A Method Based on Rough Set for Mining Multi-dimensional Association Rules

Mining association rules is an important task. Past transaction data can be analyzed to discover customer purchasing behaviors such that the quality of business decision can be improved. The association rules describe the associations among items in the large database of customer transactions. However, the size of the database can be very large. It is very time consuming to find all the association rules from a large database, and users may be only interested in the associations among some items. Moreover, the criteria of the discovered rules for the user requirements may not be the same. Many uninteresting association rules for the user requirements can be generated when traditional mining methods are applied. Hence, a data mining language needs to be provided such that users can query only interesting knowledge to them from a large database of customer transactions. A data mining language is presented. From the data mining language, users can specify the interested items and the criteria of the rules to be discovered. Also, an efficient data mining technique is proposed to extract the association rules according to the users requests.

For the multidimensional inter-time association rule, the paper advanced a solution aiming at Microsoft_ association _ rules algorithm to create association rule input transaction based on sliding window, and it can solve such kind of problems: how to use some attributes' current values and changing values to predict some other attributes' changing values. Applying this method to the association rule mining on the four traffic attributes collected by the mobile switcher of some region, the experiment results proves this method's validity.

As to the problems of low data mining efficiency, less dimensionality, and low accuracy of traditional multidimensional association rules in the university big data environment, an OLAP-based multi-dimensional association rule mining method is proposed, which combines hash function and marked transaction compression technology to solve the problem of excessive or redundant candidate sets in the Apriori algorithm, and uses On Line Analytical Processing to manage the intermediate data in the association mining process , in order to reduce the time overhead caused by repeated calculations. To verify the validity of the proposed method, a learning situation analysis system is constructed in the field of colleges and universities. The multi-dimensional association rules mining method is used to analyze more than 21,000 desensitized real data, in order to mine the key factors affecting students' academic performance. The experimental results show that the proposed multi-dimensional mining model has good mining results and significantly improves the time performance.

In this paper, we describe the basic concepts of multidimensional sets and multidimensional association rules, and propose a improved algorithm of association rule mining based on multidimensional sets. This algorithm can find out the maximal frequent item sets of each dimensional subset, and at the same time pruning the database, this can substantially reduce the workload of the subsequent mining and lead to efficient processing. Appling the algorithm to students' synthesis marks evaluation system, analyzing the related factors which influence the students' synthesis marks, for educators to improve teaching methods, to improve the quality of talent training.

Background and Objectives: Brucellosis is the most common disease in humans and animals, where its distribution is roughly global, so the control of this disease has an important impact on human health and livestock industry. The most important causes of this disease are environmental parameters (location). In this regard, identifying and discovering the relationship between environmental parameters and the outbreak and incidence of the disease can be effective in controlling and providing preventive measures and thus reducing the cost of treatment for humans and animals. Material and Methods: In this research, using spatial data and multidimensional association rules, the association between the occurrence of Brucellosis with environmental and human parameters such as temperature, humidity, altitude, land use, occupation and history of contact with the livestock and use of non-pasteurized dairy has been investigated with emphasis on location. The statistical population of this study is people with brucellosis in Hamedan province in 1394. Results: The results of this study indicate that factors of location and non location included temperature, altitude, humidity, history used of non-pasteurized dairy, history of contact with infected animals sick people, job and land use, can be effective in the spread of the disease. Conclusion: The results of the study show that the factors of temperature and elevation have had more effects in the discovered laws, so that areas with higher temperatures and lower altitudes than other areas include more patients. Also, people with agricultural and livestock jobs occupy the highest rates of patients in the laws that were discovered.

An animal dynamic migration optimization method for directional association rule mining

In this paper, two concepts from different research areas are addressed together, namely functional dependency (FD) and multidimensional association rule (MAR). FD is a class of integrity constraints that have gained fundamental importance in relational database design. MAR is a class of patterns which has been studied rigorously in data mining. We employ MAR to mine the interesting rules from XML databases. The mined interesting rules are considered as candidate FDs whose all confidence itemsets are 100%. To prune the weak rules, we pay attention to support and correlation itemsets. The final strong rules are used to generate an object-role model conceptual schema diagram.

Association rules mining methods have been recently applied to gene expression data analysis to reveal relationships between genes and different conditions and features. However, not much effort has focused on detecting the relation between gene expression maps and related gene functions. Here we describe such an approach to mine association rules among gene functions in clusters of similar gene expression maps on mouse brain. The experimental results show that the detected association rules make sense biologically. By inspecting the obtained clusters and the genes having the gene functions of frequent itemsets, interesting clues were discovered that provide valuable insight to biological scientists. Moreover, discovered association rules can be potentially used to predict gene functions based on similarity of gene expression maps.

PC cluster is recently regarded as one of the most promising platforms for heavy data intensive applications, such as decision support query processing and data mining. We proposed some new parallel algorithms to mine association rule and generalized association rule with taxonomy and showed that PC cluster can handle large scale mining with them. During development of high performance parallel mining system on PC cluster, we found that heterogeneity is inevitable to take the advantage of rapid progress of PC hardware. However we can not naively apply existing parallel algorithms since they assume homogeneity. We proposed the new dynamic load balancing methods for association rule mining, which works under heterogeneous system. Two strategies, called candidate migration and transaction migration are proposed. Initially first one is invoked. When the load imbalance cannot be resolved with the first method, the second one is employed, which is costly but more effective for strong imbalance. The experimental results confirm that the proposed approach can very effectively balance the workload among heterogeneous PCs.KeywordsAssociation RuleParallel AlgorithmMinimum SupportAssociation Rule MiningExecution TraceThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Association rule mining is a data mining task on a great deal of academic research has been done and many algorithms are proposed. Association rule mining is treated as a twofold process by most of the methods. It increases the complexity of the system and takes up more time and space. Evolutionary Computation (EC) are fast growing search based optimization method for association rule mining. Among ECs particle swarm optimization (PSO) is more suited for mining association rules. The bottleneck of PSO is setting the precise values for their control parameters. Setting values to the control parameter is done either through parameter tuning or parameter control. This paper proposes an adaptive methodology for the control parameters in PSO namely, acceleration coefficients and inertia weight based on estimation of evolution state and fitness value respectively. Both of the proposed adaptive methods when tested on five datasets from University of California Irvine (UCI) repository proved to generate association rules with better accuracy and rule measures compared to simple PSO.

The Gene Ontology (GO) has become the internationally accepted standard for representing function, process, and location aspects of gene products. The wealth of GO annotation data provides a valuable source of implicit knowledge of relationships among these aspects. We describe a new method for association rule mining to discover implicit co-occurrence relationships across the GO sub-ontologies at multiple levels of abstraction. Prior work on association rule mining in the GO has concentrated on mining knowledge at a single level of abstraction and/or between terms from the same sub-ontology. We have developed a bottom-up generalization procedure called Cross-Ontology Data Mining-Level by Level (COLL) that takes into account the structure and semantics of the GO, generates generalized transactions from annotation data and mines interesting multi-level cross-ontology association rules. We applied our method on publicly available chicken and mouse GO annotation datasets and mined 5368 and 3959 multi-level cross ontology rules from the two datasets respectively. We show that our approach discovers more and higher quality association rules from the GO as evaluated by biologists in comparison to previously published methods. Biologically interesting rules discovered by our method reveal unknown and surprising knowledge about co-occurring GO terms.

Among several methods of extracting association rules that have been reported, a new evolutionary method named Genetic Network Programming (GNP) has also shown its effectiveness for dense databases. However, the conventional GNP data mining method can not find comparative relations and hidden patterns among a large amount of data. In this paper, we present a method of comparative association rules mining using Genetic Network Programming (GNP) with attributes accumulation mechanism in order to uncover comparative association rules between different datasets. GNP is an evolutionary approach recently developed, which can evolve itself and find the optimal solutions. The objective of the comparative association rules mining is to check two or more databases instead of one, so as to find the hidden relations among them. The proposed method measures the importance of association rules by using the absolute values of the confidence differences of the rules obtained from different databases and can get a number of interesting rules. Association rules obtained by comparison can help us to find and analyze the explicit and implicit patterns among a large amount of data. On the other hand, the calculation is very time-consuming, when the conventional GNP based data mining is used for the large attributes case. So, we have proposed an attributes accumulation mechanism to improve the performances. Then, the comparative association rules mining using GNP has been applied to a complicated traffic system. By mining and analyzing the rules under different traffic situations, it was found that we can get interesting information of the traffic system.

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.

In recent years, the mining technology of ″roof cutting and pressure releasing″ has appeared in China. It is called China’s third mining revolution. The technology of ″roof cutting and pressure releasing″ has changed the traditional working face ventilation system and the boundary conditions of a goaf. The law of air leakage in the goaf has changed, resulting in changes in the distributions of CO and other disaster gases. In order to ensure the promotion of this advanced mining technology safely, research on the distributions of CO and other disaster gases is very necessary. By installing CO sensors in the air intake lanes, gob-side entry retaining, and goaf, the distribution of CO in the goaf during the advancement of the working face under the ″roof cutting and pressure releasing″ mining method is studied. The concentration of CO in the upper corners of the working face under the traditional mining method and the ″roof cutting and pressure releasing″ mining method was compared and analyzed. The results show that the CO in the experimental working face mainly comes from the oxidation of the residual coal; after analysis, the CO concentration in the goaf is divided into three areas: the slowly increasing area, sharply increasing area, and attenuation area; the CO concentration in the upper corner of the working face of Y-shaped ventilation with ″roof cutting and pressure releasing″ mining is much lower than that in the upper corner of the working face of U-shaped ventilation in the traditional mining; In order to prevent the oxidation and heating of the residual coal in the goaf to produce CO, comprehensive prevention measures for CO escape in the goaf have been adopted. After actual production verification, the prevention and control measures show good effects to ensure the safe and effective production of the working face.

Association analysis of amino acids in molecular sequences can reveal crucial information and knowledge for understanding structure, function and interaction of proteins. The traditional methods of association rule mining like apriori, F-P Growth etc. fail to generate appropriate patterns due to inherent uncertainty present in data. The uncertainty in sequence data caused by variation in the length of sequences and lack of parameterization lead to under prediction and over prediction of the results. In this paper an attempt has been made to develop a soft set based approach for mining fuzzy association patterns in peptide sequences of dengue virus. The fuzzy set approach is employed to incorporate the degree of relationships among amino acids due to variation in length of the sequences. The soft set approach is employed to incorporate the relationship of parameters with amino acid association patterns. The 12,581 sequences of dengue virus are downloaded from NCBI and screened for redundancy to obtain non redundant 6995 sequences. The amino acid associations are explored and analyzed using soft fuzzy approach. Also the results obtained by soft fuzzy approach are compared with the results obtained individually by ordinary, fuzzy and soft set approaches. The soft fuzzy approach is able to overcome the issue of under prediction and over prediction of the results obtained by other approaches. Also the interesting association rules have been generated to predict the structure and physico chemical properties of the peptide sequences.