IMPLEMENTATION OF THE DBSCAN ALGORITHM FOR CLUSTERING STUNTING PREVALENCE TYPOLOGY IN WEST JAVA, CENTRAL JAVA, AND EAST JAVA REGIONS
Stunting, a condition where children are malnourished for a long period, causes growth failure in children. West Java, Central Java, and East Java are the 3 provinces with the highest prevalence of stunting in 2021. This study aims to group districts/cities in these provinces based on factors that i...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Pattimura
2025-07-01
|
| Series: | Barekeng |
| Subjects: | |
| Online Access: | https://ojs3.unpatti.ac.id/index.php/barekeng/article/view/17132 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849237897920643072 |
|---|---|
| author | Bagus Sumargo Kadir Kadir Dena Safariza Munawar Asikin Dania Siregar Nilam Novita Sari Danu Umbara Rizky Hilmianto Robert Kurniawan Irman Firmansyah |
| author_facet | Bagus Sumargo Kadir Kadir Dena Safariza Munawar Asikin Dania Siregar Nilam Novita Sari Danu Umbara Rizky Hilmianto Robert Kurniawan Irman Firmansyah |
| author_sort | Bagus Sumargo |
| collection | DOAJ |
| description | Stunting, a condition where children are malnourished for a long period, causes growth failure in children. West Java, Central Java, and East Java are the 3 provinces with the highest prevalence of stunting in 2021. This study aims to group districts/cities in these provinces based on factors that influence stunting using the DBSCAN method (there has been no previous research using this method for this case), so the typology of stunting prevalence is implied. The group results can be valuable input for policy priorities in overcoming stunting. The study used the DBSCAN (Density-Based Spatial Clustering of Application with Noise) method, which can also detect noises (outliers). The determination of eps and MinPts is based on the average value of the distance from each data to its closest neighbor. The distance obtained then was used in the KNN algorithm to determine eps and MinPts parameters. Clustering is done using standardized data and DBSCAN parameters obtained from the k-dist plot, eps is 1.92, and MinPts is 2. The validation test used is the silhouette coefficient to determine the goodness of the cluster results. The clustering results show that there are 2 clusters and 1 noise that have special characteristics related to factors that influence the prevalence of stunting. Cluster 1 consisted of 97 districts/cities and was characterized by a high percentage of infants under 6 months receiving exclusive breastfeeding and the lowest average per capita household expenditure. Cluster 2 (Bekasi City and Depok City) was characterized by the lowest percentage of households with proper health facilities and infants aged 0-59 months receiving complete immunization. The noise (high stunting prevalence) in Bandung City is characterized by the lowest percentage of households having proper sanitation. |
| format | Article |
| id | doaj-art-2606e07aff5744cc8e8d1b87b5acec7e |
| institution | Kabale University |
| issn | 1978-7227 2615-3017 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Universitas Pattimura |
| record_format | Article |
| series | Barekeng |
| spelling | doaj-art-2606e07aff5744cc8e8d1b87b5acec7e2025-08-20T04:01:48ZengUniversitas PattimuraBarekeng1978-72272615-30172025-07-011931779179010.30598/barekengvol19iss3pp1779-179017132IMPLEMENTATION OF THE DBSCAN ALGORITHM FOR CLUSTERING STUNTING PREVALENCE TYPOLOGY IN WEST JAVA, CENTRAL JAVA, AND EAST JAVA REGIONSBagus Sumargo0Kadir Kadir1Dena Safariza2Munawar Asikin3Dania Siregar4Nilam Novita Sari5Danu Umbara6Rizky Hilmianto7Robert Kurniawan8Irman Firmansyah9Department of Statistics, Faculty of Mathematics and Natural Sciences, Universitas Negeri Jakarta, IndonesiaEconomist, BPS Statistics-Indonesia, IndonesiaDepartment of Statistics, Faculty of Mathematics and Natural Sciences, Universitas Negeri Jakarta, IndonesiaDepartment of Economic, Universitas Al Azhar, IndonesiaDepartment of Statistics, Faculty of Mathematics and Natural Sciences, Universitas Negeri Jakarta, IndonesiaDepartment of Statistics, Faculty of Mathematics and Natural Sciences, Universitas Negeri Jakarta, IndonesiaDepartment of Statistics, Faculty of Mathematics and Natural Sciences, Universitas Negeri Jakarta, IndonesiaDepartment of Statistics, Faculty of Mathematics and Natural Sciences, Universitas Negeri Jakarta, IndonesiaDepartment of Statistical Computing, Politeknik Statistika STIS, IndonesiaSystem Dynamics Centre SDC, IndonesiaStunting, a condition where children are malnourished for a long period, causes growth failure in children. West Java, Central Java, and East Java are the 3 provinces with the highest prevalence of stunting in 2021. This study aims to group districts/cities in these provinces based on factors that influence stunting using the DBSCAN method (there has been no previous research using this method for this case), so the typology of stunting prevalence is implied. The group results can be valuable input for policy priorities in overcoming stunting. The study used the DBSCAN (Density-Based Spatial Clustering of Application with Noise) method, which can also detect noises (outliers). The determination of eps and MinPts is based on the average value of the distance from each data to its closest neighbor. The distance obtained then was used in the KNN algorithm to determine eps and MinPts parameters. Clustering is done using standardized data and DBSCAN parameters obtained from the k-dist plot, eps is 1.92, and MinPts is 2. The validation test used is the silhouette coefficient to determine the goodness of the cluster results. The clustering results show that there are 2 clusters and 1 noise that have special characteristics related to factors that influence the prevalence of stunting. Cluster 1 consisted of 97 districts/cities and was characterized by a high percentage of infants under 6 months receiving exclusive breastfeeding and the lowest average per capita household expenditure. Cluster 2 (Bekasi City and Depok City) was characterized by the lowest percentage of households with proper health facilities and infants aged 0-59 months receiving complete immunization. The noise (high stunting prevalence) in Bandung City is characterized by the lowest percentage of households having proper sanitation.https://ojs3.unpatti.ac.id/index.php/barekeng/article/view/17132clusteringdbscanknn-distance graphstunting prevalencetypology |
| spellingShingle | Bagus Sumargo Kadir Kadir Dena Safariza Munawar Asikin Dania Siregar Nilam Novita Sari Danu Umbara Rizky Hilmianto Robert Kurniawan Irman Firmansyah IMPLEMENTATION OF THE DBSCAN ALGORITHM FOR CLUSTERING STUNTING PREVALENCE TYPOLOGY IN WEST JAVA, CENTRAL JAVA, AND EAST JAVA REGIONS Barekeng clustering dbscan knn-distance graph stunting prevalence typology |
| title | IMPLEMENTATION OF THE DBSCAN ALGORITHM FOR CLUSTERING STUNTING PREVALENCE TYPOLOGY IN WEST JAVA, CENTRAL JAVA, AND EAST JAVA REGIONS |
| title_full | IMPLEMENTATION OF THE DBSCAN ALGORITHM FOR CLUSTERING STUNTING PREVALENCE TYPOLOGY IN WEST JAVA, CENTRAL JAVA, AND EAST JAVA REGIONS |
| title_fullStr | IMPLEMENTATION OF THE DBSCAN ALGORITHM FOR CLUSTERING STUNTING PREVALENCE TYPOLOGY IN WEST JAVA, CENTRAL JAVA, AND EAST JAVA REGIONS |
| title_full_unstemmed | IMPLEMENTATION OF THE DBSCAN ALGORITHM FOR CLUSTERING STUNTING PREVALENCE TYPOLOGY IN WEST JAVA, CENTRAL JAVA, AND EAST JAVA REGIONS |
| title_short | IMPLEMENTATION OF THE DBSCAN ALGORITHM FOR CLUSTERING STUNTING PREVALENCE TYPOLOGY IN WEST JAVA, CENTRAL JAVA, AND EAST JAVA REGIONS |
| title_sort | implementation of the dbscan algorithm for clustering stunting prevalence typology in west java central java and east java regions |
| topic | clustering dbscan knn-distance graph stunting prevalence typology |
| url | https://ojs3.unpatti.ac.id/index.php/barekeng/article/view/17132 |
| work_keys_str_mv | AT bagussumargo implementationofthedbscanalgorithmforclusteringstuntingprevalencetypologyinwestjavacentraljavaandeastjavaregions AT kadirkadir implementationofthedbscanalgorithmforclusteringstuntingprevalencetypologyinwestjavacentraljavaandeastjavaregions AT denasafariza implementationofthedbscanalgorithmforclusteringstuntingprevalencetypologyinwestjavacentraljavaandeastjavaregions AT munawarasikin implementationofthedbscanalgorithmforclusteringstuntingprevalencetypologyinwestjavacentraljavaandeastjavaregions AT daniasiregar implementationofthedbscanalgorithmforclusteringstuntingprevalencetypologyinwestjavacentraljavaandeastjavaregions AT nilamnovitasari implementationofthedbscanalgorithmforclusteringstuntingprevalencetypologyinwestjavacentraljavaandeastjavaregions AT danuumbara implementationofthedbscanalgorithmforclusteringstuntingprevalencetypologyinwestjavacentraljavaandeastjavaregions AT rizkyhilmianto implementationofthedbscanalgorithmforclusteringstuntingprevalencetypologyinwestjavacentraljavaandeastjavaregions AT robertkurniawan implementationofthedbscanalgorithmforclusteringstuntingprevalencetypologyinwestjavacentraljavaandeastjavaregions AT irmanfirmansyah implementationofthedbscanalgorithmforclusteringstuntingprevalencetypologyinwestjavacentraljavaandeastjavaregions |