Implementasi Self Organizing Maps untuk Pengelompokan Kabupaten/Kota Berdasarkan Indeks Pembangunan Manusia

Penulis

  • Dwi Marisa Midyanti Universitas Tanjungpura, Pontianak
  • Syamsul Bahri Universitas Tanjungpura, Pontianak

DOI:

https://doi.org/10.25126/jtiik.1067647

Abstrak

Indeks Pembangunan Manusia (IPM) merupakan indikator untuk mengukur keberhasilan dalam membangun kualitas hidup manusia. Di tahun 2022, empat indikator IPM berubah menjadi Umur Harapan Hidup Saat Lahir (UHH), Harapan Lama Sekolah (HLS), Rata-rata Lama Sekolah (RLS), dan Pengeluaran Kapita Pertahun. Namun empat indikator tersebut dianggap sebagian pihak kurang mewakili pembangunan. Penelitian ini bertujuan untuk melakukan pengelompokan IPM Kalimantan Barat dengan adanya penambahan variabel kepadatan penduduk, jumlah guru dan murid, dan jumlah pengangguran menggunakan Self Organizing Maps (SOM). Metode SOM dipilih karena memiliki kelebihan untuk memetakan data berdimensi tinggi kedalam bentuk peta berdimensi rendah. Selain itu digunakan normalisasi Min-Max normalization Benefit dan cost agar normalisasi sesuai dengan kriteria setiap variabel. Hasil penelitian ini menunjukkan bahwa, dengan menggunakan learning rate 0.001, maksimum iterasi 1100, dihasilkan sejumlah 4 cluster dengan nilai Silhouette Coefficients sebesar 0.331611 untuk penambahan variabel kepadatan penduduk, 0.290092 untuk penambahan variabel jumlah guru dan murid, 0.298582 untuk penambahan variabel jumlah pengangguran , dan 0.273734 untuk adanya penambahan variabel kepadatan penduduk, jumlah guru dan murid, dan jumlah pengangguran. Profiling cluster menghasilkan karakteristik dan anggota cluster yang berbeda di setiap penambahan variabel.

 

Abstract

The Human Development Index (IPM) is an indicator to measure success in building the quality of human life. In 2022, the four HDI indicators changed to Life Expectancy at Birth (UHH), Years of School Expectation (HLS), Average Years of Schooling (RLS), and Annual Capita Spending. However, some consider the four indicators to be less representative of development. This study aims to carry out the West Kalimantan IPM cluster by adding population density variables, the number of teachers and students, and the number of unemployed using Self Organizing Maps (SOM). The SOM method was chosen because it has the advantage of mapping high-dimensional data into low-dimensional maps. Besides that, Min-Max normalization Benefit and cost normalization are used so that normalization is in accordance with the criteria for each variable. The results of this study indicate that using a learning rate of 0.001, maximum iteration of 1100, a total of 4 clusters are produced with Silhouette Coefficients values of 0.331611 for the addition of the population density variable, 0.290092 for the addition of the number of teachers and students variable, 0.298582 for the addition of the number of unemployed variables, and 0.273734 for the addition of the variable population density, number of teachers and students, and number of unemployed. Cluster profiling produces different characteristics and cluster members in each variable addition.

Downloads

Download data is not yet available.

Biografi Penulis

  • Dwi Marisa Midyanti, Universitas Tanjungpura, Pontianak
    Jurusan Rekayasa Sistem Komputer
  • Syamsul Bahri, Universitas Tanjungpura, Pontianak
    Jurusan Rekayasa Sistem Komputer

Referensi

ANAM, S., 2017. Segmentasi Exudate Pada Citra Fundus Menggunakan Self Organizing Maps. Pangkalpinang.

BADAN PUSAT STATISTIK PROVINSI KALIMANTAN BARAT, 2023. Indeks Pembangunan Manusia Kalimantan Barat 2022. Pontianak.

BADAN PUSAT STATISTIK PROVINSI KALIMANTAN BARAT, 2022. Indeks Pembangunan Manusia Kalimantan Barat 2021. Pontianak.

BADAN PUSAT STATISTIK PROVINSI KALIMANTAN BARAT, 2023. Provinsi Kalimantan Barat dalam Angka 2023. Pontianak.

BUCUR, C. et al., 2021. Insights Into Energy Indicators Analytics Towards European Green Energy Transition Using Statistics and Self-Organizing Maps. IEEE Access, Volume 9, pp. 64427-64444.

CAO, W., WANG, X., MING, Z. & GAO, J., 2018. A review on neural networks with random weights. Neurocomputing, Volume 275, p. 278–287.

DELGADO, S., MORÁN, F., JOSÉ, J. C. S. & BURGOS, D., 2021. Analysis of Students' Behavior Through User Clustering in Online Learning Settings, Based on Self Organizing Maps Neural Networks. IEEE Access, Volume 9, pp. 132592-132608.

EESA, A. S. & ARABO, W. K., 2017. Normalization Methods for Backpropagation: A Comparative Study. Science Journal of University of Zakho, 5(4), p. 319 –323.

GAO, S., LU, M. & MIAO, N., 2018. Physical Fitness Clustering Analysis Based on Self-Organizing Feature Maps Network. s.l., 2018 4th Annual International Conference on Network and Information Systems for Computers.

ILBEIGIPOUR, S., ALBADVI, A. & NOUGHABI, E. A., 2021. Insights into Energy Indicators Analytics towards European Green Energy Transition Using Statistics and Self-Organizing Maps. IEEE Access, Volume 9, p. 64427–64444.

KIHA, K. E., SERAN, S. & LAU, H. T., 2021. Pengaruh Jumlah Penduduk, Pengangguran, dan Kemiskinan terhadap Indeks Pembangunan Manusia (IPM) di Kabupaten Belu. INTELEKTIVA : Jurnal Ekonomi, Sosial & Humaniora, 2(07), pp. 60-84.

KOHONEN, T., 2001. Self-Organizing Maps. s.l.:Springer Series in Information Sciences.

MELIN, P., MONICA, J. C., SANCHEZ, D. & CASTILLO, O., 2020. Analysis of Spatial Spread Relationships of Coronavirus (COVID-19) Pandemic in the World using Self Organizing Maps. Chaos, Solitons and Fractals, Volume 138, pp. 1-7.

SANGKERENG, W., ENGKA, D. S. & SUMUAL, J. I., 2019. Faktor-Faktor Yang Mempengaruhi Indeks Pembangunan Manusia di Provinsi Sulawesi Utara. Jurnal Berkala Ilmiah Efisiensi, 19(04), pp. 60-71.

SETIANI, D. & HAKIM, F. R., 2015. Clustering Indikator Pembangunan Berkelanjutan Di Indonesia Menggunakan Algoritma Self-Organizing Maps (Soms) Kohonen. s.l., Prosiding Seminar Nasional Matematika dan Pendidikan Matematika UMS.

SINHA, S., SINGH, T. N., SINGH, V. K. & VERMA, A. K., 2010. Epoch determination for neural network by self-organized map (SOM). Computational Geosciences, Volume 14, p. 199–206.

SIVANANDAM, S. N., SUMATHI, S. & DEEPA, S. N., 2006. Introduction to Neural Networks Using MATLAB 6.0.. s.l.:Tata McGraw-Hill Publishing Company Limited.

SOTO, R., CRAWFORD, B., MOLINA, F. G. & OLIVARES, R., 2021. Human Behaviour Based Optimization Supported With Self-Organizing Maps for Solving the S-Box Design Problem. IEEE Access, Volume 9, pp. 84605-84618.

SOUSA, M. A. D. A. D., PIRES, R. & DEL-MORAL-HERNANDEZ, E., 2020. SOMprocessor: A high throughput FPGA-based architecture for implementing Self-Organizing Maps and its application to video processing. Neural Networks, Volume 125, p. 349–362.

TALAKUA, M. W., LELEURY, Z. A. & TALLUTA, A. W., 2017. Analisis Cluster Dengan Menggunakan Metode K-Means Untuk Pengelompokkan Kabupaten/Kota Di Provinsi Maluku Berdasarkan Indikator Indeks Pembangunan Manusia Tahun 2014. Barekeng : Jurnal Ilmu Matematika dan Terapan, 11(2), p. 119 – 128.

VAFAEI, N., RIBEIRO, R. A. & CAMARINHA-MATOS, L. M., 2015. Importance of Data Normalization in Decision Making: case study with TOPSIS method. s.l., ICDSST 2015 Proceedings – The 1st Int. Conference On Decision Support Systems Technologies An Ewg-Dss Conference.

Diterbitkan

29-12-2023

Terbitan

Bagian

Ilmu Komputer

Cara Mengutip

Implementasi Self Organizing Maps untuk Pengelompokan Kabupaten/Kota Berdasarkan Indeks Pembangunan Manusia. (2023). Jurnal Teknologi Informasi Dan Ilmu Komputer, 10(6), 1265-1272. https://doi.org/10.25126/jtiik.1067647