Article Per Year (5 Year)
p-Index From 2021 - 2026
1.745
P-Index
This Author published in this journals
All Journal Desimal: Jurnal Matematika Cyberspace: Jurnal Pendidikan Teknologi Informasi JTAM (Jurnal Teori dan Aplikasi Matematika) Vocatech : Vocational Education and Technology Journal Jurnal Natural International Journal of Applied Mathematics, Sciences, and Technology for National Defense J-SIGN (Journal Of Informatics, Information System, And Artificial Intelligence)
Mahyus Ihsan
Universitas Syiah Kuala
Agriculture, Biological Sciences & Forestry Astronomy Biochemistry, Genetics & Molecular Biology Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Education Electrical & Electronics Engineering Energy Immunology & microbiology Mathematics Mechanical Engineering Neuroscience Physics Social Sciences Other

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 13 Documents
Search

 1   2 
PENERAPAN HIERARKI CERTIFICATE AUTHORITY DAN PUBLIC KEY INFRASTRUCTURE UNTUK MEMPERKUAT KEAMANAN JARINGAN Husaini, Husaini; Ramadhan, Teuku Hafiez; Ihsan, Mahyus
CYBERSPACE: Jurnal Pendidikan Teknologi Informasi Vol 9 No 1 (2025)
Publisher : Universitas Islam Negeri Ar-Raniry Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22373/cj.v9i1.27159

Abstract

Dewasa ini, keamanan jaringan telah menjadi semakin krusial terutama dalam lingkungan bisnis yang saling terhubung secara global. Komunikasi antara kantor cabang dan kantor pusat melalui jaringan global memunculkan risiko seperti pencurian data, pengawasan, dan serangan siber. Hal ini tentu akan menjadi ancaman yang nyata terhadap kerahasiaan dan integritas informasi sensitif perusahaan. Untuk mengurangi risiko ini, penelitian ini mengusulkan implementasi sistem hierarki Certificate Authority (CA) dan Public Key Infrastructure (PKI) dengan memanfaatkan kunci asimetris untuk meningkatkan keamanan. Sistem hierarki CA memastikan langkah-langkah keamanan yang kuat melalui praktik manajemen kunci yang efektif. Tujuan utama dari penelitian ini adalah untuk meningkatkan keamanan jaringan dengan melindungi komunikasi antara kantor cabang dan kantor pusat menggunakan Site-to-Site Virtual Private Network (VPN) yang diimplementasikan dengan teknologi OpenVPN. Pendekatan komprehensif ini melibatkan berbagai metodologi, termasuk simulasi Graphical Network Simulator-3 (GNS3) untuk pengujian arsitektur jaringan, evaluasi ketat terhadap keamanan sertifikat digital, pemantauan lalu lintas yang berkelanjutan, pengujian kinerja jaringan secara menyeluruh, dan protokol keamanan server yang teliti. Hasil yang diharapkan dari penelitian ini diharapkan dapat memberikan wawasan berharga bagi organisasi yang bertujuan untuk mengurangi risiko keamanan jaringan secara efektif. Selain itu, temuan penelitian ini diharapkan dapat memberikan kontribusi signifikan terhadap pengembangan kerangka kerja keamanan jaringan yang disesuaikan dengan kebutuhan lingkungan bisnis yang terhubung secara global.
Pengembangan Aplikasi Pembelajaran Bahasa Isyarat Indonesia (BISINDO) yang Interaktif Berbasis Deep Learning Husaini, Husaini; Ardiansyah, Ardiansyah; Ihsan, Mahyus; Saputra, Kurnia
VOCATECH: Vocational Education and Technology Journal Vol 8, No 1 (2026): April
Publisher : Akademi Komunitas Negeri Aceh Barat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38038/vocatech.v8i1.290

Abstract

AbstractCommunication involving persons with hearing impairments and the wider Indonesian society continues to face various challenges, particularly due to the limited availability of accessible and interactive learning media for Indonesian Sign Language (BISINDO). This study focused on the development of an innovative and user-friendly Android-based BISINDO learning application designed as a supportive medium for beginner-level sign language learning. The developed application integrates real-time hand gesture recognition technology using a deep learning approach, employing a combination of MobileNetV2, MediaPipe Hands, and Convolutional Neural Networks (CNN). The application features three main components: sign language alphabet detection, a gesture dictionary presented in the form of visual animations, and an interactive quiz for learning evaluation. The application was developed following the Waterfall model, encompassing requirements analysis, design, implementation, testing, and deployment. Functional testing using Black-Box Testing method was conducted to ensure that all features operated according to specifications, while application usability was evaluated using the System Usability Scale (SUS) involving 32 respondents. The functional testing results indicate that all application features functioned properly and met the specified requirements. Meanwhile, the SUS evaluation yielded an average score of 74.8, which falls within the Good category, indicating that the application is well accepted by users. Thus, this application is intended to serve as an effective BISINDO learning medium and contribute to fostering more inclusive communication involving persons with hearing impairments and the wider community.AbstrakKomunikasi antara penyandang tunarungu dan masyarakat umum di Indonesia masih menghadapi beragam kendala, terutama berkaitan dengan terbatasnya media pembelajaran Bahasa Isyarat Indonesia (BISINDO) yang mudah diakses dan interaktif. Penelitian ini difokuskan pada pengembangan aplikasi pembelajaran BISINDO berbasis Android yang inovatif dan mudah digunakan sebagai media pendukung pembelajaran bahasa isyarat bagi pemula. Aplikasi yang dikembangkan mengintegrasikan teknologi pengenalan gerakan tangan secara real-time menggunakan pendekatan deep learning, dengan memanfaatkan kombinasi MobileNetV2, MediaPipe Hands, dan Convolutional Neural Network (CNN). Aplikasi ini dilengkapi dengan tiga fitur utama, yaitu deteksi abjad bahasa isyarat, kamus gerak dalam bentuk animasi visual, serta kuis interaktif sebagai sarana evaluasi pembelajaran. Pengembangan aplikasi dilakukan menggunakan model Waterfall yang meliputi analisis kebutuhan, desain, implementasi, pengujian, dan penerapan. Pengujian fungsionalitas sistem menggunakan metode Black-Box dilakukan untuk memastikan seluruh fitur berjalan sesuai spesifikasi, sementara tingkat kegunaan aplikasi dievaluasi menggunakan System Usability Scale (SUS) terhadap 32 responden. Hasil pengujian fungsionalitas mengindikasikan bahwa seluruh fitur aplikasi telah berfungsi secara baik dan dinyatakan memenuhi spesifikasi yang ditetapkan. Sementara itu, hasil evaluasi SUS memperoleh skor rata-rata sebesar 74,8 yang termasuk dalam kategori Good, menandakan bahwa aplikasi dapat diterima dengan baik oleh pengguna. Dengan demikian, aplikasi ini diharapkan dapat menjadi media pembelajaran BISINDO yang efektif serta mendukung terciptanya komunikasi yang lebih inklusif antara penyandang tunarungu dan masyarakat umum
Hybrid random forest–catboost ensemble for heart disease prediction on imbalanced datasets: Toward applications in military health systems Mahyus Ihsan; Zahnur; Iftahul Fadlan; Ikhsan Maulidi
International Journal of Applied Mathematics, Sciences, and Technology for National Defense Vol. 4 No. 1 (2026): International Journal of Applied Mathematics, Sciences, and Technology for Nati
Publisher : FoundAE

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58524/app.sci.def.v4i1.1148

Abstract

ackground: Heart disease is one of the main causes of death worldwide, with cases increasing every year. This situation highlights the urgent need for early detection systems that are not only fast but also accurate and reliable. In recent years, machine learning has emerged as a promising alternative approach for analyzing medical data, particularly for disease classification and risk prediction tasks. Aims: This study aims to develop a heart disease prediction model by integrating Random Forest and CatBoost in a hybrid ensemble framework and evaluating its performance on an imbalanced medical dataset. Method: This study employs a quantitative approach based on supervised learning using the Behavioral Risk Factor Surveillance System (BRFSS) 2021 dataset, which consists of more than 300,000 observations. Data preprocessing includes duplicate removal, BMI categorization, encoding of categorical variables, and exploratory analysis. To address class imbalance, the Borderline-SMOTE technique was applied before splitting the dataset using an 80:20 train-test split. Random Forest and CatBoost models were trained and combined using a soft voting ensemble. Result: The evaluation results indicate that Random Forest achieved the highest accuracy of 0.94, with well-balanced precision and recall across all classes. CatBoost demonstrated relatively stable performance with accuracy around 0.84. The ensemble approach achieved an accuracy of 0.91 with strong metric stability and good sensitivity to positive cases. Conclusion: The results indicate that Random Forest performs best for the dataset used in this study, while the ensemble model provides a balanced compromise between predictive performance and robustness. The analysis also shows that Age Category, General Health, and BMI are the most influential predictors of heart disease risk. This model can support early cardiovascular risk detection in military personnel, contributing to maintaining operational readiness in defense systems. Furthermore, the proposed approach provides a reliable decision-support tool for large-scale medical screening in resource-constrained healthcare environments.
Co-Authors Al Aiyub ARDIANSYAH ARDIANSYAH DEDI SUHAIMI Fahrul Razi Hafnani Hafnani Husaini Husaini Husaini Husaini Iftahul Fadlan Ikhsan Maulidi IKHSAN MAULIDI Ikhsan Maulidi Marwan Ramli Marwan Ramli Maulidi, Ikhsan Rahma Zuhra Rahmadsyah, Rizki Rahmah Zuhra Ramadhan, Teuku Hafiez Reza Wafdan RR. Ella Evrita Hestiandari Saputra, Kurnia Syarifah Meurah Yuni Vina Apriliani Zahnur Zahnur, Zahnur