cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
+6282161108110
Journal Mail Official
jurnal.json@gmail.com
Editorial Address
STMIK Budi Darma Jln. Sisingamangaraja No. 338 Telp 061-7875998
Location
Kota medan,
Sumatera utara
INDONESIA
Jurnal Sistem Komputer dan Informatika (JSON)
Published by Sekolah Tinggi Manajemen Informatika dan Komputer Budi Darma
ISSN : -     EISSN : 2685998X     DOI : https://dx.doi.org/10.30865/json.v1i3.2092
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering
The Jurnal Sistem Komputer dan Informatika (JSON) is a journal to managed of STMIK Budi Darma, for aims to serve as a medium of information and exchange of scientific articles between practitioners and observers of science in computer. Focus and Scope Jurnal Sistem Komputer dan Informatika (JSON) journal: Embedded System Microcontroller Artificial Neural Networks Decision Support System Computer System Informatics Computer Science Artificial Intelligence Expert System Information System, Management Informatics Data Mining Cryptography Model and Simulation Computer Network Computation Image Processing etc (related to informatics and computer science)
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 800 Documents
 74   75   76   77   78 
Prediksi Harga Tandan Buah Segar dengan Algoritma K-Nearest Neighbor Silvi Joya Arditna Br Bukit; Rakhmat Kurniawan R.
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 1 (2023): September 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i1.6818

Abstract

Palm oil and its derivative products are a source of foreign exchange for this country, because efforts are needed to maintain and develop the sustainability of palm oil as a potential natural resource. The company carries out statistical analysis on the factors inhibiting the previous month's harvest with a correction value of 5% – 12%. However, this kind of analysis still produces inaccurate prediction results, this is because the calculation process still involves estimation techniques from personal experience, looking at previous production patterns and other determining factors such as land area, principal amount and planting age. As a result, prediction targets often experience errors and production results are excessive or less than the target. Therefore, better predictive calculations are needed in determining palm oil production targets. Accurate predictions can help companies make decisions to increase production output. To carry out forecasting, it is necessary to apply the K-Nearest Neighbor Algorithm which can be used to predict palm oil prices in the future. Based on the results of data mining calculations using palm oil FFB prices from 2018 to 2023 (May 2023), it was concluded that the prediction of palm oil FFB prices in the 67th month (July 2023) had an accuracy level of 10,667 with k=3 and 19,200 with k=5.
Perbandingan Metode Dempster Shafer Dan Teorema Bayes Dalam Sistem Pakar Mendiagnosa Moyamoya Disease Naufal Rifqi; Agus Iskandar
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 1 (2023): September 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i1.6819

Abstract

The main aim of this research is to compare two analytical approaches, namely the Dempster-Shafer Method and the Bayes Theorem, in the context of a system developed for diagnosing Moyamoya disease. Moyamoya is a rare condition involving the narrowing or blocking of blood vessels in the brain, which can lead to disrupted blood flow and an increased risk of stroke. In the medical field, diagnosing Moyamoya disease is a crucial initial step for appropriate treatment planning. The Dempster-Shafer Method is an approach used to address uncertainty and combine uncertain information into a conclusion. On the other hand, the Bayes Theorem is a statistical principle that connects the probability of a hypothesis before and after new evidence emerges. Both of these approaches are vital in the medical diagnostic process. In this study, both methods are implemented in an expert system specifically developed for diagnosing Moyamoya disease. Data from Moyamoya cases are used to evaluate the performance of both methods. Performance measurement is conducted by observing diagnostic accuracy, computational time, and resource usage. The results of this research provide valuable insights into the effectiveness and performance of the Dempster-Shafer Method and the Bayes Theorem in medical applications, particularly in diagnosing Moyamoya disease. Strengths and weaknesses of each approach are revealed, aiding in understanding situations where each method is most suitable. The Dempster-Shafer Method is effective in dealing with complex uncertainties and combining uncertain evidence. Meanwhile, the Bayes Theorem excels in probability calculations. The implications of this research are important in developing more advanced medical expert systems. In the medical realm, where diagnostic decisions impact patient care, a better understanding of these approaches helps in selecting the most appropriate method for specific situations. The results of comparing both methods indicate that the Dempster-Shafer Method yields a high probability of around 91%, indicating a substantial likelihood that the patient is suffering from this disease. Conversely, the Bayes Theorem yields a low probability of around 22%, suggesting a relatively small likelihood that the patient has Moyamoya Disease.
Prioritas Penanganan Anemia pada Ibu Hamil Menggunakan Metode TOPSIS Naufal Rifqi; Agus Iskandar
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 1 (2023): September 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i1.6820

Abstract

During pregnancy, women experience anemia which can negatively impact maternal health and fetal development. The government has taken various measures to address anemia in pregnant women, but the reduction in anemia rates has not been significant. Therefore, the treatment needs to be focused on individuals with high risk to be more effective. Decision Support System (DSS) is a tool used in complex decision-making processes and one of the methods is TOPSIS. TOPSIS is used to set priorities by comparing each alternative against predetermined positive and negative ideal solutions. In this study, there are 10 alternatives and 5 criteria. Based on the results of calculations with the TOPSIS method, Alternative 3 (A3) with a preference value of 0.246561061 is designated as a pregnant woman who must be prioritized in handling anemia.
Sistem Pendukung Keputusan Rekomendasi Objek Wisata Menerapkan Metode MABAC dan Pembobotan ROC Fifto Nugroho; Agung Triayudi; Mesran Mesran
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 1 (2023): September 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i1.6822

Abstract

North Sumatra possesses abundant potential for tourist attractions, yet achieving the optimal selection of these attractions poses a challenge. Therefore, a decision support system is required to aid in the decision-making process for choosing the most suitable tourist attractions. In this study, the Multi Atributive Border Approximation Area Comparison (MABAC) method is employed to rank tourist attractions based on predefined criteria. MABAC combines geometric approaches with boundary approximation area comparison analysis to calculate priority scores for each tourist attraction. Additionally, the Rank Order Centroid (ROC) method is used to assign weights to the identified criteria. This research reveals various issues in the selection of tourist attractions in North Sumatra, such as complex criteria, variations in criteria weights, and insufficient tools to address these challenges. The primary objective of this study is to develop a decision support system capable of assisting stakeholders in selecting tourist attractions aligned with their preferences and objectives. The outcome of this research is the development of an efficient decision support system to aid in the selection of tourist attractions in North Sumatra. This system reduces subjectivity in decision-making, provides more accurate ranking based on established criteria, and assists stakeholders in understanding the process of selecting tourist attractions in a more transparent manner. The implications of this research include enhancing the quality of decision-making in the tourism industry and optimizing the utilization of tourist attraction potential in North Sumatra. As for the tourism recommendation with the highest rank, alternative 3 is obtained with a value of 0.6343, namely Paropo natural tourism.
Penentuan Mahasiswa Berprestasi dengan Menerapkan Metode Multi Attribute Utility Theory (MAUT) Wulan Kartika Murti; Agung Triayudi; Mesran Mesran
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 1 (2023): September 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i1.6823

Abstract

Being an outstanding student in higher education is certainly a positive and proud thing. Where national education aims to develop the potential of students, in order to become educated, creative students and become democratic and responsible citizens. In determining outstanding students, there are several criteria that must be met by each student as a condition for determining outstanding students. The problem that occurs is that sometimes there are obstacles when assessing the criteria set for each prospective participant. To help the evaluation team in determining outstanding students, a decision support system is needed, sometimes experiencing obstacles when assessing the criteria set for each candidate. In the assessment carried out directly there are prospective candidates who do not meet the criteria standards but excel in other criteria. The Multi Attribute Utility Theory (MAUT) method is a quantitative comparison method used to convert several interests into numerical values on a scale of 0-1 with 0 representing the worst value and 1 the best value. The result of this research is a student determination decision that has the highest score value, namely Netralman (A1) with a utility value of 0.462.
Sistem Pendukung Keputusan Perbandingan Metode MOORA Dengan MOOSRA Dalam Pemilihan Hair Stylish Mohammad Aldinugroho Abdullah; Rima Tamara Aldisa
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 1 (2023): September 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i1.6824

Abstract

This study aims to compare the effectiveness of the MOORA (Multi-Objective Optimization on the basis of Ratio Analysis) and MOOSRA (Multi-objective Optimization on the Basis of Simple Ratio Analysis) methods in the context of selecting stylish hair at the barbershop. In the growing hair care industry, the selection of stylish hair does not only affect the appearance of the customer but also plays an important role in the image and success of the barbershop itself. Therefore, it is important for barbershop owners to choose the right stylish hair. The MOORA method is known for its ability to solve multi-objective decision-making problems by utilizing ratio analysis. Meanwhile, MOOSRA is another method that focuses on optimization by considering relative preferences. In the context of selecting stylish hair, both can be useful tools in guiding barbershop owners to choose stylish hair according to customer needs and preferences. This research involves collecting data regarding customer preferences and hair stylish characteristics from various barbershops. This data was then analyzed using the MOORA and MOOSRA methods to choose the most suitable hair style for each scenario. The results of the analysis will be compared to assess the relative performance of the two methods in this context. It is hoped that the results of this research will provide valuable insights for barbershop owners and the hair care industry in general. By understanding the advantages and limitations of each method, barbershop owners will be able to make more informed decisions in selecting stylish hair. In addition, this research can also contribute to the development of a methodology in more complex multi-objective decision-making, by providing concrete examples in practical applications. The final results of the calculations of the two methods are proven to produce the same highest ranking result, which is obtained by alternative 1 on behalf of Poppy Sukma.
Integration of Deepfake Technology in Promotional Videos to Enhance MSME Economic Utility in Bireuen Regency Heri Gustami; Deni Sumantri; Najmuddin Najmuddin
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 7 No. 3 (2026): Maret 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v7i3.9676

Abstract

This study examines the integration of deepfake technology in UMKM promotional practices by focusing on its strategic value, ethical dimensions, implementation risks, and economic utility. A qualitative approach with a naturalistic phenomenological design was employed to explore the experiences, perceptions, and readiness of UMKM actors, promotion teams, and consumers in using deepfake-based promotional content. Data were collected through participatory observation, in-depth interviews, and documentation, and analyzed using the interactive model of Miles, Huberman, and Saldaña with NVivo support. The findings indicate that deepfake is perceived as a promising promotional innovation because it can enhance visual appeal, extend promotional reach, and improve cost and time efficiency in content production. However, its adoption is shaped by important constraints, particularly content authenticity, ethical considerations, audience response, human resource capacity, and the risk of misleading consumers. The study also shows that the economic utility of deepfake in UMKM promotion is meaningful only when promotional efficiency is balanced with ethical control, digital literacy, and consumer trust. These findings suggest that deepfake adoption in UMKM should not be understood merely as a technological issue, but as a negotiation between economic value, digital capability, reputational risk, and moral legitimacy.Abstract is a brief summary of the paper to help readers quickly determine the main research problem, solutions to solving problems encountered, research objectives and temporary research results which can be in the form of numbers/percentages according to research needs. Abstract should be clear and informative, providing a statement for the problem under study and its solution. Abstract length between 90 to 230 words. Avoid unusual abbreviations and define all symbols used in the abstract. Using keywords related to the research topic is recommended.
Perbandingan SVM dan Logistic Regression Berbasis SMOTE pada Analisis Sentimen Menteri Keuangan di YouTube Sirozul Huda; Afril Efan Pajri; Sahri
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 7 No. 4 (2026): Juni 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v7i4.9632

Abstract

YouTube telah berkembang menjadi salah satu ruang utama bagi masyarakat untuk menyampaikan opini terhadap isu publik, termasuk respons terhadap figur pejabat pemerintah. Penelitian ini bertujuan untuk mengevaluasi dan memetakan persepsi publik terhadap Menteri Keuangan Republik Indonesia melalui analisis sentimen berbasis machine learning, dengan mengkomparasikan kinerja algoritma Support Vector Machine dan Logistic Regression. Data berjumlah 4.003 data komentar  dikumpulkan dari komentar berbagai kanal YouTube berdasarkan pencarian topik terkait, kemudian melalui tahapan pre-processing dan pelabelan otomatis menggunakan Indonesian Sentiment Lexicon (InSet). Meskipun pelabelan otomatis berbasis leksikon ini efisien, pendekatan ini memiliki keterbatasan untuk mendeteksi sarkasme dan menangkap konteks kalimat yang kompleks. Setelah fitur diekstraksi menggunakan pembobotan TF-IDF, teknik Synthetic Minority Over-sampling Technique (SMOTE) diterapkan untuk mengatasi masalah ketidakseimbangan label pada data latih. Pengujian model membuktikan bahwa pendekatan yang diusulkan berhasil melakukan klasifikasi dengan sangat baik. Hasil evaluasi menunjukkan bahwa Support Vector Machine memberikan tingkat akurasi tertinggi sebesar 90%, sedikit mengungguli Logistic Regression yang mencatatkan akurasi sebesar 89%. Kontribusi ilmiah dalam studi ini menegaskan bahwa algoritma klasifikasi berbasis SMOTE efektif dalam menangani masalah ketimpangan data, dengan menunjukkan peningkatan performa model dibandingkan penelitian terdahulu yang serupa.
Benchmarking CNN and Vision Transformer Architectures for Corn Leaf Disease Classification on the Kaggle Maize Dataset Juni Ismail; Raja Anan Nasution; Evi Handayani; Annisa Shafira Zuhri
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 7 No. 4 (2026): Juni 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v7i4.9679

Abstract

Foliar diseases in corn pose a critical constraint on agricultural productivity, particularly in developing countries. Deep learning-based automated detection has emerged as a viable alternative to conventional manual inspection. This study presents a comparative evaluation of four contemporary deep learning architectures—EfficientNet-B3, MobileNetV3-Large, ResNet50, and Vision Transformer Small (ViT-Small)—on the publicly available Corn or Maize Leaf Disease Dataset hosted on Kaggle (4,188 image samples; four classes: Blight, Common Rust, Gray Leaf Spot, and Healthy). Class imbalance was addressed through a combination of WeightedRandomSampler and Focal Loss, while all architectures were trained via transfer learning from ImageNet pretrained weights, augmented with MixUp and CutMix. Experimental results demonstrate that ViT-Small achieved the highest classification performance, attaining 97.14% accuracy, a weighted F1-Score of 0.9716, and an AUC-ROC of 0.9961, outperforming EfficientNet-B3 (96.66%), MobileNetV3-Large (96.18%), and ResNet50 (95.71%). As an external reference, these results are also compared indicatively with the DenseNet121 accuracy (93.48%) reported by Waheed et al. (2020); it must be emphasized that this baseline was not reproduced in the present experiments, and therefore the comparison should be interpreted as indicative rather than conclusive. McNemar’s test confirmed that ViT-Small’s superiority is statistically significant (p<0.05). An ablation study verified the positive contribution of the Focal Loss and WeightedRandomSampler combination. Grad-CAM visualization corroborated that all models direct their attention to pathologically relevant lesion regions.
STAB-AD: Framework Deteksi Anomali Mobile Banking Berbasis Perilaku Dan Spatio-Temporal Tri Wiyono; Asrul Helmandi; Ibnu Afandi Manao; Andika Dwi Aryo; Ardiansyah
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 7 No. 4 (2026): Juni 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v7i4.9685

Abstract

Perkembangan mobile banking meningkatkan risiko fraud, seperti unauthorized transaction dan account takeover (ATO), yang semakin kompleks dan sulit dideteksi. Penelitian ini mengusulkan metode Spatio-Temporal and Behavioral Agreement-based Anomaly Detection (STAB-AD) untuk mendeteksi anomali transaksi melalui integrasi fitur perilaku dan spatio-temporal. Model mengombinasikan Isolation Forest, Local Outlier Factor, dan One-Class SVM dengan mekanisme agreement-based untuk mengukur konsistensi antar model dan mengklasifikasikan tingkat risiko. Fitur yang digunakan mencakup frekuensi transaksi, deviasi nilai, time gap, perubahan perangkat, serta indikator spatio-temporal seperti jarak geografis, velocity, dan impossible travel. Evaluasi dilakukan menggunakan precision, recall, F1-score, dan ROC-AUC dengan pendekatan pseudo-labeling berbasis aturan sebagai proksi ground truth pada data tidak berlabel. Hasil menunjukkan bahwa STAB-AD mampu meningkatkan kinerja deteksi dibandingkan baseline serta efektif dalam risk stratification, dengan hanya 0,72% transaksi teridentifikasi sebagai risiko tinggi. Fitur spatio-temporal terbukti signifikan dalam mengidentifikasi pola perpindahan tidak wajar yang mengindikasikan potensi ATO. Namun, penelitian ini masih terbatas pada penggunaan threshold berbasis asumsi dan validasi tanpa label aktual, sehingga diperlukan pendekatan yang lebih data-driven serta evaluasi berbasis ground truth pada penelitian selanjutnya.

Page 76 of 80 | Total Record : 800

 74   75   76   77   78 

Filter by Year

2019 2026


Reset
Filter By Issues
All Issue Vol. 7 No. 4 (2026): Juni 2026 Vol. 7 No. 3 (2026): Maret 2026 Vol. 7 No. 2 (2025): Desember 2025 Vol. 7 No. 1 (2025): September 2025 Vol 6, No 4 (2025): Juni 2025 Vol. 6 No. 4 (2025): Juni 2025 Vol. 6 No. 3 (2025): Maret 2025 Vol 6, No 3 (2025): Maret 2025 Vol 6, No 2 (2024): Desember 2024 Vol. 6 No. 2 (2024): Desember 2024 Vol. 6 No. 1 (2024): September 2024 Vol 6, No 1 (2024): September 2024 Vol 5, No 3 (2024): Maret 2024 Vol. 5 No. 3 (2024): Maret 2024 Vol. 5 No. 2 (2023): Desember 2023 Vol 5, No 1 (2023): September 2023 Vol. 5 No. 1 (2023): September 2023 Vol 4, No 4 (2023): Juni 2023 Vol. 4 No. 4 (2023): Juni 2023 Vol 4, No 3 (2023): Maret 2023 Vol. 4 No. 3 (2023): Maret 2023 Vol 4, No 2 (2022): Desember 2022 Vol. 4 No. 2 (2022): Desember 2022 Vol 4, No 1 (2022): September 2022 Vol. 4 No. 1 (2022): September 2022 Vol. 3 No. 4 (2022): Juni 2022 Vol 3, No 4 (2022): Juni 2022 Vol 3, No 3 (2022): Maret 2022 Vol. 3 No. 3 (2022): Maret 2022 Vol 3, No 2 (2021): Desember 2021 Vol. 3 No. 2 (2021): Desember 2021 Vol. 3 No. 1 (2021): September 2021 Vol 3, No 1 (2021): September 2021 Vol 2, No 3 (2021): Mei 2021 Vol. 2 No. 3 (2021): Mei 2021 Vol 2, No 2 (2021): Januari 2021 Vol. 2 No. 2 (2021): Januari 2021 Vol 2, No 1 (2020): September 2020 Vol. 2 No. 1 (2020): September 2020 Vol 1, No 3 (2020): Mei 2020 Vol. 1 No. 3 (2020): Mei 2020 Vol. 1 No. 2 (2020): Januari 2020 Vol 1, No 2 (2020): Januari 2020 Vol. 1 No. 1 (2019): September 2019 Vol 1, No 1 (2019): September 2019 More Issue