Class Association Rules Research Articles

Identifying attribute associations in fatal speeding crashes using latent class clustering and association rule mining

Identifying attribute associations in fatal speeding crashes using latent class clustering and association rule mining

CfExplainer: Explainable just-in-time defect prediction based on counterfactuals

Just-in-time (JIT) defect prediction helps rationally allocate testing resources and reduce testing costs. However, most JIT defect prediction models lack explainability, which significantly affects their credibility. Recently, the local interpretable model-agnostic explanations (LIME) method has been used widely in model-explainable research, and many improved LIME-based methods have been proposed. However, problems with respect to explanation effectiveness and reliability remain, which seriously affects the practical use of LIME. To address this problem, CfExplainer, a local rule-based model-agnostic approach, is proposed. The approach first applies counterfactuals to generate synthetic instances. It then mines weighted class association rules based on synthetic instances, and it optimises the process of generating, ranking, pruning, and predicting the class association rules. Next, it employs the rules with the highest priority to explain the prediction results of the model. Experiments were conducted using the public datasets employed in related studies. Compared to other state-of-the-art methods, in terms of explanation effectiveness, CfExplainer's instance similarity improves by 26.5 %-31.2 %, and local model fittness improves by 2.0 %-3.5 %, 2.3 %-3 %, and 0.7 %-7.5 % on the AUC, F1-score, and Popt metrics, respectively. In terms of the reliability of the explanation, explanations that are 2.6 %-4.7 % more unique and 2.5 %-5.9 % more consistent with the actual characteristics of defect-introducing commits than other state-of-the-art methods. Thus, the explanations of the proposed approach can enhance the model credibility and help guide developers in fixing defects and reducing the risk of introducing them.

N-SOFT SETS ASSOCIATION RULE AND ITS APPLICATION FOR PROMOTION STRATEGY IN DISTANCE EDUCATION

In everyday life, we always encounter obstacles in seeing the interrelationships between several events to make the right decisions. Universitas Terbuka is a pioneer in distance education that implements digital transformation for new student registration, student services, and alums. The obstacle faced is determining a suitable promotion strategy for new students. As a result, a representative model is needed to handle such cases. As an extension of soft sets, N-soft sets can handle decision-making for binary and non-binary assessments. However, research has yet to be related to N-soft sets decision-making in data mining, especially association rule classification. This article proposes a new combination of N-soft sets with Association Rule (NSSAR). This article also introduces and applies the decision-making procedure using NSSAR to real. The population is new students of Universitas Terbuka Jakarta in the 2023/2024 odd semester. Samples were taken randomly using a questionnaire—primary data obtained by 201 new students. The following results are obtained based on the processed sample data using the NSSAR algorithm: 1) new students from Universitas Terbuka Jakarta are predominantly from Vocational High Schools domiciled in Bekasi, majoring in Bachelor of Management from the Faculty of Economics and Business; 2) The most favorite media information used by new UT Jakarta students is Instagram. Based on the results, the NSSAR algorithm gave relationship patterns between the number of new students based on region, study program, diploma of origin, and information media. Therefore, policymakers should consider the right promotional strategy to increase the number of students.

Investigating the contributing factors of crashes on interstate bridges in Louisiana using latent class clustering and association rule mining

Drivers on long bridges on interstates often face unique challenges, such as restricted lane width, inadequate shoulders, and a lack of clear zones for safe recoveries. Studies on understanding the factors that contribute to crash severity on such high-risk sections of interstates are limited. This research study applies latent class clustering (LCC) to detect homogeneous clusters while accounting for unobserved heterogeneity in a dataset of 10,036 crashes that occurred over a 6-year period (2015–2020) on eight selected bridges. Utilizing the LCC method, the research identifies four optimal clusters in bridge crashes, characterized by attributes such as ‘4-lane,’ ‘6-lane,’ ‘single-vehicle crashes,’ and ‘unknown driver.’ The Association Rule Mining (ARM) approach is used to identify the important collective factors to visible injury (KAB – fatal, severe and moderate) and property damage only (PDO or no injury). In Cluster 1 (4-lane), KAB and PDO crashes differ in collision type and visibility conditions, with rear-end crashes linked to KAB and sideswipe crashes to PDO. Cluster 2 (6-lane) shows similar distinctions but lacks specific lighting associations for PDO. In Cluster 3 (single-vehicle crashes), KAB involves moderate traffic and low visibility, while PDO has lower speed limits and non-dry surfaces. Cluster 4 (unknown driver), despite overrepresenting hit-and-run cases, underscores challenges in injury crash data collection in high-volume mobility scenarios. The discussions of the findings on the severity factors in this study are expected to help traffic safety engineers, policymakers, and planners to identify effective safety countermeasures on major elevated sections.

Research on the Application of Improved Apriori Algorithm in Sport-Adaptive Online Teaching System Under Big Data Environment

Each student in an adaptive education system has significant differences in knowledge background, ability level and cognitive style. Therefore, to build an adaptive teaching system, it is necessary to establish an operable, reasonable and individualized student model by clarifying students’ abilities and differences. The improved Apriori algorithm under big data is the most classic association rule algorithm, which is generated by a set of candidates, and it uses the iterative method of hierarchical search to traverse a set of frequency items in the transaction database. After finding the set of frequency items, select the association according to the trust rules. This paper studies how to apply the improved Apriori algorithm to an adaptive online education system in a big data environment. An evolutionary algebra is taken with mean fit of 80, population size of 20, mean fit of 0.28, population size of 60, mean fit of 0.26, population size of 80, mean fit of 0.25, mean population size of 0.25. The population size is 200, and the average fitting is 0.24. The larger the error, the smaller the error between each indicator of the test paper and the corresponding value specified by the user. The improved Apriori algorithm in the big data environment has designed five themes of rule mining, which are mainly used for class management: class linkage, class category linkage, student basic information linkage, lecture and basic information linkage, and lecture mode linkage. They play the role of teaching assistants with a specific role.

Understanding risky driving behaviors among young novice drivers in Nigeria: A latent class analysis coupled with association rule mining approach

Traffic crashes are significant public health concern in Nigeria, particularly among young drivers. The study aims to explore the underlying pattern of risky driving behaviors and the associations with demographic factors among young drivers in Nigeria. A combined approach of Latent Class Analysis (LCA) and Association Rule Mining is applied to the dataset comprising responses from 684 young drivers who complete the “Behavior of Young Novice Drivers Scale” (BYND) questionnaires. The LCA identifies four distinct classes of drivers based on the risky behavior profiles: Reckless-Speedsters, Cautious Drivers, Distracted Multitaskers, and Emotion-impacted Drivers. Association rule mining further connects these driver classes to demographic and driving history variables, uncovering intriguing insights. Reckless-Speedsters predominantly consist of young males who engage in riskier driving behaviors, including exceeding speed limits and disregarding traffic rules. Conversely, Cautious Drivers, also predominantly young males, exhibit a safer driving profile marked by rule adherence and a notably lower crash rate. Distracted Multitaskers, sharing a demographic profile with Cautious Drivers, diverge significantly due to their higher crash involvement, hinting at a propensity for distracted driving practices. Lastly, Emotion-Impacted Drivers, primarily comprising young employed males, display behaviors influenced by emotions, shorter driving distances, and prior unsupervised driving experience. Most of the behaviors are attributed to inadequate traffic control, absence of traffic signs in most of the roads, preferential treatment, and lack of strict law enforcement in the country. The findings hold substantial implications for road safety interventions in Nigeria, urging targeted approaches to address the unique challenges presented by each driver class. With acknowledging the study limitations and advocating for future research in objective measures and emotion-behavior interactions, the comprehensive approach provides a robust foundation for enhancing road safety in the Nigerian context.

Adaptive fuzzy-evidential classification based on association rule mining

As one of the most promising classification approaches, association classification (AC) integrates data classification and association discovery techniques for generating a compact set of classification association rules. Recently, the fuzzy set and evidence theories are successively applied into AC in order to improve the classification performance in terms of accuracy and interpretability. However, from the perspectives of applicability and universality, there still exists two important issues in the current AC framework. On one hand, several key parameters, such as the number of fused rules in classification and the minimum support threshold in association discovery, are difficult to be accurately predefined in practice. On the other hand, the fixed grid-based fuzzy partition is not benefit to adapt for those datasets with large number of features. In this paper, an association rule-based adaptive fuzzy-evidential classification framework (AR-AFEC) is developed for overcoming the above limitations. To do so, an optimal rule fusion strategy and a dynamic minimum support threshold setting scheme are proposed for adaptively learning the parameters during classification and association mining respectively. In addition, an entropy-based trapezoidal fuzzy partition technique is proposed to adaptively obtain the fuzzy sets defined on each continuous feature domain. Experiments on 26 benchmark datasets and a human activity recognition application demonstrate that the proposal can achieve better accuracy than some state-of-the-art rule-based classification approaches, using less rules with more general structure.

A Meta-Heuristic Approach for Enhancing Performance of Associative Classification

Associative Classification is an interesting approach in data mining to create more accurate and easilyinterpretable predictive systems. This approach is often built on both association rule mining and classification techniques, to find a set of rules called association rules for classification (CAR) of label attributes. There are many kinds of associative classification such as CPAR, CBA, CMAR but the accuracy is still low on large datasets, and the running time is not reasonable as well. This paper proposes a heuristic approach to significantly enhance the performance of Associative Classification algorithms in running time, reducing the rule set, and accuracy on large data. Experimental results show that heuristic searching the optimal data set makes the associative classification more useful on big data, and reasonable in practice.

A hybrid machine learning model combining association rule mining and classification algorithms to predict differentiated thyroid cancer recurrence.

Differentiated thyroid cancer (DTC) is the most prevalent endocrine malignancy with a recurrence rate of about 20%, necessitating better predictive methods for patient management. This study aims to create a relational classification model to predict DTC recurrence by integrating clinical, pathological, and follow-up data. The balanced dataset comprises 550 DTC samples collected over 15 years, featuring 13 clinicopathological variables. To address the class imbalance in recurrence status, the Synthetic Minority Over-sampling Technique for Nominal and Continuous (SMOTE-NC) was utilized. A hybrid model combining classification algorithms with association rule mining was developed. Two relational classification approaches, regularized class association rules (RCAR) and classification based on association rules (CBAR), were implemented. Binomial logistic regression analyzed independent predictors of recurrence. Model performance was assessed through accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score. The RCAR model demonstrated superior performance over the CBAR model, achieving accuracy, sensitivity, and F1 score of 96.7%, 93.1%, and 96.7%, respectively. Association rules highlighted that papillary pathology with an incomplete response strongly predicted recurrence. The combination of incomplete response and lymphadenopathy was also a significant predictor. Conversely, the absence of adenopathy and complete response to treatment were linked to freedom from recurrence. Incomplete structural response was identified as a critical predictor of recurrence risk, even with other low-recurrence conditions. This study introduces a robust and interpretable predictive model that enhances personalized medicine in thyroid cancer care. The model effectively identifies high-risk individuals, allowing for tailored follow-up strategies that could improve patient outcomes and optimize resource allocation in DTC management.

A novel software defect prediction approach via weighted classification based on association rule mining

Software defect prediction technology is used to assist software practitioners in effectively allocating test resources and identifying hidden defects in a timely manner. However, the prediction of defect-prone software using association rule mining algorithms is limited because of the unbalanced distribution of defect data. Furthermore, although the existing weighted association rule mining approach considers item strength, the weight calculation still relies on expert experience and lacks fine granularity. We propose a novel software defect prediction approach based on mutual information and correlation coefficient weighted class association rule mining (MCWCAR). The MCWCAR model employs a cost-sensitive strategy and generates frequent itemsets according to three mining objectives while maintaining the original item distribution: defective class rules, non-defective class rules, and feature association relationships. During the weighted frequent itemset mining process, it combines feature selection and itemset screening to determine the appropriate feature combination through mutual information weighted support. Meanwhile, the correlation coefficient is applied to accurately depict the correlation between feature items and defect classes, serving as the weight to mine class association rules. Additionally, to ensure that interestingness measures have asymmetry and effectively represent negative associations under the condition of class imbalance, the addedvalue is adopted in the filtering association rules. We conducted experiments on 27 open-source datasets and evaluated the performance differences between MCWCAR and state-of-the-art baseline classifiers. Experimental results demonstrate that the proposed algorithm significantly outperforms other baselines in terms of Balance, Gmean, MCC, and F-measure.

ACMKC: A Compact Associative Classification Model Using K-Modes Clustering with Rule Representations by Coverage

The generation and analysis of vast amounts of data have become increasingly prevalent in diverse applications. In this study, we propose a novel approach to address the challenge of rule explosion in association rule mining by utilizing the coverage-based representations of clusters determined by K-modes. We utilize the FP-Growth algorithm to generate class association rules (CARs). To further enhance the interpretability and compactness of the rule set, we employ the K-modes clustering algorithm with a distance metric that binarizes the rules. The optimal number of clusters is determined using the silhouette score. Representative rules are then selected based on their coverage within each cluster. To evaluate the effectiveness of our approach, we conducted experimental evaluations on both UCI and Kaggle datasets. The results demonstrate a significant reduction in the rule space (71 rules on average, which is the best result among all state-of-the-art rule-learning algorithms), aligning with our goal of producing compact classifiers. Our approach offers a promising solution for managing rule complexity in association rule mining, thereby facilitating improved rule interpretation and analysis, while maintaining a significantly similar classification accuracy (ACMKC: 80.0% on average) to other rule learners on most of the datasets.

C-MWCAR: Classification Based on Multiple Weighted Class Association Rules

Classification is a very important task in data mining and pattern analysis, which have been widely used to solve various real-world problems. To obtain better classification performance, in this paper, we propose a novel classification framework based on multiple weighted class association rules (C-MWCAR), whose key idea is to transform the association among features into a set of class association rules (CARs), then classify unknown instances based on the CARs obtained. Concretely, C-MWCAR consists of a dictionary order-based CAR mining algorithm (DOCMA), a branch-based CAR selection algorithm (BCSA), and a multiple weighted CARs-based classifier (MWCC). Specifically, DOCMA mines the complete set of CARs, from which BCSA further selects a representative and concise set of CARs based on the distribution, coverage, and redundancy of the mined CARs. When classifying an unknown instance, MWCC picks out a set of CARs that are most similar to the given instance and computes the weighted importance of those CARs. Finally, the class label of the given instance will be determined by the similarities between the instance and the CARs and the weighted importance of the CARs. Furthermore, we apply the proposed C-MWCAR to a real-world classification task, i.e., hypertension diagnosis, based on a real dataset of 128 subjects. Experimental results indicate that C-MWCAR outperforms four baseline methods and achieves 93.3%, 93.8%, and 92.7% in terms of accuracy, sensitivity, and specificity, respectively.

QCBA: improving rule classifiers learned from quantitative data by recovering information lost by discretisation

A prediscretisation of numerical attributes which is required by some rule learning algorithms is a source of inefficiencies. This paper describes new rule tuning steps that aim to recover lost information in the discretisation and new pruning techniques that may further reduce the size of rule models and improve their accuracy. The proposed QCBA method was initially developed to postprocess quantitative attributes in models generated by Classification based on associations (CBA) algorithm, but it can also be applied to the results of other rule learning approaches. We demonstrate the effectiveness on the postprocessing of models generated by five association rule classification algorithms (CBA, CMAR, CPAR, IDS, SBRL) and two first-order logic rule learners (FOIL2 and PRM). Benchmarks on 22 datasets from the UCI repository show smaller size and the overall best predictive performance for FOIL2+QCBA compared to all seven baselines. Postoptimised CBA models have a better predictive performance compared to the state-of-the-art rule learner CORELS in this benchmark. The article contains an ablation study for the individual postprocessing steps and a scalability analysis on the KDD’99 Anomaly detection dataset.

Association rules and prediction of transportation mode choice: Application to national travel survey data

Predicting transportation mode choice is a classic challenge of travel behavior research. Over the years, different theoretical concepts and modeling approaches have been applied. This paper elaborates the application of class association rules (CARs) and examines their predictive performance using data extracted from the 2015 National Dutch Travel Survey. To solve the problem how to activate rules that have high confidence but low support, the information gain (IG) concept is introduced in the model building process. The modeling process in this study first involves extracting frequent items from the data using the FP-Growth algorithm and deriving CARs from these frequent items. Next, the IG statistic is used to construct a novel model (named CARIG), which consists of a set of decision rules that formally represent behavioral scripts, for predicting individuals’ transportation mode choice. The performance of CARIG is compared with the performance of conventional class-based association rules (CBA), decision trees (DT), a convolutional neural network (CNN) and a logistic regression (LR) model. In addition, a 10-fold cross validation test using a grid search parameter optimization method is conducted to validate the proposed approach. The results show that the proposed method is promising in predicting transportation mode choices observed in the national travel survey data.

A Novel Incremental Framework for Building Classifier Using Constraint Class Association Rules

Associative classification (AC) performs much better than other traditional classifiers. It generates a huge number of class association rules (CARs). Since users are interested in the subset of rules, constraints are introduced in the generation of CARs. Real-world databases are record-based in which data is continuously added which demands incremental mining. Hence, constraint class association rules (CCAR) is mined from incremental data. To limit the number of rules and to remove the duplicate rules, redundant rule pruning and duplicate rule pruning techniques are applied. To improve the accuracy of the classifier, the rule selection using principality metric has been applied and the classifier is constructed with rules possessing high principality. Then, classifier is evaluated using single rule and multiple rule prediction methods and the accuracy of the proposed classifier are measured. Experimental results show that the accuracy of the proposed classifier is relatively higher when compared to other algorithms.

Mining association rules for classification using frequent generator itemsets in arules package

Mining frequent itemsets is an attractive research activity in data mining whose main aim is to provide useful relationships among data. Consequently, several open-source development platforms are continuously developed to facilitate the users' exploitation of new data mining tasks. Among these platforms, the R language is one of the most popular tools. In this paper, we propose an extension of arules package by adding the option of mining frequent generator itemsets. We discuss in detail how generators can be used for a classification task through an application example in relation with COVID-19.

FORENSIC BIOMETRICS IDENTIFICATION SYSTEM FOR DNA PROFILE HUMAN BASED ON ASSOCIATION RULES

It should be noted that there is a joint work between biomedicine such as forensic medicine and information technology through the use of information technology technologies in all fields, including determining the of DNA profile. One of the leading biotechnologies in this field is data mining techniques. There are many ways to identify disaster victims, such as fingerprints, dental record and DNA profile matching. DNA matching is a highly accurate identification way that does not need specific parts of the victim's body. Deoxyribose Nucleic Acid (DNA) is the basic elements that make up an entire section of a human. The core elements store unique information for each individual and will be passed on through generations. DNA also helps in identifying the father in paternity testing,. The limitation of applying DNA matching for disaster victim identification lies on expensive and time consuming process. To address this situation, in this paper, we performed a method to measure the confidence of matching of human DNA profiles identification using Association Rule Classification System is proposed. In this Classification system, DNA profile data is used as an input that stores human identity along with its DNA profile. advisable information or good patterns from present datasets for certain objective. The results were satisfactory and characterized by large percentage and high accuracy. Finally, performance of this system is evaluated and in turns the proposed system proves its capability in forensic human identification and scalability to handle huge amounts of data.

H-DAC: discriminative associative classification in data streams

In this paper, we propose an efficient and highly accurate method for data stream classification, called discriminative associative classification. We define class discriminative association rules (CDARs) as the class association rules (CARs) in one data stream that have higher support compared with the same rules in the rest of the data streams. Compared to associative classification mining in a single data stream, there are additional challenges in the discriminative associative classification mining in multiple data streams, as the Apriori property of the subset is not applicable. The proposed single-pass H-DAC algorithm is designed based on distinguishing features of the rules to improve classification accuracy and efficiency. Continuously arriving transactions are inserted at fast speed and large volume, and CDARs are discovered in the tilted-time window model. The data structures are dynamically adjusted in offline time intervals to reflect each rule supported in different periods. Empirical analysis shows the effectiveness of the proposed method in the large fast speed data streams. Good efficiency is achieved for batch processing of small and large datasets, plus 0–2% improvements in classification accuracy using the tilted-time window model (i.e., almost with zero overhead). These improvements are seen only for the first 32 incoming batches in the scale of our experiments and we expect better results as the data streams grow.

Attribute Selection Based Genetic Network Programming for Intrusion Detection System

Intrusion detection, as a technology used to monitor abnormal behavior and maintain network security, has attracted many researchers’ attention in recent years. Thereinto, association rule mining is one of the mainstream methods to construct intrusion detection systems (IDS). However, the existing association rule algorithms face the challenges of high false positive rate and low detection rate. Meanwhile, too many rules might lead to the uncertainty increase that affects the performance of IDS. In order to tackle the above problems, a modified genetic network programming (GNP) is proposed for class association rule mining. Specifically, based on the property that node connections in the directed graph structure of GNP can be used to construct attribute associations, we propose to introduce information gain into GNP node selection. The most important attributes are thus selected, and the irrelevant attributes are removed before the rule is extracted. Moreover, not only the uncertainty among the class association rules is alleviated and also time consumption is reduced. The extracted rules can be applied to any classifier without affecting the detection performance. Experiment results based on NSL-KDD and KDDCup99 verify the performance of our proposed algorithm.

ARTC: feature selection using association rules for text classification

ARTC: feature selection using association rules for text classification