Comparison of Network and Data Correlation in Modeling Revise Stage of Case Based Learning

DOI

10.2991/978-94-6463-413-6_9How to use a DOI?

Keywords

Case-Based Reasoning; Revise; Data Correlation; Student Performance

Abstract

Case-based reasoning (CBR) is a method that models and adapts experience to find the right solution for new problems. CBR stages consist of retrieve, reuse, revise, and retain. Revise stage is one of important key in CBR method to adapt a new case. This is because if a problem cannot be found the right solution in the knowledge base, then this stage will adapt experience to become an appropriate solution. Based on the research reviewed, the revise stage still uses active intervention by experts on the system. The involvement of experts directly in the system requires costs and is limited by space and time, so it is necessary to create a mechanism that can work automatically. The mechanism created is expected to be able to approach the expertise of an expert. However, in optimizing the process, it is necessary to carry out correlation analysis on knowledge data owned by CBR, so that data features that are highly correlated with the class can be selected. Otherwise neural network (NN) use to find the role revise model on the CBR data by learning its distance. In this study, we will create a CBR system which at the revise stage utilizes data correlation, CBR system which at the revise stage utilizes NN role modelling, and also creates a CBR system that still uses an expert, namely a teacher. The test results of the 10 testdata for both models, obtained an accuracy value of 70% for the CBR system at the revise stage using expert assistance, 90% for the CBR system at the revise stage using a data correlation model, and 87% for the CBR system at the revise stage using NN model. Based on these tests, the results of this study can be said that the CBR system with the data correlation model at the revise stage is able to approach or exceed the expertise of an expert.

Copyright

© 2024 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  - I Gede Santi Astawa
AU  - Desak Putu Sri Wulandari
AU  - Luh Putu Ida Harini
PY  - 2024
DA  - 2024/05/13
TI  - Comparison of Network and Data Correlation in Modeling Revise Stage of Case Based Learning
BT  - Proceedings of the First International Conference on Applied Mathematics, Statistics, and Computing (ICAMSAC 2023)
PB  - Atlantis Press
SP  - 86
EP  - 94
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-413-6_9
DO  - 10.2991/978-94-6463-413-6_9
ID  - Astawa2024
ER  -