Frequent Pattern Mining Research Articles

A Performance Comparison of Unsupervised Techniques for Event Detection from Oscar Tweets.

People's lives are influenced by social media. It is an essential source for sharing news, awareness, detecting events, people's interests, etc. Social media covers a wide range of topics and events to be discussed. Extensive work has been published to capture the interesting events and insights from datasets. Many techniques are presented to detect events from social media networks like Twitter. In text mining, most of the work is done on a specific dataset, and there is the need to present some new datasets to analyse the performance and generic nature of Topic Detection and Tracking methods. Therefore, this paper publishes a dataset of real-life event, the Oscars 2018, gathered from Twitter and makes a comparison of soft frequent pattern mining (SFPM), singular value decomposition and k-means (K-SVD), feature-pivot (Feat-p), document-pivot (Doc-p), and latent Dirichlet allocation (LDA). The dataset contains 2,160,738 tweets collected using some seed words. Only English tweets are considered. All of the methods applied in this paper are unsupervised. This area needs to be explored on different datasets. The Oscars 2018 is evaluated using keyword precision (K-Prec), keyword recall (K-Rec), and topic recall (T-Rec) for detecting events of greater interest. The highest K-Prec, K-Rec, and T-Rec were achieved by SFPM, but they started to decrease as the number of clusters increased. The lowest performance was achieved by Feat-p in terms of all three metrics. Experiments on the Oscars 2018 dataset demonstrated that all the methods are generic in nature and produce meaningful clusters.

Mining Order-preserving Submatrices under Data Uncertainty: A Possible-world Approach and Efficient Approximation Methods

Given a data matrix\( D \), a submatrix\( S \)of\( D \)is an order-preserving submatrix (OPSM) if there is a permutation of the columns of\( S \), under which the entry values of each row in\( S \)are strictly increasing. OPSM mining is widely used in real-life applications such as identifying coexpressed genes and finding customers with similar preference. However, noise is ubiquitous in real data matrices due to variable experimental conditions and measurement errors, which makes conventional OPSM mining algorithms inapplicable. No previous work on OPSM has ever considered uncertain value intervals using the well-established possible world semantics.We establish two different definitions of significant OPSMs based on thepossible world semantics: (1) expected support-based and (2) probabilistic frequentness-based. An optimized dynamic programming approach is proposed to compute the probability that a row supports a particular column permutation, with a closed-form formula derived to efficiently handle the special case of uniform value distribution and an accurate cubic spline approximation approach that works well with any uncertain value distributions. To efficiently check the probabilistic frequentness, several effective pruning rules are designed to efficiently prune insignificant OPSMs; two approximation techniques based on the Poisson and Gaussian distributions, respectively, are proposed for further speedup. These techniques are integrated into our two OPSM mining algorithms, based on prefix-projection and Apriori, respectively. We further parallelize our prefix-projection-based mining algorithm using PrefixFPM, a recently proposed framework for parallel frequent pattern mining, and we achieve a good speedup with the number of CPU cores. Extensive experiments on real microarray data demonstrate that the OPSMs found by our algorithms have a much higher quality than those found by existing approaches.

FPMBot: Discovering the frequent pattern of IoT-botnet domain queries in large-scale network

With the rapid development of Internet of Things (IoT), new types of security issues has emerged, and one of the most severe one is the IoT-based botnet. A number of traditional works dedicate in analyzing DNS traffic for its wide misuse in botnets. However, most works are limited to specific behaviors, such as regularity in domains queries and periodicity in C&C(Command and Control) processes, which are often sheltered by attackers. Moreover, ever-growing numbers of domains and queries caused by IoT devices make most approaches not effective anymore since their architectures are hard to confront traffic explosion. In this paper, we illustrate the essential property of botnet, i.e., the frequent pattern of DNS request relationships, and propose a generic and scalable IoT-botnet detection system, named FPMBot, to detect bots domain queries in large-scale DNS traffic. The key insight is that bots in the same botnet inevitably query same sets of domains or servers whenever they try to conduct attacks or connect to C&C servers, and form frequent patterns in a bipartite graph of requesters and responsers. This frequent pattern in domain queries is an essential behavior for bots since a significant advantage of bots is the ability to launch large-scale attacks synchronously. We utilize a frequent pattern mining algorithm to detect such patterns and implement FPMBot based on Apache Spark parallel computing architecture to handle the daily increasing traffic. The experiment result on more than 14 billion records in four days real-world DNS logs shows that FPMBot has a high detection precision over 95% and performs well in large-scale network.

An intelligent feature selection approach with systolic tree structures for efficient association rules in big data environment

Frequent Pattern Mining (FPM) is regularly used in data mining applications for identifying objects of interest that frequent transactional databases. Traditional ARM algorithms work on minimum levels of support and confidence metrics which have to be defined and are subjective. This work attempts to solve this issue by proposing techniques for the automatic determination of these metrics. The Kernel Possibilistic Fuzzy Local Information C-Means (KPFLICM) Clustering and K-means Clustering-based Feature Selection algorithm for Association Rules (KCFSAR) is used where FPMs are based on Systolic Tree Structures (STS). These structures aim to achieve better accuracy by mimicking internal memory structures of the Frequent Pattern Growths (FPG) algorithm. Moreover, Chaotic Butterfly Optimization Method (CBOAs) is used to obtain the optimal support value and CBOA subsequently discovers global optimal solutions. This work's suggested scheme demonstrates its efficacy and superiority in experimental findings when compared to other approaches in terms of feature subset sizes, accuracies, execution times, and memory consumptions.

An Improving Approach for Top-Rank-k Frequent Pattern Mining

Mining frequent patterns (FPs) received a lot of research interest which is a fundamental problem in the field of data mining. It has been studied on many database types with various applications in intelligent systems. However, the traditional methods using a given threshold to mine FPsterns suffer from a crucial drawback, that is, the number of resulting patterns is uncontrollable, sometimes very large. Mining top-rank-[Formula: see text] FPs is one of the current research directions to solve the aforementioned disadvantage of mining FPs. Many methods have been proposed to mine effectively top-rank-[Formula: see text] frequent patterns. However, these methods also have many limitations regarding memory consumption and suboptimal mining time. Therefore, this study proposes a new method based on [Formula: see text]-list structure using the Priority Queue, the Hash Table structure, and some fast pruning strategies for efficient mining top-rank-[Formula: see text] FPs from binary transaction databases. The experimental results on many datasets demonstrate that the proposed method is more effective than the previous methods in the terms of runtime and memory usage.

Forecasting ground-level ozone concentration levels using machine learning

Ground-level ozone (GLO) has been widely recognized as a critical air pollutant that has the potential to induce various adverse environmental and health effects. To eliminate its hazardous impacts, the development of an accurate and effective approach to forecast the upcoming pollution concentration levels is in urgent need. Recent studies show that machine learning algorithms have excellent abilities in ground-level ozone concentration forecasting, however many of their forecasting models do not consider the contributing effects on meteorological measurements and traffic situations which were also identified as potential influencing factors to ground-level ozone concentration by some previous research. In the meantime, most of the existing models target short-term forecasting with rough temporal resolutions, such as daily and weekly scales. This paper aims to propose a methodology that can provide long-term GLO concentration forecasting with a high temporal resolution. To achieve this, a frequent pattern mining approach is utilized to analyze the local intercorrelation between GLO concentration and contributing factors such as meteorological parameters and transportation situations. Then, a series of machine learning algorithms were identified to forecast the ground-level ozone concentration levels using traffic and meteorological measurements data. A case study was conducted in the Houston region with 10 years of historical measurements, each of the historical ground-level ozone concentration records is associated with a series of meteorology and traffic situation parameters. Data from 2010 to 2019 was used to select and train the machine learning models, and data from 2020 was used to perform the final validation and evaluation. Results show that the extreme gradient boost (XGBoost) machine learning algorithm provides the most accurate prediction of the hourly ground-level ozone concentration on a yearly scale, which shows the annually forecasting ability and the robustness of the model built. The proposed approach could be applied to other similar regions and other critical air pollutants that are also influenced by transportation and meteorological factors.

Mining high occupancy patterns to analyze incremental data in intelligent systems

High occupancy pattern mining has been recently studied as an improved method for frequent pattern mining. It considers the proportion of each pattern in the transactions where the pattern occurred. The results of high occupancy pattern mining can be employed for automated control systems in order to make decisions. Meanwhile, the features of the databases have changed, because information technology has advanced. In real-world databases, new transactions are inserted in real time. However, the state-of-the-art approach to high occupancy pattern mining cannot handle incremental databases. Moreover, the existing method also requires a large amount of memory space, because it adopted a BFS-based search in order to find patterns. In this paper, we propose an approach, which is called HOMI (High Occupancy pattern Mining on Incremental databases), that uses a DFS-based search in order to detect patterns, and it mines high occupancy patterns on incremental databases. The performance analysis for both real and synthetic datasets indicates that HOMI has better performance than the state-of-the-art approaches and related algorithms.

Prefix-Pruning-Based Distributed Frequent Trajectory Pattern Mining Algorithm

An important problem to be solved in smart city construction is how to improve the efficiency of mining frequent patterns that can be used for location prediction and location-based services of massive trajectory datasets. Owing to uncertain personal trajectory and non-explicit trajectory items, the existing sequence mining algorithms cannot be used directly. To solve this problem, this study proposes a distributed trajectory frequent pattern mining algorithm (SparkTraj) based on prefix pruning. First, a grouping and partitioning technique is used to abstract the original trajectory data and convert them into a common time series.Then, the generation of a redundant trajectory pattern is avoided by using the path adjacency pruning method. Second, to improve mining efficiency, SparkTraj is designed and implemented in Spark, which employs cluster memory computing. Finally, experiments on common datasets show that the proposed algorithm can effectively extract frequent trajectory patterns, and, in particular, deal with the massive amounts of trajectory data. Compared with common trajectory pattern mining algorithms, the SparkTraj algorithm not only improves the overall performance but also has good scalability.

A cost-effective approach for mining near-optimal top-[formula omitted] patterns

Frequent pattern mining (FPM) on large graphs has received more and more attention due to its importance in various applications, including social media analysis. The FPM models are designed to find the patterns in a large graph with a frequency above a user-defined threshold. However, this problem is nontrivial due to the mining process’s unaffordable computational and space costs. In light of this, we propose a cost-effective approach to mining near-optimal top-k patterns. Our approach applies a “level-wise” strategy to detect frequent patterns incrementally, hence can terminate once top-k patterns are discovered. Moreover, we develop a technique to compute the lower bound of support with a smart traverse strategy and compact data structures. Extensive experimental studies on real-life and synthetic graphs show that our approach performs well by outperforming traditional competing methods in efficiency, memory footprint, recall, and scalability.

Examination of Children’ Playing Game Tendencies and Digital Game Preferences Based on Gender

This study reports on a survey of 4-8th grade students’ (N=10139) playing game tendencies and digital game preferences based on gender. Descriptive statistics were used to determine the children’ playing game tendencies and digital game preferences. And also, frequent pattern mining was used to discover which digital games are played frequently and together by children. The findings showed that children have an increase time spent playing games on weekend and boys tend to playing game more than girls. On the other hand, action games stood out as the most common choice among the children both girls and boys. In terms of game language, Turkish and English games were preferred almost equally. In addition, children mostly preferred digital games that can be played online, offering in-app purchases, and played on mobile devices. According to the frequency of playing, it was found that the children mostly preferred to play Minecraft, followed by Subway Surfers and Hay Day, respectively. In terms of gender, it was concluded that girls mostly preferred Subway Surfers, while boys played Hay Day. When the games were considered according to the frequency of playing together, Temple Run and Subway Surfers games among girls, and FIFA and Piano Tiles games among boys can be played together. The research reveals more detailed information about children’ game preferences in terms of gender.

Risk and Pattern Analysis of Pakistani Crime Data Using Unsupervised Learning Techniques

To reduce crime rates, there is a need to understand and analyse emerging patterns of criminal activities. This study examines the occurrence patterns of crimes using the crime dataset of Lahore, a metropolitan city in Pakistan. The main aim is to facilitate crime investigation and future risk analysis using visualization and unsupervised data mining techniques including clustering and association rule mining. The visualization of data helps to uncover trends present in the crime dataset. The K-modes clustering algorithm is used to perform the exploratory analysis and risk identification of similar criminal activities that can happen in a particular location. The Apriori algorithm is applied to mine frequent patterns of criminal activities that can happen on a particular day, time, and location in the future. The data were acquired from paper-based records of three police stationsin the Urdu language. The data were then translated into English and digitized for automatic analysis. The result helped identify similar crime-related activities that can happen in a particular location, the risk of potential criminal activities occurring on a specific day, time, and place in the future, and frequent crime patterns of different crime types. The proposed work can help the police department to detect crime events and situations and reduce crime incidents in the early stages by providing insights into criminal activity patterns.

Leveraging tourist trajectory data for effective destination planning and management: A new heuristic approach

Understanding tourist movements provides insights for destination planning, service design and marketing. The key challenge is to develop a tool that can capture the value in the tourist mobility data. This study presents a new heuristic approach that combines adaptive spatial clustering with frequent pattern mining to improve the performance and efficiency of trajectory data analytics. The aim is to fully leverage the semantic information in the tourist data and the duration that tourists stay at an attraction. Anonymous mobile positioning data from 741 tourists to one of China's leading destinations are used to illustrate the application of the new analytical approach. The results reveal a four-level destination spatial structure ranging from core to peripheral areas. The findings provide practical implications for facilitating intra-destination cooperation and optimizing destination resource allocation and service design.

Deep active reinforcement learning for privacy preserve data mining in 5G environments

Frequent pattern mining (FIM) identifies the most important patterns in data sets. However, due to the huge and high-dimensional nature of transactional data, classical pattern mining techniques suffer from the limitations of dimensions and data annotations. Recently, data mining while preserving privacy is considered as an important research area. Information privacy is a tradeoff that must be considered when using data. Through many years, privacy-preserving data mining (PPDM) made use of methods that are mostly based on heuristics. The operation of deletion was used to hide the sensitive information in PPDM. In this study, we used deep active learning to protect private and sensitive information. This paper combines entropy-based active learning with an attention-based approach to effectively hide sensitive patterns. The constructed models are then validated using high-dimensional transactional data with attention-based and active learning methods in a reinforcement environment. The results show that the proposed model can support and improve the effectiveness of decision-making by increasing the number of training instances through the use of a pooling technique and an entropy uncertainty measure. The proposed paradigm can achieve data sanitization by the hiding sensitive items and avoiding to hide the non-sensitive items. The model outperforms greedy, genetic, and particle swarm optimization approaches.

Map-Matching on Low Sampling Rate Trajectories through Frequent Pattern Mining

Map-matching, an important preprocessing task in many location-based services (LBS), projects each point of the global positioning system (GPS) within a trajectory dataset onto a digital map. The state-of-the-art map-matching algorithms typically employ Hidden Markov model (HMM) via shortest path computation. But the computation of the shortest path might not work well on low-sampling-rate trajectory data (e.g., one GPS point every 1–5 min), leading to low matching precision and high running time. To solve the problem, this paper firstly identifies frequent patterns (FPs) in historical trajectories to capture meaningful mobility behaviors, and then extracts mobile behavior criterion (MBC) of mobile users. Such a criterion generally represents the route choice of mobile users on road networks. Moreover, the temporal information within trajectory data was employed to estimate the speed of mobile users on road segments. The identified FPs, coupled with MBC and moving speed, help to improve the map-matching precision of low-sampling-rate trajectories. In addition, an FP-forest structure was proposed to index the identified FPs. The structure could greatly speed up the lookup of frequent paths for shorter running time. Furthermore, the FP-forest structure was pruned to reduce redundancy with smaller space cost. Finally, experiments were carried out on real-world datasets. The results confirm that our FP-matching method outperforms state-of-the-art in terms of effectiveness and efficiency.

SOWCompact: A federated process mining method for social workflows

The exaggerated use of smartphones and growing informatization of the environment allows modeling people’s behavior as a process, namely, a social workflow, where both individual actions and interactions with other people are captured. This modelling includes actions that are part of an individual’s routine, as well as less frequent events. Although infrequent actions may provide relevant information, it is routine behaviors that characterize users. However, the extraction of this knowledge is not simple. Current process mining techniques face problems when analyzing large amounts of traces generated by many users. When very different behavioral patterns are integrated, the resulting social workflow does not clearly depict their behavior, either individually or as a group. Proposals based on frequent pattern mining aim to distinguish traces that characterize frequent behaviors from the rest. However, tools that allow grouping/filtering of users with a common behavior pattern are needed beforehand, to analyze each of these groups separately. This study presents the so-called federated process mining and an associated tool, SOWCompact, based on this concept. Its potential is validated through the case study called activities of daily living (ADL). Using federated process mining, along with current process mining techniques, more compact processes using only the social workflow’s most relevant information are obtained, while allowing (event enabling) the analysis of these social workflows.

Semantic Trajectory Frequent Pattern Mining Model

A method for mining frequent patterns of individual user trajectories is proposed based on location semantics. The semantic trajectory is obtained by inverse geocoding and preprocessed to obtain the Top-k candidate frequent location item sets, and then the spatio-temporal sequence intersection and the divide and conquer merge methods are used to convert the frequent iterative calculation of long itemsets into hierarchical sets' regular operations, the superset and subset of frequent sequences are found. This kind of semantic trajectory frequent pattern mining can actively identify and discover potential carpooling needs, and provide higher accuracy for location-based intelligent recommendations such as carpooling and HOV lane travel (High-Occupancy Vehicle Lane). Carpool matching and recommendation based on semantic trajectory in this paper is suitable for single carpooling and relay-ride carpooling. the results of simulation carpooling experiments prove the applicability and efficiency of the method.

IAMnet: Presentation of Parallelization Approach for Repetitive Mining on Network Topologies with an Improved Apriori Method

Recently, the discovery of association rules and the consequent mining frequent patterns have attracted the attention of many researchers to discover unknown relationships in big data, especially in networking and distributed environments. In this research, a parallelization-based approach is proposed to improve the performance of the Apriori algorithm in repetitive mining patterns on network topologies. The proposed approach includes two main features: (1) combining centrality criteria of the node and the Apriori algorithm to identify repetitive patterns and (2) using the mapping/reduction method to create parallel processing and achieve optimal values in the shortest time. This approach also pursues three main objectives: reducing the temporal and spatial complexity of the Apriori algorithm, improving the association rules mining process and identifying repetitive patterns, and comparing the proposed approach’s performance on different network topologies to determine the advantages and disadvantages of each topology. Comparing our proposed method and the basic Apriori algorithm, it is concluded that our approach provides acceptable efficiency in terms of evaluation criteria such as energy consumption, network lifetime, and runtime compared to other methods. Experimental results also show that when using our proposed method compared to the basic Apriori algorithm, network life is increased by 7.1%, the runtime is reduced by 43.2%, and the energy consumption is saved by about 41.2%.

Towards identifying context-enriched multimodal behavioral patterns for digital phenotyping of human behaviors

Digital phenotyping is a research area that proposes the automatic collection of context data through sensors available in pervasive devices, so allowing computational techniques capable of processing this data to automatically detect human behaviors (e.g., sociability, physical activity). This objective information can support professionals specialized in the process of monitoring and treating mental health of individuals. Based on this scenario, we present a solution capable of processing behavioral inference streams to recognize multimodal patterns of sociability, physical activity, and home stay. The proposed solution combines frequent pattern mining with complex event processing, enabling it to incrementally learn periods of the day that compose individuals’ behavioral habits (i.e., behavioral patterns). The identification of these patterns is performed based on context attributes to model individuals’ behavior in specific situations, such as weekends and working days. Our solution also recognizes behavioral changes through knowledge modeling of the mental health specialist from fuzzy logic concepts. The experiments performed identified that the routine stability of individuals presents a high positive correlation with the ability of our solution to recognize multimodal behavioral patterns capable of modeling the behavioral routine. This evaluation also recognizes that our solution has sensitivity to identify behavioral changes.

Special issue on big data in transportation

Optimization and analysis of transportation systems have become considerably more autonomous and smarter by using connectivity and automation to overcome urbanization problems, such as an ever-growing population, increasing personal travel activities, limited budgets for infrastructure deployments and so on. With this in mind, there is an increasing need for high cooperation both strategically and operationally among different types of transportation modes, each with different objectives and policies. More than ever, Intelligent Transportation Systems (ITS) are playing a significant role in providing efficient integration and cooperation among different technologies and services, and complex and diverse multi-source ITS data have increased massively. Those valuable vast amounts of data can be handled by big data analytics in terms of providing efficient, safe and convenient ITS operations. Through big data–oriented emerging technologies, traffic becomes more intelligent, more manageable and safer. This special issue focusses on data science, data systems and transportation science and their applications to deliver effective and efficient solutions to the current challenges of handling big data in real-world ITS applications. From 19 submitted articles to this special issue, 4 articles were selected based on their reviews. Each article was reviewed by at least two reviewers and went through at least two rounds of reviews. The contributions of these articles are discussed in brief below. Claudio Teixeira, Luana Fragoso, Marta Mattoso, Diego Carvalho, Eduardo Bezerra, Jorge Soares, Glauco Amorim and Eduardo Ogasawara, ‘A horizontal partitioning-based method for frequent pattern mining in transport timetable’. A public transportation timetable is a document that provides information about public transportation service times to help passengers plan their trip. The timetable will often include the times when a service is scheduled to arrive and depart from specific places. T-mine, a unique frequent pattern mining (FPM) technique for improving knowledge discovery in timetable datasets, is presented in this study to solve the issues of lowering FPM computational cost and redundancy in association rules (AR). Authors show that the T-mine can generate a greater number of distinct, non-redundant and contextualized ARs than the traditional approach without functional dependency. Zain Ul Abideen, Heli Sun, Zhou Yang and Hamza Fahim, ‘Regional based Multi-Module Spatial-Temporal Networks Predicting City-wide Taxi Pickup/Dropoff demand from Origin to Destination’. Accurate forecasting of taxi demand is essential for drivers, riders, ride-hailing businesses and zonal directors. The goal of this work, in the future time interval between all areas estimating taxi demand, is to handle city-wide taxi demand origin–destination (OD) forecasting by Multi-Module Spatial–Temporal Networks (MMSTNs), which is a subject worth studying. Authors do a lot of tests on a real-world dataset called NYCTaxi to show how they can anticipate taxi demand around the city. They also show that their method surpasses prior strategies in terms of accuracy. Fethullah Gocer and Nazmi Sener, ‘Spherical Fuzzy Extension of AHP-ARAS Methods Integrated with Modified k-Means Clustering for Logistics Hub Location Problem’. A hub location problem (HLP) is concerned with where facilities should be located and how demand nodes should be allocated to hubs in order to route goods flow to o-d lowest cost pathways. Using a modified weighted k-means clustering algorithm and Multi-Criteria Decision-Making (MCDM) tools under a spherical fuzzy set environment, this work suggests a two-layered methodology to address the logistic HLP. An application of the network structure for postal/cargo operations in Turkey demonstrates the validity of the suggested assessment model. Iván García-Aguilar, Rafael Marcos Luque-Baena and Ezequiel López-Rubio, ‘Improved detection of small objects in road network sequences using CNN and super resolution’. The authors provide a new approach that uses deep convolutional neural networks for super-resolution to identify small-scale visual objects (educed size elements) and enhance the accuracy of class prediction. The results demonstrate that using super-resolution techniques improves the detections made on an image from video surveillance systems. The guest editors hope that the research contributions and findings in this special issue will benefit the readers in enhancing their knowledge and encouraging them to work on various aspects of Big Data in transportation. We want to express our sincere thanks to the Editor-in-Chief for and Special Issue Editor of Expert Systems for allowing us to organize this issue. The editorial office staff are excellent, and we thank them for their support. We are also thankful to all the authors who made this special issue possible and to the reviewers for their thoughtful contributions.

An Efficient Parallel Algorithm for Frequent Itemsets Mining Using BitTable on Spark

A variety of techniques have been used to improve the performance of an algorithm in finding frequent item sets, which is one of the important processes to obtain frequent pattern mining. It was found that today’s technology has resulted in an ever-increasing amount of information, which should be analyzed for various benefits. Therefore, efforts have been made to improve the aalgoruthm’s efficiency to accommodate the nature of data stored through the working process of the main internal memory. Efforts have been made to prepare algorithms for the ever-increasing information. This research provided an appropriate data structure of BitTable to help improve the functionality of the algorithms. Moreover, the principle of parallel frequent itemset mining algorithm based on Map-Reduce design was used in this research to assess the performance of algorithms, named as Adaptive Hybrid Parallel Algorithm (AHP). Additionally, to investigate the performance of the AHP Algorithm Using Apache Spark Technology with the type of data that was accumulated during the process of the main internal memory.