Izwan Nizal Mohd Shaharanee

Interestingness measures for association rules based on statistical validity

Assessing rules with interestingness measures is the pillar of successful application of association rules discovery. However, association rules discovered are normally large in number, some of which are not considered as interesting or significant for the application at hand. In this paper, we present a systematic approach to ascertain the discovered rules, and provide a precise statistical approach supporting this framework. The proposed strategy combines data mining and statistical measurement techniques, including redundancy analysis, sampling and multivariate statistical analysis, to discard the non- significant rules. Moreover, we consider real world datasets which are characterized by the uniform and non-uniform data/items distribution with a mixture of measurement levels throughout the data/items. The proposed unified framework is applied on these datasets to demonstrate its effectiveness in discarding many of the redundant or non-significant rules, while still preserving the high accuracy of the rule set as a whole.

Interestingness of Association Rules Using Symmetrical Tau and Logistic Regression

While association rule mining is one of the most popular data mining techniques, it usually results in many rules, some of which are not considered as interesting or significant for the application at hand. In this paper, we conduct a systematic approach to ascertain the discovered rules and provide a rigorous statistical approach supporting this framework. The strategy proposed combines data mining and statistical measurement techniques, including redundancy analysis, sampling and multivariate statistical analysis, to discard the non significant rules. A real world dataset is used to demonstrate how the proposed unified framework can discard many of the redundant or non significant rules and still preserve high accuracy of the rule set as a whole.

Evaluation and optimization of frequent, closed and maximal association rule based classification

Real world applications of association rule mining have well-known problems of discovering a large number of rules, many of which are not interesting or useful for the application at hand. The algorithms for closed and maximal itemsets mining significantly reduce the volume of rules discovered and complexity associated with the task, but the implications of their use and important differences with respect to the generalization power, precision and recall when used in the classification problem have not been examined. In this paper, we present a systematic evaluation of the association rules discovered from frequent, closed and maximal itemset mining algorithms, combining common data mining and statistical interestingness measures, and outline an appropriate sequence of usage. The experiments are performed using a number of real-world datasets that represent diverse characteristics of data/items, and detailed evaluation of rule sets is provided as a whole and w.r.t individual classes. Empirical results confirm that with a proper combination of data mining and statistical analysis, a large number of non-significant, redundant and contradictive rules can be eliminated while preserving relatively high precision and recall. More importantly, the results reveal the important characteristics and differences between using frequent, closed and maximal itemsets for the classification task, and the effect of incorporating statistical/heuristic measures for optimizing such rule sets. With closed itemset mining already being a preferred choice for complexity and redundancy reduction during rule generation, this study has further confirmed that overall closed itemset based association rules are also of better quality in terms of classification precision and recall, and precision and recall on individual class examples. On the other hand maximal itemset based association rules, that are a subset of closed itemset based rules, show to be insufficient in this regard, and typically will have worse recall and generalization power. Empirical results also show the downfall of using the confidence measure at the start to generate association rules, as typically done within the association rule framework. Removing rules that occur below a certain confidence threshold, will also remove the knowledge of existence of any contradictions in the data to the relatively higher confidence rules, and thus precision can be increased by disregarding contradictive rules prior to application of confidence constraint.

Selection of suitable e-learning approach using TOPSIS technique with best ranked criteria weights

This paper compares the performances of four rank-based weighting assessment techniques, Rank Sum (RS), Rank Reciprocal (RR), Rank Exponent (RE), and Rank Order Centroid (ROC) on five identified e-learning criteria to select the best weights method. A total of 35 experts in a public university in Malaysia were asked to rank the criteria and to evaluate five e-learning approaches which include blended learning, flipped classroom, ICT supported face to face learning, synchronous learning, and asynchronous learning. The best ranked criteria weights are defined as weights that have the least total absolute differences with the geometric mean of all weights, were then used to select the most suitable e-learning approach by using TOPSIS method. The results show that RR weights are the best, while flipped classroom approach implementation is the most suitable approach. This paper has developed a decision framework to aid decision makers (DMs) in choosing the most suitable weighting method for solving MCDM problems.This paper compares the performances of four rank-based weighting assessment techniques, Rank Sum (RS), Rank Reciprocal (RR), Rank Exponent (RE), and Rank Order Centroid (ROC) on five identified e-learning criteria to select the best weights method. A total of 35 experts in a public university in Malaysia were asked to rank the criteria and to evaluate five e-learning approaches which include blended learning, flipped classroom, ICT supported face to face learning, synchronous learning, and asynchronous learning. The best ranked criteria weights are defined as weights that have the least total absolute differences with the geometric mean of all weights, were then used to select the most suitable e-learning approach by using TOPSIS method. The results show that RR weights are the best, while flipped classroom approach implementation is the most suitable approach. This paper has developed a decision framework to aid decision makers (DMs) in choosing the most suitable weighting method for solving MCDM problems.

Analyzing the factors that influencing the success of post graduates in achieving graduate on time (GOT) using analytic hierarchy process (AHP)

In the globalization era, education plays an important role in educating and preparing individuals to face the demands and challenges of 21st century. Thus, this contributes to the increase of the number of individuals pursuing their studies in Doctor of Philosophy (Ph.D) program. However, the ability of Ph.D students in heading to the four years Graduate on Time (GOT) mission that is stipulated by University has become a major concern of students, institution and government. Therefore, the main objective of this study is to investigate the factors that influence the Ph.D students in Universiti Utara Malaysia (UUM) to achieve GOT. Through the reviewing of previous research, six factors which are student factor, financial factor, supervisor factor, skills factor, project factors and institution factor had been identified as the domain factors that influence the Ph.D students in achieving GOT. The level of importance for each factor will be ranked by the experts from three graduate schools using Analytic Hierarchy Process (AHP) technique. This study will bring a significant contribution to the understanding of factors that affecting the Ph.D students in UUM to achieve GOT. In Addition, this study can also succor the university in planning and assisting the Ph.D students to accomplish the GOT in future.In the globalization era, education plays an important role in educating and preparing individuals to face the demands and challenges of 21st century. Thus, this contributes to the increase of the number of individuals pursuing their studies in Doctor of Philosophy (Ph.D) program. However, the ability of Ph.D students in heading to the four years Graduate on Time (GOT) mission that is stipulated by University has become a major concern of students, institution and government. Therefore, the main objective of this study is to investigate the factors that influence the Ph.D students in Universiti Utara Malaysia (UUM) to achieve GOT. Through the reviewing of previous research, six factors which are student factor, financial factor, supervisor factor, skills factor, project factors and institution factor had been identified as the domain factors that influence the Ph.D students in achieving GOT. The level of importance for each factor will be ranked by the experts from three graduate schools using Analytic Hi...

Student profiling on university co-curricular activities using cluster analysis

In higher learning institutions, the co-curricular programs are needed for the graduation besides the standard academic programs. By actively participating in co-curricular, students can attain many of soft skills and proficiencies besides learning and adopting campus environment, community and traditions. Co-curricular activities are implemented by universities mainly for the refinement of the academic achievement along with the social development. This studies aimed to analyse the academic profile of the co-curricular students among uniform units. The main objective of study is to develop a profile of student co-curricular activities in uniform units. Additionally, several variables has been selected to serve as the characteristics for student co-curricular profile. The findings of this study demonstrate the practicality of clustering technique to investigate student’s profiles and allow for a better understanding of student’s behavior and co-curriculum activities.In higher learning institutions, the co-curricular programs are needed for the graduation besides the standard academic programs. By actively participating in co-curricular, students can attain many of soft skills and proficiencies besides learning and adopting campus environment, community and traditions. Co-curricular activities are implemented by universities mainly for the refinement of the academic achievement along with the social development. This studies aimed to analyse the academic profile of the co-curricular students among uniform units. The main objective of study is to develop a profile of student co-curricular activities in uniform units. Additionally, several variables has been selected to serve as the characteristics for student co-curricular profile. The findings of this study demonstrate the practicality of clustering technique to investigate student’s profiles and allow for a better understanding of student’s behavior and co-curriculum activities.

Student profiling on university co-curriculum activities using data visualization tools

Co-curricular activities are playing a vital role in the development of a holistic student. Co-curriculum can be described as an extension of the formal learning experiences in a course or academic program. There are many co-curriculum activities such as students’ participation in sports, volunteerism, leadership, entrepreneurship, uniform body, student council, and other social events. The number of student involves in co-curriculum activities are large, thus creating an enormous volume of data including their demographic facts, academic performance and co-curriculum types. The task for discovering and analyzing these information becomes increasingly difficult and hard to comprehend. Data visualization offer a better ways in handling with large volume of information. The need for an understanding of these various co-curriculum activities and their effect towards student performance are essential. Visualizing these information can help related stakeholders to become aware of hidden and interesting informa...

Exploring mathematics anxiety and attitude: Mathematics students’ experiences

A quantitative and correlational, survey methods were used to investigate the relationships among mathematical anxiety and attitude toward student’s mathematics performance. Participants were 100 students volunteer to enroll in undergraduate Industrial Statistics, Decision Sciences and Business Mathematics at one of northern university in Malaysia. Survey data consisted of demographic items and Likert scale items. The collected data was analyzed by using the idea of correlation and regression analysis. The results indicated that there was a significant positive relationship between students’ attitude and mathematics anxiety. Results also indicated that a substantial positive effect of students’ attitude and mathematics anxiety in students’ achievement. Further study can be conducted on how mathematical anxiety and attitude toward mathematics affects can be used to predict the students’ performance in the class.

Profiling Oman education data using data mining approach

Nowadays, with a large amount of data generated by many application services in different learning fields has led to the new challenges in education field. Education portal is an important system that leads to a better development of education field. This research paper presents an innovative data mining techniques to understand and summarizes the information of Oman’s education data generated from the Ministry of Education Oman “Educational Portal”. This research embarks into performing student profiling of the Oman student database. This study utilized the k-means clustering technique to determine the students’ profiles. An amount of 42484-student records from Sultanate of Oman has been extracted for this study. The findings of this study show the practicality of clustering technique to investigating student’s profiles. Allowing for a better understanding of student’s behavior and their academic performance. Oman Education Portal contain a large amounts of user activity and interaction data. Analyses of this large data can be meaningful for educator to improve the student performance level and recognize students who needed additional attention.Nowadays, with a large amount of data generated by many application services in different learning fields has led to the new challenges in education field. Education portal is an important system that leads to a better development of education field. This research paper presents an innovative data mining techniques to understand and summarizes the information of Oman’s education data generated from the Ministry of Education Oman “Educational Portal”. This research embarks into performing student profiling of the Oman student database. This study utilized the k-means clustering technique to determine the students’ profiles. An amount of 42484-student records from Sultanate of Oman has been extracted for this study. The findings of this study show the practicality of clustering technique to investigating student’s profiles. Allowing for a better understanding of student’s behavior and their academic performance. Oman Education Portal contain a large amounts of user activity and interaction data. Analyses of...

A system dynamic simulation model for managing the human error in power tools industries

In the era of modern and competitive life of today, every organization will face the situations in which the work does not proceed as planned when there is problems occur in which it had to be delay. However, human error is often cited as the culprit. The error that made by the employees would cause them have to spend additional time to identify and check for the error which in turn could affect the normal operations of the company as well as the company’s reputation. Employee is a key element of the organization in running all of the activities of organization. Hence, work performance of the employees is a crucial factor in organizational success. The purpose of this study is to identify the factors that cause the increasing errors make by employees in the organization by using system dynamics approach. The broadly defined targets in this study are employees in the Regional Material Field team from purchasing department in power tools industries. Questionnaires were distributed to the respondents to obtain their perceptions on the root cause of errors make by employees in the company. The system dynamics model was developed to simulate the factor of the increasing errors make by employees and its impact. The findings of this study showed that the increasing of error make by employees was generally caused by the factors of workload, work capacity, job stress, motivation and performance of employees. However, this problem could be solve by increased the number of employees in the organization.