Article Per Year (5 Year)
p-Index From 2021 - 2026
0.835
P-Index
This Author published in this journals
All Journal CAUCHY: Jurnal Matematika Murni dan Aplikasi Journal of Applied Data Sciences Journal of Mathematics, Computation and Statistics (JMATHCOS)
Siti Amiroch
Universitas Islam Darul 'Ulum
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Mathematics

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Minor-Eigenvalue Spectral Analysis in Intuitionistic Fuzzy Soft Sets for Multicriteria Decision Making Silfiatis Sabila Azra Shofa; Siti Amiroch; Awawin Mustana Rohmah
CAUCHY: Jurnal Matematika Murni dan Aplikasi Vol 11, No 1 (2026): CAUCHY: JURNAL MATEMATIKA MURNI DAN APLIKASI
Publisher : Mathematics Department, Maulana Malik Ibrahim State Islamic University of Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18860/cauchy.v11i1.41247

Abstract

Multi-criteria decision making (MCDM) under uncertain data requires a framework capable of capturing ambiguity and non-linear interactions among criteria. This study develops an Intuitionistic Fuzzy Soft Set (IFSS)-based MCDM model using spectral analysis of aggregation matrices constructed with the Einstein operator. Unlike approaches that rely mainly on global eigenvalues, the proposed method utilizes dominant eigenvalues of principal minors to capture local structural variations among alternatives. The method is validated using subdistrict-level economic facility data from Lamongan Regency. The results produce spectral scores ranging from 0.0683 to 2.0000, with Bluluk obtaining the lowest score and Lamongan obtaining the highest score. Several alternatives with comparable global structural characteristics also exhibit distinct minor-eigenvalue responses, indicating that the proposed approach can reveal local structural variations that may not be reflected in global spectral analysis. These findings suggest that minor-eigenvalue-based spectral analysis provides an alternative local perspective for distinguishing alternatives within the IFSS framework. The proposed framework contributes theoretically to IFSS-based spectral modeling and practically supports decision-makers in prioritizing subdistrict development based on local structural characteristics.
Newton Divided Difference Optimization for Fingerprint-Based Neural Virtual Screening against Avian Influenza A/H9N2 Siti Amiroch; Mohammad Jamhuri; Awawin Mustana Rohmah; Mohammad Hamim Zajuli Al Faroby; Chairul Anwar Nidom; Reviany Vibrianita Nidom
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1416

Abstract

Avian influenza A/H9N2 poses persistent zoonotic and veterinary threats, yet efficient computational tools for antiviral compound prioritization remain underdeveloped, particularly with respect to optimizer behavior in high-dimensional neural screening. This study proposes Newton Divided Difference (NDD) optimization, a lightweight positive diagonal curvature-aware training strategy, as a novel optimizer for fingerprint-based neural virtual screening against avian influenza A/H9N2, with the objective of evaluating its performance across aligned molecular fingerprint representations and chemically structured validation protocols. An aligned benchmark of 1,459 molecules consisting of 615 candidate active compounds and 844 decoys was represented by EState (79 features), PubChem (881 features), and Klekota–Roth (4,860 features) fingerprints, sharing identical molecule identities, labels, and split assignments. A fixed multilayer perceptron (MLP) classifier was trained with NDD and seven baseline optimizers under stratified, scaffold-key, and similarity-cluster split protocols across five repeated seeds. NDD achieved the highest descriptive ROC-AUC (Receiver Operating Characteriztic – Area Under the Curve) and PR-AUC (Precision-Recall Area Under the Curve) on Klekota–Roth fingerprints under scaffold-key and similarity-cluster protocols, and remained competitive under the stratified split with ROC-AUC of 0.9872. Architecture-sensitivity tests confirmed stable NDD performance across multiple network configurations, with ROC-AUC values ranging from 0.9876 to 0.9890. Compared with Hessian-free optimization, NDD reduced per-run runtime from approximately 50–54 seconds to approximately 8 seconds on Klekota–Roth under the same CPU-only configuration while achieving comparable ranking performance. The novelty of this work lies in the first systematic assessment of NDD for H9N2 neural virtual screening, demonstrating that positive diagonal curvature-aware scaling provides a practical, stable, and computationally efficient optimization alternative in sparse high-dimensional ligand-based screening settings, although external validation and prospective experimental confirmation remain necessary before practical antiviral prioritization.
Application of the Light Gradient Boosting Machine (LightGBM) Method in Predicting the Risk of Anemia Rani Islamiyati; Siti Amiroch; Awawin Mustana Rohmah; Dicka Yale Kardono
Journal of Mathematics, Computations and Statistics Vol. 9 No. 2 (2026): Volume 09 Issue 02 (June 2026)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/12189

Abstract

Anemia is one of the public health problems that requires serious attention, considering the relatively high percentage of anemia cases across various regions, including mild, moderate, and severe levels. To reduce the number of cases, a method capable of accurately predicting the risk of anemia is needed. This study aims to identify the most influential features in predicting the risk of anemia and to assess the performance of the LightGBM method in predicting this risk. The research process began with several stages: preprocessing, feature selection using the mutual information method, data balancing with SMOTE, parameter optimization via grid search, and evaluation of the LightGBM method on Complete Blood Count (CBC) data from hematology laboratory tests. The results indicate that the top 6 features out of the 16 in the original dataset are Hb, RBC, LYMP, HCT, MCV, and MCH. The application of the LightGBM method yielded optimal performance with an accuracy exceeding 97% and an AUC of 0.99. These values demonstrate that the LightGBM method possesses optimal capability in predicting the risk of anemia.
Implementation of Long Short-Term Memory for Forecasting the Indonesian Rupiah Exchange Rate against the Saudi Arabian Riyal Lisna Fauziyah; Siti Amiroch; Siti Alfiatur Rohmaniah
Journal of Mathematics, Computations and Statistics Vol. 9 No. 2 (2026): Volume 09 Issue 02 (June 2026)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/Jmathcos12190

Abstract

Exchange rates are a key indicator of a country’s economic condition and are inherently volatile and difficult to predict. Indonesian Rupiah exchange rate against Saudi Arabian Riyal (SAR) exhibits complex time series characteristics influenced by various macroeconomic factors. This study aims to forecast the Rupiah–SAR exchange rate using the Long Short-Term Memory (LSTM) method. The dataset consists of secondary data obtained from Bank Indonesia, covering the period from January 2, 2015, to February 27, 2026, with a total of 2,725 observations. The research methodology includes data preprocessing, transformation using a sliding window approach, data splitting, and LSTM modeling with hyperparameter tuning. The best performing model from the research results shows that achieved with a 90:10 train–test split, using 32 LSTM units, a learning rate of 0.001, 100 epochs, a dropout rate of 0.1, and a batch size of 32, yielding a Mean Absolute Percentage Error (MAPE) of 0.240376%, which falls into the highly accurate category. The 30-day forecasting results show a gradual downward trend in the exchange rate. These findings suggest that the LSTM model not only provides high predictive accuracy but also effectively captures the underlying nonlinear dynamics and temporal dependencies of exchange rate movements. Furthermore, the results reflect broader economic interactions, indicating that the model outputs can be utilized as a practical reference for financial planning and economic decision-making.
Comparison of Backpropagation Neural Network and Long Short-Term Memory for Rainfall Prediction in Lamongan Regency Andri Hardiyansyah; Siti Amiroch; Siti Alfiatur Rohmaniah
Journal of Mathematics, Computations and Statistics Vol. 9 No. 2 (2026): Volume 09 Issue 02 (June 2026)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/Jmathcos12238

Abstract

Rainfall is one of the important factors in the agricultural sector and water resource management especially in Lamongan Regency, which has a seasonal rainfall pattern. Variability and uncertainty of rainfall can affect agricultural activities as well as water availability for irrigation needs and water resource management. As an effort to minimise crop failure, an accurate prediction method is needed to support future planning. This study aims to predict rainfall using Backpropagation Neural Network and Long Short-Term Memory (LSTM) methods, as well as to compare the performance of both methods to determine the most optimal method in rainfall prediction to support planting time planning and water management. The data used are historical rainfall data, particularly from areas known as rice production centres in Lamongan Regency. The data underwent preprocessing stages, including data cleaning, normalisation, and time series data formation. The models were trained using three data splitting scenarios, namely 70:30, 80:20, and 90:10, and were then evaluated using the Root Mean Square Error (RMSE). The best model was determined based on the smallest RMSE value and subsequently used to predict rainfall for the next year. The results show that the best model was obtained using the LSTM method, with RMSE values of 24.70 mm for Lamongan, 26.74 mm for Kembangbahu, 44.77 mm for Tikung, 33.12 mm for Sugio, and 33.67 mm for Sukodadi. Therefore, the LSTM method is considered more optimal than the Backpropagation method in predicting rainfall in Lamongan Regency. The effective rice planting period occurs from May to July, as rainfall during this period is relatively sufficient and stable to support crop growth. In addition, planting activities can be carried out two to three times in a year.
Co-Authors Andri Hardiyansyah Awawin Mustana Rohmah Chairul Anwar Nidom Dicka Yale Kardono Lisna Fauziyah Mohammad Hamim Zajuli Al Faroby Mohammad Jamhuri Rani Islamiyati Reviany Vibrianita Nidom Silfiatis Sabila Azra Shofa Siti Alfiatur Rohmaniah