Emerging Pattern Mining Research Articles

A distributed evolutionary fuzzy system-based method for the fusion of descriptive emerging patterns in data streams

Nowadays the amount of networks of devices and sensors, such as smart homes or smart cities, is rapidly increasing. Each of these devices generates massive amounts of data on a continuous basis where an interpretable description of its state is interesting for the experts. This knowledge can be extracted by means of emerging pattern mining techniques. In fact, it can be extracted locally on each device and joined together afterwards in order to obtain a global vision of the system without transferring any data. However, the traditional massive data processing frameworks are focused on the extraction of this global model, which produces huge amounts of data transfers throughout the network.This paper proposes a distributed method based on evolutionary fuzzy systems for both the extraction and subsequent fusion of descriptive emerging patterns in data streams from different sources of the same kind. First, an evolutionary algorithm following an informed approach for efficient data processing is presented for the extraction of emerging patterns on the data stream generated by each device, in order to obtain a local model for each stream. Then, several fusion methods are proposed for the aggregation of these patterns in order to extract the global model. A wide experimental study has been carried out to analyse the suitability of the evolutionary algorithm for the extraction of high-quality emerging patterns and its capacity to deal with concept drift. Finally, the quality of the proposed fusion methods is also analysed.

High average-utility itemset mining with multiple minimum utility threshold: A generalized approach

High Average-Utility Itemset (HAUI) mining is an emerging pattern mining technique to extract meaningful patterns from a transaction dataset. In the past, several HAUI mining algorithms have been developed with efficient upper-bounds and pruning strategies. However, all these algorithms use a single value of the minimum average-utility threshold for all the itemsets, which limits their applicability to real-life datasets. In order to address this issue, several HAUI mining algorithms with multiple average-utility thresholds have been developed that process the items in ascending order of their minimum average-utility threshold. However, it makes them inapplicable on traditional HAUI mining algorithms. Moreover, the perturbation in preference of items may reduce the performance of the algorithms. This paper presents an HAUI mining algorithm named Generalized High Average-utility Itemset Miner (GHAIM) that processes the items in ascending order of their Average Utility Upper-Bound (AUUB) like the traditional HAUI mining algorithms. A new approach named suffix minimum average-utility is proposed to retain the downward closure property of AUUB and several pruning methods. Besides, a compact list structure is also proposed to mine the HAUIs in one phase. Several pruning methods have been introduced for reducing search space and improving efficiency. Extensive experiments were performed with different sparse and dense types of datasets to determine GHAIM efficiency compared to two existing algorithms. It was observed from the results that GHAIM outperforms both the current algorithms in run time, memory consumption, number of candidate itemsets, and scalability.

Study on the use of different quality measures within a multi-objective evolutionary algorithm approach for emerging pattern mining in big data environments

BackgroundEmerging pattern mining is a data mining task that extracts rules describing discriminative relationships amongst variables. These rules should be understandable for the experts. Comprehensibility of a rule is traditionally determined by several objectives, which can be calculated by different measures. In this way, multi-objective evolutionary algorithms are suitable for this task. Currently, the growing amount of data makes traditional data mining tasks unable to process them in a reasonable time. These huge amounts of data make even more interesting the extraction of rules that can easily describe the underlying phenomena of this big data. So far there is only one algorithm for emerging pattern mining developed based on multi-objective evolutionary algorithms for big data, the BD-EFEP algorithm. The influence of the selection of different quality measures as objectives in the search process is analysed in this paper.ResultsThe results show that the use of the combination based on Jaccard index and false positive rate is the one with the best trade-off for descriptive induction of emerging patterns.ConclusionsIt is recommended the use of this combination of quality measure as optimisation objectives in future multi-objective evolutionary algorithm developments for emerging pattern mining focused in big data.

A Big Data Approach for the Extraction of Fuzzy Emerging Patterns

Nowadays, the growth of available data, known as big data, and machine learning techniques are changing our lives. The extraction of insights related to the underlying phenomena in data is key in order to improve decision-making processes. These underlying phenomena are described in emerging pattern mining by means of the description of the discriminative characteristics between the outputs of interest, which is a very important characteristic in machine learning. However, emerging pattern mining algorithms for big data environments have not been widely developed yet. This paper presents the first multi-objective evolutionary algorithm for emerging pattern mining in big data environments called BD-EFEP. BD-EFEP implements novelties for emerging pattern mining such as the MapReduce approach to improve the efficiency of the evaluation of the individuals, or the use of a token-competition-based procedure in order to boost the extraction of simple, general and reliable emerging pattern models. The experimental study performed using datasets with high number of examples shows the advantages of the algorithm proposed for the emerging pattern mining task in big data problems. Results show that the approach used by BD-EFEP opens new research lines for the extraction of high descriptive emerging patterns in big data environments.

MOEA-EFEP: Multi-Objective Evolutionary Algorithm for Extracting Fuzzy Emerging Patterns

Emerging pattern mining is a data mining task that belongs to the supervized descriptive rule discovery framework. Its objective is to find rules that describe emerging behavior or differentiating characteristics with respect to a property of interest. A multiobjective evolutionary algorithm for the extraction of fuzzy emerging patterns (MOEA-EFEP) is described and analyzed in this paper. MOEA-EFEP is the first multi-objective evolutionary algorithm proposed for emerging pattern mining. This approach allows us to get rules whose descriptions of the emerging phenomena are simpler than previous approaches. It is based on the well-known NSGA-II algorithm adapted for the extraction of emerging patterns. The proposal also uses fuzzy logic to deal with numeric variables in order to obtain a knowledge representation close to human reasoning. An experimental study was performed to verify the validity of the proposal. First, it presents a comparison of different rule representations and postprocessing filter strategies, in order to determine an optimal configuration of the proposal. Finally, it is compared with other algorithms for emerging pattern mining in order to determine the quality of the knowledge extracted. The results show that MOEA-EFEP obtains rules with a better description of the emerging or discriminative behavior than other algorithms of the task. The conclusions of this study are supported by the use of statistical tests.

An overview of emerging pattern mining in supervised descriptive rule discovery: taxonomy, empirical study, trends, and prospects

Emerging pattern mining is a data mining task that aims to discover discriminative patterns, which can describe emerging behavior with respect to a property of interest. In recent years, the description of datasets has become an interesting field due to the easy acquisition of knowledge by the experts. In this review, we will focus on the descriptive point of view of the task. We collect the existing approaches that have been proposed in the literature and group them together in a taxonomy in order to obtain a general vision of the task. A complete empirical study demonstrates the suitability of the approaches presented. This review also presents future trends and emerging prospects within pattern mining and the benefits of knowledge extracted from emerging patterns. WIREs Data Mining Knowl Discov 2018, 8:e1231. doi: 10.1002/widm.1231This article is categorized under: Fundamental Concepts of Data and Knowledge > Knowledge Representation Fundamental Concepts of Data and Knowledge > Motivation and Emergence of Data Mining

A Computational Selection of Metabolite Biomarkers Using Emerging Pattern Mining: A Case Study in Human Hepatocellular Carcinoma.

The biomarker development in metabolomics aims at discriminating diseased from normal subjects and at creating a predictive model that can be used to diagnose new subjects. From a case study on human hepatocellular carcinoma (HCC), we studied for the first time the potential usefulness of the emerging patterns (EPs) that come from the data mining domain. When applied to a metabolomics data set labeled with two classes (e.g., HCC patients vs healthy subjects), EP mining can capture differentiating combinations of metabolites between the two classes. We observed that the so-called jumping emerging patterns (JEPs), which correspond to the combinations of metabolites that occur in only one of the two classes, achieved better performance than individual biomarkers. Particularly, the implementation of the JEPs in a rules-based diagnostic tool drastically reduced the false positive rate, i.e., the rate of healthy subjects predicted as HCC patients.

Distributed Maximal Clique Computation and Management

Maximal cliques are elementary substructures in a graph and instrumental in graph analysis such as the structural analysis of many complex networks, graph clustering and community detection, network hierarchy detection, emerging pattern mining, vertex importance measures, etc. However, the number of maximal cliques is also notoriously large even for many small real world graphs. This size problem gives rise to challenges in both computing and managing the set of maximal cliques. Many algorithms for computing maximal cliques have been proposed in the literature; however, most of them are sequential algorithms that cannot scale due to the high complexity of the problem, while existing parallel algorithms for computing maximal cliques are mostly immature and especially suffer from skewed workload. As for managing the set of maximal cliques, which is essential due to its large size, there is barely any efficient method for querying or updating the set of maximal cliques. In this paper, we first propose a distributed algorithm built on a share-nothing architecture for computing the set of maximal cliques. We effectively address the problem of skewed workload distribution due to high-degree vertices, which also leads to drastically reduced worst-case time complexity for computing maximal cliques in common real-world graphs. Then, we propose a set of fundamental query operations and efficient algorithms to process the queries, to aid more efficient and effective analysis of the set of maximal cliques. Finally, we also devise algorithms to support efficient update maintenance of the set of maximal cliques when the underlying graph is updated. We verify the efficiency of our algorithms for computing, querying, and updating the set of maximal cliques with a range of real-world graphs from different application domains.

Perspectives on Knowledge Discovery Algorithms Recently Introduced in Chemoinformatics: Rough Set Theory, Association Rule Mining, Emerging Patterns, and Formal Concept Analysis.

Knowledge Discovery in Databases (KDD) refers to the use of methodologies from machine learning, pattern recognition, statistics, and other fields to extract knowledge from large collections of data, where the knowledge is not explicitly available as part of the database structure. In this paper, we describe four modern data mining techniques, Rough Set Theory (RST), Association Rule Mining (ARM), Emerging Pattern Mining (EP), and Formal Concept Analysis (FCA), and we have attempted to give an exhaustive list of their chemoinformatics applications. One of the main strengths of these methods is their descriptive ability. When used to derive rules, for example, in structure-activity relationships, the rules have clear physical meaning. This review has shown that there are close relationships between the methods. Often apparent differences lie in the way in which the problem under investigation has been formulated which can lead to the natural adoption of one or other method. For example, the idea of a structural alert, as a structure which is present in toxic and absent in nontoxic compounds, leads to the natural formulation of an Emerging Pattern search. Despite the similarities between the methods, each has its strengths. RST is useful for dealing with uncertain and noisy data. Its main chemoinformatics applications so far have been in feature extraction and feature reduction, the latter often as input to another data mining method, such as an Support Vector Machine (SVM). ARM has mostly been used for frequent subgraph mining. EP and FCA have both been used to mine both structural and nonstructural patterns for classification of both active and inactive molecules. Since their introduction in the 1980s and 1990s, RST, ARM, EP, and FCA have found wide-ranging applications, with many thousands of citations in Web of Science, but their adoption by the chemoinformatics community has been relatively slow. Advances, both in computer power and in algorithm development, mean that there is the potential to apply these techniques to larger data sets and thus to different problems in the future.

New structural alerts for Ames mutagenicity discovered using emerging pattern mining techniques

The discovered patterns are used to develop new structural alerts for mutagenicity in the Derek Nexus expert system.

Identifying emerging hotel preferences using Emerging Pattern Mining technique

Hotel managers continue to find ways to understand traveler preferences, with the aim of improving their strategic planning, marketing, and product development. Traveler preference is unpredictable; for example, hotel guests used to prefer having a telephone in the room, but now favor fast Internet connection. Changes in preference influence the performance of hotel businesses, thus creating the need to identify and address the demands of their guests. Most existing studies focus on current demand attributes and not on emerging ones. Thus, hotel managers may find it difficult to make appropriate decisions in response to changes in travelers' concerns. To address these challenges, this paper adopts Emerging Pattern Mining technique to identify emergent hotel features of interest to international travelers. Data are derived from 118,000 records of online reviews. The methods and findings can help hotel managers gain insights into travelers' interests, enabling the former to gain a better understanding of the rapid changes in tourist preferences.

Emerging pattern mining to aid toxicological knowledge discovery.

Knowledge-based systems for toxicity prediction are typically based on rules, known as structural alerts, that describe relationships between structural features and different toxic effects. The identification of structural features associated with toxicological activity can be a time-consuming process and often requires significant input from domain experts. Here, we describe an emerging pattern mining method for the automated identification of activating structural features in toxicity data sets that is designed to help expedite the process of alert development. We apply the contrast pattern tree mining algorithm to generate a set of emerging patterns of structural fragment descriptors. Using the emerging patterns it is possible to form hierarchical clusters of compounds that are defined by the presence of common structural features and represent distinct chemical classes. The method has been tested on a large public in vitro mutagenicity data set and a public hERG channel inhibition data set and is shown to be effective at identifying common toxic features and recognizable classes of toxicants. We also describe how knowledge developers can use emerging patterns to improve the specificity and sensitivity of an existing expert system.

Bridging Causal Relevance and Pattern Discriminability: Mining Emerging Patterns from High-Dimensional Data

It is a nontrivial task to build an accurate emerging pattern (EP) classifier from high-dimensional data because we inevitably face two challenges 1) how to efficiently extract a minimal set of strongly predictive EPs from an explosive number of candidate patterns, and 2) how to handle the highly sensitive choice of the minimal support threshold. To address these two challenges, we bridge causal relevance and EP discriminability (the predictive ability of emerging patterns) to facilitate EP mining and propose a new framework of mining EPs from high-dimensional data. In this framework, we study the relationships between causal relevance in a causal Bayesian network and EP discriminability in EP mining, and then reduce the pattern space of EP mining to direct causes and direct effects, or the Markov blanket (MB) of the class attribute in a causal Bayesian network. The proposed framework is instantiated by two EPs-based classifiers, CE-EP and MB-EP, where CE stands for direct Causes and direct Effects, and MB for Markov Blanket. Extensive experiments on a broad range of data sets validate the effectiveness of the CE-EP and MB-EP classifiers against other well-established methods, in terms of predictive accuracy, pattern numbers, running time, and sensitivity analysis.

Toxicological knowledge discovery by mining emerging patterns from toxicity data

Predicting the risk of toxic and environmental effects of chemical compounds is of great importance to all chemical industries [1]. Expert systems have shown success in predicting toxic risk by applying established knowledge of toxicology encoded as a knowledge base of structural alerts and a reasoning model. A disadvantage of expert systems is that developing new structural alerts requires considerable time and effort from domain experts. In order to expedite this process a software tool has been developed that can automatically mine representations of activating features directly from toxicity datasets and present them in an interpretable form. Our knowledge discovery tool applies emerging pattern (EP) mining [2]: a form of association rule mining [3] that is well known to computer science, but is relatively new to chemistry [4]. The EP mining algorithm accepts any data expressed as a series of binary properties, which is divided into two classes, and extracts patterns of those properties that are frequent within the data and are more frequent in one data class compared to the other. By mining emerging patterns from toxicity datasets, encoded as fingerprints of binary descriptors, the tool generates patterns of features that distinguish toxicants from innocuous compounds. These patterns represent potentially activating features of the toxic compounds that may then be used to define new alerts. The knowledge discovery tool has been tested using a public dataset of 3489 mutagens and 2981 non-mutagens, encoded as fingerprints of approximately 2000 functional groups and ring descriptors. EPs were produced and grouped into a number of hierarchical families. Six of the EPs that represented distinct chemical classes were selected for manual inspection by a toxicology expert. Relevant literature was analysed to find a mechanistic rationale for the mined features, which resulted in four new structural alerts for in vitro mutagenicity.

Automating Knowledge Discovery for Toxicity Prediction Using Jumping Emerging Pattern Mining

The design of new alerts, that is, collections of structural features observed to result in toxicological activity, can be a slow process and may require significant input from toxicology and chemistry experts. A method has therefore been developed to help automate alert identification by mining descriptions of activating structural features directly from toxicity data sets. The method is based on jumping emerging pattern mining which is applied to a set of toxic and nontoxic compounds that are represented using atom pair descriptors. Using the resulting jumping emerging patterns, it is possible to cluster toxic compounds into groups defined by the presence of shared structural features and to arrange the clusters into hierarchies. The methodology has been tested on a number of data sets for Ames mutagenicity, oestrogenicity, and hERG channel inhibition end points. These tests have shown the method to be effective at clustering the data sets around minimal jumping-emerging structural patterns and finding descriptions of potentially activating structural features. Furthermore, the mined structural features have been shown to be related to some of the known alerts for all three tested end points.

Supervised Descriptive Rule Discovery: A Unifying Survey of Contrast Set, Emerging Pattern and Subgroup Mining

This paper gives a survey of contrast set mining (CSM), emerging pattern mining (EPM), and subgroup discovery (SD) in a unifying framework named supervised descriptive rule discovery. While all these research areas aim at discovering patterns in the form of rules induced from labeled data, they use different terminology and task definitions, claim to have different goals, claim to use different rule learning heuristics, and use different means for selecting subsets of induced patterns. This paper contributes a novel understanding of these subareas of data mining by presenting a unified terminology, by explaining the apparent differences between the learning tasks as variants of a unique supervised descriptive rule discovery task and by exploring the apparent differences between the approaches. It also shows that various rule learning heuristics used in CSM, EPM and SD algorithms all aim at optimizing a trade off between rule coverage and precision. The commonalities (and differences) between the approaches are showcased on a selection of best known variants of CSM, EPM and SD algorithms. The paper also provides a critical survey of existing supervised descriptive rule discovery visualization methods.