Search

Existing unsupervised person re-identification (Re-ID) methods use clustering to generate pseudo-labels that are generally noisy, and initializing the model with ImageNet pre-training weights introduces a large domain gap that severely impacts the model's performance. To address the aforementioned issues, we propose the data complement pseudo-label refinement and self-guided pre-training framework, referred to as DCSG. Firstly, our method utilizes image information from multiple augmentation views to complement the source image data, resulting in aggregated information. We employ this aggregated information to design a correlation score that serves as a reliability evaluation for the source features and cluster centroids. By optimizing the pseudo-labels for each sample, we enhance their robustness. Secondly, we propose a pre-training strategy that leverages the potential information within the training process. This strategy involves mining classes with high similarity in the training set to guide model training and facilitate smooth pre-training. Consequently, the model acquires preliminary capabilities to distinguish pedestrian-related features at an early stage of training, thereby reducing the impact of domain gaps arising from ImageNet pre-training weights. Our method demonstrates superior performance on multiple person Re-ID datasets, validating the effectiveness of our proposed approach. Notably, it achieves an mAP metric of 84.3% on the Market1501 dataset, representing a 2.8% improvement compared to the state-of-the-art method. The code is available at https://github.com/duolaJohn/DCSG.git. [ABSTRACT FROM AUTHOR]

A large number of association rules often minimizes the reliability of data mining results; hence, a dimensionality reduction technique is crucial for data analysis. When analyzing massive datasets, existing models take more time to scan the entire database because they discover unnecessary items and transactions that are not necessary for data analysis. For this purpose, the Fuzzy Rough Set-based Horse Herd Optimization (FRS-HHO) algorithm is proposed to be integrated with the Map Reduce algorithm to minimize query retrieval time and improve performance. The HHO algorithm minimizes the number of unnecessary items and transactions with minimal support value from the dataset to maximize fitness based on multiple objectives such as support, confidence, interestingness, and lift to evaluate the quality of association rules. The feature value of each item in the population is obtained by a Map Reduce-based fitness function to generate optimal frequent itemsets with minimum time. The Horse Herd Optimization (HHO) is employed to solve the high-dimensional optimization problems. The proposed FRS-HHO approach takes less time to execute for dimensions and has a space complexity of 38% for a total of 10 k transactions. Also, the FRS-HHO approach offers a speedup rate of 17% and a 12% decrease in input–output communication cost when compared to other approaches. The proposed FRS-HHO model enhances performance in terms of execution time, space complexity, and speed. [ABSTRACT FROM AUTHOR]

Sustainable agriculture is becoming increasingly important in the face of growing environmental challenges. One key aspect of sustainable agriculture is managing soil resources effectively. In this context, digital soil mapping (DSM) has emerged as a powerful tool to understand soil variability better and inform land management decisions. This paper proposes a comprehensive data warehouse for DSM that supports climate change analysis. Our architecture integrates frequent itemset mining (FMI) and association rules mining (ARM) to extract insights from large‐scale soil data. We review related studies in soil data warehousing and ARM, identify gaps, and propose a data warehouse architecture leveraging the galaxy multidimensional model for DSM based on the SCORPAN model, which incorporates all relevant soil forming factors. We employ and compare A‐priori, FP‐growth, and ECLAT algorithms to efficiently mine frequent itemsets and generate association rules. Our intensive experiments evaluation demonstrates that FP‐growth outperforms the other algorithms in accuracy, scalability, and speed and requires less memory. Additionally, we utilized correlation metrics for ARM, such as lift, cosine, kulc, and Imbalance ratio, to obtain the most significant and relevant association rules. These rules provide valuable insights into the complex relationships between soil properties and environmental factors, which can inform land management decisions and improve sustainable agriculture practices. This work contributes to the growing body of research on DSM and data‐driven approaches to sustainable agriculture. [ABSTRACT FROM AUTHOR]

Frequent itemset mining (FIM) is a major component in association rule mining, significantly influencing its performance. FIM is a computationally intensive nondeterministic polynomial time (NP)-hard problem. At the core of FIM is the task of computing support of candidate itemsets. This problem becomes more severe when the dataset is dense as the support is computed for millions, or even billions, of candidate itemsets. The rapid growth of data further exacerbates this problem. To achieve high scalability and efficiency, recently, researchers have proposed various approaches to approximate the support of an itemset using as small a subset of transaction data as possible. In addition to efficiency, accuracy is another important metric for these algorithms. They strive to increase true positives and reduce false negatives and false positives. One such recently proposed approximate FIM algorithm is Probabilistic Breadth-First (ProbBF), which is highly efficient for dense data due to its unique approach of not using transactional data beyond 2-size itemsets. Unlike other counterparts, this algorithm requires no additional input parameters beyond the traditional support threshold. However, ProbBF is a breadth-first algorithm, and it is well-established that breadth-first FIM algorithms consume significantly more memory than depth-first algorithms on dense datasets. It is also worth noting that significantly high memory consumption slows run-time performance of an algorithm due to low utilization of locality of reference, thrashing, and aggressive garbage collection etc. This article proposes a FIM algorithm, ProbDF, that discards transaction data after determining all frequent itemsets of sizes one and two. For frequent itemsets of size three or more, it employs a probabilistic support prediction model (PSPM) to predict their support probabilistically. PSPM, first proposed with ProbBF, uses lightweight calculations that exclude transaction data. Our experiments demonstrate that ProbDF, with its depth-first search strategy tailored to PSPM and other optimizations, is efficient in terms of time and space, and successfully generates the majority of frequent itemsets on real-world benchmark datasets. However, due to the probabilistic nature of ProbDF, some compromise in quality is inevitable.

One of the most important problems that arises during the knowledge discovery from data and data mining process in many new emerging technologies is mining data with temporal dependencies. One such application is activity recognition and prediction. Activity recognition is used in many real world settings, such as assisted living systems. Although activity recognition has been vastly studied by many researchers, the temporal features that constitute an activity, which can provide useful insights for activity models, have not been exploited to their full potentials by mining algorithms. In this paper, we utilize temporal features for activity recognition and prediction in assisted living settings. We discover temporal relations such as the order of activities, as well as their corresponding start time and duration features. Analysis of real data collected from smart homes was used to validate the proposed method. [ABSTRACT FROM AUTHOR]

It is obvious that the problem of Frequent Itemset Mining (FIM) is very popular in data mining, which generates frequent itemsets from a transaction database. An extension of the frequent itemset mining is High Utility Itemset Mining (HUIM) which identifies itemsets with high utility from the transaction database. This gains popularity in data mining, because it identifies itemsets which have more value but the same was not identified as frequent by Frequent Itemset Mining. HUIM is generally referred to as Utility Mining. The utility of the items is measured based on parameters like cost, profit, quantity or any other measures preferred by the users. Compared to high utility itemsets (HUIs) mining, high average utility itemsets (HAUIs) mining is more precise by considering the number of items in the itemsets. In state-of-the-art algorithms that mines HUIS and HAUIs use a single fixed minimum utility threshold based on which HAUIs are identified. In this paper, the proposed algorithm mines HAUIs from transaction databases using Artificial Fish Swarm Algorithm (AFSA) with computed multiple minimum average utility thresholds. Computing the minimum average utility threshold for each item with the AFSA algorithm outperforms other state-of-the-art HAUI mining algorithms with multiple minimum utility thresholds and user-defined single minimum threshold in terms of number of HAUIs. It is observed that the proposed algorithm outperforms well in terms of execution time, number of candidates generated and memory consumption when compared to the state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

High Utility Itemset Mining (HUIM) is the process of locating itemsets that are profitable and useful to users. One of the key flaws in HUIM is that as the length of the itemset increases, the utility also increases. The true utility/profit of the itemset is not revealed in HUIM. High Average Utility Itemset mining overcomes the limitations of HUIM by taking the length of the itemset into account when estimating the utility. Existing pruning methods used for eliminating weak candidates overestimate the average usefulness of itemsets, causing the mining process to slow down. To prevent processing unpromising candidate itemsets and efficiently reduce the search space and processing time, the proposed methodology employs Upper Bound using Remaining Items Utility, Maximum Itemset Utility, and Sum of Maximum Utility in a Transaction. It also uses the multithreaded parallel approach to reduce the processing time. The H-Map-based data structure (H-Map) used for storing the utility values reduces the lookup time and joins used for itemset extension compared to existing state-of-the-art High Average Utility Itemset mining algorithms. The performance of the proposed work is evaluated in terms of memory usage and the time taken for processing. The proposed work increases the overall efficiency of the system employing effective pruning algorithms for pruning poor candidate itemsets and an efficient data structure for storing utility values. [ABSTRACT FROM AUTHOR]

Local differential privacy (LDP) approaches to collecting sensitive information for frequent itemset mining (FIM) can reliably guarantee privacy. Most current approaches to FIM under LDP add "padding and sampling" steps to obtain frequent itemsets and their frequencies because each user transaction represents a set of items. The current state-of-the-art approach, namely set-value itemset mining (SVSM), must balance variance and bias to achieve accurate results. Thus, an unbiased FIM approach with lower variance is highly promising. To narrow this gap, we propose an Item-Level LDP frequency oracle approach, named the Integrated-with-Hadamard-Transform-Based Frequency Oracle (IHFO). For the first time, Hadamard encoding is introduced to a set of values to encode all items into a fixed vector, and perturbation can be subsequently applied to the vector. An FIM approach, called optimized united itemset mining (O-UISM), is proposed to combine the padding-and-sampling-based frequency oracle (PSFO) and the IHFO into a framework for acquiring accurate frequent itemsets with their frequencies. Finally, we theoretically and experimentally demonstrate that O-UISM significantly outperforms the extant approaches in finding frequent itemsets and estimating their frequencies under the same privacy guarantee. [ABSTRACT FROM AUTHOR]

Frequent itemsets are itemsets that occur frequently in a dataset. Frequent itemset mining extracts specific itemsets with supports higher than or equal to a minimum support threshold. Many mining methods have been proposed but Apriori and FP-growth are still regarded as two prominent algorithms. The performance of the frequent itemset mining depends on many factors; one of them is searching the nodes while constructing the tree. This paper introduces a new prefix-tree structure called child structured frequent pattern tree (CSFP-tree), an FP-tree attached with a child search subtree to each node. The experimental results reveal that the CSFP-tree is superior to the FP-tree and its new variations for any kind of datasets. [ABSTRACT FROM AUTHOR]

Rapid advancement of industrial internet of things (IoT) technology has changed the supply chain network to an open system to meet the high demand for individualized products and provide better customer experiences. However the open-system supply chain has forced many small and midsize enterprises (SMEs) to adopt vertical integration by being divided into smaller companies with a distinctive business for each SME but a central alliance to produce a range of products and gain competencies. Therefore, existing models do not guarantee the protection of data privacy of individual SMEs. Moreover, especially for the IoT environment, collecting data in a secure way and revealing valuable knowledge in an IoT network is difficult. How to share data in a secure framework is of paramount importance in the internet of behavior field. In this article, a privacy-preserving data-mining framework is proposed for joint-venture industrial collaborative activities by combining federated learning and a “pre-large concept” of data-mining techniques. The novelty of the proposed approach is that, while mining high-utility itemsets (HUIs) from multiple datasets, it does not require direct data sharing. In the proposed method, the federated-learning framework can learn from aggregated learning parameters without scanning all data from different sets. The pre-large concept in this approach reduces the amount of scanning into different datasets. Thus, the approach makes it possible to train federated learning more quickly while protecting the privacy of individual data owners. The approach has been tested on real industrial datasets in a collaborative environment. Extensive experimental results show that the approach achieves high accuracy compared with conventional data-mining techniques while preserving the privacy of datasets. [ABSTRACT FROM AUTHOR]

In the data era, to simultaneously relieve the heavy computational burden of mining data information from data owners and protecting data privacy, privacy-preserving frequent itemset mining (PPFIM) is presented and has attracted much attention. In PPFIM, data owners and miners outsource the complex task of data mining to the cloud server, which supports strong storage and computing power, and the cloud server cannot extract additional data privacy other than that which is shown by data owners or miners. However, most existing solutions assume that cloud servers will honestly perform the mining process and return the correct results, whereas cloud services are usually provided by a charging third party that may in practice return incorrect results due to computation errors, malicious or criminal activities, etc. To solve this problem, in this paper, we present a verifiable PPFIM protocol on vertically partitioned databases to support the verifiability of the integrity of the mining results, where data owners can authorize the cloud server to perform federated mining on vertically partitioned databases without leaking data information and detect dishonest behaviors in the cloud server from the returned results. We adopt a dual cloud setting to enable data owners to be offline after uploading their encrypted databases to the cloud server, which further relieves the burden on data owners. We implement our protocol and give a detailed analysis in terms of verification accuracy, which shows that the dishonest behaviors of the cloud server can be detected with a probability close to 1 and a sacrifice of only a 1 % increase in database size. [ABSTRACT FROM AUTHOR]

Data mining is an essential technique in knowledge discovery which is widely used for pattern extraction and information classification. Extracting useful rules and knowledge by considering the relationships and association of the data is as an important data mining technique used for data analysis, called association rule mining (ARM). Several scans of the dataset are necessary to extract frequent patterns and association rules during a time-consuming process. Discovery of frequent patterns within data is the major phase of the ARM process, which is very expensive in terms of execution times. Powerful parallel systems with multiple graphics processing units (GPUs) and multiple general-purpose graphics processing units (GPGPUs) are appropriate choices to reduce the execution time. Although GPU architectures can speed up the mining process, a single GPU is usually unable to use a large amount of data to extract frequent patterns. It is therefore necessary to use multiple GPU processors on a system or distribute them within a network to improve the efficiency of parallelization. In this paper, multiple GPUs are parallelized to propose a new framework, called GPApbmp, for parallelization of the Apriori algorithm, which is a well-known level-wise frequent pattern mining method, for faster extraction of association rules. The proposed framework uses multiple GPUs, on which the dataset is distributed to reduce the execution time and the number of database scans in the Apriori method using a vertical approach. The experimental results on standard datasets show that the proposed method reduces the execution time speeds up the mining process. The results obtained from two and four parallelized NVidia GeForce 710 processors evaluated in CUDA. [ABSTRACT FROM AUTHOR]

Frequent itemset mining (FIM) is one of the prominent techniques to extract knowledge from transactional databases. Finding frequent itemsets becomes tiresome while dealing with large-scale datasets due to the enormous demand for computational resources. Cluster-based versions of FIM algorithms become a natural choice to make FIM algorithms efficient and scalable for large-scale datasets and to meet the ever-growing data needs. A variety of MapReduce-based algorithms on the Hadoop cluster has been developed to meet the expectations. Due to the iterative nature of the FIM algorithms, they are still unable to perform adequately. Bottlenecks associated with MapReduce-based FIMs include challenges originating from adapting FIM algorithms in parallel and distributed contexts, as well as reading and publishing intermediate results to HDFS, which necessitates significant disc and communication I/O. Many FIM algorithms have been redesigned on Spark to achieve efficiency for large-scale datasets by utilizing its in-memory processing capabilities. However, Spark-based FIM adaptations still face the same challenges except achieving memory efficiency. The limitations associated with basic FIM algorithms, such as repeated scanning of input data, massive candidate generation, and maintaining large conditional trees in memory, still need to be addressed. Also, tuning of Spark's shuffle behavior becomes important to control the communication overhead. In this paper, we propose a Spark-based algorithm, namely PartEclat. It uses the Eclat method in combination with the partitioning technique to gain efficiency and scalability. Vertical data format helps to avoid repeated scanning of input data to calculate individual support values. It utilizes the benefits of the partitioning technique to limit the movement of key-value pairs across the cluster nodes (shuffle overheads) during iterations. Also, it helps to deal efficiently with the memory requirements to handle large Transaction ID (TID) sets and computational overhead imposed in computing the intersection of these large TID sets. In-depth experiments with benchmark datasets have been conducted to gain insight into the efficiency and scalability performance of the algorithm. Experimental results show that the proposed scheme outperforms other Spark-based Eclat variants by reducing network and computing loads by approx. 25–40%. [ABSTRACT FROM AUTHOR]

Abstract Association rule learning algorithms have been applied to microarray datasets to find association rules among genes. With the development of microarray technology, larger datasets have been generated recently that challenge the current association rule learning algorithms. Specifically, the large number of items per transaction significantly increases the running time and memory consumption of such tasks. In this paper, we propose the Scalable Association Rule Learning (SARL) heuristic that efficiently learns gene-disease association rules and gene–gene association rules from large-scale microarray datasets. The rules are ranked based on their importance. Our experiments show the SARL algorithm outperforms the Apriori algorithm by one to three orders of magnitude.

Mining patterns is a core task in data analysis and, beyond issues of efficient enumeration, the selection of patterns constitutes a major challenge. The Minimum Description Length (MDL) principle, a model selection method grounded in information theory, has been applied to pattern mining with the aim to obtain compact high-quality sets of patterns. After giving an outline of relevant concepts from information theory and coding, we review MDL-based methods for mining different kinds of patterns from various types of data. Finally, we open a discussion on some issues regarding these methods. [ABSTRACT FROM AUTHOR]

Data collection and processing progress made data mining a popular tool among organizations in the last decades. Sharing information between companies could make this tool more beneficial for each party. However, there is a risk of sensitive knowledge disclosure. Shared data should be modified in such a way that sensitive relationships would be hidden. Since the discovery of frequent itemsets is one of the most effective data mining tools that firms use, privacy-preserving techniques are necessary for continuing frequent itemset mining. There are two types of approaches in the algorithmic nature: heuristic and exact. This paper presents an exact itemset hiding approach, which uses constraints for a better solution in terms of side effects and minimum distortion on the database. This distortion creates an asymmetric relation between the original and the sanitized database. To lessen the side effects of itemset hiding, we introduced the sibling itemset concept that is used for generating constraints. Additionally, our approach does not require frequent itemset mining executed before the hiding process. This gives our approach an advantage in total running time. We give an evaluation of our algorithm on some benchmark datasets. Our results show the effectiveness of our hiding approach and elimination of prior mining of itemsets is time efficient. [ABSTRACT FROM AUTHOR]

The overhead contact system (OCS), as the power source of electrified railway, has a complex composition and various types of faults, so it places high requirements on its fault prevention. In recent years, with the establishment of railway OCS fault database, association analysis has been used to implement fault prevention from system-wise perspective and provide guidance for operation and maintenance. However, due to the hierarchical structure of fault database, the existing frequent itemset mining has a lot of redundancy in the results, and cannot locate the most precise faults, which affects the decision-making and makes troubleshooting lack of pertinence. To address this issue, this paper proposed a new concept, called marginal frequent itemset, which is an itemset composed of as precise items as possible in hierarchical database that meets the threshold, and an alternative mining task: mining marginal frequent itemsets instead of all the frequent itemsets. Two methods, path transform and descending depth of itemset, are proposed for achieving mining a set of marginal frequent itemsets. Two novel measures, margin degree and marginal information quantity, are proposed to evaluate the content of the mining results. An efficient algorithm, named MFIM CL , is developed for mining cross-level marginal frequent itemsets from railway OCS fault database. Our performance study shows that MFIM CL has high performance and can obtain more key information and reduce the number of results. Furthermore, marginal frequent itemset mining can simplify the fault relation network constructed by association rules and optimize the decision-making process for fault prevention of railway OCS. • Marginal frequent itemset can locate the most precise items in the database with hierarchical structure in association analysis. • Margin degree and marginal information quantity are designed to evaluate the content of mining results. • The algorithm MFIM CL outperforms existent algorithms for railway fault and can reduce the redundancy of results. • The decision-making for maintenance based on fault relation network can be optimized by marginal frequent itemset mining. [ABSTRACT FROM AUTHOR]

Cloud Computing is a leading innovation technology that guides to access applications over the web. The data owner’s data can be gotten to and controlled in the cloud. Privacy has become conclusive in information-driven applications within the distributed outsourced information. There are numerous inquiries still coming up on the best way to accomplish a confided in a climate that monitors application and information in the cloud from unapproved users. For offering protection to the users, sporadically there is a need to encode the data before accomplishing any other process. The cryptography method is embraced for data privacy. In this paper, a privacy-preserving construction is intended for vertically partitioned data in the cloud with the assistance of the Fully Homomorphic Encryption method. In this work, the homomorphic encryption and the Fully Homomorphic Encryption method is taken into consideration. The performance of the Rule Mining algorithm namely Eclat is compared with the encryption algorithms. The examination result shows that the Fully Homomorphic Encryption is less time-consuming to generate rule in the cloud, regardless of the number of transactions.

Abstract Many algorithms have proposed to solve the association rule learning problem. However, most of these algorithms suffer from the problem of scalability either because of tremendous time complexity or memory usage, especially when the dataset is large and the minimum support (minsup) is set to a lower number. This paper introduces a heuristic approach based on divide-and-conquer which may exponentially reduce both the time complexity and memory usage to obtain approximate results that are close to the accurate results. It is shown from comparative experiments that the proposed heuristic approach can achieve significant speedup over existing algorithms.

Mining frequent itemsets is a contemporary research topic in the data-mining domain. Identifying frequent itemsets has acquired its significance due to recognized objectives in the field of association mining. The frequent itemset mining problem focuses on identifying frequent patterns and correspondence between the itemsets in the transactional database. Frequent itemset mining problems are time consuming when dealing with huge amounts of data and extracting the maximum number of the frequent itemsets from a large search space is a challenging process. Since the transactional database size is enormous, a stochastic method is applied to find optimal solutions. In this article, an integrated approach to extract frequent itemsets is proposed based on the cuckoo search and genetic algorithm. This integrated methodology is performed by merging the reproduction process of cuckoo species with the operators such as crossover and mutation in GA. First, a strategy to diversify the population and to discover maximum frequent patterns in the search process, Second, a neighborhood exploration strategy is applied for recurrent solutions to improve the accuracy. Finally, the proposed integrated approach is validated with respect to the solution quality and convergence rate. The integrated approach is verified using standard data instances. The ICSGA approach efficiently discovers the frequent patterns. The comparison results of the integrated approach are eminently productive than the other approaches in the literature. [ABSTRACT FROM AUTHOR]

One of the key problems in image retrieval systems is the presence of irrelevant and noisy image content. Such content can cause significant confusion for the system. Therefore, there is a need to represent images with only informative features in order to improve the retrieval performance of the system or any subsequent process. In this article, we propose a method to identify the informative features in a large-scale image collection. We apply the frequent itemset mining (FIM) approach to extract visual features patterns from a list of images of the same object. Then, we generate feature pairs to measure the significance of each feature depending on the co-occurrence with its neighbouring features. In addition, we apply this feature selection technique to localise the landmark in the image. The performance of the proposed method is evaluated in terms of average precision (AP) on two benchmark data sets and found that it gives a comparable retrieval performance over the bag of visual words baseline system and the previous methods. [ABSTRACT FROM AUTHOR]

When mining frequent itemsets (abbr. FIs) from dense datasets, it usually produces too many itemsets and results in the mining task to suffer from a very long execution time and high memory consumption. Frequent closed itemset (abbr. FCI) is a compact and lossless representation of FI. Mining FCIs can not only reduce the execution time and memory usage, but also reserve the complete information of FIs derived from FCIs. Although many studies have been proposed with various efficient methods for mining FCIs, few of them have developed algorithms for efficiently deriving FIs from FCIs. In this work, we propose two efficient algorithms named DFI-List and DFI-Growth for efficiently deriving FIs from FCIs. The both algorithms adopt depth-first search and divide-and-conquer methodology to derive all the FIs. DFI-List efficiently derives all the FIs with a vertical index structure called Cid List. DFI-Growth compresses the information of FCIs into tree structures and applies pattern-growth strategy to derive FIs from the trees. Empirical experiments show that DFI-List is the most efficient and scalable algorithm on the dense datasets. For example, when the minimum support threshold is set to 50% on the Chess dataset, DFI-List runs faster than LevelWise (Pasquier et al. Inf Syst 24(1): 25-46, 1999b) over 100 times. As for DFI-Growth, it is the most stable and memory efficient algorithm on the sparse datasets. Both DFI-Growth and DFI-List are superior to the state-of-the-art algorithm (Pasquier et al. Inf Syst 24(1): 25-46, 199b) in terms of execution time. [ABSTRACT FROM AUTHOR]

Association rule learning algorithms have been applied to microarray datasets to find association rules among genes. With the development of microarray technology, larger datasets have been generated recently that challenge the current association rule learning algorithms. Specifically, the large number of items per transaction significantly increases the running time and memory consumption of such tasks. In this paper, we propose the Scalable Association Rule Learning (SARL) heuristic that efficiently learns gene-disease association rules and gene–gene association rules from large-scale microarray datasets. The rules are ranked based on their importance. Our experiments show the SARL algorithm outperforms the Apriori algorithm by one to three orders of magnitude. [ABSTRACT FROM AUTHOR]

Association rule mining (ARM) is a data mining technique to discover interesting associations between datasets. The frequent pattern-growth (FP-growth) is an effective ARM algorithm for compressing information in the tree structure. However, it tends to suffer from the performance gap when processing large databases because of its mining procedure. This study presents a modified FP-growth (MFP-growth) algorithm to enhance the efficiency of the FP-growth by obviating the need for recurrent creation of conditional subtrees. The proposed algorithm uses a header table configuration to reduce the complexity of the whole frequent pattern tree. Four experimental series are conducted using different benchmark datasets to analyze the operating efficiency of the proposed MFP-growth algorithm compared with state-of-the-art machine learning algorithms in terms of runtime, memory consumption, and the effectiveness of generated rules. The experimental results confirm the superiority of the MFP-growth algorithm, which focuses on its potential implementations in various contexts. [ABSTRACT FROM AUTHOR]

Laboratory tests play an essential role in the early and accurate diagnosis of diseases. In this paper, we propose SUNRISE, a visual analytics system that allows the user to interactively explore the relationships between laboratory test results and a disease outcome. SUNRISE integrates frequent itemset mining (i.e., Eclat algorithm) with extreme gradient boosting (XGBoost) to develop more specialized and accurate prediction models. It also includes interactive visualizations to allow the user to interact with the model and track the decision process. SUNRISE helps the user probe the prediction model by generating input examples and observing how the model responds. Furthermore, it improves the user's confidence in the generated predictions and provides them the means to validate the model's response by illustrating the underlying working mechanism of the prediction models through visualization representations. SUNRISE offers a balanced distribution of processing load through the seamless integration of analytical methods with interactive visual representations to support the user's cognitive tasks. We demonstrate the usefulness of SUNRISE through a usage scenario of exploring the association between laboratory test results and acute kidney injury, using large provincial healthcare databases from Ontario, Canada. [ABSTRACT FROM AUTHOR]