Claim Missing Document
Check
Articles

Generalized Additive Models for Modeling Pneumonia Cases in Toddlers in West Java based on the Penalized Spline Estimator Wahyu, Azkanul; Nurul Gusriani; Kankan Parmikanti
EKSAKTA: Berkala Ilmiah Bidang MIPA Vol. 25 No. 02 (2024): Eksakta : Berkala Ilmiah Bidang MIPA (E-ISSN : 2549-7464)
Publisher : Faculty of Mathematics and Natural Sciences (FMIPA), Universitas Negeri Padang, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/eksakta/vol25-iss02/491

Abstract

Acute Respiratory Infections (ARI) are one of the causes of high mortality in the world, such as pneumonia in toddlers. Pneumonia cases in West Java are high compared to other provinces. In this study, pneumonia cases will be modeled with Generalized Additive Models (GAM) based on penalized spline estimators. The optimal number of knots is determined using the full search algorithm and the optimal smoothing parameter is obtained based on the minimum Generalized Cross Validation (GCV) value of order one or two. Then, GAM parameter estimation is performed using the local scoring algorithm. Formed model based on the order, number of knots, and smoothing parameters of each predictor variable with order one, number of knots two, and optimal smoothing parameter one for , order two, number of knots three, and optimal smoothing parameter one for , and order one, number of knots two, and optimal smoothing parameter for  whose parameters were estimated by local scoring resulted in a coefficient of determination of 0.679. This indicates that 67.9% of the factors from the predictor variables affect the percentage of pneumonia cases among under-fives while the remaining 32.1% is influenced by other factors outside the model.
Robust Linear Discriminant Analysis with Modified One-Step M-Estimator Qn Scale for Classifying Financial Distress in Banks: Case Study Nabila Putri; Parmikanti, Kankan; Gusriani, Nurul
EKSAKTA: Berkala Ilmiah Bidang MIPA Vol. 25 No. 02 (2024): Eksakta : Berkala Ilmiah Bidang MIPA (E-ISSN : 2549-7464)
Publisher : Faculty of Mathematics and Natural Sciences (FMIPA), Universitas Negeri Padang, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/eksakta/vol25-iss02/515

Abstract

The COVID-19 pandemic has significantly disrupted the banking sector, leading to a decline in profit growth as an indicator of financial distress. Bank financial health can be evaluated using the RGEC (Risk Profile, Good Corporate Governance, Earnings, Capital) analysis. While Linear Discriminant Analysis (LDA) ideally requires normality and homogeneity of covariance matrices, financial data often fail to meet these assumptions. Therefore, this study employs robust linear discriminant analysis using the Modified One-Step M-Estimator with Qn scale estimator (MOM-Qn) to classify ‘distress’ and ‘non-distress’ bank conditions. Given these challenges, this study acts as a preventive measure for banks to evaluate financial health simultaneously. The objective is to provide a robust discriminant function for more accurate and stable classification, particularly in the presence of outliers. It focuses on conventional private banks listed on the Indonesia Stock Exchange (IDX) during December 2021-2022. The results show a classification accuracy of 69.23% and a Press’s Q value of 11.53846, indicating the method’s effectiveness in classifying real financial data.  
Penerapan Rantai Markov Terboboti Untuk Memprediksi Tingkat Inflasi Di Indonesia Diansyah D. Darmawan; Firdaniza Firdaniza; Kankan Parmikanti
SisInfo Vol 2 No 1 (2020): SisInfo
Publisher : Universitas Informatika dan Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (513.053 KB)

Abstract

Inflasi diartikan sebagai kenaikan harga barang dan jasa secara umum dan terus-menerus. Inflasi yang terus meningkat atau tidak terkendali dapat berdampak buruk terhadap perekonomian suatu negara, sehingga penentuan kebijakan moneter untuk mengendalikan tingkat inflasi agar tetap rendah harus dilakukan dengan tepat. Namun, kebijakan moneter tidak akan berdampak secara langsung terhadap perekonomian suatu negara, oleh karena itu tingkat inflasi untuk masa yang akan datang perlu diketahui agar dapat membantu lembaga keuangan dalam penentuan kebijakan moneter. Pada penelitian ini rantai Markov terboboti digunakan untuk memprediksi keadaan inflasi di Indonesia untuk enam bulan ke depan dengan penentuan prediksi tingkat inflasinya berdasarkan nilai karakteristik keadaan. Hasil prediksi pada penelitian ini menghasilkan nilai MAPE sebesar 4,48% artinya prediksi tingkat inflasi di Indonesia dengan menggunakan rantai Markov terboboti dapat dikatakan memiliki akurasi yang sangat baik.
THE LIE ALGEBRA su(3) REPRESENTATION WITH RESPECT TO ITS BASIS Kurniadi, Edi; Parmikanti, Kankan
Jurnal Matematika UNAND Vol. 13 No. 3 (2024)
Publisher : Departemen Matematika dan Sains Data FMIPA Universitas Andalas Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/jmua.13.3.163-169.2024

Abstract

The eight-dimensional Lie algebra of 3×3 anti-Hermitian matrices withits traces equal to zero is denoted by su(3) whose Lie group is denoted by SU(3). Theresearch aims to provide all representations of su(3) with respect to its basis which isrealized on the three complex variables homogeneous polynomials P1 of degree three. The first step is to construct representations of SU(3) on the space H and the second step is to find all derived representations of SU(3). The obtained results are eight explicit formulas of representations su(3) ↷ P1.
Comparison of Fuzzy Grey Markov Model (1,1) and Fuzzy Grey Markov Model (2,1) in Forecasting Gold Prices in Indonesia Soraya, Arthamevia Najwa; Firdaniza, Firdaniza; Parmikanti, Kankan
Jambura Journal of Mathematics Vol 6, No 2: August 2024
Publisher : Department of Mathematics, Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jjom.v6i2.26679

Abstract

Currently, gold investment is considered promising despite the ever-changing price of gold. However, obtaining optimal profits is a challenge for investors. Therefore, a proper forecasting method is needed to forecast the gold price so investors can know the best transaction time. This study used two forecasting methods: the Fuzzy Grey Markov Model (1,1) and a new, never-before-used approach, the Fuzzy Grey Markov Model (2,1). The Fuzzy Grey Markov Model (2,1) approach is interesting because it can be considered for forecast data that shows varying increases and decreases, such as the gold price data used in this study. Both methods are combined models that utilize fuzzy logic to handle uncertainty in data; the Grey model forms a forecasting model, and the Markov chain determines the state transition probability matrix. Next, the error rates of the two methods are compared based on the Mean Absolute Percentage Error (MAPE) value to obtain the best forecasting method. As a result of this study, the Fuzzy Grey Markov Model (1,1) was chosen as the best forecasting method with a MAPE value of 0.28%.
Comparative Analysis of Normal Pension Benefits Using the Attained Age Normal Method and the Individual Level Premium Method Hukama, Atha; Parmikanti, Kankan; Riaman, Riaman
International Journal of Quantitative Research and Modeling Vol 6, No 2 (2025)
Publisher : Research Collaboration Community (RCC)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijqrm.v6i2.946

Abstract

Pension programs are among the most important forms of employee compensation, offering financial security after retirement. This study aims to calculate the company’s initial payroll contributions to determine regular contributions, actuarial liabilities, and pension benefits using two actuarial projection methods: the Attained Age Normal (AAN) and Individual Level Premium (ILP) methods. The analysis is based on employee data from Puskesmas Binjai Estate, including age, salary, and years of service. It includes computations of pension benefits, normal costs, actuarial liabilities, and net benefits received by employees under each method. The results reveal that the length of service significantly affects both the value of contributions and the actuarial liabilities. Employees with longer service periods result in higher contribution requirements and greater liabilities. Moreover, the Attained Age Normal method produces higher pension benefits compared to the Individual Level Premium method for long-serving employees. However, both methods present financial challenges for employers, as they require higher contributions relative to the benefits promised. Consequently, companies must allocate substantial funding to meet their pension obligations. This study provides a comparative perspective that can assist decision-makers in selecting an actuarial method that balances benefit adequacy and financial sustainability.
Autoregressive neural network (AR-NN) modeling to predict the inflation rate in West Java Province Zahra, Nabila; Parmikanti, Kankan; Ruchjana, Budi Nurani
Desimal: Jurnal Matematika Vol. 7 No. 2 (2024): Desimal: Jurnal Matematika
Publisher : Universitas Islam Negeri Raden Intan Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/djm.v7i2.22626

Abstract

The Autoregressive (AR) model describes the situation where the data in the current observation of a time series depends on the previous observation data. AR models have linearity assumptions. However, in reality there is a non-linear tendency in the data so it needs to be combined with a Neural Network (NN) model. NN models can overcome nonlinear problems in data. The purpose of this research is to build an AR-NN model and apply it to the inflation rate data of West Java Province. The result of this study is an AR(2)-NN model generated by summing the AR(2) prediction results with the residual AR(2) prediction results using a NN model that has a network architecture (4-5-1). The results of data processing show that the AR(2)-NN model is able to increase the level of forecast accuracy from a reasonable forecast to an accurate forecast so that the AR(2)-NN model is better used in West Java Province inflation rate data. This is supported by the smaller MAPE values compared to the AR(2) model. The AR-NN model is expected to be a recommendation for predicting inflation rates in the future.
REGRESI LOGISTIK MULTINOMIAL BAYESIAN DENGAN ALGORITMA GIBBS SAMPLING UNTUK MENENTUKAN FAKTOR-FAKTOR TINGKAT KEMISKINAN DI INDONESIA Syifana, Hani; Gusriani, Nurul; Parmikanti, Kankan
Jurnal Matematika Integratif Vol 21, No 1: April 2025
Publisher : Department of Matematics, Universitas Padjadjaran

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24198/jmi.v21.n1.62937.89-102

Abstract

Poverty is a state of deprivation experienced by individuals or groups with monthly per capita expenditure that is insufficient to meet basic needs. Based on Indonesia's poverty profile released by the Statistics Indonesia (BPS) in March 2024, it was recorded that 9.03% of Indonesia's population was declared poor, which is still far from the poverty reduction target of 6.5% to 7.5% targeted in the National Medium-Term Development Plan 2020-2024. One of the efforts that can be made to end poverty in Indonesia is to analyze what factors affect the poverty rate. The method used in this study is Bayesian multinomial logistic regression using the Markov Chain Monte Carlo (MCMC) Gibbs Sampling algorithm and the response variable used as a measure of poverty level is the poverty line which is an official indicator sourced from BPS. The results show that after 20,000 iterations, the Markov chain reaches a stationary state with the results of the credible interval test supported by the deviance test results stating that the factors that have a significant effect on the poverty rate in Indonesia in 2024 are GRDP at constant prices and average years of schooling.
INTEGRATED OF WEB APPLICATION RSHINY FOR MARKOV CHAIN AND ITS APPLICATION TO THE DAILY CASES OF COVID-19 IN WEST SUMATERA Monika, Putri; Ruchjana, Budi Nurani; Parmikanti, Kankan; Abdullah, Atje Setiawan
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 17 No 4 (2023): BAREKENG: Journal of Mathematics and Its Applications
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol17iss4pp2397-2410

Abstract

Discrete-time of Markov chains, starting now referred to as Markov chains, have been widely used by previous researchers in predicting the phenomenon. The predictions were made by manual calculations and using separate software, including Maple, Matlab, and Microsoft Excel. The analysis takes a relatively long time, especially in calculating the number of transitions from each state. This research built an integrated R script for the Markov chain based on the web application RShiny to quickly, easily, and accurately predict a phenomenon. The Markov chain integrated R script is built via command-command to predict the day-n distribution with the n-step distribution and long-term probability using a stationary distribution. The RShiny web application built is limited to state two and three. The integrated web application RShiny for the Markov chain is used to predict the daily cases of COVID-19 in West Sumatra. Based on the analysis carried out in predicting the daily cases of COVID-19 in West Sumatra from March 26, 2020, to October 20, 2020, for the next three days and in the long term, the results show that there is a 51.2% probability of an increase in COVID-19 cases, a 43% probability that cases will decrease, and 5.8% chance of stagnant cases
Penerapan Model Seasonal Autoregressive Integrated Moving Average (SARIMA) dalam Peramalan Curah Hujan di Kabupaten Bandung Barat nadhira, valda azka; Ruchjana, Budi Nurani; Parmikanti, Kankan
KUBIK Vol 10 No 1 (2025): IN PRESS
Publisher : Jurusan Matematika, Fakultas Sains dan Teknologi, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The expansion of the Kabupaten Bandung, namely Kabupaten Bandung Barat (KBB) is located in hilly and lowland areas. Rainfall in Kabupaten Bandung Barat has an impact on the productivity and performance of key sectors, such as agriculture, plantations and tourism. Low rainfall can lead prolonged dry seasons and result in drought. Conversely, extreme rainfall can also have negative impacts, such as causing soil erosion and potentially affecting the appeal and smooth operation of tourist destinations. Therefore, rainfall forecasting is needed in making appropriate policies, especially regarding the impacts of rainfall changes in KBB. The Seasonal Autoregressive Integrated Moving Average (SARIMA) method is applied in this study to forecast rainfall in KBB. The aims of this research are to estimate the parameters of the SARIMA model using the Maximum Likelihood Estimation (MLE) method and to apply the SARIMA method in forecasting rainfall in KBB, particularly during the December-January-February (DJF) period. The results of the analysis show that the SARIMA model can be applied to forecast rainfall in KBB. The best SARIMA model obtained ARIMA(2,1,0)(0,0,1)3 with a MAPE value 17,80%, which indicates an accurate forecasting criterion. Keywords: SARIMA, MLE, Rainfall.