Performance analysis of student learning metric using K-mean clustering approach K-mean cluster

Shankar, Sonali; Sarkar, Bishal Dey; Sabitha, Sai; Mehrotra, Deepti

doi:10.1109/confluence.2016.7508140

Cited by 14 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research by Shankar et al [5] clustered students from different countries based on their attributes: average grade, the number of participated events, the number of active days, and the number of attended chapters. An optimal k value of K-means was determined by means of the Silhouette index resulting in k � 3.…”

Section: Related Workmentioning

confidence: 99%

On Characterization of Norm-Referenced Achievement Grading Schemes toward Explainability and Selectability

Banditwattanawong

Masdisornchote

2021

Applied Computational Intelligence and Soft Computing

View full text Add to dashboard Cite

Grading is the process of interpreting learning competence to inform learners and instructors of the current learning ability levels and necessary improvement. For norm-referenced grading, the instructors use a conventionally statistical method, z score. It is difficult for such a method to achieve explainable grade discrimination to resolve dispute between learners and instructors. To solve such difficulty, this paper proposes a simple and efficient algorithm for explainable norm-referenced grading. Moreover, the rise of artificial intelligence nowadays makes machine learning techniques attractive to the norm-referenced grading in general. This paper also investigates two popular clustering methods, K-means and partitioning around medoids. The experiment relied on the data sets of various score distributions and a metric, namely, Davies–Bouldin index. The comparative evaluation reveals that our algorithm overall outperforms the other three methods and is appropriate for all kinds of data sets in almost all cases. Our findings however lead to a practically useful guideline for the selection of appropriate grading methods including both clustering methods and z score.

show abstract

Section: Related Workmentioning

confidence: 99%

On Characterization of Norm-Referenced Achievement Grading Schemes toward Explainability and Selectability

Banditwattanawong

Masdisornchote

2021

Applied Computational Intelligence and Soft Computing

View full text Add to dashboard Cite

show abstract

“…Therefore comparing with the learner paradigm marks of particular country & it has been done that the marks are not the simplest thing to signify the appropriate patient of the subject. The examination can be widespread to obtain into deliberation the last characteristic such as 'certified', 'explored' etc [12,13].…”

Section: Learnermentioning

confidence: 99%

Design of Intelligent E-Learning Assessment Framework Using Bayesian Belief Network

Kaliwal¹,

Deshpande²

2021

JEET

View full text Add to dashboard Cite

An Intelligent Tutoring Systems is a type of knowledge-based system whose main agenda is to efficiently supplement a human tutor with a machine. Dissimilar to conventional classroom teaching, Intelligent Tutoring Systems (ITSs) have the ability to fit according to the necessity of an individual learner. More emphasis has been laid on various types of e-learning systems. In this work, a probability-based ITSs system is proposed consisting of four models specifically the learner's behaviour model, pedagogical model, knowledge base model and learner assessment model. The importance has been given to the learner assessment model where an element of uncertainty has been introduced and handled by the Bayesian Belief Network (BBN). The purpose of the learner assessment model is to rightly detect the knowledge level of each learner based on their reply to the level of questions, where the level of questions is random to the process of assessment to the learner. The uncertainty factor has been defined in terms of success and failure parameters. Success is the probability that a learner of low cleverness level gives a right reply to a level of questions and is increased by a small probability of 0.07, whereas Failure is the probability that a learner of high cleverness level gives a wrong reply to a level of questions and is reduced by a small probability of 0.04. In this work during an assessment of the knowledge level of a learner, the system has incorporated the uncertainty factors of Success and Failure with the help of Bayes' rule and has found promising results that take into account the possibility of Success or Failure.

show abstract

“…Cerezo et al [4] Singh et al [17] Najdi et al [18] Li et al [19] Fan et al [20] Yamasari et al [21] Yamasari et al [23] Shankar et al [31] Rosa et al [33] Campagni et al [34] the categorybased feature extraction Yes, the random selection The outcomes of the clustering depend on the group members ' study The clustering result depends on the group members ' study Clustering of students' interaction patterns on LMS using EM and K-means Clustering of students' academic performance using K-means Clustering of students' typologies using Kmeans…”

Section: Descriptionmentioning

confidence: 99%

“…Accordingly, the clustering evaluation mostly is categorized as the unsupervised evaluation because this task only works the evaluation by the internal indices. Relating to the evaluation clustering, the previous research in [31] apply the clustering task by K-means to analysis the performance of student learning and measure the clustering performance using unsupervised evaluation, namely: silhouette index.…”

Section: Clustering Evaluation In Educational Data Miningmentioning

confidence: 99%

Identifying Dominant Characteristics of Students’ Cognitive Domain on Clustering-based Classification

Yamasari¹,

Nugroho²,

Yoshimoto³

et al. 2020

IJIES

View full text Add to dashboard Cite

The rapid growth of information and communications technology-based educational tools generates a large volume of student data with many features (characteristics). However, the mining process in the clustering task of student data is not often done optimally, so the performance of the system decreases. To overcome this problem, we propose a discretization method on logistic regression to determine the most optimal number of clusters. Additionally, we introduce a technique that combines the features selection using a filter-and wrapper-based procedures (HFS) to identify the dominant features of the students' cognitive domains. Furthermore, we evaluate the identification result by three clustering methods, namely: K-means, EM, and Farthest first. Finally, we propose the clustering-based classification so the results can be measured by using the classification metrics. Here, we apply two evaluation techniques, namely: cross-validation and percentage split. The experimental results indicate that our approach describes predominance, in terms of classification metrics over conventional methods. Our approach is around 10,847-11,134 percent higher in terms of accuracy average than the original features on both the assessment techniques. Also, this approach significantly reduces the time taken to create a prototype between 0.0167-0.027 seconds. This gives the impact on a significant reduction in the model created to the number of unsuitable students on classes based on the cognitive domain, namely: 3-12 students.

show abstract

Performance analysis of student learning metric using K-mean clustering approach K-mean cluster

Cited by 14 publications

References 9 publications

On Characterization of Norm-Referenced Achievement Grading Schemes toward Explainability and Selectability

On Characterization of Norm-Referenced Achievement Grading Schemes toward Explainability and Selectability

Design of Intelligent E-Learning Assessment Framework Using Bayesian Belief Network

Identifying Dominant Characteristics of Students’ Cognitive Domain on Clustering-based Classification

Contact Info

Product

Resources

About