Article Per Year (5 Year)
p-Index From 2021 - 2026
1.686
P-Index
This Author published in this journals
All Journal CAUCHY: Jurnal Matematika Murni dan Aplikasi Bulletin of Electrical Engineering and Informatics Telematika : Jurnal Informatika dan Teknologi Informasi Journal of Innovation and Applied Technology Natural B Jurnal Berkala Epidemiologi Proceeding of the Electrical Engineering Computer Science and Informatics Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Prosiding Seminar Nasional Teknoka Jurnal Irigasi Indonesian Journal of Electrical Engineering and Computer Science COMSERVA: Jurnal Penelitian dan Pengabdian Masyarakat
Anam, Syaiful
Brawijaya University
Agriculture, Biological Sciences & Forestry Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Immunology & microbiology Industrial & Manufacturing Engineering Mathematics Public Health Social Sciences

Published : 25 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 25 Documents
Search

 1   2   3 
Klasifikasi Fungsi Senyawa Aktif berdasarkan Notasi Simplified Molecular Input Line Entry System (SMILES) menggunakan Metode Random Forest Faiz Anggiananta Winantoro; Dian Eka Ratnawati; Syaiful Anam
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 4 (2021): April 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

A compound is a single substance composed of two or more elements that form chemical bonds. There are two types of compounds, namely active compounds and inactive compounds. Active compounds are compounds that have physiological effects on other organisms. In Indonesia, there are still many active compounds whose function is unknown. Therefore, a classification method is needed to help determine the function of the active compound. Classification is done with data written in SMILES notation. From the SMILES notation, features such as the number of atoms B, C, N, O, P, S, F, Cl, Br, I, OH, =, #, @, -, +, COC, C = C, are taken. O-], N +, C = O, and () go through the preprocessing process. Before being used for the classification process, all these features are divided by the length of the SMILES notation to get their value. This research was conducted to classify the function of active compounds by applying the Random Forest (RF) method with the SMILES data object with 4 classes of compound functions. RF was chosen because this method has almost no overfitting conditions, is able to handle data with many features, and this method is not affected by datasets that have missing values. The best accuracy resulted in testing with 4 class data is 69% and the best average in testing with the K-Fold Cross Validation method is 63%. Then, on the data with 3 classes of compound functions, the best accuracy is 76% and the best average in testing with the K-Fold Cross Validation method is 70%. Finally, testing data with 2 classes of compound functions produces the highest accuracy of 86% and the best average of 80%.
Adaptive Portfolio Rebalancing for NASDAQ-100 Stocks with Hippopotamus Optimization Algorithm under Transaction Costs Safrizal Ardana Ardiyansa; Mohamad Muslikh; Syaiful Anam
CAUCHY: Jurnal Matematika Murni dan Aplikasi Vol 11, No 2 (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.v11i2.43876

Abstract

This study proposes a transaction cost-aware portfolio optimization framework for NASDAQ-100 stocks based on the Hippopotamus Optimization Algorithm (HOA). The mathematical model extends the classical mean-variance framework by incorporating transaction costs into a Net Sharpe Ratio (NSR) objective function. Daily adjusted closing prices of NASDAQ-100 constituent stocks from 2021 to 2025 are employed, with the twenty highest-ranked stocks according to the Sharpe Ratio (SR) selected as the candidate investment universe. Each optimization experiment is independently repeated 25 times to evaluate robustness and solution stability. The results indicate that the proposed HOA consistently achieves competitive optimization performance with very small variability across repeated runs throughout the investment horizon. Although several competing algorithms attain comparable or slightly better objective values during particular rebalancing periods, HOA remains among the strongest-performing methods while exhibiting stable convergence behavior. Throughout the investment horizon, the proposed algorithm produces the highest average cumulative portfolio value of \$5,307.87 \$125.71 from an initial investment of \$1,000, corresponding to an average annual return of 40.03% 0.68%, together with the highest average SR and NSR of 1.5736 0.0151, while maintaining competitive maximum drawdown and transaction costs. These findings demonstrate that incorporating transaction costs directly into the optimization objective enables HOA to achieve a favorable balance between portfolio growth, risk-adjusted performance, and trading efficiency under dynamic market conditions.
Health Insurance Claim Classification using Support Vector Machine with Velocity Pausing Particle Swarm Optimization Luh Putu Dharma Jayanti; Syaiful Anam; Safrizal Ardana Ardiyansa; Natasha Clarissa Maharani
CAUCHY: Jurnal Matematika Murni dan Aplikasi Vol 10, No 2 (2025): 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.v10i2.31914

Abstract

classification is a serious problem. Identifying claim classification is difficult. Machine Learning (ML) can predict potential claim decisions. Support Vector Machine (SVM) is a ML model that can generalize well to test data. SVM achieves an -score of 73.39% and 89.88% with a linear kernel, 73.34% and 73.34% with Radial Basis Function (RBF) kernel. Particle Swarm Optimization (PSO) improves the performance, because it can find the best parameters for SVM. However, the SVM parameters found by PSO are not guaranteed to be the global optimum. Velocity Pausing PSO (VPPSO) can address this problem. SVM-VPPSO performs better compared with SVM and SVM-PSO. SVM-VPPSO with linear kernel achieves -score of 90.17%, 90.16%, and 90.06% with 10, 20, and 30 particles respectively. The linear kernel also performs better than RBF kernel with a difference of 0.39% on the testing data. The best configuration is SVM-Linear-VPPSO with 10 particles. This configuration also achieves computation time of 46.938 seconds, which faster than SVM-Linear-VPPSO with 20 particles. The variance in computational time with 10 particles is 1.832 seconds, which better than with 20 particles with variance of 37.909 seconds.
Combination of Extreme Learning Machine and Binary Bat Algorithm for Customer Churn Prediction Arifin Arifin; Syaiful Anam; Marsudi Marsudi
CAUCHY: Jurnal Matematika Murni dan Aplikasi Vol 10, No 1 (2025): 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.v10i1.31815

Abstract

AbstractOne of the important assets in a company is customers. Customers determine the company's stability because they are source of income and determine the company's competitiveness. It shows the importance of predicting which customers have the potential to switch to another company. These predictions can be done using Machine Learning (ML). One of ML methods is the Extreme Learning Machine (ELM). The advantages of ELM compared to other methods are fast computing time, ease of use, and can reach a global optimum. However, ELM has weaknesses when solving problems with high-dimensional datasets, so feature selection is required. The Binary Bat Algorithm (BBA) is a swarm intelligence method that can be used to optimize ELM performance. The advantages of BBA compared to other are few parameters and much better in effectiveness or accuracy. This research was carried out with preprocessing data, training data and testing data. The research results showed that ELM-BBA is better than ELM and ELM-Binary Particle Swarm Optimization (BPSO) in evaluation metric values. However, ELM-BBA tended to be slower than ELM-BPSO. The best results on evaluation metrics achieved by ELM-BBA were 0.97, 0.97, 0.96, and 0.97 in accuracy, precision, recall, and F1 score, respectively.
Fractional Perona–Malik-based processing for noise reduction and structure preservation in red, green, blue Pap smear images Syaiful Anam; Normi Abdul Hadi; Avin Maulana; Indah Yanti; Suhaila Abd Halime
Bulletin of Electrical Engineering and Informatics Vol 15, No 4: August 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i4.11246

Abstract

Cervical cancer screening relies heavily on Pap smear analysis, yet image noise, low contrast, and overlapping cellular structures continue to limit diagnostic accuracy and the performance of automated systems. This study introduces a fractional Perona–Malik diffusion (FPMD) framework that extends the classical anisotropic diffusion model using fractional-order operators to achieve more flexible, edge-sensitive smoothing. The method is applied to red, green, blue (RGB) Pap smear images and benchmarked against classical PMD and conventional filters using entropy, blind/referenceless image spatial quality evaluator (BRISQUE), and edge preservation index (EPI). FPMD yields substantial improvements, achieving the lowest BRISQUE score (18.88) and the highest EPI values (>0.92) across all channels, indicating superior structural preservation and perceptual quality. While classical PMD produces slightly higher entropy, it introduces artifacts that degrade visual realism. FPMD provides a more controlled enhancement, producing diagnostically meaningful contrast and clearer cytological boundaries. These results highlight its potential as a robust preprocessing tool for both manual assessment and artificial intelligence (AI)-assisted cervical cancer screening.
Co-Authors A.S. Adhiwibawa, Marcelinus Abu Bakar Sambah Agus Suryanto Agus Widodo Ahmad Afif Supianto Arifin Arifin Avin Maulana Candra Dewi Corina Karim, Ari Andari Dian Eka Ratnawati Dwi Agus Kuncoro Dwi Febry Indarwati Dwi Mifta Mahanani Faiz Anggiananta Winantoro Fery Widhiatmoko Helen Yuliana Angmalisang Hidayat, Noor Indah Yanti Indah Yanti Isti Marlisa Fitriani Ivan C. Onggara Kestrilia Rega Prilianti Luh Putu Dharma Jayanti Marcelinus A.S. Adhiwibawa Marsudi Marsudi Mochamad Hakim Akbar Assidiq Maulana Mochamad Hakim Akbar Assidiq Maulana Mochammad Iskandar Ardiyansyah Rochman Mohamad Handri Tuloli Mohamad Muslikh Musafir, Raqqasyi Rahmatullah Natasha Clarissa Maharani Normi Abdul Hadi Nur Khilmiyatul Ilmiyah Nyimas Ayu Widi Indriana Onggara, Ivan C. Onky Prasetyo Raden Rizky Widdie Tigusti Revi Anistia Masykuroh Safrizal Ardana Ardiyansa Sherly Witanto Sobri Abusini Suhaila Abd Halime Suhhy Ramzini Suryanto, Agus Tatas H.P. Brotosudarmo Trisilowati, Trisilowati Wuryansari Muharini K. Yunita Dwi Alfiyanti Zuraidah Fitriah ZURAIDAH FITRIAH