A New Approach on Rare Association Rule Mining

Hoque, Nazrul; Nath, Bhabesh; Bhattacharyya, Dhruba K.

doi:10.5120/8398-2001

Cited by 11 publications

(9 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The measure of Comprehensibility determines the significance of a rule based on the number of items presented in both the antecedent and consequent domains (Aher & Lobo, 2013; Hoque et al ., 2012; Sikka et al ., 2012), which can be represented as:

C o m p r e h e n s i b i l i t y (A \to B) = \frac{l o g (1 + |B|)}{l o g (1 + |A \cup B|)}

…”

Section: Association Rule Discovery and Generation In Adaptive Micro mentioning

confidence: 99%

“…Particularly, in micro open learning, instructors or the service‐oriented system (eg, MLaaS) is responsible for identifying the students potentially at risk. This minority normally requires extra assistance or instructors’ intervention (Hoque, Nath, & Bhattacharyya, 2012). The value of minimum Support is set too high or too low can cause omission or combinatorial explosion of rules (Kiran & Reddy, 2010).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Refinement and augmentation for data in micro open learning activities with an evolutionary rule generator

Sun¹,

Lin²,

Shen³

et al. 2020

Brit J Educational Tech

View full text Add to dashboard Cite

Improving both the quantity and quality of existing data are placed at the center of research for adaptive micro open learning. To cover this research gap, our work targets on the current scarcity of both data and rules that represent open learning activities. An evolutionary rule generator is constructed, which consists of an outer loop and an inner loop. The outer loop runs a genetic algorithm (GA) to produce association rules that can be effective in the micro open learning scenario from a small amount of available data sources; while the inner loop optimizes generated candidates by taking into account both rare and negative association rules (NARs). These optimized rules are further applied in refining and augmenting data denoting learners’ behaviors in open learning into a low‐dimensional, descriptive and interpretable form. The performance of rule discovery and data processing have been empirically evaluated using genuine open learning data.

show abstract

C o m p r e h e n s i b i l i t y (A \to B) = \frac{l o g (1 + |B|)}{l o g (1 + |A \cup B|)}

…”

Section: Association Rule Discovery and Generation In Adaptive Micro mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Refinement and augmentation for data in micro open learning activities with an evolutionary rule generator

Sun¹,

Lin²,

Shen³

et al. 2020

Brit J Educational Tech

View full text Add to dashboard Cite

show abstract

“…As the most important purpose of rule mining is to find some hidden information, it should extract those rules that have comparatively less occurrence in the database. The following expression can be used to quantify the interestingness [8, 9, 14, 15]:

\begin{matrix} Interestingness (X \to Y) \\ = \frac{SUP (X \cup Y)}{SUP (X)} \times \frac{SUP (X \cup Y)}{SUP (Y)} \\ \times (1 - \frac{SUP (X \cup Y)}{| D |}), \end{matrix}

where | D | indicates the total number of transactions in the database. …”

Section: Preliminariesmentioning

confidence: 99%

“…Qodmanan et al applied MOGA to association rule mining without taking the minimum support and confidence into account by applying the FP-tree algorithm [9]. Hoque et al presented a method to generate both frequent and rare itemsets using multiobjective genetic algorithm [14]. Fung et al suggested a novel MOGA based rule mining method for affective product design, which can discover a set of rules relating design attributes with customer evaluation based on survey data [44].…”

Section: Preliminariesmentioning

confidence: 99%

Attribute Index and Uniform Design Based Multiobjective Association Rule Mining with Evolutionary Algorithm

Zhang

Wang

Feng

2013

The Scientific World Journal

View full text Add to dashboard Cite

In association rule mining, evaluating an association rule needs to repeatedly scan database to compare the whole database with the antecedent, consequent of a rule and the whole rule. In order to decrease the number of comparisons and time consuming, we present an attribute index strategy. It only needs to scan database once to create the attribute index of each attribute. Then all metrics values to evaluate an association rule do not need to scan database any further, but acquire data only by means of the attribute indices. The paper visualizes association rule mining as a multiobjective problem rather than a single objective one. In order to make the acquired solutions scatter uniformly toward the Pareto frontier in the objective space, elitism policy and uniform design are introduced. The paper presents the algorithm of attribute index and uniform design based multiobjective association rule mining with evolutionary algorithm, abbreviated as IUARMMEA. It does not require the user-specified minimum support and minimum confidence anymore, but uses a simple attribute index. It uses a well-designed real encoding so as to extend its application scope. Experiments performed on several databases demonstrate that the proposed algorithm has excellent performance, and it can significantly reduce the number of comparisons and time consumption.

show abstract

“…There is less research on subjective interestingness and it is relatively immature. Hoque et al and Zhang et al presented methods to generate both frequent and rare itemsets using multiobjective genetic algorithm [10,11]. How to mine the real and effective association rules reflecting interests of users is the common goal for researchers.…”

Section: Introductionmentioning

confidence: 99%

A Novel Method of Interestingness Measures for Association Rules Mining Based on Profit

Bao

et al. 2015

Discrete Dynamics in Nature and Society

View full text Add to dashboard Cite

Association rules mining is an important topic in the domain of data mining and knowledge discovering. Some papers have presented several interestingness measure methods; the most typical areSupport,Confidence,Lift,Improve, and so forth. But their limitations are obvious, like no objective criterion, lack of statistical base, disability of defining negative relationship, and so forth. This paper proposes three new methods,Bi-lift, Bi-improve, andBi-confidence, forLift, Improve, and Confidence, respectively. Then, on the basis of utility function and the executing cost of rules, we propose interestingness function based on profit (IFBP) considering subjective preferences and characteristics of specific application object. Finally, a novel measure framework is proposed to improve the traditional one through experimental analysis. In conclusion, the new methods and measure framework are prior to the traditional ones in the aspects of objective criterion, comprehensive definition, and practical application.

show abstract

A New Approach on Rare Association Rule Mining

Cited by 11 publications

References 17 publications

Refinement and augmentation for data in micro open learning activities with an evolutionary rule generator

Refinement and augmentation for data in micro open learning activities with an evolutionary rule generator

Attribute Index and Uniform Design Based Multiobjective Association Rule Mining with Evolutionary Algorithm

A Novel Method of Interestingness Measures for Association Rules Mining Based on Profit

Contact Info

Product

Resources

About