Article Per Year (5 Year)
p-Index From 2021 - 2026
0.659
P-Index
This Author published in this journals
All Journal CAUCHY: Jurnal Matematika Murni dan Aplikasi Jurnal POINTER BAREKENG: Jurnal Ilmu Matematika dan Terapan
Mila Kurniawaty
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Energy Engineering Mathematics Mechanical Engineering Physics Transportation

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Prediksi Profil Asam Amino Pada Family Protein Menggunakan Hidden Markov Model Endang Wahyu Handamari; Kwardiniya A; Mila Kurniawaty; Emilia S I
Jurnal POINTER Vol 2, No 2 (2011): Jurnal Pointer - Ilmu Komputer
Publisher : Ilmu Komputer, Universitas Brawijaya

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

Abstract

ABSTRAK Sequence  alignment adalah metode dasar dalam analisis sekuens, yang  merupakan proses penyusunan atau penjajaran dua atau lebih sequence primer sehingga persamaan sequence - sequence tersebut tampak nyata. Salah satu kegunaan  metode ini adalah untuk  memprediksi karakteristik dari suatu protein, yaitu memprediksi struktur atau fungsi protein yang belum diketahui menggunakan protein yang telah diketahui informasi struktur atau informasi fungsinya jika protein tersebut memiliki kesamaan sequence dengan sequence yang terdapat dalam database. Protein merupakan makromolekul yang menyusun lebih dari separuh bagian dari sel.  Protein merupakan  rantai dari gabungan 20 jenis asam amino, di mana setiap jenis protein mempunyai jumlah dan sequence asam amino yang khas. Metode yang dapat diterapkan untuk sequence  alignment di samping algoritma genetika adalah  metode yang berhubungan dengan Hidden Markov Model (HMM). Hidden Markov Model (HMM)  merupakan bentuk pengembangan dari rantai Markov, yang dapat diterapkan dalam kasus yang tidak dapat diamati secara langsung. Sebagai observed state untuk sequence  alignment adalah sequence asam amino dalam tiga kategori yaitu : deletion(1), insertion(2) dan match(3),  sedangkan  untuk hidden state adalah residu asam amino, yang  dapat menentukan  family protein  bersesuaian dengan observasi O .               Implementasi melalui perangkat lunak HMM terhadap sequence asam amino telah dilakukan namun perlu diuji keakuratan  terhadap data sebenarnya melalui PDB (Protein Data Bank). ABSTRACT Sequence alignment is the basic method in sequence analysis,  which is the process of  two or more primer  sequences  so  that  the  equation sequences are apparent.  One of  the  usefulness  of  this  method to predict the characteristics of a protein, which predicts the structure or function of unknown proteins using known protein structure information  if the information  these proteins have sequence similarity to sequences contained in the data base. Proteins are  macromolecules  which  make up more  than half of  the cell. Proteins  are  chains  of a combination of  20 kinds of amino acids,  where each type protein  has  a number of proteins and amino acid sequences are typical.   The  method  can be  applied  to sequence  alignment besides  the genetic algorithm is a method associated with the Hidden Markov Model  (HMM). Hidden Markov Model (HMM) is a form of development of Markov chains, which can be applied in cases that can not be observed directly. As observed state for sequence alignment is the sequence of amino acids into three categories namely: deletion (1), insertion (2) and match (3), while for the hidden state is an amino acid residue, which can determine the family of proteins corresponding to the observation O. Implementation through HMM software for  the amino acid sequence has been done but needs to be tested against actual data accuracy through the PDB  (Protein Data Bank).
Actuarial Modeling of COVID-19 Insurance Kurniawaty, Mila; Arifin, Maulana Muhamad; Kurniawan, Bagus; Sukarno, Sadam Laksamana; Prayoga, Muhammad Teguh
CAUCHY: Jurnal Matematika Murni dan Aplikasi Vol 7, No 3 (2022): CAUCHY: JURNAL MATEMATIKA MURNI DAN APLIKASI
Publisher : Mathematics Department, Universitas Islam Negeri Maulana Malik Ibrahim Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18860/ca.v7i3.14999

Abstract

In this article, we provide an actuarial model expected to be able to help financial arrangements to cover losses due to the outbreak of coronavirus disease (COVID-19). We construct the dynamical models of premium and benefit based on generalized SEIR (Susceptible-Exposed-Infected-Recovered). Based on its dynamical model, we formulate the premium and the premium reserves on hospitalization and death benefits of the COVID-19 insurance.
COMBINING FUZZY ANP AND FUZZY ARAS METHODS FOR DETERMINING THE BEST LAND INVESTMENT LOCATION Idris, Chasib; Kurniawaty, Mila; Fitri, Sa`adatul
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 19 No 3 (2025): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol19iss3pp1499-1512

Abstract

Determining a location for land investment cannot solely rely on intuition, as land investment is one of the economic sectors that frequently changes. Therefore, selecting a land location requires accurate analysis. The purpose of this research is to find the best land investment location using a combination of MCDM (Multi-Criteria Decision Making) methods. The scope of this research focuses on selecting land in Malang City, with the alternatives being all sub-districts in the city. As an initial step, this research employs the Delphi Technique to identify, shortlist, and evaluate the criteria considered by experts in land investment assessment. Six land investment experts participated in this study. The MCDM method used in this research involves two approaches. The weighting of criteria is conducted using the Analytic Network Process (ANP) method, chosen for its ability to account for interrelationships between criteria and alternatives. Following this, the ranking stage utilizes the Additive Ratio Assessment (ARAS) method, which provides utility function values to determine the efficiency of alternatives. To reduce panelist subjectivity, this research uses trapezoidal fuzzy numbers, which are generally better than triangular fuzzy numbers often used in other studies. The assessment results of criteria and sub-criteria indicate that the panelist weightings achieved good hierarchical consistency. From the ANP method combined with the Delphi technique, the Road Access sub-criterion was identified as having the highest weight, followed by the Land Profitability Index sub-criterion, and subsequently by seven other sub-criteria considered in this investment problem. The final outcome of this research, which combines the ANP and ARAS methods with fuzzy usage, shows that the relative efficiency of viable alternatives is directly proportional to the relative impact of the main criteria values and weights considered in the investment. The Arjowinangun sub-district also emerged as the best alternative for land investment.
DEVELOPMENT OF HEALTH INSURANCE CLAIM PREDICTION METHOD BASED ON SUPPORT VECTOR MACHINE AND BAT ALGORITHM Anam, Syaiful; Guci, Abdi Negara; Widhiatmoko, Fery; Kurniawaty, Mila; Wijaya, Komang Agus Arta
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/barekengvol17iss4pp2281-2292

Abstract

Health insurance industry is very much needed by the community in handling the financial risks in the health sector. The number of claims greatly affects the achievement of profits and the sustainability of the health insurance industry. Therefore, filing claims by insurance users from year to year is important to be predicted in insurance firm. The Machine Learning (ML) method promises to be a good solution for predicting health insurance claims compared to conventional data analytics methods. Support Vector Machine (SVM) is one of the superior ML approaches. Nonetheless, SVM performance is controlled by the suitable selection of SVM parameters. The SVM parameters is typically selected by trial and error, sometimes resulting in not optimal performance and taking a long time to complete. Swarm intelligence-based algorithms can be used to select the best parameters from SVM. This method is capable of locating the global best solution, is simple to implemented, and doesn't involve derivatives. One of the best swarm intelligence algorithms is the Bat Algorithm (BA). BA has a faster convergence rate than other algorithms, for example Particle Swarm Optimization (PSO). Based on this situation, this paper offers the new classification model for predicting health insurance claim based on SVM and BA. The metrics utilized for evaluation are accuracy, recall, precision, f1-score, and computing time. The experimental outcomes show that the proposed approach is superior to the conventional SVM and the hybrid of SVM and PSO in forecasting health insurance claims. In addition, the proposed method has a substantially shorter computing time than the hybrid of SVM and PSO. The outcomes of the experiments also indicate that the new classification model for predicting health insurance claim based on the SVM and BA can avoid over-fitting condition.
Co-Authors Arifin, Maulana Muhamad Bagus Kurniawan, Bagus Emilia S I Endang Wahyu Handamari Fery Widhiatmoko Fitri, Sa`adatul Guci, Abdi Negara Idris, Chasib Kwardiniya Andawaningtyas Prayoga, Muhammad Teguh Sukarno, Sadam Laksamana Syaiful Anam Wijaya, Komang Agus Arta