Pattern Mining Process Research Articles

Heuristic approaches for non-exhaustive pattern-based change detection in dynamic networks

Dynamic networks are ubiquitous in many domains for modelling evolving graph-structured data and detecting changes allows us to understand the dynamic of the domain represented. A category of computational solutions is represented by the pattern-based change detectors (PBCDs), which are non-parametric unsupervised change detection methods based on observed changes in sets of frequent patterns over time. Patterns have the ability to depict the structural information of the sub-graphs, becoming a useful tool in the interpretation of the changes. Existing PBCDs often rely on exhaustive mining, which corresponds to the worst-case exponential time complexity, making this category of algorithms inefficient in practice. In fact, in such a case, the pattern mining process is even more time-consuming and inefficient due to the combinatorial explosion of the sub-graph pattern space caused by the inherent complexity of the graph structure. Non-exhaustive search strategies can represent a possible approach to this problem, also because not all the possible frequent patterns contribute to changes in the time-evolving data. In this paper, we investigate the viability of different heuristic approaches which prevent the complete exploration of the search space, by returning a concise set of sub-graph patterns (compared to the exhaustive case). The heuristics differ on the criterion used to select representative patterns. The results obtained on real-world and synthetic dynamic networks show that these solutions are effective, when mining patterns, and even more accurate when detecting changes.

Toward Better Structure and Constraint to Mine Negative Sequential Patterns.

Nonoccurring behavior (NOB) studies have attracted the growing attention of scholars as a crucial part of behavioral science. As an effective method to discover both NOB and occurring behaviors (OB), negative sequential pattern (NSP) mining is successfully used in analyzing medical treatment and abnormal behavior patterns. At this time, NSP mining is still an active and challenging research domain. Most of the algorithms are inefficient in practice. Briefly, the key weaknesses of NSP mining are: 1) an inefficient positive sequential pattern (PSP) mining process, 2) a strict constraint of negative containment, and 3) the lack of an effective Negative Sequential Candidate (NSC) generation method. To address these weaknesses, we propose a highly efficient algorithm with improved techniques, named sc-NSP, to mine NSP efficiently. We first propose an improved PrefixSpan algorithm in the PSP mining process, which connects to a bitmap storage structure instead of the original structure. Second, sc-NSP loosens the frequency constraint and exploits the NSC generation method of positive and negative sequential patterns mining (PNSP) (a classic NSP mining method). Furthermore, a novel pruning strategy is designed to reduce the computational complexity of sc-NSP. Finally, sc-NSP obtains the support of NSC by using the most efficient bitwise-based calculation operation. Theoretical analyses show that sc-NSP performs particularly well on data sets with a large number of elements and items in sequence. Comparison and extensive experiments along with case studies on health data show that sc-NSP is 10 times more efficient than other state-of-the-art methods, and the number of NSPs obtained is 5 times greater than other methods.

Real-time recommendations for energy-efficient appliance usage in households.

According to several studies, the most influencing factor in a household's energy consumption is user behavior. Changing user behavior to improve energy usage leads to efficient energy consumption, saving money for the consumer and being more friendly for the environment. In this work we propose a framework that aims at assisting households in improving their energy usage by providing real-time recommendations for efficient appliance use. The framework allows for the creation of household-specific and appliance-specific energy consumption profiles by analyzing appliance usage patterns. Based on the household profile and the actual electricity use, real-time recommendations notify users on the appliances that can be switched off in order to reduce consumption. For instance, if a consumer forgets their A/C on at a time that it is usually off (e.g., when there is no one at home), the system will detect this as an outlier and notify the consumer. In the ideal scenario, a household has a smart meter monitoring system installed, that records energy consumption at the appliance level. This is also reflected in the datasets available for evaluating such systems. However, in the general case, the household may only have one main meter reading. In this case, non-intrusive load monitoring (NILM) techniques, which monitor a house's energy consumption using only one meter, and data mining algorithms that disaggregate the consumption into appliance level, can be employed. In this paper, we propose an end-to-end solution to this problem, starting with the energy disaggregation process, and the creation of user profiles that are then fed to the pattern mining and recommendation process, that through an intuitive UI allows users to further refine their energy consumption preferences and set goals. We employ the UK-DALE (UK Domestic Appliance-Level Electricity) dataset for our experimental evaluations and the proof-of-concept implementation. The results show that the proposed framework accurately captures the energy consumption profiles of each household and thus the generated recommendations are matching the actual household energy habits and can help reduce their energy consumption by 2–17%.

An Efficient Temporal Inter-Object Association Rule Mining Algorithm on Time Series

Time series is acknowledged as one of the most common crucial data types in our daily lives. Among the time series mining tasks, rule discovery is important to provide valuable knowledge that brings us a profound insight view of relationships between different objects through time. One challenge is that when the number of objects and their lengths increase, it easily leads to a combinatorial explosion. Therefore, we propose a temporal inter-object association rule mining algorithm, NPTR, to discover new informative temporal inter-object association rules from time series and overcome the challenge with parallelization. Another remarkable point is that NPTR defines a concurrent approach by performing the frequent pattern mining process and rule mining one simultaneously. From the experiments on real-world data, NPTR returns the rules exactly with less time and memory costs than others do. Those rules can be further utilized for other tasks such as prediction, classification, and clustering.

Personalized insulin dose manipulation attack and its detection using interval-based temporal patterns and machine learning algorithms

Many patients with diabetes are currently being treated with insulin pumps and other diabetes devices which improve their quality of life and enable effective treatment of diabetes. These devices are connected wirelessly and thus, are vulnerable to cyber-attacks which have already been proven feasible. In this paper, we focus on two types of cyber-attacks on insulin pump systems: an overdose of insulin, which can cause hypoglycemia, and an underdose of insulin, which can cause hyperglycemia. Both of these attacks can result in a variety of complications and endanger a patient's life. Specifically, we propose a sophisticated and personalized insulin dose manipulation attack; this attack is based on a novel method of predicting the blood glucose (BG) level in response to insulin dose administration. To protect patients from the proposed sophisticated and malicious insulin dose manipulation attacks, we also present an automated machine learning based system for attack detection; the detection system is based on an advanced temporal pattern mining process, which is performed on the logs of real insulin pumps and continuous glucose monitors (CGMs). Our multivariate time-series data (MTSD) collection consists of 225,780 clinical logs, collected from real insulin pumps and CGMs of 47 patients with type I diabetes (13 adults and 34 children) from two different clinics at Soroka University Medical Center in Beer-Sheva, Israel over a four-year period. We enriched our data collection with additional relevant medical information related to the subjects. In the extensive experiments performed, we evaluated the proposed attack and detection system and examined whether: (1) it is possible to accurately predict BG levels in order to create malicious data that simulate a manipulation attack and the patient's body in response to it; (2) it is possible to automatically detect such attacks based on advanced machine learning (ML) methods that leverage temporal patterns; (3) the detection capabilities of the proposed detection system differ for insulin overdose and underdose attacks; and (4) the granularity of the learning model (general / adult vs. pediatric clinic / individual patient) affects the detection capabilities. Our results show that (a) it is possible to predict, with nearly 90% accuracy, BG levels using our proposed methods, and by doing so, enable malicious data creation for our detection system evaluation; (b) it is possible to accurately detect insulin manipulation attacks using temporal patterns mining using several ML methods, including Logistic Regression, Random Forest, TPF class model, TPF top k, and ANN algorithms; (c) it is easier to detect an overdose attack than an underdose attack in more than 25%, in terms of AUC scores; and (d) the adult vs. pediatric model outperformed models of other granularities in the detection of overdose attacks, while the general model outperformed the other models in the case of detecting underdose attacks; for both attacks, attack detection among children was found to be more challenging than among adults. In addition to its use in the evaluation of our detection system, the proposed BG prediction method has great importance in the medical domain where it can contribute to improved care of patients with diabetes.

Hiding Sensitive High Utility and Frequent Itemsets Based on Constrained Intersection Lattice

Abstract Hiding high utility and frequent itemset is the method used to preserve sensitive knowledge from being revealed by pattern mining process. Its goal is to remove sensitive high utility and frequent itemsets from a database before sharing it for data mining purposes while minimizing the side effects. The current methods succeed in the hiding goal but they cause high side effects. This paper proposes a novel algorithm, named HSUFIBL, that applies a heuristic for finding victim item based on the constrained intersection lattice theory. This algorithm specifies exactly the condition that allows the application of utility reduction or support reduction method, the victim item, and the victim transaction for the hiding process so that the process needs the fewest data modifications and gives the lowest number of lost non-sensitive itemsets. The experimental results indicate that the HSUFIBL algorithm achieves better performance than previous works in minimizing the side effect.

Frequent pattern mining augmented by social network parameters for measuring graduation and dropout time factors: A case study on a production engineering course

Identifying factors that lead students either not to graduate on time or drop out helps Higher Education Institutions improve retention and decrease attrition. This paper tackles this problem by introducing a novel approach to discovering such factors through pattern mining using association rules. The novelty of the method arises from introducing social network analysis inside the pattern mining process. The social networks metrics for each student and the degree of propagation of grade point average are computed and integrated with students’ records for pattern mining serving as a proxy for the existing bond among students, which is a relevant factor for attrition and dropout analysis. This paper examines the Bachelor Program in Production Engineering at the Federal Center for Technological Education of Rio de Janeiro from 2011 to 2017. Our experiments indicate congruence with the literature: (i) lower school performance leading to delay; (ii) higher performance leading to graduation in optimal time. Besides, our new method sheds light on students with little participation in the social network who are more likely to delay or drop out. Our findings may aid managers in discovering students with patterns that can indicate imminent lateness or dropout.

Decorative Art Pattern Mining and Discovery based on Group User Intelligence

With the continuous developments of real estates and the increasing personalization of people, more and more house owners are willing to search for and discover their preferred decorative art patterns via various house decoration cases sharing websites or platforms. Through browsing and analyzing existing house decoration cases on the Web, a new house owner can find out his or her interested decorative art patterns; however, the above decorative art pattern mining and discovery process is often time-consuming and boring due to the big volume of existing house decoration cases on the Web. Therefore, it is becoming a challenging task to develop a time-efficient decorative art pattern mining and discovery method based on the available house decoration cases provided by historical users. Considering this challenge, a novel LSH-based similar house owners clustering approach is proposed. A set of experiments are designed to validate the effectiveness and efficiency of our proposal.

Decorative Art Pattern Mining and Discovery Based on Group User Intelligence

With the continuous developments of real estates and the increasing personalization of people, more and more house owners are willing to search for and discover their preferred decorative art patterns via various house decoration cases sharing websites or platforms. Through browsing and analyzing existing house decoration cases on the Web, a new house owner can find out his or her interested decorative art patterns; however, the above decorative art pattern mining and discovery process is often time-consuming and boring due to the big volume of existing house decoration cases on the Web. Therefore, it is becoming a challenging task to develop a time-efficient decorative art pattern mining and discovery method based on the available house decoration cases provided by historical users. Considering this challenge, a novel LSH-based similar house owners clustering approach is proposed. A set of experiments are designed to validate the effectiveness and efficiency of our proposal.

Mining the sequential patterns of water quality preceding the biological status of waterbodies

We have implemented a specific data mining process to explore the relationship between biological indices and physico-chemical pressures in rivers. Data were collected in the framework of the French National monitoring network set up to assess the ecological status of rivers under the European Water Framework Directive (WFD). Chemical parameters and biological indices were collected regularly from 1.781 locations in metropolitan France from 2007 to 2013. The sequential pattern mining process generates closed partially ordered patterns representing a succession of physico-chemical events that precede a given biological index in a given status, validated using a subset of data. This paper focuses on the patterns and their occurrence. We showed that biological statuses depend on these temporal successions of alterations and not only on the last alterations. The physico-chemical statuses of water bodies usually appeared to be higher than their biological statuses, suggesting synergism between toxicants and/or an additive impact of other stressors related to hydromorphology or hydrology. Patterns found in the highest biological status for the biological indices based on macroinvertebrates, diatoms, macrophytes or fish, were characterised by the constancy of a high physico-chemical status over time. By contrast, before indices based on macroinvertebrates and macrophytes, two types of patterns were observed for bad biological status: (1) a chronic multi-pressure pattern, in which pressure categories such as nitrates, pesticides and other organic hydrocarbons, in moderate, poor or bad status, repeated themselves several times over time, or (2) a single occurrence of a degraded pressure category, such as one moderate nitrogen, excluding nitrate, or one poor oxidizable organic matter, among other pressure categories in good status. Extracting such patterns is a promising solution both to disentangle the effects of the different stressors on water quality, and to identify the key temporal sequences among them in a context of multi-stress conditions, which is a challenge currently facing the WFD.

Mining subsequent trend patterns from financial time series

Chart patterns are one of the important tools used by the financial analysts for predicting future price trends (subsequent trends) in stock markets. Although many works related to the descriptions of chart patterns and several effective methods to identify chart patterns from the financial time series have been proposed in recent years, there is no in-depth study about the general characteristics of the subsequent trends. In this paper, we proposed a general framework for mining subsequent trend for chart patterns. We extensively analyze the characteristics of subsequent trends of chart patterns found with the proposed framework. Based on the analysis, we propose a concept called subsequent trend pattern by mining frequently occurring shapes from these trends. The process of subsequent trend pattern mining was evaluated on a dataset containing 502 time series from S&P 500 and a test dataset containing 494 stocks from Yahoo finance. The proposed concept of subsequent trend pattern provides a solid foundation for the understanding of chart patterns in predicting future price movement and extends the formal definition of chart patterns.

Lean User Research for Agile Organizations

In the context of Digital Transformation, organizations need to react in a flexible manner to rapidly changing markets and disruptive technologies. Customer and user satisfaction are important in order to succeed. Agile User Experience (UX) Design and Lean User Research enable the organization to focus on the needs of its customers and users. The objective of this paper is to investigate the best practices that exist for user research in agile product development. In particular, we want to answer the following question: What impact does Lean User Research have and how is it conducted in industry? We have carried out several studies to answer our questions. First, we created the pattern Lean User Research by means of a systematic pattern mining process. Next, we gathered quantitative data by means of a questionnaire study. This was followed by the collection of qualitative data in a panel discussion with experts from academia and industry. The results reveal that Agile has an impact on how user research is conducted because of the speed of agile product development. In addition, we provide best practices of Lean User Research and show how they are applied in industry by giving practical examples. Moreover, we found that the UX community values the aspects of Lean User Research as important, but do not constantly apply it in their practical work. We can conclude that people have to experiment and adapt the best practices of Lean User Research to their special contexts as well as develop an agile mindset.

An Efficient Method for Mining Closed Potential High-Utility Itemsets

High-utility itemset mining (HUIM) has become a key phase of the pattern mining process, which has wide applications, related to both quantities and profits of items. Many algorithms have been proposed to mine high-utility itemsets (HUIs). Since these algorithms often return a large number of discovered patterns, a more compact and lossless representation has been proposed. The recently proposed closed high utility itemset mining (CHUIM) algorithms were designed to work with certain types of databases (e.g., those without probabilities). In fact, real-world databases might contain items or itemsets associated with probability values. To effectively mine frequent patterns from uncertain databases, several techniques have been developed, but there does not exist any method for mining CHUIs from this type of databases. This work presents a novel and efficient method without generating candidates, named CPHUI-List, to mine closed potential high-utility itemsets (CPHUIs) from uncertain databases. The proposed algorithm is DFS-based and utilizes the downward closure property of high transaction-weighted probabilistic mining to prune non-CPHUIs. It can be seen from the experiment evaluations that the proposed algorithm has better execution time and memory usage than the CHUI-Miner.

Privacy preserving classification on local differential privacy in data centers

With the rise of cloud service providers and the continuous virtualization of data centers, data center networks are also developing rapidly. As data centers become more and more complex, the demand for security increases dramatically. This paper discusses the privacy inherent in data centers. However, there is no general solution to the privacy problem in data centers due to the device heterogeneity. In this paper, we proposed a local differential privacy-based classification algorithm for data centers. In data mining of data centers, the differential privacy protection mechanism is added to deal with Laplace noise of sensitive information in the pattern mining process. We designed a method to quantify the quality of privacy protection through strict mathematical proof. Experiments demonstrated that the differential privacy-based classification algorithm proposed in this paper has higher iteration efficiency, better security and feasible accuracy. On the premise of ensuring availability, the algorithm has reliable privacy protection characteristics and excellent timeliness.

A Pattern-Based Academic Reviewer Recommendation Combining Author-Paper and Diversity Metrics

With the rapid increase of publishable research articles and manuscripts, the pressure to find reviewers often overwhelms the journal editors. This paper incorporates the major entity level metrics found in the heterogeneous publication networks into a pattern mining process in order to recommend academic reviewers and potential research collaborators. In essence, the paper integrates authors’ h-index and papers’ citation count and proposes a quantification to account for the author diversity into one formula duped impact to measure the real influence of a scientific paper. Thereafter, this paper formulates two kinds of target patterns and mines them harnessing the high-utility itemset mining (HUIM) framework. The first pattern, researcher-general topic patterns (RGP), is a pattern that includes only researchers; whereas, the researcher-specific topic patterns (RSP) is comprised of combinations of researchers and keywords that summarize their niche of expertise. The HUI algorithms of Two Phase, IHUP, UP-Growth, FHM, FHN, HUINIV-Mine, D2HUP, and EFIM were compared on two real-world citation datasets related to Deep Learning and HUIM, in addition to the open source mushroom dataset. The EFIM algorithm showed good performance in terms of run time and memory usage. Consequently, it was then used to mine the patterns within the proposed framework. The discovered patterns of RGP and RSP showed high coverage, proving the efficiency of the proposed framework.

Significance-based discriminative sequential pattern mining

Discriminative sequential patterns are sub-sequences whose occurrences exhibit significant differences across sequential data sets with different class labels. The discovery of such types of patterns has many practical applications in different fields. To date, various algorithms for mining discriminative sequential patterns have been proposed. However, the reported patterns from these methods usually contain many false positives that only hold in the sample data by chance. To alleviate this issue, we put forward the concept of significance-based discriminative sequential pattern mining and a corresponding algorithm DSPM-MTC (Discriminative Sequential Pattern Mining with Multiple Testing Correction). The key idea of DSPM-MTC is to integrate the multiple hypothesis testing correction procedure into the pattern mining process to generate a pattern set with error rate control. To demonstrate the effectiveness of DSPM-MTC, we conduct a series of experiments on real sequential data sets and simulation data sets. The experimental results show that DSPM-MTC can effectively recognize false discoveries to generate a pattern set with statistical quality control.

A gossip based information fusion protocol for distributed frequent itemset mining

ABSTRACTThe computational complexity, huge memory space requirement, and time-consuming nature of frequent pattern mining process are the most important motivations for distribution and parallelization of this mining process. On the other hand, the emergence of distributed computational and operational environments, which causes the production and maintenance of data on different distributed data sources, makes the parallelization and distribution of the knowledge discovery process inevitable. In this paper, a gossip based distributed itemset mining (GDIM) algorithm is proposed to extract frequent itemsets, which are special types of frequent patterns, in a wireless sensor network environment. In this algorithm, local frequent itemsets of each sensor are extracted using a bit-wise horizontal approach (LHPM) from the nodes which are clustered using a leach-based protocol. Heads of clusters exploit a gossip based protocol in order to communicate each other to find the patterns which their global support is equal to or more than the specified support threshold. Experimental results show that the proposed algorithm outperforms the best existing gossip based algorithm in term of execution time.

Mining Context-Aware Association Rules Using Grammar-Based Genetic Programming.

Real-world data usually comprise features whose interpretation depends on some contextual information. Such contextual-sensitive features and patterns are of high interest to be discovered and analyzed in order to obtain the right meaning. This paper formulates the problem of mining context-aware association rules, which refers to the search for associations between itemsets such that the strength of their implication depends on a contextual feature. For the discovery of this type of associations, a model that restricts the search space and includes syntax constraints by means of a grammar-based genetic programming methodology is proposed. Grammars can be considered as a useful way of introducing subjective knowledge to the pattern mining process as they are highly related to the background knowledge of the user. The performance and usefulness of the proposed approach is examined by considering synthetically generated datasets. A posteriori analysis on different domains is also carried out to demonstrate the utility of this kind of associations. For example, in educational domains, it is essential to identify and understand contextual and context-sensitive factors that affect overall and individual student behavior and performance. The results of the experiments suggest that the approach is feasible and it automatically identifies interesting context-aware associations from real-world datasets.

Mining and Quality Assessment of Mashup Model Patterns with the Crowd

Pattern mining, that is, the automated discovery of patterns from data, is a mathematically complex and computationally demanding problem that is generally not manageable by humans. In this article, we focus on small datasets and study whether it is possible to mine patterns with the help of the crowd by means of a set of controlled experiments on a common crowdsourcing platform. We specifically concentrate on mining model patterns from a dataset of real mashup models taken from Yahoo! Pipes and cover the entire pattern mining process, including pattern identification and quality assessment. The results of our experiments show that a sensible design of crowdsourcing tasks indeed may enable the crowd to identify patterns from small datasets (40 models). The results, however, also show that the design of tasks for the assessment of the quality of patterns to decide which patterns to retain for further processing and use is much harder (our experiments fail to elicit assessments from the crowd that are similar to those by an expert). The problem is relevant in general to model-driven development (e.g., UML, business processes, scientific workflows), in that reusable model patterns encode valuable modeling and domain knowledge, such as best practices, organizational conventions, or technical choices, that modelers can benefit from when designing their own models.

Explaining mixture models through semantic pattern mining and banded matrix visualization

This paper presents an approach to semi-automated data analysis, supported by tools for pattern construction, exploration and explanation. The proposed three-part methodology for multiresolution 0---1 data analysis consists of data clustering with mixture models, extraction of rules from clusters, as well as data and rule visualization using banded matrices. The results of the three-part process: clusters, rules from clusters, and banded structure of the data matrix are finally merged in a unified visual banded matrix display. The incorporation of multiresolution data is enabled by the supporting ontology, describing the relationships between the different resolutions, which is used as background knowledge in the semantic pattern mining process of descriptive rule induction. The presented experimental use case highlights the usefulness of the proposed methodology for analyzing complex DNA copy number amplification data, studied in previous research, for which we provide new insights in terms of induced semantic patterns and cluster/pattern visualization. The methodology is successfully evaluated on four other publicly available data sets, which further demonstrates the utility of the proposed approach.