Article Per Year (5 Year)
p-Index From 2021 - 2026
9.152
P-Index
This Author published in this journals
All Journal EXPERT: Jurnal Manajemen Sistem Informasi dan Teknologi RABIT: Jurnal Teknologi dan Sistem Informasi Univrab JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING SCIENCE TECH: Jurnal Ilmiah Ilmu Pengetahuan dan Teknologi JURNAL ILMIAH INFORMATIKA Jurnal Manajemen Informatika JUSIM (Jurnal Sistem Informasi Musirawas) Antivirus : Jurnal Ilmiah Teknik Informatika Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Jurnal Teknologi Informasi dan Multimedia Jurnal Teknologi Dan Sistem Informasi Bisnis ILKOMNIKA: Journal of Computer Science and Applied Informatics Prosiding National Conference for Community Service Project JISA (Jurnal Informatika dan Sains) JOURNAL OF INFORMATION SYSTEM MANAGEMENT (JOISM) Jurnal E-Komtek Jurnal Digital Teknologi Informasi Infotech: Journal of Technology Information Journal of Computer Networks, Architecture and High Performance Computing Telcomatics Journal of Information System and Technology (JOINT) STORAGE: Jurnal Ilmiah Teknik dan Ilmu Komputer Conference on Management, Business, Innovation, Education and Social Sciences (CoMBInES) Conference on Business, Social Sciences and Technology (CoNeScINTech) Madani: Jurnal Pengabdian Masyarakat dan Kewirausahaan Jurnal Penelitian Teknologi Informasi dan Sains Jurnal Tiyasadarma: Jurnal Pengabdian Kepada Masyarakat Jurnal Pengabdian Masyarakat Indonesia (JPMI) The Indonesian Journal of Computer Science Jurnal Pengabdian Masyarakat Tekno Jurnal ilmiah teknologi informasi Asia INOVTEK Polbeng - Seri Informatika
Prasetyo, Stefanus Eko
Universitas Internasional Batam
Aerospace Engineering Agriculture, Biological Sciences & Forestry Arts Humanities Automotive Engineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Materials Science & Nanotechnology Social Sciences Other

Published : 64 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 64 Documents
Search

 3   4   5   6   7 
Klasifikasi Kematangan Buah Pisang Menggunakan YOLOv12 Berbasis Deep Learning Prasetyo, Stefanus Eko; Wijaya, Gautama; Kwan, Allan
STORAGE: Jurnal Ilmiah Teknik dan Ilmu Komputer Vol. 5 No. 1 (2026): Februari
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/storage.v5i1.7557

Abstract

Sebagai komoditas hortikultura dengan permintaan pasar yang tinggi dan nilai jual strategis, pisang memerlukan penanganan pascapanen yang tepat, khususnya dalam penentuan fase kematangan. Selama ini, proses penyortiran kematangan buah umumnya dilakukan secara konvensional melalui inspeksi visual manual, yang bersifat subjektif dan berpotensi menghasilkan penilaian yang tidak konsisten. Oleh karena itu, penelitian ini berfokus pada perancangan sistem otomatis berbasis deep learning untuk menghasilkan klasifikasi kematangan yang lebih objektif dan terstandar. Algoritma YOLOv12 digunakan sebagai metode utama untuk mendeteksi serta mengklasifikasikan citra buah ke dalam tiga fase, yaitu mentah, matang, dan lewat matang. Data latih dikembangkan melalui proses anotasi serta augmentasi citra untuk meningkatkan variasi visual dan mencegah overfitting. Hasil evaluasi menunjukkan bahwa model mencapai Mean Average Precision (mAP@0.5) sebesar 95,2% dengan waktu deteksi di bawah 50 ms per gambar. Temuan ini menunjukkan potensi penerapan sistem secara real-time pada lingkungan industri penyortiran buah.
Implementasi Multi-Factor Authentication Pada Aplikasi Berbasis Website dan Pengembangan Company Profile PT Raflesia Berjaya Properti Haeruddin Haeruddin; Stefanus Eko Prasetyo; Avista Mindy
Jurnal Pengabdian Masyarakat Indonesia (JPMI) Vol. 1 No. 6 (2024): Agustus
Publisher : Publikasi Inspirasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62017/jpmi.v1i6.2051

Abstract

PT Raflesia Berjaya Properti (PT RBP), sebuah pengembang properti di Batam, menghadapi tantangan kritis dalam keamanan data dan branding perusahaan. Untuk mengatasi hal ini, Program Pengabdian Kepada Masyarakat (PKM) dilaksanakan dengan dua tujuan utama yaitu meningkatkan keamanan sistem informasi dan pembuatan website profil perusahaan untuk mengingkatkan branding. Fokus keamanan melibatkan penerapan Multi-Factor Authentication (MFA) menggunakan Auth0 untuk mencegah akses tidak sah dan melindungi data sensitif. Peningkatan branding melalui pembuatan website profil perusahaan yang profesional untuk meningkatkan visibilitas PT RBP secara global dan meningkatkan kepercayaan. Pengembangan website dan MFA ini menggunakan metodologi Network Development Life Cycle (NDLC), yang meliputi tahap analisis, desain, implementasi, dan pengujian. Implementasi MFA berhasil mengurangi risiko akses tidak sah, dan website profil perusahaan yang baru meningkatkan kehadiran PT RBP di pasar global. Meskipun terdapat beberapa tantangan adaptasi bagi pengguna MFA dan kemungkinan penyesuaian fitur website, PKM ini secara signifikan meningkatkan keamanan data dan branding PT RBP untuk memastikan keberlanjutan operasional dan daya saing pasar yang lebih baik.
Penyusunan Sertifikasi ISO 27001 Di PT. Pundi Mas Berjaya Haeruddin Haeruddin; Stefanus Eko Prasetyo; Ari Wahyuni Kaharuddin
Jurnal Pengabdian Masyarakat Indonesia (JPMI) Vol. 1 No. 6 (2024): Agustus
Publisher : Publikasi Inspirasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62017/jpmi.v1i6.2052

Abstract

Persiapan untuk sertifikasi ISO 27001 di PT Pundi Mas Berjaya merupakan proses yang melibatkan pemahaman mendalam tentang persyaratan standar, penyusunan SOP yang terstruktur, penilaian risiko yang cermat, kolaborasi antar departemen, dan dokumentasi yang teliti. Hasil dari persiapan ini menunjukkan komitmen perusahaan dalam meningkatkan keamanan informasi secara menyeluruh. Saran yang diambil adalah untuk terus berkomitmen pada peningkatan kontinu dalam manajemen keamanan informasi, sesuai dengan prinsip-prinsip ISO 27001. Dengan demikian, persiapan ini bukan hanya memenuhi persyaratan formal, tetapi juga membawa dampak positif dalam memperkuat keamanan informasi di PT Pundi Mas Berjaya.
Penerapan Logika Fuzzy Untuk Analisis Tingkat Kepuasan Layanan Pelabuhan Domestik Sekupang Kota Batam Joni Eka Candra; Noviardi, Refli; Eko Prasetyo, Stefanus; Burhan, Rifa’atul M.; Rushadi
The Indonesian Journal of Computer Science Vol. 12 No. 6 (2023): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v12i6.3558

Abstract

Penelitian ini bertujuan untuk menganalisis dan mengetahui seberapa besar pengaruh tingkat layanan yang diberikan terhadap respon kepuasan bagi para penumpang kapal di pelabuhan domestik Sekupang kota Batam. Dalam kelancaran penelitian ini digunakan metode studi kepustakaan, observasi, dan penyebaran kuesioner dengan menggunakan skala likert, serta metode fuzzy. Berdasarkan analisis dan pembahasan yang dilakukan terhadap 50 orang responden, dengan metode skala likert responden menyatakan cukup puas. Ini berarti pelabuhan sekupang Kota Batam, cukup berhasil memberikan layanan yang terbaik atau cukup memuaskan kepada para penumpang, baik dari Dimensi Kehandalan, Dimensi Daya Tanggap, Dimensi Kepastian, Dimensi Empati dan Dimensi Berwujud secara keseluruhan konsumen merasa cukup puas, dengan rata-rata presentase sebesar 71 % (35,5 dari 50 responden). Tidak jauh berbeda dengan hasil uji coba Fuzzy Logic metode Mamdani dilihat dari hasil nilai output untuk kepuasan konsumen sebesar 150 (dengan range 50-250) yang artinya tingkat kepuasan konsumen cukup puas akan pelayanan yang diberikan oleh Pelabuhan Sekupang Kota Batam.
Generalization Analysis of a Long Short-Term Memory Model for Cross-Domain Malware Detection Prasetyo, Stefanus Eko; Haeruddin, Haeruddin; Jason, Jason
ILKOMNIKA Vol 8 No 1 (2026): Volume 8, Number 1, April 2026
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28926/ilkomnika.v8i1.856

Abstract

The increasing diversity of malware targeting heterogeneous computing environments poses significant challenges to conventional detection approaches that rely on domain-specific assumptions. In particular, detection models optimized for a single dataset often exhibit limited robustness when applied to data with different structural and behavioral characteristics. This study analyzes the generalization capability of a Long Short-Term Memory (LSTM) model for behavior-based malware detection across multiple domains. A fixed two-layer LSTM architecture is evaluated using one primary dataset, CIC-MalMem-2022, and four additional datasets representing Android applications, Internet of Things network traffic, botnet behavior, and static Windows Portable Executable analysis. Although each dataset undergoes a dataset-specific preprocessing pipeline, all experiments employ an identical model architecture and hyperparameter configuration to ensure consistent and comparable evaluation. Model performance is assessed using standard classification metrics, supported by single train–test evaluation and five-fold cross-validation to examine performance stability and robustness. The experimental results demonstrate that the LSTM model maintains consistently high detection performance across datasets with diverse characteristics, including both sequential and non-sequential data representations. These findings indicate that the model effectively captures fundamental malware behavior patterns that generalize beyond a single domain, highlighting its potential applicability in heterogeneous cybersecurity environments where cross-domain robustness is required. At the same time, the evaluation is conducted under controlled experimental conditions and does not explicitly address adversarial adaptation or fully dynamic runtime deployment, which should be considered when interpreting the results for practical operational use.
Analisis Kinerja Smart Door Hybrid Haar Cascade dan ArcFace pada Raspberry Gautama Wijaya; Stefanus Eko Prasetyo; Haeruddin Haeruddin; Kevin Kevin
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol 15, No 2 (2026): April 2026
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v15i2.3537

Abstract

Implementing biometric security systems on deep learning devices faces a major challenge in balancing identity verification accuracy with computational resource efficiency. This study presents a performance analysis of a Raspberry Pi 5-based Smartdoor system integrating the detection speed of Haar Cascade with the recognition accuracy of ArcFace. System performance was evaluated based on RAM usage, CPU load, FPS stability, and access Success Rate parameters. Empirical evaluation results indicate that integrating Deep learning ArcFace increased RAM usage by 33.7% and CPU load from 33% to 53%. However, due to the processing capacity of the Raspberry Pi 5, the system maintained stable real-time performance with an average of 18.3 FPS. In terms of security, the Hybrid method proved superior with an access success rate of 73.7%, surpassing the conventional Haar Cascade method which only reached 68.4%. This study concludes that the Hybrid method is a viable solution for home security systems, where the increased computational load is justified by a significant improvement in identity verification reliability.Keyword: Raspberry Pi 5; Smartdoor; Haar Cascade; ArcFace; Computational Performance. AbstrakImplementasi sistem keamanan biometrik pada perangkat deep learning menghadapi tantangan utama dalam menyeimbangkan akurasi verifikasi dengan efisiensi sumber daya. Penelitian ini menyajikan analisis kinerja sistem Smartdoor berbasis Raspberry Pi 5 yang mengintegrasikan kecepatan deteksi Haar Cascade dengan akurasi pengenalan wajah ArcFace. Kinerja sistem dievaluasi berdasarkan parameter penggunaan RAM, beban CPU, stabilitas FPS, dan tingkat keberhasilan akses. Hasil evaluasi empiris menunjukkan bahwa integrasi Deep learning ArcFace meningkatkan penggunaan RAM sebesar 33,7% dan beban CPU dari 33% menjadi 53%. Namun, berkat kapasitas pemrosesan Raspberry Pi 5, sistem mampu mempertahankan stabilitas kinerja real-time dengan rata-rata 18,3 FPS. Dari segi keamanan, metode Hybrid terbukti lebih unggul dengan akurasi pengenalan wajah sebesar 73,7%, melampaui metode konvensional Haar Cascade yang hanya mencapai 68,4%. Penelitian ini menyimpulkan bahwa metode Hybrid merupakan solusi yang layak untuk sistem keamanan rumah, di mana peningkatan beban komputasi terbayar dengan peningkatan reliabilitas verifikasi identitas yang signifikan. 
An Optimized Lightweight CNN with Randomized Hyperparameter Search for Real-Time Image-Based Malware Detection Stefanus Eko Prasetyo; Kevin Chandra Wijaya; Haeruddin
Journal of Computer Networks, Architecture and High Performance Computing Vol. 8 No. 1 (2026): Articles Research Januari 2026
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v8i1.7765

Abstract

While image-based malware detection using deep learning has shown promise, existing methodologies predominantly rely on computationally expensive pre-trained architectures (e.g., VGG, ResNet) that create significant bottlenecks for real-time deployment on resource-constrained gateways. This research addresses this critical gap by proposing a streamlined, lightweight custom Convolutional Neural Network (CNN) specifically optimized for real-time operation. The novelty of this work lies in the strategic integration of Randomized Search Cross-Validation (RS-CV) to automate the discovery of an optimal configuration of filters, dense units, and dropout rates, eliminating the inefficiencies and biases of manual hyperparameter tuning. The proposed method transforms binary files into 64x64 grayscale images—reducing computational input by over 90% compared to standard architectures—which are then processed by the optimized custom network. Experimental results demonstrate the scientific significance of this approach, as the model achieved a near-perfect Area Under the Curve (AUC) of 0.9996 and identified threats with an average inference time of only 12–15 milliseconds. Out of 1,068 test samples, only 10 misclassifications were recorded, proving that a mathematically optimized lightweight model can outperform heavy ensemble frameworks in both accuracy and speed. These findings provide a reproducible framework for high-speed, front-line cybersecurity systems capable of detecting obfuscated threats in live network environments.
Artificial Intelligence Adoption in Learning Systems: Systematic Literature Review Hendi Sama; Aisyah Nurkayla; Stefanus Eko Prasetyo
JISA(Jurnal Informatika dan Sains) Vol 9, No 1 (2026): JISA(Jurnal Informatika dan Sains)
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/jisa.v9i1.2705

Abstract

The integration of Artificial Intelligence (AI) in education has accelerated rapidly, reshaping teaching and learning processes through intelligent, adaptive, and data-driven systems. Despite its widespread adoption, a consolidated understanding of implementation trends, benefits, and challenges across educational contexts remains limited. This study aims to examine the current state of AI adoption in education by identifying key applications, success factors, and implementation barriers. A systematic literature review (SLR) was conducted by analyzing 32 peer-reviewed journal articles published within the last five years and indexed in reputable academic databases. The reviewed studies focus on adaptive learning systems, intelligent tutoring systems, and learning analytics. The findings demonstrate that AI contributes significantly to personalized learning, real-time performance assessment, and improved learner engagement. However, effective implementation is strongly influenced by institutional readiness, educator digital literacy, data quality, and ethical governance. Major challenges identified include data privacy concerns, lack of standardization, and unequal access to technological infrastructure. This study concludes that AI has substantial potential to support more adaptive and inclusive educational systems, but sustainable integration requires coordinated efforts among educators, policymakers, and technology developers.
Literasi Digital, Keamanan Digital, dan Komunikasi Digital terhadap Pencegahan Cyberbullying pada Generasi Z di Platform Tiktok Stefanus Eko Prasetyo; Tony Wibowo; Melisa Melisa
Jurnal Penelitian Teknologi Informasi dan Sains Vol. 4 No. 2 (2026): Juni: JURNAL PENELITIAN TEKNOLOGI INFORMASI DAN SAINS (JPTIS)
Publisher : Institut Teknologi dan Bisnis (ITB) Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54066/jptis.v4i2.4240

Abstract

The proliferation of social media interactions frequently results in an increased risk of cyberbullying. This study aims to evaluate the impact of digital literacy, digital security, and digital communication on cyberbullying prevention among Generation Z TikTok users. Employing an explanatory quantitative approach, data were collected through online questionnaires distributed to Generation Z students in the Information Systems Study Program at Universitas Internasional Batam. The respondent data were then analyzed using the Partial Least Square-Structural Equation Modeling (PLS-SEM) technique. The analytical results reveal that digital literacy does not significantly affect cyberbullying prevention. Conversely, both digital security and digital communication demonstrate a significant impact on cyberbullying prevention. Among the investigated variables, digital communication exerts the most dominant influence on preventing cyberbullying. These findings suggest that preventing cyberbullying requires more than merely digital knowledge; it heavily relies on the implementation of digital security measures and the capacity for ethical communication in digital environments. Ultimately, this research is expected to serve as a valuable reference for formulating effective cyberbullying mitigation strategies for Generation Z across social media platforms.
PERBANDINGAN SISTEM AUTENTIKASI WPA2 EAP-PSK PADA JARINGAN WIRELESS DENGAN METODE PENETRATION TESTING MENGGUNAKAN FLUXION TOOLS Stefanus Eko Prasetyo; Try Windranata
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 7 No 1 (2022): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v7i1.2206

Abstract

Wireless Network is a collection of electronic devices that connect to each other using air devices or frequencies as a data traffic flow. Today, there are many users who use WPA2-PSK or WPA2-EAP as a wireless network security system that aims to prevent people from accessing it without permission. This research uses a wireless penetration testing technique that uses fluxion tools by comparing and analyzing the WPA2 authentication security system with EAP-PSK on a wireless network which aims to determine the vulnerability of a network security system. To carry out penetration testing, the author refers to the "Wireless Network Penetration Testing Methodology." Which consists of intelligence gathering, vulnerability analysis, threat modeling, password cracking, and reporting. From this study, it will be concluded that WPA2-PSK is less safe to use because it can be seen in the penetration testing that WPA2-PSK was successfully hacked in an unhide SSID state, while WPA2-EAP was successful in making Web Interfaces but failed to obtain information such as usernames and passwords. If the WPA2-PSK SSID is in a hide state, it will fail the hack, so that both security systems have their own advantages and disadvantages depending on the user's needs.
Co-Authors ., Arron ., Kennedi Abner Onesimus Sijabat Agung Wijaya Aisyah Nurkayla Ardyansyah Wijaya Ari Wahyuni Kaharuddin Ari Wibowo Ariesryo, Kelvin Aripradono, Heru Wijayanto Avista Mindy Basri, Germen Benny Benny Burhan, Rifa’atul M. Candra, Boby candra, joni eka Christina, Lidya Conny Agustin Dede Hilman Rasyid Dendi, Dendi Deven Lee Dini Sari Melati Dominggo Givarel Elia Elia Elvin Elvin Elvin Tan Elvin Tan Elvis Elvis Elvis Fadil Mahendra Favian, Felix Febby Anggellya Felix Felix Yeovandi Fiona Livianti Frandika Antonius Saputra Frans Hadinata Gautama Wijaya Gautama Wijaya Gusti Irawan Haeruddin Haeruddin Haeruddin Haeruddin, . Haryono Haryono Hasanah, Nafisatul Hendi Sama Jackson Jackson Jason Jason Jason, Jason Jefri Jefri Jemmy Jemmy Jemmy, Jemmy Jhon Lim Jimmy Cung Johan Johan Jonathan Felix Andrianto Kaharuddin, Ari Wahyuni Kelvin Ariesryo Kevin Chandra Wijaya Kevin Kevin Kwan, Allan Lidya Christina Melisa Melisa Melisa Melisa Mindy, Avista Mitha Veronica Muhammad Jufri Muhammad Yaasin Nafisatul Hasanah Nafisatul Hasanah Nimatul Mamuriyah Noviardi, Refli Nurul Hassanah Princessa Princessa Puteri, Vier Adinda Putri Syahfira Raja Muhammad Isnu Prayoga Ricardo Ricky Chandra Lee Robby Robby Ruby Shafira Rushadi Sabariman Sabariman Sabariman Sabariman Sama, Hendi Sama, Hendi Sijabat, Abner Onesimus Sopiyan, Sopiyan Stefanie Stefanie Steny Steny Steven Lie Sugianto Sugianto Sun Pho Syaeful Anas Aklani, Syaeful Syahfira, Putri Tony Jack Tan Ding Try Windranata Vincent Theo Weni Vivianti Wibowo, Tony Wilsen Lau Yuki Estrada Yulfan Salimin Yulianto, Andik