Optimization of Data Mining for Grouping Courses Using the MDDS and MAR Methods

DOI

10.2991/978-94-6463-084-8_16How to use a DOI?

Keywords

Optimization; Data Mining; MDDS; MAR

Abstract

To find meaningful clusters from a data set, attribute clustering is carried out, so that the attributes in the created cluster will have a high or very good correlation, as well as interdependence with each other. While the attributes in the other clusters are less correlated or more independent. The experimental results show how to determine the list of dominant attribute ratings using soft set theory. A series of experiments were conducted to evaluate the clustering performance, clustering efficiency and scalability of the MAR and MDDS algorithms. The experimental results show that, MDDS achieves better clustering accuracy and stability than the MAR algorithm, at the same time increasing efficiency. MDDS has clear advantages over MAR on large data sets in terms of clustering efficiency as well as clustering accuracy. In addition, the MDDS technique has better scalability. It can be applied to small category data sets as well as large category data sets. The clustering of data under soft set theory can be considered as a technique for data mining. Maximum Degree of Domination in soft set theory is applied to select grouping attributes. In the assessment of student lectures to determine the optimal clustering attributes, and get the best value is very urgent in data clustering. So in the assessment of lecturers’ lectures on the subjects being taught, in order to get optimal results, clustering of lecture assessments is needed. Actually, there are five types of methods and techniques, based on coarse and soft sets, to select the attributes for grouping course assessments, namely TR, MMR, MDA, NSS, and MAR. However, the MAR method has better numerical computational time, compared to the other four approaches. In the MAR method, there is a drawback, namely the execution time is still slow, because in the iteration process it determines the relative attributes. So to overcome these problems, use an alternative technique based on soft sets to select clustering attributes, namely the Maximum Degree of Domination in Soft set theory (MDDS) method. In this method, the steps in defining the multi soft set are explained first. Then determine the dominance of the soft set and its degree. Then the maximum degree of dominance will be used to determine the best grouping attributes in the assessment of student lectures. The results of the experimental data obtained show that the MDDS technique is very good, and can significantly reduce the numerical computation time. The MDDS method is better than MAR with a working percentage of 43.99%. The MDDS method also has better scalability, which is indicated by the execution time increasing linearly, with increasing data size. While the accuracy of the experimental data set has a class attribute, and has increased by 3.23%. So the MDDS technique can be a solution to the problem solving above, so that in the assessment of lecturers’ lectures on the subjects being taught, they can get optimal results.

Copyright

© 2022 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Paryati
AU  - Agung Mulyo Widodo
AU  - Shankar Rao Munjam
AU  - Krit Salahddine
AU  - Sagayam Martin
PY  - 2022
DA  - 2022/12/26
TI  - Optimization of Data Mining for Grouping Courses Using the MDDS and MAR Methods
BT  - Proceedings of the First Mandalika International Multi-Conference on Science and Engineering 2022, MIMSE 2022 (Informatics and Computer Science) (MIMSE-I-C-2022)
PB  - Atlantis Press
SP  - 169
EP  - 183
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-084-8_16
DO  - 10.2991/978-94-6463-084-8_16
ID  - 2022
ER  -