Frequent Pattern Mining Research Articles

Exploring Crowd Travel Demands Based on the Characteristics of Spatiotemporal Interaction between Urban Functional Zones

As a hot research topic in urban geography, spatiotemporal interaction analysis has been used to detect the hotspot mobility patterns of crowds and urban structures based on the origin-destination (OD) flow data, which provide useful information for urban planning and traffic management applications. However, existing methods mainly focus on the detection of explicit spatial interaction patterns (such as spatial flow clusters) in OD flow data, with less attention to the discovery of underlying crowd travel demands. Therefore, this paper proposes a framework to discover the crowd travel demands by associating the dynamic spatiotemporal interaction patterns and the contextual semantic features of the geographical environment. With urban functional zones (UFZs) as the basic units of human mobility in urban spaces, this paper gives a case study in Wuhan, China, to detect and interpret the human mobility patterns based on the characteristics of spatiotemporal interaction between UFZs. Firstly, we build the spatiotemporal interaction matrix based on the OD flows of different UFZs and analyze the characteristics of the interaction matrix. Then, hotspot poles, defined as the local areas where people gather significantly, are extracted using the Gi-statistic-based spatial hotspot detection algorithm. Next, we develop a frequent interaction pattern mining method to detect the frequent interaction patterns of the hotspot poles. Finally, based on the detected frequent interaction patterns, we discover the travel demands of crowds with semantic features of corresponding urban functional zones. The characteristics of crowd travel distance and travel time are further discussed. Experiments with floating car data, road networks, and POIs in Wuhan were conducted, and results show that the underlying travel demands can be better discovered and interpreted by the proposed framework and methods in this paper. This study helps to understand the characteristics of human movement and can provide support for applications such as urban planning and facility optimization.

T-FSM: A Task-Based System for Massively Parallel Frequent Subgraph Pattern Mining from a Big Graph

Finding frequent subgraph patterns in a big graph is an important problem with many applications such as classifying chemical compounds and building indexes to speed up graph queries. Since this problem is NP-hard, some recent parallel systems have been developed to accelerate the mining. However, they often have a huge memory cost, very long running time, suboptimal load balancing, and possibly inaccurate results. In this paper, we propose an efficient system called T-FSM for parallel mining of frequent subgraph patterns in a big graph. T-FSM adopts a novel task-based execution engine design to ensure high concurrency, bounded memory consumption, and effective load balancing. It also supports a new anti-monotonic frequentness measure called Fraction-Score, which is more accurate than the widely used MNI measure. Our experiments show that T-FSM is orders of magnitude faster than SOTA systems for frequent subgraph pattern mining. Our system code has been released at https://github.com/lyuheng/T-FSM.

Incrementally Mining Column Constant Biclusters with FVSFP Tree

Bicluster mining has been frequently studied in the data mining field. Because column constant biclusters (CCB) can be transformed to be discriminative rules, they have been widely applied in various fields. However, no research on incrementally mining CCB has been reported in the literature. In real situations, due to the limitation of computation resources (such as memory), it is impossible to mine biclusters from very large datasets. Therefore, in this study, we propose an incremental mining CCB method. CCB can be deemed as a special case of frequent pattern (FP). Currently the most frequently used method for incrementally mining frequent patterns is FP tree based method. In this study, we innovatively propose an incremental mining CCB method with modified FP tree data structure. The technical contributions lie in two aspects. The first aspect is that we propose a modified FP tree data structure, namely Feature Value Sorting Frequent Pattern (FVSFP) tree that can be easily maintained. The second aspect is that we innovatively design a method for mining CCB from FVSFP tree. To verify the performance of the proposed method, it is tested on several datasets. Experimental results demonstrated that the proposed method has good performance for incrementally handling a newly added dataset.

MBA: Market Basket Analysis Using Frequent Pattern Mining Techniques

This Market Basket Analysis (MBA) is a data mining technique that uses frequent pattern mining algorithms to discover patterns of co-occurrence among items that are frequently purchased together. It is commonly used in retail and e-commerce businesses to generate association rules that describe the relationships between different items, and to make recommendations to customers based on their previous purchases. MBA is a powerful tool for identifying patterns of co-occurrence and generating insights that can improve sales and marketing strategies. Although a numerous works has been carried out to handle the computational cost for discovering the frequent itemsets, but it still needs more exploration and developments. In this paper, we introduce an efficient Bitwise-Based data structure technique for mining frequent pattern in large-scale databases. The algorithm scans the original database once, using the Bitwise-Based data representations as well as vertical database layout, compared to the well-known Apriori and FP-Growth algorithm. Bitwise-Based technique enhance the problems of multiple passes over the original database, hence, minimizes the execution time. Extensive experiments have been carried out to validate our technique, which outperform Apriori, Éclat, FP-growth, and H-mine in terms of execution time for Market Basket Analysis.

Bidirectional Recurrent Network and Neuro-fuzzy Frequent Pattern Mining for Heart Disease Prediction

Bidirectional Recurrent Network and Neuro-fuzzy Frequent Pattern Mining for Heart Disease Prediction

Fast Frequent Patterns Mining by Multiple Sampling With Tight Guarantee Under Bayesian Statistics.

Sampling from large dataset is commonly used in the frequent patterns (FPs) mining. To tightly and theoretically guarantee the quality of the FPs obtained from samples, current methods theoretically stabilize the supports of all the patterns in random samples, despite only FPs do matter, so they always overestimate the sample size. We propose an algorithm called multiple sampling-based FPs mining (MSFP). The MSFP first generates the set of approximate frequent items (AFI), and uses the AFI to form the set of approximate FPs without supports ( AFP*), where it does not stabilize the value of any item's or pattern's support, but only stabilizes the relationship ≥ or < between the support and the minimum support, so the MSFP can use small samples to successively obtain the AFI and AFP*, and can successively prune the patterns not contained by the AFI and not in the AFP*. Then, the MSFP introduces the Bayesian statistics to only stabilize the values of supports of AFP*'s patterns. If a pattern's support in the original dataset is unknown, the MSFP regards it as random, and keeps updating its distribution by its approximations obtained from the samples taken in the progressive sampling, so the error probability can be bound better. Furthermore, to reduce the I/O processes in the progressive sampling, the MSFP stores a large enough random sample in memory in advance. The experiments show that the MSFP is reliable and efficient.

MaNIACS : Approximate Mining of Frequent Subgraph Patterns through Sampling

We present MaNIACS , a sampling-based randomized algorithm for computing high-quality approximations of the collection of the subgraph patterns that are frequent in a single, large, vertex-labeled graph, according to the Minimum Node Image-based (MNI) frequency measure. The output of MaNIACS comes with strong probabilistic guarantees, obtained by using the empirical Vapnik–Chervonenkis (VC) dimension, a key concept from statistical learning theory, together with strong probabilistic tail bounds on the difference between the frequency of a pattern in the sample and its exact frequency. MaNIACS leverages properties of the MNI-frequency to aggressively prune the pattern search space, and thus to reduce the time spent in exploring subspaces that contain no frequent patterns. In turn, this pruning leads to better bounds to the maximum frequency estimation error, which leads to increased pruning, resulting in a beneficial feedback effect. The results of our experimental evaluation of MaNIACS on real graphs show that it returns high-quality collections of frequent patterns in large graphs up to two orders of magnitude faster than the exact algorithm.

Frequent Alarm Pattern Mining of Industrial Alarm Flood Sequences by an Improved PrefixSpan Algorithm

Alarm systems are essential to the process safety and efficiency of complex industrial facilities. However, with the increasing size of plants and the growing complexity of industrial processes, alarm flooding is becoming a serious problem and posing challenges to alarm systems. Extracting alarm patterns from an alarm flood database can assist with an alarm root cause analysis, decision support, and the configuration of an alarm suppression model. However, due to the large size of the alarm database and the problem of sequence ambiguity in the alarm sequence, existing algorithms suffer from excessive computational overhead, incomplete alarm patterns, and redundant outputs. In order to solve these problems, we propose an alarm pattern extraction method based on the improved PrefixSpan algorithm. Firstly, a priority-based pre-matching strategy is proposed to cluster similar sequences in advance. Secondly, we improved PrefixSpan by considering timestamps to tolerate short-term order ambiguity in alarm flood sequences. Thirdly, an alarm pattern compression method is proposed for the further distillation of pattern information in order to output representative alarm patterns. Finally, we evaluated the effectiveness and applicability of the proposed method by using an alarm flood database from a real diesel hydrogenation unit.

SMS SPAM DETECTION USING MACHINE LEARNING

In recent times, there has been considerable interest among people to use short communication service (SMS) as one of the essential and straightforward dispatches services on mobile bias. The increased popularity of this service also increased the number of mobile bias attacks similar as SMS spam dispatches. SMS spam dispatches constitute a real problem to mobile subscribers. this worries telecommunication service providers as it disturbs their guests and causes them to lose business. to enhanced SMS spam filtering performance by combining two of data mining task association and bracket. FP- growth in association is employed for mining frequent pattern on SMS and Naive Bayes Classifier is used to classify whether SMS is spam or ham. Training data was using SMS spam collection from former exploration. The result of using collaboration of Naive Bayes and FP- Growth performs the highest average accuracy of 98,506 and 0.025% better than without using FP- Growth for dataset SMS Spam Collection v. 1, and improves the perfection score; therefore, the bracket result is more accurate.

Human behavior in the time of COVID-19: Learning from big data.

Since the World Health Organization (WHO) characterized COVID-19 as a pandemic in March 2020, there have been over 600 million confirmed cases of COVID-19 and more than six million deaths as of October 2022. The relationship between the COVID-19 pandemic and human behavior is complicated. On one hand, human behavior is found to shape the spread of the disease. On the other hand, the pandemic has impacted and even changed human behavior in almost every aspect. To provide a holistic understanding of the complex interplay between human behavior and the COVID-19 pandemic, researchers have been employing big data techniques such as natural language processing, computer vision, audio signal processing, frequent pattern mining, and machine learning. In this study, we present an overview of the existing studies on using big data techniques to study human behavior in the time of the COVID-19 pandemic. In particular, we categorize these studies into three groups-using big data to measure, model, and leverage human behavior, respectively. The related tasks, data, and methods are summarized accordingly. To provide more insights into how to fight the COVID-19 pandemic and future global catastrophes, we further discuss challenges and potential opportunities.

Frequent pattern-based parallel search approach for time-dependent agile earth observation satellite scheduling

To address the time-dependent agile earth observation satellite (AEOS) scheduling problem more effectively, the frequent pattern-based parallel search (FPBPS) algorithm is proposed, which is composed of a parallel local search procedure, a competition-based algorithm and operator adaptive selection procedure and the new solutions construction method based on frequent pattern. First, the algorithm and the operator are selected from the algorithm pool and operator pool and run in parallel. As a result, some high-quality and diverse solutions are obtained in a short time. Second, we update the probability of each algorithm and operator to strengthen the self-adaptive ability of the algorithm. Third, frequent pattern mining method is used to extract knowledge with respect to AEOS scheduling to construct new solutions, and parallel local search is applied to further improve these solutions. Finally, extensive experiments prove that the FPBPS algorithm has a better performance than other comparison algorithms in the quality of solution, computation time, and robustness.

Frequent pattern mining-based log file partition for process mining

Process mining is a technique for exploring models based on event sequences, growing in popularity in the process industry. Process mining algorithms assume that the processed log files contain events generated by only one unknown process, which can lead to extremely complex and inaccurate models when this assumption is not met. To address this issue, this article proposes a frequent pattern mining-based method for log file partitioning, allowing for the exploration of parallel processes. The key idea is that frequent pattern mining can identify grouped events and generate sub-logs of overlapping sub-processes. Thanks to the pre-processing of the log files, more compact and interpretable process models can be identified. We developed a set of goal-oriented metrics to evaluate the complexity of process mining problems and the resulting models. The applicability and effectiveness of the method are demonstrated in the analysis of process alarms of an industrial plant. The results confirm that the proposed method enables the discovery of targeted sub-process models by partitioning the log file using frequent pattern mining, and the effectiveness of the method increases with the number of parallel processes stored in the same log file. We recommend applying the method in every case where there is no clear start and end of the logged events so that the log file can describe different processes.

Mining periodic high-utility itemsets with both positive and negative utilities

Mining high-utility patterns in databases containing items with both positive and negative profits is useful in market basket databases, since negative profits are common in the real world. Obviously, in the market basket database, patterns with stable long-term profits have more meaning. The discovery of itemsets with a consistent high frequency is known as periodic frequent pattern mining. Therefore, mining periodic high-utility patterns in a database containing items with both positive and negative profits is an interesting and useful task. However, this task has two main challenges. First, the utility measure does not have the download closure property. Second, the huge search space needs to be pruned more effectively. In this paper, we propose a vertical data structure-based algorithm called PHMN to discover periodic high-utility patterns (PHUPs) or itemsets in a transaction database with both positive and negative utilities. To be more efficient, we propose a new upper bound to prune the search space and an improved algorithm to discover the PHUPs. Finally, experiments are conducted to verify the effectiveness and efficiency of algorithms.

Discovering periodic frequent travel patterns of individual metro passengers considering different time granularities and station attributes

Periodic frequent pattern discovery is a non-trivial task to discover frequent patterns based on user interests using a periodicity measure. Although conventional algorithms for periodic frequent pattern detection have numerous applications, there is still little research on periodic frequent pattern detection of individual passengers in the metro. The travel behavior of individual passengers has complex spatio-temporal characteristics in the metro network, which may pose new challenges in discovering periodic frequent patterns of individual metro passengers and developing mining algorithms based on real-world smart card data. This study addresses these issues by proposing a novel pattern for metro passenger travel pattern called periodic frequent passenger traffic patterns with time granularities and station attributes (PFPTS). This discovered pattern can automatically capture the features of the temporal dimension (morning and evening peak hours, week) and the spatial dimension (entering and leaving stations). The corresponding complete mining algorithm with the PFPTS-tree structure has been developed. To evaluate the performance of PFPTS-tree, several experiments are conducted on one-year real-world smart card data collected by an automatic fare collection system in a certain large metro network. The results show that PFPTS-Tree is efficient and can discover numerous interesting periodic frequent patterns of metro passengers in the real-world dataset.

Performance analysis of frequent pattern mining algorithm on different real-life dataset

&lt;span lang="EN-US"&gt;The efficient finding of common patterns: a group of items that appear frequently in a dataset is a critical task in data mining, especially in transaction datasets. The goal of this paper is to look into the efficiency of various algorithms for frequent pattern mining in terms of computing time and memory consumption, as well as the problem of how to apply the algorithms to different datasets. In this paper, the algorithms investigated for mining the frequent patterns are; Pre-post, Pre-post+, FIN, H-mine, R-Elim, and estDec+ algorithms. These algorithms have been implemented and tested on four real-life datasets that are: The retail dataset, the Accidents dataset, the Chess dataset, and the Mushrooms dataset. From the results, it has been observed that, for the Retail dataset, estDec+ algorithm is the fastest among all algorithms in terms of run time as well as consumes less memory for its execution. Pre-post+ algorithm performs better than all other algorithms in terms of run time and maximum memory for the Mushrooms dataset. Pre-Post outperforms other algorithms in terms of performance. And for Accident datasets, in terms of execution time and memory consumption, the FIN method outperforms other algorithms.&lt;/span&gt;

Seq2Pat: Sequence‐to‐pattern generation to bridge pattern mining with machine learning

AbstractPattern mining is an essential part of knowledge discovery and data analytics. It is a powerful paradigm, especially when combined with constraint reasoning. In this overview, we showcase Seq2Pat, a constraint‐based sequential pattern mining (SPM) tool with a high‐level declarative user interface. The library finds frequent patterns in large sequence databases subject to constraints. We highlight key benefits especially desirable in industrial settings where scalability, explainability, rapid experimentation, reusability, and reproducibility are of great practical interest. We then bridge SPM with supervised machine learning via dichotomic pattern mining (DPM). DPM exploits the dichotomy between outcomes correlated with patterns that uniquely distinguish them. Last, we present an automated feature extraction powered by Seq2Pat and DPM to discover high‐level insights and boost downstream machine learning models for intent prediction in digital behavior analysis.

A Vertex-extension based Algorithm for Frequent Pattern Mining from Graph Databases

Frequent pattern mining is a core problem in data mining. Algorithms for frequent pattern mining have been proposed for itemsets, sequences, and graphs. However, existing graph mining frameworks follow an edge-growth approach to building patterns which limits many applications. Motivated by real-life problems, in this work, we define a novel graph mining framework that incorporates vertex-based extensions along with the edge-growth approach. We also propose an efficient algorithm for mining frequent subgraphs. To deal with the exploding search space, we introduce a canonical labeling technique for isomorphic candidates as well as downward closure property-based search space pruning. We present an experimental analysis of our algorithm on real-life benchmark graph datasets to demonstrate the performance in terms of runtime. DUJASE Vol. 7(1) 58-65, 2022 (January)

Planning Flexible Bus Service as an Alternative to Suspended Bicycle-Sharing Service: A Data-Driven Approach

Many free-floating bicycle-sharing (FFBS) operators in cold region cities will put bicycles in warehouses and suspend services in winter due to factors such as safety and maintenance costs, resulting in the corresponding travel demand no longer be met. Considering the short-distance and green travel characteristics of FFBS, the flexible bus, as a sustainable demand-responsive transit service, is a suitable alternative transportation mode. To operate such a flexible bus system, service area and operation time planning is a key stage, however, the planning methods in relevant studies are not suitable for this research scenario. In view of the above, this paper proposed a data-driven method to determine the service area and operation time of flexible buses based on FFBS data. Firstly, an FFBS trip path reconstruction algorithm consists of fine-grained road network modelling and trajectory matching is proposed. Then, in the defined time slice, incorporating the idea of ride-sharing routes generation, according to the density-based clustering principle and considering topology between trajectories, a path clustering algorithm PATHSCAN is developed to generate the one-day path clusters. After that, a frequent pattern mining algorithm is applied to the multiday path clusters, and frequent pattern results with spatio-temporal correlation will be merged into the final service area. The generated planning results will cover ride-matching trips and high-frequency riding paths. Detailed application analysis and verification are carried out by using the real data from Tianjin, China. Through the evaluation and verification under the relatively limited experimental data set, the proposed data-driven method shows ideal planning results. Flexible bus service can supplement the green short-distance travel mode after the suspension of FFBS and can avoid FFBS travel demands switched to unsustainable transportation modes to a large extent. This study will contribute to urban sustainable transportation development and improving greenness.

A Multi-Label Classification with an Adversarial-Based Denoising Autoencoder for Medical Image Annotation

Medical image annotation aims to automatically describe the content of medical images. It helps doctors to understand the content of medical images and make better informed decisions like diagnoses. Existing methods mainly follow the approach for natural images and fail to emphasize the object abnormalities, which is the essence of medical images annotation. In light of this, we propose to transform the medical image annotation to a multi-label classification problem, where object abnormalities are focused directly. However, extant multi-label classification studies rely on arduous feature engineering, or do not solve label correlation issues well in medical images. To solve these problems, we propose a novel deep learning model where a frequent pattern mining component and an adversarial-based denoising autoencoder component are introduced. Extensive experiments are conducted on a real retinal image dataset to evaluate the performance of the proposed model. Results indicate that the proposed model significantly outperforms image captioning baselines and multi-label classification baselines.

Optimization assisted frequent pattern mining for data replication in cloud: Combining sealion and grey wolf algorithm

It is critical in cloud computing to have excellent data accessibility and system performance. To improve system availability, commonly used data should be duplicated to many places, allowing users to access it from a nearby site. Deciding on a sensible number and location for replicas is a difficult problem in cloud computing. Therefore, a novel Data Replication system based on data mining techniques is being proposed in this research work. The data replication is done here by locating commonly utilized data patterns in a node's massive database. This will be accomplished using an optimization-assisted frequent pattern mining approach, with a novel hybrid algorithm performing the best threshold selection. The proposed hybrid algorithm referred to as Greywolves Updated Exploration and Exploitation with Sealion Behaviour (GUEES), hybrids the concept of Sealion Optimization Model (SLnO) and Grey wolf optimization (GWO) algorithms. Apart from this, the mining will be carried out under the defining dual constraints such as (i) Prioritization and (ii) Cost. The prioritization falls under two cases: queuing both high and low-priority data, and the cost relies on the evaluation of storage demand. The high-priority queues are optimized with the GUEES model. Finally, a comparative validation is carried out to validate the efficiency of the adopted model. Accordingly, when the number of requests=1000, the network usage of the proposed model is 35.07%, 34.9%, 30.5%, 29.23%, 24.57%, 16.8%, and 16.85% higher than the existing methods like SMO, LA, ROA, GWO, SLnO, PSO, HCS, respectively.