Fadi Abdeljaber Thabtah

A review of associative classification mining

Associative classification mining is a promising approach in data mining that utilizes the association rule discovery techniques to construct classification systems, also known as associative classifiers. In the last few years, a number of associative classification algorithms have been proposed, i.e. CPAR, CMAR, MCAR, MMAC and others. These algorithms employ several different rule discovery, rule ranking, rule pruning, rule prediction and rule evaluation methods. This paper focuses on surveying and comparing the state-of-the-art associative classification techniques with regards to the above criteria. Finally, future directions in associative classification, such as incremental learning and mining low-quality data sets, are also highlighted in this paper.

A greedy classification algorithm based on association rule

Classification and association rule discovery are important data mining tasks. Using association rule discovery to construct classification systems, also known as associative classification, is a promising approach. In this paper, a new associative classification technique, Ranked Multilabel Rule (RMR) algorithm is introduced, which generates rules with multiple labels. Rules derived by current associative classification algorithms overlap in their training objects, resulting in many redundant and useless rules. However, the proposed algorithm resolves the overlapping between rules in the classifier by generating rules that does not share training objects during the training phase, resulting in a more accurate classifier. Results obtained from experimenting on 20 binary, multi-class and multi-label data sets show that the proposed technique is able to produce classifiers that contain rules associated with multiple classes. Furthermore, the results reveal that removing overlapping of training objects between the derived rules produces highly competitive classifiers if compared with those extracted by decision trees and other associative classification techniques, with respect to error rate.

Improving rule sorting predictive accuracy and training time in associative classification

Traditional classification techniques such as decision trees and RIPPER use heuristic search methods to find a small subset of patterns. In recent years, a promising new approach that mainly uses association rule mining in classification called associative classification has been proposed. Most associative classification algorithms adopt the exhaustive search method presented in the famous Apriori algorithm to discover the rules and require multiple passes over the database. Furthermore, they find frequent items in one phase and generate the rules in a separate phase consuming more resources such as storage and processing time. In this paper, a new associative classification method called Multi-class Classification based on Association Rules (MCAR) is presented. MCAR takes advantage of vertical format representation and uses an efficient technique for discovering frequent items based on recursively intersecting the frequent items of size n to find potential frequent items of size n+1. Moreover, since rule ranking plays an important role in classification and the majority of the current associative classifiers like CBA and CMAR select rules mainly in terms of their confidence levels. MCAR aims to improve upon CBA and CMAR approaches by adding a more tie breaking constraints in order to limit random selection. Finally we show that shuffling the training data objects before mining can impact substantially the prediction power of some well known associative classification techniques. After experimentation with 20 different data sets, the results indicate that the proposed algorithm is highly competitive in term of an error rate and efficiency if compared with decision trees, rule induction methods and other popular associative classification methods. Finally, we show the effectiveness of MCAR rule sorting method on the quality of the produced classifiers for 12 highly dense benchmark problems.

Mining the data from a hyperheuristic approach using associative classification

Associative classification is a promising classification approach that utilises association rule mining to construct accurate classification models. In this paper, we investigate the potential of associative classifiers as well as other traditional classifiers such as decision trees and rule inducers in solutions (data sets) produced by a general-purpose optimisation heuristic called the hyperheuristic for a personnel scheduling problem. The hyperheuristic requires us to decide which of several simpler search neighbourhoods to apply at each step while constructing a solutions. After experimenting 16 different solution generated by a hyperheuristic called Peckish using different classification approaches, the results indicated that associative classification approach is the most applicable approach to such kind of problems with reference to accuracy. Particularly, associative classification algorithms such as CBA, MCAR and MMAC were able to predict the selection of low-level heuristics from the data sets more accurately than C4.5, RIPPER and PART algorithms, respectively.

Rule Preference Effect in Associative Classification Mining

Classification based on association rule mining, also known as associative classification, is a promising approach in data mining that builds accurate classifiers. In this paper, a rule ranking process within the associative classification approach is investigated. Specifically, two common rule ranking methods in associative classification are compared with reference to their impact on accuracy. We also propose a new rule ranking procedure that adds more tie breaking conditions to the existing methods in order to reduce rule random selection. In particular, our method looks at the class distribution frequency associated with the tied rules and favours those that are associated with the majority class. We compare the impact of the proposed rule ranking method and two other methods presented in associative classification against 14 highly dense classification data sets. Our results indicate the effectiveness of the proposed rule ranking method on the quality of the resulting classifiers for the majority of the benchmark problems, which we consider. This provides evidence that adding more appropriate constraints to break ties between rules positively affects the predictive power of the resulting associative classifiers.

The Impact of Rule Ranking on the Quality of Associative Classifiers

Associative classification is a promising approach that utilises association rule mining to build classifiers. Associative classification techniques such as CBA and CMAR rank rules mainly in terms of their confidence, support and cardinality. We propose a rule sorting method that adds more tie breaking conditions than existing methods in order to reduce rule random selection. In particular, our method looks at the class distribution frequency associated with the tied rules and favours those that are associated with the majority class. We compare the impact of the proposed rule ranking method and two other methods presented in associative classification against 12 highly dense classification data sets. Our results indicate the effectiveness of the proposed rule ranking method on the quality of the resulting classifiers for the majority of the benchmark problems, which we consider. In particular, our method improved the accuracy on average +0.62% and +0.40% for the 12 benchmark problems if compared with (support, confidence) and (support, confidence, lower cardinality) rule ranking approaches, respectively. This provides evidence that adding more appropriate constraints to break ties between rules positively affects the predictive power of the resulting associative classifiers.

Machine learning in autistic spectrum disorder behavioral research: A review and ways forward

ABSTRACT Autistic Spectrum Disorder (ASD) is a mental disorder that retards acquisition of linguistic, communication, cognitive, and social skills and abilities. Despite being diagnosed with ASD, some individuals exhibit outstanding scholastic, non-academic, and artistic capabilities, in such cases posing a challenging task for scientists to provide answers. In the last few years, ASD has been investigated by social and computational intelligence scientists utilizing advanced technologies such as machine learning to improve diagnostic timing, precision, and quality. Machine learning is a multidisciplinary research topic that employs intelligent techniques to discover useful concealed patterns, which are utilized in prediction to improve decision making. Machine learning techniques such as support vector machines, decision trees, logistic regressions, and others, have been applied to datasets related to autism in order to construct predictive models. These models claim to enhance the ability of clinicians to provide robust diagnoses and prognoses of ASD. However, studies concerning the use of machine learning in ASD diagnosis and treatment suffer from conceptual, implementation, and data issues such as the way diagnostic codes are used, the type of feature selection employed, the evaluation measures chosen, and class imbalances in data among others. A more serious claim in recent studies is the development of a new method for ASD diagnoses based on machine learning. This article critically analyses these recent investigative studies on autism, not only articulating the aforementioned issues in these studies but also recommending paths forward that enhance machine learning use in ASD with respect to conceptualization, implementation, and data. Future studies concerning machine learning in autism research are greatly benefitted by such proposals.

Looking at the Class Associative Classification Training Algorithm

Associative classification (AC) is a branch in data mining that utilises association rule discovery methods in classification problems. In this paper, we propose a new training method called Looking at the Class (LC), which can be adapted by any rule-based AC algorithm. Unlike the traditional Classification based on Association rule (CBA) training method, which joins disjoint itemsets regardless of their class labels, our method joins only itemsets with similar class labels during the training phase. This prevents the accumulation of too many unnecessary merging during learning, and consequently results in huge saving (58%-91%) with reference of computational time and memory on large datasets.

Ranked Multi-Label Rules Associative Classifier

Associative classification is a promising approach in data mining, which integrates association rule discovery and classification. In this paper, we present a novel associative classification technique called Ranked Multilabel Rule (RMR) that derives rules with multiple class labels. Rules derived by current associative classification algorithms overlap in their training data records, resulting in many redundant and useless rules. However, RMR removes the overlapping between rules using a pruning heuristic and ensures that rules in the final classifier do not share training records, resulting in more accurate classifiers. Experimental results obtained on twenty data sets show that the classifiers produced by RMR are highly competitive if compared with those generated by decision trees and other popular associative techniques such as CBA, with respect to prediction accuracy.