge there has not previously been a theoretical foundation established for using association rules in supervised learning. We present two simple algorithms that incorporate association rules. These algorithms can be used both for sequential event prediction and for supervised classification. We provide generalization guarantees on these algorithms based on algorithmic stability analysis from statistical learning theory. We include a discussion of the strict minimum support threshold often used in association rule mining, and introduce an adjusted confidence measure that provides a weaker minimum support condition that has advantages over the strict minimum support. The paper brings together ideas from statistical learning theory, association rule mining and Bayesian analysis.

Temporal data mining with up-to-date pattern trees

Mining interesting and useful frequent patterns from large databases attracts much attention in recent years. Among the mining approaches, finding temporal patterns and regularities is very important due to its practicality. In the past, Hong et al. proposed the up-to-date patterns, which were frequent within their up-to-date lifetime. Formally, an up-to-date pattern is a pair with the itemset and its valid corresponding lifetime in which the user-defined minimum support threshold must be satisfied. They also proposed an Apriori-like approach to find the up-to-date patterns. This paper thus proposes the up-to-date pattern tree (UDP tree) to keep the up-to-date 1-patterns in a tree structure for reducing database scan. It is similar to the FP-tree structure but more complex due to the requirement of up-to-date patterns. The UDP-growth mining approach is also designed to find the up-to-date patterns from the UDP tree. The experimental results show that the proposed approach has a better performance than the level-wise mining algorithm.

Design and behavior study of a grammar-guided genetic programming algorithm for mining association rules

This paper presents a proposal for the extraction of association rules called G3PARM (Grammar-Guided Genetic Programming for Association Rule Mining) that makes the knowledge extracted more expressive and flexible. This algorithm allows a context-free grammar to be adapted and applied to each specific problem or domain and eliminates the problems raised by discretization. This proposal keeps the best individuals (those that exceed a certain threshold of support and confidence) obtained with the passing of generations in an auxiliary population of fixed size n. G3PARM obtains solutions within specified time limits and does not require the large amounts of memory that the exhaustive search algorithms in the field of association rules do. Our approach is compared to exhaustive search (Apriori and FP-Growth) and genetic (QuantMiner and ARMGA) algorithms for mining association rules and performs an analysis of the mined rules. Finally, a series of experiments serve to contrast the scalability of our algorithm. The proposal obtains a small set of rules with high support and confidence, over 90 and 99% respectively. Moreover, the resulting set of rules closely satisfies all the dataset instances. These results illustrate that our proposal is highly promising for the discovery of association rules in different types of datasets.

New and efficient knowledge discovery of partial periodic patterns with multiple minimum supports

The problem of mining partial periodic patterns is an important issue with many applications. Previous studies to find these patterns encounter efficiency and effectiveness problem. The efficiency problem is that most previous methods were proposed to find frequent partial periodic patterns by extending the well-known Apriori-like algorithm. However, these methods generate many candidate partial periodic patterns to calculate the patterns’ supports, spending much time for discovering patterns. The effective problem is that only one minimum support threshold is set to find frequent partial periodic patterns but the results is not practical for real-world. In real-life circumstances, some rare or specific events may occur with lower frequencies but their occurrences may offer some vital information to be referred in decision making. If the minimum support is set too high, the associations between events along with higher and lower frequencies cannot be evaluated so that significant knowledge will be ignored. In this study, an algorithm to overcome these two problems has been proposed to generating redundant candidate patterns and setting only one minimum support threshold. The algorithm greatly improves the efficiency and effectiveness. First, it eliminates the need to generate numerous candidate partial periodic patterns thus reducing database scanning. Second, the minimum support threshold of each event can be specified based in its real-life occurring frequency.

Efficient prime-based method for interactive mining of frequent patterns

Over the past decade, an increasing number of efficient algorithms have been proposed to mine frequent patterns by satisfying the minimum support threshold. Generally, determining an appropriate value for minimum support threshold is extremely difficult. This is because the appropriate value depends on the type of application and expectation of the user. Moreover, in some real-time applications such as web mining and e-business, finding new correlations between patterns by changing the minimum support threshold is needed. Since rerunning mining algorithms from scratch is very costly and time-consuming, researchers have introduced interactive mining of frequent patterns. Recently, a few efficient interactive mining algorithms have been proposed, which are able to capture the content of transaction database to eliminate possibility of the database rescanning. In this paper, we propose a new method based on prime number and its characteristics mainly for interactive mining of frequent patterns. Our method isolates the mining model from the mining process such that once the mining model is constructed; it can be frequently used by mining process with various minimum support thresholds. During the mining process, the mining algorithm reduces the number of candidate patterns and comparisons by using a new candidate set called candidate head set and several efficient pruning techniques. The experimental results verify the efficiency of our method for interactive mining of frequent patterns.

Mining Rare Itemset with Automated Support Thresholds

Problem statement: Frequent itemset mining is an important task in data mining to discover the hidden, interesting associations between items in the database based on the user-specified support and confidence thresholds. Approach: In order to find important associations, an appropriate support threshold has to be specified. The support threshold plays a key role in deciding the interesting itemsets. The rare itemsets may not found if a high threshold is set. Some uninteresting itemsets may appear if a low threshold is set. Results: This study proposes an approach to obtain the frequent itemsets involving rare items by setting the support thresholds automatically. Experimental results show that this approach produces rare and frequent itemsets in sparse and dense datasets. According to T20I6D100K, 97.76% of the FIs are generators wherein Mushrooms 1.38% of the FIs are the generators. Conclusion: The proposed algorithm produces both frequent and rare itemsets in an effective way. In future, computational efforts can still be reduced by implementing the algorithm as parallel algorithm.

Mining top−k frequent patterns without minimum support threshold

Finding frequent patterns play an important role in mining association rules, sequences, episodes, Web log mining and many other interesting relationships among data. Frequent pattern mining methods often produce a huge number of frequent itemsets that is not feasible for effective usage. The number of highly correlated patterns is usually very small and may even be one. Most of the existing frequent pattern mining techniques often require the setting of many input parameters and may involve multiple passes over the database. Minimum support is the widely used parameter in frequent pattern mining to discover statistically significant patterns. Specifying appropriate minimum support is a challenging task for a data analyst as the choice of minimum support value is somewhat arbitrary. Generally, it is required to repeatedly execute an algorithm, heuristically tuning the value of minimum support over a wide range, until the desired result is obtained, certainly, a very time-consuming process. Setting up an inappropriate minimum support may also cause an algorithm to fail in finding the true patterns. We present a novel method to efficiently retrieve top few maximal frequent patterns in order of significance without use of the minimum support parameter. Instead, we are only required to specify a more human understandable parameter, namely the desired number itemsets k. Our technique requires only a single pass over the database and generation of length two itemsets. The association ratio graph is proposed as a compact structure containing concise information, which is created in time quadratic to the size of the database. Algorithms are described for using this graph structure to discover top-most and top-k maximal frequent itemsets without minimum support threshold. To effectively achieve this, the method employs construction of an all path source-to-destination tree to discover all maximal cycles in the graph. The results can be ranked in decreasing order of significance. Results are presented demonstrating the performance advantages to be gained from the use of this approach.

A parallel, distributed algorithm for relational frequent pattern discovery from very large data sets

The amount of data produced by ubiquitous computing applications is quickly growing, due to the pervasive presence of small devices endowed with sensing, computing and communication capabilities. Heterogeneity and strong interdependence, which characterize 'ubiquitous data', require a (multi-)relational approach to their analysis. However, relational data mining algorithms do not scale well and very large data sets are hardly processable. In this paper we propose an extension of a relational algorithm for multi-level frequent pattern discovery, which resorts to data sampling and distributed computation in Grid environments, in order to overcome the computational limits of the original serial algorithm. The set of patterns discovered by the new algorithm approximates the set of exact solutions found by the serial algorithm. The quality of approximation depends on three parameters: the proportion of data in each sample, the minimum support thresholds and the number of samples in which a pattern has to be frequent in order to be considered globally frequent. Considering that the first two parameters are hardly controllable, we focus our investigation on the third one. Theoretically derived conclusions are also experimentally confirmed. Moreover, an additional application in the context of event log mining proves the viability of the proposed approach to relational frequent pattern mining from very large data sets.

Mop: An Efficient Algorithm for Mining Frequent Pattern with Subtree Traversing

Mining frequent patterns in database has emerged as an important task in knowledge discovery and data mining. In this paper, we present an efficient algorithm called Mop for fast frequent pattern discovery. Mop utilizes a new kind of data structure called OP_tree (ordered pattern tree) and some particular properties of frequent patterns to facilitate the process of mining frequent patterns. An OP_tree is a special frequent pattern tree, where the children of any node are sorted according to the supports of corresponding items. Efficiency of Mop is achieved with three techniques: (1) it adopts OP_tree to store a large database to avoid repetitive database scans, (2) it finds all frequent 2-patterns in the construction of OP_tree to avoid the costly generation of a large number of candidate 2-patterns, (3) the supports of candidate k-patterns (k>2) can be obtained by traversing a few of specific subtrees of the OP_tree, which greatly reduces the search space and avoid multi-scans of a database. We experimentally compare our algorithm with the Apriori algorithm and the FP-growth algorithm on one real database and one synthetical database. The experimental results show that Mop is about an order of magnitude faster than the Apriori algorithm. Mop also outperforms the FP-growth algorithm, especially when support threshold is very low and databases are quite large.