Article Per Year (5 Year)
p-Index From 2021 - 2026
1.556
P-Index
This Author published in this journals
All Journal Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control METIK JURNAL JoMMiT : Jurnal Multi Media dan IT SAINTEK Journal of Multiscale Materials Informatics
Usman Sudibyo
Universitas Dian Nuswantoro
Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
Kriptografi Audio MP3 Menggunakan RSA dan Transposisi Kolom Cinantya Paramita; Usman Sudibyo
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 5 No 3 (2021): Juni 2021
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (242.672 KB) | DOI: 10.29207/resti.v5i3.2996

Abstract

Mp3 is one form of audio file extension that is widely used today. With a variety of uses in a variety of mp3 systems become one of the audio extensions that are commonly found in technology systems of the Internet of Things era. However, with the many uses of the .mp3 file extension, there is a new problem, namely the security of the data itself. From these problems, the author aims to examine the security of the mp3 file by designing cryptographic science-based applications. The cryptographic algorithm used in the application is a combination of the asymmetric RSA 2048 algorithm and symmetric columnic transpositions. RSA 2048 algorithm was chosen because it has a key length in accordance with NIST standards in securing data. By combining the two algorithms, the application system will have the ability to manage mp3 files and encrypt mp3 files with the results of data that cannot be played like mp3 files in general. This application system will be developed by prototype method which is the best method in developing a system with trial and error in algorithm development.
Artificial Intelligence Berbasis QSPR Dalam Kajian Inhibitor Korosi Muhamad Akrom; Usman Sudibyo; Achmad Wahid Kurniawan; Noor Ageng Setiyanto; Ayu Pertiwi; Aprilyani Nur Safitri; Novianto Hidayat; Harun Al Azies; Wise Herawati
JoMMiT Vol 7, No 1 (2023)
Publisher : Politeknik Negeri Media Kreatif

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46961/jommit.v7i1.721

Abstract

Baja termasuk material yang memiliki ketahanan rendah terhadap serangan korosi Ketika berada pada lingkungan korosif. Inhibitor organik mampu menghambat korosi dengan efisiensi inhibisi yang tinggi. Tinjauan komparatif penting bagi pengembangan metode evaluasi kinerja inhibitor disajikan dalam karya ini. Kami mereview perkembangan artificial intelligence berbasis mesin learning dengan model QSPR dalam kajian penghambatan korosi. Makalah ini menjelaskan bagaimana metode pembelajaran mesin berbasis data dapat menghasilkan model yang menghubungkan sifat-aktivitas molekuler dengan penghambatan korosi oleh inhibitor berbasis bahan alam (green inhibitor). Teknik ini dapat digunakan untuk memprediksi kinerja senyawa yang belum disintesis atau diuji. Keberhasilan model ini memberikan paradigma untuk penemuan senyawa baru yang cepat, penghambat korosi yang efektif untuk berbagai logam dan paduan.
Klasifikasi Curah Hujan di Kota Semarang Menggunakan Machine Learning Carissa Devina Usman; Usman Sudibyo
Prosiding Sains dan Teknologi Vol. 1 No. 1 (2022): Seminar Nasional Sains dan Teknologi (SAINTEK) ke 1 - Juli 2022
Publisher : DPPM Universitas Pelita Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37366/SAINTEK0101.0105

Abstract

The erratic distribution of rainfall greatly affects people's daily activities, especially in the Semarang City. Therefore, it is necessary to predict rainfall in Semarang City. Correct prediction of rainfall can improve community preparedness in dealing with various natural disasters caused by rain. Machine learning algorithms and data mining have been widely used in research for rainfall data in various regions. The main purpose of this study is to obtain predictions of rainfall in the city of Semarang using machine learning algorithms and to find out the best algorithm for classifying. The dataset used was obtained from the Meteorology, Climatology and Geophysics Agency (BMKG) which is the daily rainfall data in Semarang City. From the dataset, three machine learning algorithms will be classified, namely Logistic Regression, Random Forest, and Gradient Boosting. To measure the performance of the machine learning algorithm, the classification accuracy of each algorithm is measured. From the research results, the performance of the Gradient Boosting algorithm is better than other algorithms, with an accuracy value of 71.6%. Keywords: Machine Learning, Logistic Regression, Random Forest, Gradient Boosting, Rainfall Prediction
Regularization Techniques to Improve the Stability and Accuracy of MLC Algorithm Usman Sudibyo; Noor Ageng Setyanto; Ahmad Wahid Kurniawan; Carissa Devina Usman
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 11, No. 3, August 2026 (Article in Progress)
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v11i3.2583

Abstract

Maximum Likelihood Classification (MLC) is a classification algorithm that has important applications in the fields of image processing and remote sensing. No use of MLC was found in other fields. MLC assumes that data comes from a certain probability distribution (for example, a normal distribution), which may be too simple to describe complex data or have a non-normal distribution. This can lead to poor performance in situations where distribution assumptions are not met. That is why in various literatures there is no use of MLC for classification problems other than remote sensing. We propose a regularization technique to reduce distribution assumption errors in MLC called Regularization on maximum likelihood classification (RMLC). Regularization techniques are integrated into the covariance matrix, where regularization can make the data variance larger or smaller than the actual variance. This technique can also overcome singularities in the covariance matrix, non-Gaussian data, and data containing outliers. Experimental results on 13 public datasets show a significant increase in accuracy performance. The average accuracy increase reaches more than 11%, from 0.802 to 0.919, highlighting its potential for broader applicability and enhanced performance
Machine Learning-Assisted Discovery and Optimization of Sodium-Ion Batteries: A Review Gustina Alfa Trisnapradika; Harun Al Azies; Muhamad Akrom; Usman Sudibyo; Noor Ageng Setiyanto
Journal of Multiscale Materials Informatics Vol. 3 No. 1 (2026): April
Publisher : Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/jimat.v3i1.15954

Abstract

Sodium-ion batteries (SIBs) have emerged as a promising alternative to lithium-ion batteries due to the natural abundance, low cost, and wide geographic availability of sodium resources. However, their practical implementation is hindered by challenges such as lower energy density, slower ion diffusion, and limited cycle stability. In recent years, machine learning (ML) has been increasingly applied to accelerate the discovery, design, and optimization of SIB materials and systems. This review provides a comprehensive overview of ML applications in sodium-ion battery research, including electrode material discovery, electrolyte optimization, performance prediction, and degradation analysis. Various ML techniques, such as supervised learning, unsupervised learning, and deep learning, are discussed in relation to their roles in materials informatics. Additionally, challenges such as data scarcity, model interpretability, and transferability are critically analyzed. Finally, future perspectives on integrating ML with high-throughput experiments and quantum computing are highlighted to guide next-generation sodium-ion battery research.
Prediksi Aksebilitas Molekul Tamu pada Metal-Organic Framework dengan SMOTE dan AdaBoost-Machine Learning Moch Anjas Aprihartha; Harun Al Azies; Wahyu Aji Eko Prabowo; Usman Sudibyo; Ika Puspitasari; Indah Putianik; Fatma Ahardika Nurfaizal
METIK Jurnal Vol. 10 No. 1 (2026): METIK Jurnal Issue Published
Publisher : LPPM Universitas Mulia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47002/45crx119

Abstract

Metal-Organic Frameworks (MOFs) are a special class of organic-inorganic hybrid materials widely known for their regular and periodic crystal structures. MOFs are composed of metal ions or clusters connected by organic linkers that form a three-dimensional lattice-shaped series. The advantage of MOFs is their ability to capture guest molecules in their pores. Based on these capabilities, MOFs can be utilized in various applications such as gas absorption and separation processes, catalysts, and therapeutic compound delivery systems. Currently, in creating new materials, the MOFs synthesis process still applies a conventional trial-and-error approach that has the potential for high failure rates. The purpose of this study is to develop a machine learning model as an efficient tool design in creating new MOFs materials before the experimental process is carried out. This study implements the SMOTE and AdaBoost methods integrated with machine learning algorithms in classifying MOFs pores based on the pore limiting diameter (PLD) size. The results obtained from the CART-Gentle AdaBoost model provide the best performance with an accuracy of 72.82%; precision 71.32%; recall 73.53%; specificity 72.88%; and f1 score 72.39%. This model is quite suitable for use in identifying MOF structures that are accessible to guest molecules compared to other classification models.
A Machine Learning Model for Evaluation of the Corrosion Inhibition Capacity of Quinoxaline Compounds Noor Ageng Setiyanto; Harun Al Azies; Usman Sudibyo; Ayu Pertiwi; Setyo Budi; Muhamad Akrom
Journal of Multiscale Materials Informatics Vol. 1 No. 1 (2024): April
Publisher : Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/jimat.v1i1.10429

Abstract

Investigating potential corrosion inhibitors via empirical research is a labor- and resource-intensive process. In this work, we evaluated various linear and non-linear algorithms as predictive models for corrosion inhibition efficiency (CIE) values using a machine learning (ML) paradigm based on the quantitative structure-property relationship (QSPR) model. In the quinoxaline compound dataset, our analysis showed that the XGBoost model performed the best predictor of other ensemble-based models. The coefficient of determination (R2), mean absolute percentage error (MAPE), and root mean squared error (RMSE) metrics were used to objectively assess this superiority. To sum up, our study offers a fresh viewpoint on the effectiveness of machine learning algorithms in determining the ability of organic compounds like quinoxaline to suppress corrosion on iron surfaces.
Co-Authors Achmad Wahid Kurniawan Ahmad Wahid Kurniawan Aprilyani Nur Safitri Ayu Pertiwi Carissa Devina Usman Carissa Devina Usman Cinantya Paramita Fatma Ahardika Nurfaizal Gustina Alfa Trisnapradika Harun Al Azies Ika Puspitasari Indah Putianik Moch Anjas Aprihartha Muhamad Akrom Noor Ageng Setiyanto, Noor Ageng Noor Ageng Setyanto Novianto Hidayat Setyo Budi Wahyu Aji Eko Prabowo Wise Herawati