Application of particle swarm optimization (PSO) to improve k-means accuracy in clustering eligible province to receive fish seed assistance in java
By: Majdina, Nur Syahrani.
Contributor(s): Soeleman, M. Arief.
Publisher: Haryana IOSR - International Organization of Scientific Research 2022Edition: Vol.24(1), Jan-Feb.Description: 43-49p.Subject(s): Computer EngineeringOnline resources: Click here In: IOSR Journal of Computer Engineering (IOSR-JCE)Summary: Background: The k-means algorithm is to divides the data into clusters based on the closest distance by using the Euclidean distance formula. K-means is often used because the resulting approach is easy to implement, but has the disadvantage that the central point depends on the choice of K, resulting in a decrease in the speed and quality of a cluster. Methodology: The research method uses the Cross-Industry Standard Process for Data Mining (CRISP-DM) cycle using 6 phases. The purpose of this research is to automate the selection of numbering on K-means so as to further increase the speed and quality of a cluster. Discussion: The algorithm used is the K-means algorithm and Particle Swarm Optimization (PSO) which is validated using the K-nn algorithm because if it is calculated using the confusion matrix it has an accuracy of 97.78% and has a Davies-Bouldin Index (DBI) ) value of 0.369877333 which is included in the high category when applied to data on the volume of fishery products on the island of Java. Conclusion: The final result of this study is that it has succeeded in automating the selection of numbering on K-means so that the speed and quality of a cluster is to determine which provinces are entitled to receive assistance in the form of fish seeds to increase the volume of fishery products on the island of Java because of the results of the calculation of K-means clustering and Particle Swarm Optimization ( PSO) which was tested using the K-nn classification which was calculated using the confusion matrix and the Davies-Bouldin Index ( DBI) the accuracy value increased, there were 261 fishery production volume data that we're entitled to receive assistance in the form of fish seeds on the island of Java.Item type | Current location | Call number | Status | Date due | Barcode | Item holds |
---|---|---|---|---|---|---|
Articles Abstract Database | School of Engineering & Technology Archieval Section | Not for loan | 2022-2075 |
Background: The k-means algorithm is to divides the data into clusters based on the closest distance by using
the Euclidean distance formula. K-means is often used because the resulting approach is easy to implement, but
has the disadvantage that the central point depends on the choice of K, resulting in a decrease in the speed and
quality of a cluster.
Methodology: The research method uses the Cross-Industry Standard Process for Data Mining (CRISP-DM)
cycle using 6 phases. The purpose of this research is to automate the selection of numbering on K-means so as
to further increase the speed and quality of a cluster.
Discussion: The algorithm used is the K-means algorithm and Particle Swarm Optimization (PSO) which is
validated using the K-nn algorithm because if it is calculated using the confusion matrix it has an accuracy of
97.78% and has a Davies-Bouldin Index (DBI) ) value of 0.369877333 which is included in the high category
when applied to data on the volume of fishery products on the island of Java.
Conclusion: The final result of this study is that it has succeeded in automating the selection of numbering on
K-means so that the speed and quality of a cluster is to determine which provinces are entitled to receive
assistance in the form of fish seeds to increase the volume of fishery products on the island of Java because of
the results of the calculation of K-means clustering and Particle Swarm Optimization ( PSO) which was tested
using the K-nn classification which was calculated using the confusion matrix and the Davies-Bouldin Index (
DBI) the accuracy value increased, there were 261 fishery production volume data that we're entitled to receive
assistance in the form of fish seeds on the island of Java.
There are no comments for this item.