Claim Missing Document
Check
Articles

Found 24 Documents
Search

Cluster Analysis of Environmental Pollution in Indonesia Using Complete Linkage Method with Elbow Optimization Damayanti, Adelia; Utami, Wika Dianita; Novitasari, Dian Candra Rini; Intan, Putroue Keumala; Kurniawan, Mohammad Lail
JTAM (Jurnal Teori dan Aplikasi Matematika) Vol 7, No 2 (2023): April
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jtam.v7i2.12961

Abstract

The issue of environmental contamination remains unsolved. The problem continues to have a substantial detrimental impact. This research aimed to identify provinces in Indonesia with high or low levels of environmental pollution so that the government may offer treatment to provinces with high levels of pollution and seek a significant reduction in the incidence of environmental pollution in Indonesia. Clustering is required to identify provinces with high and low pollution levels using the complete linkage method because this method can provide tight clusters and is less impacted by outliers. The analysis of the complete linkage method with Elbow optimization revealed two optimal clusters, namely high and low clusters. The high cluster consists of three provinces: Central Java, West Java, and East Java. The low cluster consists of 31 provinces. This research used a Silhouette Coefficient validity test. The value of the Silhouette Coefficient is 0.75. The value indicates that the data object is in the correct cluster and that the cluster structure is relatively strong.
MODELLING THE NUMBER OF CRIMES IN EAST JAVA USING A TRUNCATED SPLINE SEMIPARAMETRIC REGRESSION APPROACH Saputra, Yahya Vigo Tri; Hafiyusholeh, Moh.; Khaulasari, Hani; Farida, Yuniar; Intan, Putroue Keumala
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 20 No 2 (2026): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol20iss2pp1627-1642

Abstract

High crime rates can lead to unrest and financial losses for the community. East Java is one of the provinces with high crime rates, with a total of 21,046 reported crimes in 2023. This study aims to identify the factors that influence crime rates in East Java and evaluate the goodness of the model through truncated spline semiparametric regression. Truncated spline semiparametric regression is a combination of parametric and nonparametric methods that can adjust changes in data patterns through the presence of knot points. The data used in this study were sourced from the Central Statistics Agency, including variables such as the number of people living in poverty, average years of schooling, gross regional domestic product, population, Gini ratio, per capita expenditure, and open unemployment rate. The results of the analysis indicate that the predictor variables have a significant influence on the number of crimes simultaneously. Partially, the variables that influence the number of crimes in East Java Province are average years of schooling, population, Gini ratio, per capita expenditure, and open unemployment rate. The best regression model is obtained using the combination knot point (4,2,4,3) with a minimum GCV value of 49636.60. The coefficient of determination obtained is 93.60%, indicating that the predictor variables can explain 93.60% of the variation in the crime rate, while the remaining 6.40% is attributed to variables outside the scope of the study.
Clustering Data Kecelakaan Lalu Lintas melalui Algoritma K-Means dengan Seleksi Fitur Chi-Square Margaretha, Adellia Putri; Ulinnuha, Nurissaidah; Intan, Putroue Keumala
INTEGER: Journal of Information Technology Vol 10, No 2 (2025): September
Publisher : Fakultas Teknologi Informasi Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31284/j.integer.0.v10i2.7529

Abstract

Kecelakaan lalu lintas merupakan permasalahan signifikan di Indonesia, dengan dampak fatal dan kerugian ekonomi yang besar. Penelitian ini bertujuan untuk menerapkan algoritma K-means untuk mengelompokkan data kecelakaan lalu lintas dengan menggunakan seleksi fitur. Data kecelakaan lalu lintas yang digunakan diperoleh dari sebuah perusahaan asuransi kecelakaan di Sidoarjo dan diproses untuk menghasilkan fitur-fitur yang relevan. Proses seleksi fitur dilakukan untuk menentukan fitur-fitur yang memiliki kepentingan dan informasi yang paling relevan dalam proses pengelompokkan. Metode seleksi fitur yang digunakan dalam penelitian ini adalah seleksi fitur Chi-Square, yang bertujuan untuk memilih fitur-fitur yang memiliki hubungan signifikan dengan variabel target kecelakaan. Hasil penelitian menunjukkan bahwa data terbagi menjadi 2 cluster dengan seleksi fitur maupun tanpa seleksi fitur, yaitu wilayah dengan tingkat kecelakaan tinggi dan rendah. Nilai koefisien sillhouette cluster sebelum dilakukan seleksi fitur adalah sebesar 0,57. Sedangkan setelah diterapkan seleksi fitur dengan Chi-Square, diperoleh hasil yang lebih baik yaitu sebesar 0,72. Penelitian ini menunjukkan bahwa dengan menerapkan metode seleksi fitur dapat meningkatkan performa pengelompokkan data kecelakaan lalu lintas dengan algoritma K-means.
Optimal control using pontryagin’s maximum principle: Tuberculosis spread case Muhammad Iqbal Widiaputra; Ahmad Hanif Asyhar; Wika Dianita Utami; Putroue Keumala Intan; Dian Yuliati; Muhammad Fahrur Rozi
(IJCSAM) International Journal of Computing Science and Applied Mathematics Vol. 10 No. 2 (2024)
Publisher : LPPM Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j24775401.ijcsam.v10i2.4602

Abstract

Tuberculosis is one of the deadliest infectious diseases in the world. In 2020, 9.9 million people were infected and 1.5 million died. East Java province ranks third with 43,268 tuberculosis cases. This research aims to determine the results of the tuberculosis disease model and simulation without and with the use of optimal control. The mathematical model SEIR is a model that can analyze the spread of the disease tuberculosis. In this research, a variable treatment compartment to the SEIR model. It used 4 antibiotics in the intensive phase and added Isoniazid and Rifampicin in the advanced phase as the optimal control parameters. Optimal control uses Pontriagin’s maximum principle as the derivative to modify the SEIR model and is described by a Runge-Kutta order 4 scheme. It shows both the useful parameters in the optimal control with a maximum value of 1 and plots where the effect of optimal control exists further constrained the people infected with Tuberculosis.