Application of K-Means Algorithm for Cluster Analysis on Poverty of Provinces in Indonesia

Sano, Albert Verasius Dian; Nindito, Hendro

doi:10.21512/comtech.v7i2.2254

Cited by 19 publications

(11 citation statements)

References 11 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The method used for the classification of sound feature is K-Means Clustering. K-Means is one of the algorithms in data mining that can be used to group/clustering data [14]. The K-Means method is a method included in the distance-based clustering algorithm that divides the data into a number of clusters, and this algorithm only works on numeric attributes [15].…”

Section: E Classifiermentioning

confidence: 99%

Speech classification using combination virtual center of gravity and k-means clustering based on audio feature extraction

2020

View full text Add to dashboard Cite

show abstract

Section: E Classifiermentioning

confidence: 99%

Speech classification using combination virtual center of gravity and k-means clustering based on audio feature extraction

2020

View full text Add to dashboard Cite

show abstract

“…Weng et al menggunakan teknik data mining dan machine learning untuk membuat suatu model prediksi dalam mengidentifikasi karbonilasi protein (protein carbonylation) [5]. Penerapan lainnya diberikan oleh Sano and Nindito yang mengelompokkan daerah miskin di Indonesia menggunakan algoritma K-Means Clustering [6]. Hasil penelitian tersebut menunjukkan kelompok provinsi yang harus dijadikan prioritas pengentasan kemiskinan oleh para pembuat kebijakan.…”

Section: Pendahuluanunclassified

Penerapan Algoritma J48 Decision Tree Untuk Analisis Tingkat Kemiskinan di Indonesia

Kaunang

2019

CogITo Smart Journal

View full text Add to dashboard Cite

Kemiskinan telah menjadi masalah sosial dan tantangan bagi masyarakat di seluruh dunia yang terus dicari penyelesaiannya. Berdasarkan identifikasi dari Badan Program Pembangunan PBB (UNDP) yang bekerjasama dengan Oxford Poverty and Human Development Initiative (OPHI), 1.3 miliar penduduk dunia teridentifikasi sebagai penduduk miskin pada bulan September tahun 2018. Di tingkat nasional, Indonesia, tingkat kemiskinan tertinggi terjadi pada tahun 1999 dengan persentase sebesar 23.43%. Berdasarkan data dari Badan Pusat Statistik Indonesia (BPS), penduduk miskin di Indonesia mencapai 25.95 juta orang dengan persentase 9.82% pada tahun Maret 2018. Oleh karena itu penelitian ini bertujuan untuk menganalisis tingkat kemiskinan menggunakan dimensi dasar dari indeks pembangunan manusia (IPM) menggunakan metode data mining dan machine learning yakni algoritma J48 Decision Tree. Akurasi dari model prediksi yang telah dibuat menunjukan hasil yang baik yakni sebesar 88.6% dimana dengan kata lain model prediksi yang dikembangkan dapat digunakan untuk membantu para pembuat kebijakan maupun para pemangku kepentingan untuk mengambil keputusan. Kata kunci—Angka Kemiskinan, Indeks Pembangunan Manusia, Algoritma J48 Decision Tree, Data Mining, Machine Learning

show abstract

“…K-means is one of the clustering algorithms widely used in environmental science, medicine, biology, astronomy, and economics because of its simple and effective features (Roy & Sharma, 2010). However, the K-means algorithm must be in the form of a vector in the calculation process and is sensitive to noise and abnormalities (Haut, Paoletti, Plaza, Plaza, &Plaza, 2017 andSano &Nindito, 2016). The clustering performance is determined by the choice of the initial representative point, which means that K representative points are selected from N data objects.…”

Section: Clustering Algorithmmentioning

confidence: 99%

Modular configuration of service elements based on the improved K‐means algorithm

Zhang

2018

Expert Systems

View full text Add to dashboard Cite

To reduce the vagueness and subjectivity of customer demand in the process of product–service system design, a fuzzy semantic calculation method is proposed to obtain the importance of service demand. In addition, according to the demand of the clustering of service modules, a new clustering method is proposed to analyse discrete data based on the improved K‐means algorithm that is based on the Kruskal algorithm. According to the criterion of the service module division and its weight, the correlation coefficient between any two service activities is judged to form the comprehensive correlation coefficient matrix, and the comprehensive dissimilarity matrix can be obtained by the additive model. Then, this method calculates the minimum cost spanning tree (MCST) using the Kruskal algorithm. The different clusters of service activities with different centres can be found based on the MCST, and the edge values can be calculated by the improved K‐means algorithm. This paper uses 28 service activities of excavators. These activities can be divided into K (K = 4, 5, 6, and 7) clusters by the improved K‐means algorithm. Finally, the service element configuration model is established based on the demand weight, which is optimized by using the maximum customer satisfaction of competition.

show abstract

Application of K-Means Algorithm for Cluster Analysis on Poverty of Provinces in Indonesia

Abstract: ABSTRACT

Cited by 19 publications

References 11 publications

Speech classification using combination virtual center of gravity and k-means clustering based on audio feature extraction

Speech classification using combination virtual center of gravity and k-means clustering based on audio feature extraction

Penerapan Algoritma J48 Decision Tree Untuk Analisis Tingkat Kemiskinan di Indonesia

Modular configuration of service elements based on the improved K‐means algorithm

Contact Info

Product

Resources

About