Article Per Year (5 Year)
p-Index From 2021 - 2026
4.6
P-Index
This Author published in this journals
All Journal InfoTekJar : Jurnal Nasional Informatika dan Teknologi Jaringan Sinkron : Jurnal dan Penelitian Teknik Informatika JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING JITK (Jurnal Ilmu Pengetahuan dan Komputer) Jurnal Sisfokom (Sistem Informasi dan Komputer) Jusikom: Jurnal Sistem Informasi Ilmu Komputer Jurnal Sains dan Teknologi REMIK : Riset dan E-Jurnal Manajemen Informatika Komputer INFOKUM Jurnal Sistem Komputer dan Informatika (JSON) Journal of Computer Networks, Architecture and High Performance Computing JURNAL MITRA PRIMA Jurnal Ilmiah Betrik : Besemah Teknologi Informasi dan Komputer
Banjarnahor, Jepri
Universitas Prima Indonesia
Aerospace Engineering Humanities Astronomy Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Health Professions Immunology & microbiology Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Materials Science & Nanotechnology Mathematics Mechanical Engineering Physics Social Sciences Veterinary

Published : 35 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 35 Documents
Search

 1   2   3   4 
Analisis Kinerja Komparatif Metode Machine Learning Dalam Klasifikasi Sentimen Terhadap Ulasan Aplikasi Dompet Digital Yanto, Willi; Panjaitan, Mega Lastarida; Khosandy, Vincent; Banjarnahor, Jepri
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 6 No. 4 (2025): Juni 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v6i4.8831

Abstract

Saat ini, kemajuan teknologi telah merambah di berbagai aspek kehidupan, termasuk sektor keuangan. Salah satu teknologi keuangan yang populer digunakan di Indonesia adalah dompet digital. Penggunaan aplikasi dompet digital memungkinkan transaksi keuangan dilakukan secara daring tanpa perlu menggunakan uang tunai atau kartu fisik, mendukung sistem pembayaran non-tunai (cashless). Aplikasi dompet digital yang sangat populer saat ini, seperti Dana, OVO, dan Gopay, memiliki banyak pengguna, sehingga sering kali terdapat ulasan yang tidak relevan dengan aplikasi serta rating yang diberikan di Google Play Store. Tujuan penelitian ini adalah untuk membandingkan performa empat algoritma machine learning, yaitu Random Forest, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), dan Naïve Bayes dalam melakukan analisis sentimen pada ulasan aplikasi dompet digital. Data ulasan dompet digital diperoleh melalui teknik data scraping dan selanjutnya dilakukan text preprocessing untuk membersihkan teks agar dapat dieksekusi dengan baik. Hasil penelitian menunjukkan bahwa algoritma Naïve Bayes dan Random Forest memiliki performa terbaik dalam analisis sentimen aplikasi dompet digital. Naïve Bayes mencapai akurasi tertinggi pada aplikasi Gopay dengan nilai 84.44%, recall 84.44%, dan F1-score 82.44%. Sementara itu, Random Forest menunjukkan performa yang konsisten dengan akurasi terbaik pada aplikasi OVO sebesar 81.82% dan recall 81.82%, serta pada aplikasi Gopay dengan akurasi 83.06% dan F1-score 80.84%. Hal ini menunjukkan bahwa kedua algoritma tersebut memiliki potensi yang baik dalam menganalisis sentimen ulasan aplikasi dompet digital
Application of Deep Learning for Cardiac Arrhythmia Classification Based on ECG Signals Gabriela Septiani Simbolon; Gresia Cesilia Sirait; Sarah Theresia Aruan; Rivaldo Robertus Turnip; Jepri Banjarnahor; Mardi Turnip
Journal of Computer Networks, Architecture and High Performance Computing Vol. 8 No. 3 (2026): Research Paper July 2026
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v8i3.8672

Abstract

Cardiac arrhythmia is a dangerous heart rhythm disorder, so early detection is crucial for effective treatment. Manual ECG (Electrocardiogram) analysis is less accurate, while deep learning can detect arrhythmias more quickly and precisely. The proposed algorithm uses a deep learning Convolutional Neural Network (CNN) model for arrhythmia classification. The model is trained on labeled normal and arrhythmia ECG datasets to recognize important patterns in sequential data. The ECG data is obtained from PhysioNet, which provides thousands of labeled recordings for training and testing. Additional clinical data from hospitals/clinics can be included for further validation with patient consent according to ethical protocols. The expected result is that this system can detect arrhythmias with high accuracy and optimal sensitivity. The benefits are to improve the quality of healthcare services and reduce the risk of serious complications.
Pemulihan Ekonomi Pascabencana melalui Digitalisasi UMKM Pesisir Berbasis Pendampingan Mahasiswa di Tapanuli Tengah Yonata Laia; Elly Romy; Lilis Handayani Napitupulu; Jepri Banjarnahor; Tri Suci; Johannes Bastira Ginting
Jurnal Mitra Prima Vol. 8 No. 1 (2026): JURNAL MITRA PRIMA
Publisher : Mitra prima

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

Abstract

Kabupaten Tapanuli Tengah merupakan salah satu kawasan pesisir di Provinsi Sumatera Utara yang dalam kurun waktu belakangan ini mengalami dampak bencana alam yang cukup signifikan terhadap berbagai dimensi kehidupan masyarakat. Kondisi tersebut berdampak langsung pada tatanan sosial-ekonomi masyarakat setempat, terutama pada sektor Usaha Mikro, Kecil, dan Menengah (UMKM) yang berperan sebagai fondasi utama perekonomian lokal. Berdasarkan hasil observasi lapangan serta kajian mendalam melalui interaksi dengan pemangku kepentingan lokal, ditemukan bahwa sebagian besar pelaku UMKM mengalami penurunan produktivitas yang cukup berarti, keterbatasan aksesibilitas informasi, serta stagnasi inovasi dalam proses pengolahan maupun strategi pemasaran produk. Kondisi ini mencerminkan kondisi dan permasalahan mitra pemerintah dan desa yang memerlukan intervensi berbasis pendekatan pemberdayaan masyarakat yang terprogram guna mempercepat pemulihan ekonomi pasca bencana.
Hybrid Deep Learning Model for Coffee Leaf Disease Detection Using CNN DeiT Jepri Banjarnahor; Reclesia Br Harianja; Syafridatul maulidah; Nenda Sartika Manalu
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 3 (2026): Article Research July 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i3.16200

Abstract

Coffee production plays a crucial role in the agricultural economy; however, its productivity is significantly affected by plant diseases that are difficult to detect at early stages. Accurate disease identification remains challenging due to subtle visual differences and high intra-class variability in leaf symptoms. To address this problem, this study proposes a hybrid deep learning framework that integrates Convolutional Neural Networks (CNN) and Data-efficient Image Transformers (DeiT) for automated coffee leaf disease classification. The proposed architecture leverages CNN to capture fine-grained local features, while DeiT models global contextual relationships through self-attention mechanisms, enabling a more comprehensive feature representation. The model is trained and evaluated on a dataset of 6,048 labeled images across four classes: Healthy, Rust, Red Spider, and Leaf Miner. Experimental results demonstrate that the proposed CNN–DeiT model outperforms baseline CNN and Transformer-based approaches, achieving an accuracy of 93.1%, an F1-score of 92.3%, and a ROC-AUC of 95.6%. Robustness analysis shows that performance degradation remains limited (1.6%–3.4%) under various perturbation conditions, while out-of-distribution evaluation indicates strong generalization capability with only a minor accuracy decrease. These findings confirm that the hybrid CNN–Transformer architecture effectively enhances classification performance, robustness, and generalization. This study contributes to the advancement of deep learning methodologies in agricultural image analysis by providing a robust and scalable framework for plant disease classification, with potential applications in precision agriculture and data-driven crop management.
Explainable Hybrid XGBoost Fuzzy Logic Model for Accurate Anemia Risk Classification Jepri Banjarnahor; Natasya Sigalingging; Rio Brelly Pasaribu; Yessi Sesilia Sitompul; Jogi Devrant Sibarani
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 3 (2026): Article Research July 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i3.16216

Abstract

Anemia remains a major global health concern that impairs oxygen transport and contributes to fatigue, cognitive decline, reduced productivity, and severe clinical complications. Although machine learning has shown promise for automated anemia detection, multiclass classification remains challenging due to class imbalance, overlapping hematological characteristics, and limited model interpretability. This study proposes an explainable hybrid framework integrating Extreme Gradient Boosting (XGBoost), SHapley Additive exPlanations (SHAP), and Fuzzy Logic to improve anemia risk classification and clinical decision support. The publicly available SKILICARSLAN dataset containing 15,300 anonymized patient records across five anemia-related classes was utilized. Seven hematological parameters, namely hemoglobin (HGB), mean corpuscular volume (MCV), mean corpuscular hemoglobin (MCH), mean corpuscular hemoglobin concentration (MCHC), red blood cell count (RBC), hematocrit (HCT), and ferritin, were employed as predictive features. The workflow comprised data auditing, stratified train–test splitting, Synthetic Minority Oversampling Technique (SMOTE), hyperparameter optimization, multiclass XGBoost modeling, SHAP-based explainability analysis, and fuzzy risk interpretation. Experimental results demonstrated 82.94% accuracy, 87.27% weighted precision, 82.94% weighted recall, and 84.78% weighted F1-score, with a mean cross-validation F1-score of 87.00%. The model further achieved a macro-average ROC–AUC of 0.81 and a weighted-average ROC–AUC of 0.90, indicating robust discriminative performance despite class imbalance. SHAP analysis identified HGB, ferritin, and RBC-related variables as the most influential predictors. Moreover, the fuzzy logic layer enhanced interpretability by translating model outputs into clinically meaningful risk levels. These findings demonstrate the potential of explainable hybrid intelligence for transparent and reliable anemia screening and decision-support applications.
Co-Authors -, Amalia -, Evta Indra Alfred Army Man Duha Andreas Nababan Aurelia Xinara Lim Barasa, Randy Aldany Bawamenewi, Deskarya Chau, Sugandi Damanik, Ruth Tetra David C. Hutajulu Dikky Irfansyah Dina Pratiwi, Dina Elekda Permata Sari Manurung Elly Romy Fransisca Gabriela Septiani Simbolon Giawa, Well Friend Gresia Cesilia Sirait Gulo, Esthin Mitra Haposan Lumbantoruan Hutagalung, Jessy Putrionom Indra, Evta Ira Monalisa Irfansyah, Dikky JetaJones, Catherine Jogi Devrant Sibarani Johannes Bastira Ginting Junita Sari Ninggolan Kasa Lopian Kelvin Kelvin Khosandy, Vincent Kumala, Sinta Lumbantobing, Christian Frederic Mardi Turnip Mardi Turnip, Mardi Medalsan C Monalisa, Ira Munte, Syahrian Peralla Nainggolan , Dicky Wijaya Napitupulu, Lilis Handayani Natasya Sigalingging Nenda Sartika Manalu NK Nababan, Marlince Oloan Sihombing Oloan Sihombing, Oloan Ompusunggu, Elvis Sastra Panjaitan, Mega Lastarida Purba, Windania Rahil, Rafif Reclesia Br Harianja Reinaldo, Erick Relungwangi, Galuh Wira Ridho, Muhammad Alfathan Rio Brelly Pasaribu Rivaldo Robertus Turnip Ruth Agnes E. Tarihoran Sarah Theresia Aruan Saut Parsaoran Tamba Setiawan, Wendy Shandika , Muhammad Faja Shriram ram Siahaan, Mikael Sianturi, Angelia Chrismeshi Sheila Sihombing , Nissi Grace Dian Simamora, Wanda Pratama Putra Simatupang, Silvina Enjelia Br Sinaga, Wilson Sinta Kumala Sinurat, Stiven Hamonangan Sirait , Janiali Siregar, Regina Sitanggang, Wahyu Adventus Andreas Siti Aisyah Sitorus, Dedi Setiadi Sitorus, Ferdinand Jery Wilkinson Sri Hartati Sinaga Sugandi Chau Syafridatul maulidah Syahrian Peralla Munte Tanoto, Carvin Tanzil, Alferedo Tri Suci Unggul Siregar Wibowo, Yonatan Adi Winata, Jaspin Yanmil V. H. Purba Yanto, Willi Yessi Sesilia Sitompul Yonata Laia Yulianus Zega Zai , Ferman Zuhdi, Muhammad Fikri Akbar