Claim Missing Document
Check
Articles

Found 13 Documents
Search

PEMODELAN TINGKAT KUALITAS AIR DI KOTA PONTIANAK DENGAN MENGGUNAKAN MULTIVARIATE GEOGRAPHICALLY WEIGHTED REGRESSION Kusnandar, Dadan; Debataraja, Naomi Nessyana; Utari, Shindy
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 15 No 3 (2021): BAREKENG: Jurnal Ilmu Matematika dan Terapan
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (600.308 KB) | DOI: 10.30598/barekengvol15iss3pp493-502

Abstract

Ketersediaan air bersih dan sanitasi yang layak merupakan salah satu tujuan dalam Sustainable Development Goals. Kualitas air cenderung mengalami penurunan terutama di daerah permukiman akibat tercemar limbah dari hasil kegiatan manusia. Penyebab pencemaran air bisa jadi berbeda-beda di setiap lokasi pengamatan, sehingga faktor letak geografis perlu dipertimbangkan pada proses pengambilan keputusan. Multivariat Geographically Weighted Regression digunakan untuk mengatasi adanya pengaruh heterogenitas spasial dalam data yang disebabkan oleh perbedaan kondisi lokasi yang satu dengan lokasi lain. Tujuan dari penelitian ini adalah menentukan model dan faktor-faktor apa saja yang berpengaruh terhadap kualitas air di Kota Pontianak. Data yang digunakan pada penelitian ini adalah data kualitas air di Kota Pontianak sebanyak 42 titik sampel lokasi. Variabel responnya terdiri dari Y1 (COD) dan Y2 (TDS), sedangkan untuk variabel prediktor terdiri dari X1 (warna), X2 (pH), X3 (kandungan zat besi), dan X4 (kesadahan). Hasil penelitian menunjukkan bahwa variabel yang mempengaruhi COD adalah warna, sedangkan variabel TDS dipengaruhi oleh warna dan kesadahan.
MULTI-STATE MODEL FOR CALCULATION OF LONG-TERM CARE INSURANCE PRODUCT PREMIUM IN INDONESIA Perdana, Hendra; Satyahadewi, Neva; Kusnandar, Dadan; Tamtama, Ray
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 16 No 4 (2022): BAREKENG: Journal of Mathematics and Its Applications
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (487.771 KB) | DOI: 10.30598/barekengvol16iss4pp1293-1302

Abstract

Long Term Care (LTC) insurance is a type of health insurance. One of the LTC products is Annuity as A Rider Benefit. This insurance provides benefits for medical care costs during the term and death benefits if the insured dies. This insurance product can be modeled with a multi-state model. The multi-state model is a stochastic process in which the subject can switch states at a specified number of states. This paper discusses the calculation of LTC insurance premiums with the Annuity as A Rider Benefit product using a multi-state model for critically ill patients in Indonesia. The state used consisted of eight states, namely healthy, cancer, heart disease, stroke, died from the illness from each disease, and died from others. The premium calculation also utilized Markov chain transition probabilities. The data used were data on Indonesia's population in 2018, data on the prevalence of cancer, heart disease, stroke, and Indonesia's 2019 mortality table. The stages of this study were calculating the net single premium value, benefit annuity value, and insurance premium value. The case study was conducted on a 25 years old male in good health following LTC insurance with a coverage period of 5 years. It was known that the compensation value for someone who dies was IDR 100,000,000 and the interest rate used was 5%. The calculation results obtained an annual premium of IDR 5,308,915 which was then varied based on gender and varied interest. Insurance premiums for men were more expensive than for women since men had a greater chance of dying. Then, the higher the interest rate taken; the lower premium paid. This was because the interest rate is a discount variable.
CLUSTER MAPPING OF HOTSPOTS USING KERNEL DENSITY ESTIMATION IN WEST KALIMANTAN Cahyani, Cristy Framedia; Kusnandar, Dadan; Debataraja, Naomi Nessyana; Martha, Shantika
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 18 No 4 (2024): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol18iss4pp2353-2362

Abstract

Forest and land fires pose a recurring concern every year in Indonesia, often taking place in West Kalimantan Province, particularly during the dry season. This study aims to use the Kernel Density Estimation (KDE) to categorize the data of the hotspots in the province of West Kalimantan according to their density and to map the cluster level of the fire risks in the region. The data utilized in this study are secondary data obtained from the images of the MODIS (Moderate Resolution Imaging Spectroradiometer) instrument, which are available on firms.modaps.eosdis.nasa.gov and provided by NASA. The data focuses on hotspots dispersed across West Kalimantan province during 2020. The variables examined in the study were the confidence level (≥80%) of forest and land fire hotspots, the distance from each point to the nearest river, and the distance from each point to the nearest road. The kernel density estimation method with a Gaussian kernel function yielded clustering results into three distinct groups according to their vulnerability levels. Low vulnerability areas comprise Cluster 1, which consists of 127 points or 50.97% of the total hotspots. Medium vulnerability areas belong to Cluster 2, which has 47 points or 30.32% of the total. Cluster 3 includes high vulnerability locations, consisting of 29 points or 18.71% of the total. The most susceptible areas to forest and land fires are located within the Ketapang regency.