A Novel Educational Data Mining Model using Classification Algorithm for evaluating Students E-learning Performance

Arumugam, S.; Kovalan, A.; Narayanan, Arun

doi:10.26438/ijcse/v7i5.616624

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e SVM (Support Vector Machine) algorithm often classifies samples incorrectly near the optimal classification hyperplane. For the NB classification algorithm, theoretically, the NB algorithm has very good efficiency and minimum error rate [23,24], and the assumption of class condition independence reduces the computational cost of the algorithm. However, in practical application, such a hypothesis is impossible.…”

Section: Big Data Classification Algorithmmentioning

confidence: 99%

Reflections on the Innovation of University Scientific Research Management in the Era of Big Data

2022

Scientific Programming

View full text Add to dashboard Cite

In China, universities are important centers for SR (scientific research) and innovation, and the quality of SR management has a significant impact on university innovation. The informatization of SR management is a critical component of university development in the big data environment. As a result, it is crucial to figure out how to improve SR management. As a result, this paper builds a four-tier B/W/D/C (Browser/Web/Database/Client) university SR management innovation information system based on big data technology and thoroughly examines the system’s hardware and software configuration. The SVM-WNB (Support Vector Machine-Weighted NB) classification algorithm is proposed, and the improved algorithm runs in parallel on the Hadoop cloud computing platform, allowing the algorithm to process large amounts of data efficiently. The optimization strategy proposed in this paper can effectively optimize the execution of scientific big data applications according to a large number of simulation experiments and real-world multidata center environment experiments.

show abstract

Section: Big Data Classification Algorithmmentioning

confidence: 99%

Reflections on the Innovation of University Scientific Research Management in the Era of Big Data

2022

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…In our previous works [2], [3], the converted multidimensional text data are taken into training and testing the grades available in the excel file. Then it was analyzed using a J48 classifier and random tree classifier, neural network algorithms like MLPNN and RBFNN.…”

Section: Dataset and Algorithms Used In This Association Rule Minmentioning

confidence: 99%

“…In our previous work [1], instead of treating it as time-series data, we proposed a model to convert it as simple multidimensional numerical data to make it suitable to check with clustering and classification. In our previous works [1], [2], [3], we examined the dataset using J48, MLPNN, RBFNN algorithms and compared the precision, recall and f-measures.…”

Section: Introductionmentioning

confidence: 99%

An Association Rule Mining Based Model to Predict Learning Performance of a student with e-Learning Activity Log Data

Arumugam¹,

Kovalan²,

Narayanan³

2020

IJITEE

View full text Add to dashboard Cite

There is a wider scope in research on log data of computed aided learning and interactive learning. We have an enormous collection of log data of students’ activities during their learning process. Data Mining(DM) algorithms help us to discover knowledge and information from a huge and complex data sets. In a time-series log data, it is very complicated to verify the DM algorithms to mine the dataset. e-Learning activity log data is taken and converted into categorical data to predict the learning behavior of the students to implement the algorithms. The excavated knowledge can be used to modify the e-learning system. It is very easy from the result to note the slow learners and advanced learners well in advance before conducting an examination. Time series data is a numeric data that measures in a time period in successive order. The dataset used in this work is a UCI EPM dataset. It is a Non-Linear Time-Series Data. The converted dataset is used to apply a rule mining algorithm to predict the performance of a student. The measurements support and confidence will help us to predict the students’ performance. The results also have been compared with other classification mining algorithms. It assists to improve and to build an educational model on e-Learning. In turn it supports students, teachers, and educational system as well Learning Management System.

show abstract

A Novel Educational Data Mining Model using Classification Algorithm for evaluating Students E-learning Performance

Cited by 2 publications

References 0 publications

Reflections on the Innovation of University Scientific Research Management in the Era of Big Data

Reflections on the Innovation of University Scientific Research Management in the Era of Big Data

An Association Rule Mining Based Model to Predict Learning Performance of a student with e-Learning Activity Log Data

Contact Info

Product

Resources

About