Overbeek, Marlinda Vasty and Kaesmetan, Yampi R. (2020) Data Train Reduction on Data Image With K Support Vector Nearest Neighbor (Case Study : Maize Leaf Image). Indonesian Journal of Artificial Intelligence and Data Mining, 7 (2).
Full text not available from this repository.Abstract
In this study, we applied the K Support Vector Nearest Neighbor algorithm to reduce data train on data image. The data image that we used is the maize leaves image infected with fungi and healthy maize leave. The aim of data train reduction in this study is to get faster and more accurate prediction results. This because by using the K Support Vector Nearest Neighbor algorithm, a support vector that is formed from the algorithm really characterize the objective function of the problem. The accuracy obtained from this study is 0.20 or 20% mean error for the value of nearest neighbor K = 3 and using K Nearest Neighbor as a model construction algorithm. The error value is smaller than when we compared to the construction of the model without performing data train reduction. The error value if not doing any reduction is 0.209 or 20.9%. Whereas in terms of time efficiency, working with the K Support Vector Nearest algorithm is 24 seconds faster than without performing data train reduction
| Item Type: | Article |
|---|---|
| Subjects: | 000 Computer Science, Information and General Works > 000 Computer Science, Knowledge and Systems > 006 Special Computer Methods |
| Divisions: | Faculty of Engineering & Informatics > Informatics |
| Depositing User: | Administrator UMN Library |
| Date Deposited: | 10 Oct 2021 14:30 |
| Last Modified: | 10 Oct 2021 14:30 |
| URI: | https://kc.umn.ac.id/id/eprint/18604 |
Actions (login required)
 |
View Item |
