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
 76   77   78   79   80 
Identifikasi Faktor Dominan Risiko Depresi Remaja Menggunakan XGBoost dengan Interpretasi SHAP Hartati Tammamah Lubis; Randy Brilliant Chandra; Muhammad Nasri Gea; Erica Rian Safitri
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.v7i4.9864

Abstract

Depresi pada remaja merupakan salah satu masalah kesehatan mental yang dapat memengaruhi kesejahteraan psikologis, prestasi akademik, dan interaksi sosial. Identifikasi faktor-faktor yang berkontribusi terhadap risiko depresi diperlukan untuk mendukung upaya deteksi dini dan pencegahan yang lebih efektif. Penelitian ini bertujuan mengidentifikasi faktor dominan yang berkontribusi terhadap prediksi risiko depresi remaja menggunakan Extreme Gradient Boosting (XGBoost) dengan interpretasi SHapley Additive exPlanations (SHAP). Penelitian memanfaatkan dataset publik yang terdiri atas 1.200 sampel remaja dengan atribut karakteristik individu, kondisi psikologis, penggunaan media sosial, dan aspek gaya hidup. Untuk mengatasi ketidakseimbangan kelas digunakan pendekatan scale_pos_weight, sedangkan evaluasi model dilakukan menggunakan Repeated Stratified Cross Validation. Hasil pengujian menunjukkan rata-rata F1-score sebesar 96,11% dengan standar deviasi 5,66%, yang mengindikasikan performa klasifikasi yang baik dan konsisten. Analisis SHAP menunjukkan bahwa sleep_hours, stress_level, daily_social_media_hours, dan anxiety_level merupakan variabel yang memberikan kontribusi terbesar terhadap prediksi model. Temuan ini menunjukkan bahwa pada dataset yang digunakan, berkurangnya durasi tidur, tingginya tingkat stres dan kecemasan, serta penggunaan media sosial yang lebih intens berkontribusi terhadap peningkatan prediksi risiko depresi. Selain menghasilkan performa klasifikasi yang baik, pendekatan XGBoost dengan SHAP juga meningkatkan transparansi model dalam menjelaskan kontribusi masing-masing variabel terhadap hasil prediksi. Hasil penelitian ini bersifat prediktif berdasarkan dataset yang digunakan dan tidak dimaksudkan sebagai dasar diagnosis klinis depresi.
Implementasi Deep Factorization Machine Berbasis Profil Minat RIASEC untuk Rekomendasi Program Kepemudaan Sihabuddin Rifqi; Erna Dwi Astuti; Hidayatus Sibyan
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.v7i4.9873

Abstract

Pemilihan program kepemudaan yang kurang tepat akibat keterbatasan informasi dan pemetaan minat yang belum terstruktur menjadi kendala dalam pengembangan potensi pemuda. Penelitian ini bertujuan mengimplementasikan dan mengevaluasi efektivitas model Deep Factorization Machine (DeepFM) berbasis data profil minat instrumen RIASEC untuk menghasilkan rekomendasi program kepemudaan dari Kementerian Pemuda dan Olahraga (Kemenpora) yang terpersonalisasi. Penelitian kuantitatif eksperimental ini menggunakan dataset dari 485 responden yang dipetakan ke dalam lima program pemberdayaan. Fitur pengguna dibangun menggunakan vektor skor numerik enam dimensi RIASEC tanpa rekayasa fitur manual, yang diproses bersama fitur kategorikal program melalui integrasi komponen Factorization Machine dan Deep Neural Network. Hasil pengujian empiris menunjukkan arsitektur yang diusulkan memiliki performa prediktif yang sangat representatif. Sistem berhasil mencapai nilai Normalized Discounted Cumulative Gain (NDCG@3) sebesar 0,7064, Area Under the Curve (AUC) 0,7217, Recall@3 0,8018, dan Precision@3 0,4144. Capaian ini menunjukkan bahwa model DeepFM memberikan performa yang baik dalam menghasilkan serta menyusun peringkat 3 rekomendasi program teratas secara presisi sesuai dengan karakteristik psikometrik pengguna.
Komparasi Algoritma Random Forest dan SVM dalam Klasifikasi Kondisi Aliran Air Berdasarkan Getaran MPU6050 Aknes Tasia Pratama; Ahmad Taqwa; Lindawati
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.v7i4.9875

Abstract

Ketersediaan informasi mengenai kondisi aliran air pada sistem distribusi masih menjadi permasalahan di beberapa wilayah, terutama pada jaringan yang tidak beroperasi secara kontinu. Penelitian ini bertujuan mengembangkan model klasifikasi kondisi aliran air pada pipa distribusi berdasarkan data getaran yang diperoleh menggunakan sensor MPU6050. Data getaran direpresentasikan melalui fitur akselerasi tiga sumbu (ax, ay, dan az) serta fitur statistik berupa mean dan Root Mean Square (RMS). Dataset yang digunakan terdiri atas 4.406 sampel yang dikelompokkan ke dalam dua kelas, yaitu kondisi air mengalir dan pipa kosong. Tahapan penelitian meliputi pra-pemrosesan data menggunakan StandardScaler, penanganan ketidakseimbangan kelas menggunakan Synthetic Minority Over-sampling Technique (SMOTE), serta pelatihan model menggunakan algoritma Random Forest dan Support Vector Machine (SVM). Hasil pengujian menunjukkan bahwa Random Forest memperoleh akurasi 95,92%, presisi 96,60%, recall 96,22%, dan F1-score 96,41%, sedangkan Support Vector Machine (SVM) memperoleh akurasi 95,80%, presisi 95,50%, recall 97,21%, dan F1-score 96,35%. Hasil tersebut menunjukkan bahwa kedua algoritma mampu mengklasifikasikan kondisi aliran air dengan baik, dengan Random Forest memberikan performa keseluruhan yang sedikit lebih unggul dibandingkan Support Vector Machine (SVM). Penelitian ini menunjukkan bahwa data getaran dari sensor MPU6050 berpotensi digunakan sebagai solusi pemantauan kondisi aliran air secara non-intrusif pada sistem distribusi air.
Perbandingan CatBoost dan Elastic Net untuk Estimasi Komposisi Tubuh Berbasis Antropometri Aditiya Ari Wicaksono; Khanun Roisatul Ummah
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.v7i4.9887

Abstract

Pemantauan komposisi tubuh diperlukan untuk memberi gambaran kondisi tubuh yang lebih informatif dibandingkan BMI, terutama terkait persentase lemak dan massa otot. Pemeriksaan standar seperti Dual-Energy X-ray Absorptiometry (DXA) memiliki keterbatasan biaya dan aksesibilitas, sehingga diperlukan pendekatan estimasi berbasis antropometri yang lebih praktis. Penelitian ini bertujuan membandingkan performa CatBoost dan Elastic Net dalam mengestimasi komposisi tubuh menggunakan dataset National Health and Nutrition Examination Survey (NHANES) 2017–2018. Data yang digunakan berjumlah 3.551 data setelah proses cleaning, terdiri atas delapan fitur input antropometri dan dua target berbasis DXA. Metode penelitian mengikuti CRISP-DM, meliputi pemahaman data, persiapan data, pemodelan, evaluasi, dan deployment sederhana. Data dibagi menjadi 2.840 data latih dan 711 data uji, kemudian model dievaluasi menggunakan MAE, RMSE, dan R². Hasil pengujian menunjukkan CatBoost memperoleh performa terbaik dengan Mean MAE 1,588891, Mean RMSE 2,044905, dan Mean R² 0,862830, sedangkan Elastic Net memperoleh Mean MAE 1,888025, Mean RMSE 2,408882, dan Mean R² 0,819884. Selain itu, prototipe berbasis Streamlit dikembangkan untuk simulasi inferensi terhadap data antropometri baru. Hasil penelitian ini masih terbatas pada dataset NHANES 2017–2018 sehingga generalisasi ke populasi lain memerlukan validasi lanjutan
Comparative Evaluation of Machine Learning Algorithms for Diabetes Prediction with SMOTE and Principal Component Analysis Badia Inaya Sazrade; Ken Ditha Tania; Ferdiansyah
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.v7i4.9903

Abstract

Diabetes mellitus is a chronic disease that requires early detection to reduce the risk of severe complications. However, machine learning-based diabetes prediction is often affected by class imbalance and high-dimensional data. This study investigates the effectiveness of integrating Synthetic Minority Over-sampling Technique (SMOTE) and Principal Component Analysis (PCA) for diabetes prediction. A total of 80,437 records from a Kaggle diabetes dataset were processed using the Knowledge Discovery in Databases (KDD) framework. Six machine learning algorithms, namely Random Forest, XGBoost, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naïve Bayes, and Neural Network, were evaluated using train-test split ratios of 70:30, 80:20, and 90:10. Performance was measured using accuracy, precision, recall, and F1-score. Without oversampling, XGBoost consistently achieved the highest accuracy across all split ratios, peaking at 94.04% at the 80:20 ratio; however, recall for the minority (diabetic) class remained substantially lower than for the majority class, indicating that high overall accuracy masked weaker detection of actual diabetes cases. After applying SMOTE, overall accuracy declined across all models (e.g., XGBoost fell to 87.52% at 80:20), but minority-class recall improved markedly, indicating a more balanced classification between classes at the cost of overall accuracy. Notably, at the 80:20 split, the Neural Network achieved a marginally higher accuracy (87.67%) than XGBoost under SMOTE, although XGBoost remained the top performer at the 70:30 and 90:10 ratios, suggesting that its advantage under class-balanced conditions is not uniform across split ratios. PCA was applied to reduce data dimensionality and did not substantially affect predictive performance; however, the present results do not include quantitative evidence, such as the change in feature count or computation time, needed to substantiate claims about its contribution to efficiency. These findings suggest that XGBoost with an 80:20 split is the most effective configuration when class imbalance is not addressed, while the application of SMOTE narrows the performance gap between models and shifts the trade-off toward more balanced, rather than purely accuracy-maximizing, classification.
Analysis And Prediction Of Job Training Suitability For Job Seekers’ Professions At The Department Of Employment, Industry, And Trade Of Batu Bara Regency Using The Naive Bayes Algorithm And Feature Selection Eko Budianto; Muhammad Iqbal; Zulham Sitorus
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

Abstract

Public vocational training effectiveness depends on alignment between training programs and job seekers’ professional profiles. In practice, training placement is often determined manually and subjectively, causing competency mismatches that reduce program effectiveness. This study develops an optimized computational framework to predict the suitability of vocational training programs for job seekers at the Department of Employment, Industry, and Trade of Batu Bara Regency. Using the Knowledge Discovery in Databases (KDD) framework, 1,434 historical records containing demographic data, education, work experience, occupational interests, and competency indicators were analyzed. To address the conditional independence limitation of the Naive Bayes classifier, three filter-based feature selection methods Information Gain, Mutual Information, and Chi-Square were implemented and compared. Results show that feature selection improved model performance, increasing accuracy from 91.26% to 93.01% across all methods. The consistent performance indicates that all methods identified the same dominant predictor, primarily professional interest, while removing redundant attributes. The proposed hybrid model demonstrates strong stability and generalization capability, providing a reliable decision support system for reducing employment mismatches and improving workforce development resource allocation.
Analysis of Weaknesses and Recommendations for IT Governance Development in SIGAP at the Bureau of Leadership Administration, Regional Secretariat of North Sumatra Province Efriansyah Putra Bahari Barus; Andysah Putera Utama Siahaan; Muhammad Amin
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.v7i4.9943

Abstract

The implementation of effective information technology governance is necessary to support the quality of digital-based personnel administration services at the Bureau of Leadership Administration of the Regional Secretariat of North Sumatra Province. The problem faced is that the capability level of information technology governance in the Salary and Employe Appreciation Information System (SIGAP) is not yet known, so an evaluation is needed to identify areas that require improvement. This research aims to evaluate the capability level of information technology governance in the Employe Salary and Appreciation Information System (SIGAP) using the COBIT 2019 framework. The method used is descriptive quantitative with data collection techniques thru questionnaires, interviews, observations, and document studies. The evaluation was conducted on the domains EDM01, EDM02, EDM03, EDM04, EDM05, APO02, APO03, APO07, APO11, and APO14. The research results show that seven domains, namely EDM01, EDM02, EDM03, EDM04, APO02, APO03, and APO07, achieved Capability Level 3 (Established Process), while EDM05, APO11, and APO14 are at Capability Level 2 (Managed Process). Gap analysis shows that all domains still have a gap of one level against the set target. As a corrective solution, it is recommended to enhance process performance measurement, stakeholder engagement, quality management, data governance, and the development of SIGAP digital services to support the continuous improvement of information technology governance.
Analysis Of The Decision Tree (C4.5) And Random Forest Algorithms To Determine Student Eligibility For Final Project Assignments Based On Academic Requirements Eisyaniah Desvazulinda; Muhammad Iqbal; Muhammad Syahputra Novelan
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.v7i4.9947

Abstract

Determining student eligibility for undertaking a final project is an important process in higher education, which is often still conducted manually and subjectively. This study aims to develop a classification model based on machine learning to determine the eligibility of students at Batam University using Decision Tree (C4.5) and Random Forest algorithms. The data used includes Grade Point Average (GPA), total completed credits (SKS), prerequisite course grades, and academic records. This research employs a quantitative approach with stages including data collection, data preprocessing, model development, and performance evaluation using accuracy, precision, and recall metrics. The results show that both algorithms are capable of classifying student eligibility effectively. The Decision Tree (C4.5) algorithm produces an interpretable model in the form of decision rules, while Random Forest demonstrates superior performance in terms of accuracy and prediction stability. The comparison indicates that Random Forest is more effective in handling complex data, whereas C4.5 provides better model transparency. In conclusion, the implementation of Decision Tree (C4.5) and Random Forest algorithms can serve as an effective solution to support objective and data-driven academic decision-making. The resulting model has the potential to be developed into a decision support system to improve the efficiency and quality of determining student eligibility for final project enrollment.
Audit And Evaluation Of CBT Examination System At SMK Muhammadiyah-10 Kisaran Using Cobit 2019 Framework Zulfan; Khairul; Andysah Putera Utama Siahaan
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

Abstract

This study aims to audit and evaluate the Computer Based Test (CBT) system for Academic Ability Tests (TKA) at SMK Muhammadiyah 10 Kisaran using the COBIT 2019 framework through a mixed-methods descriptive approach with data collection techniques including observation, semi-structured interviews, questionnaires based on COBIT 2019 capability indicators, and documentation studies, focusing on five COBIT 2019 domains: EDM03 (Ensure Risk Optimization), APO12 (Manage Risk), APO13 (Manage Security), DSS01 (Manage Operations), and DSS05 (Manage Security Services), with 8 respondents consisting of the principal, curriculum vice principal, IT team, proctors, technicians, and teachers determined through purposive sampling based on RACI chart analysis. The results show that the overall capability level of CBT system governance is at Level 2 (Managed Process) with an average score of 2.22, while DSS01 reaches Level 3 (Established Process) with a score of 3.01, and the gap analysis reveals significant discrepancies between actual conditions and the expected Level 4 (Predictable Process), with EDM03 having the largest gap (2.08) and only 48% achievement, identifying EDM03, APO12, APO13, and DSS05 as priority domains requiring immediate improvement due to their high impact on TKA implementation reliability and security. This research contributes a comprehensive evaluation model integrating risk analysis, IT-Related Goals, and COBIT 2019 capability levels for CBT systems in vocational high schools, which is still rarely studied in the Indonesian educational context, providing both theoretical contributions to the development of information system audit studies in education and practical benefits as evaluation material and a basis for CBT system improvement for school management.
IoT-Based Real-Time Monitoring System for Post-Harvest Fish Storage Quality Adyanata Lubis; Firman Santosa; Purnama Wirawan
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.v6i4.8224

Abstract

This study develops an Internet of Things (IoT)-based system for continuously monitoring the environmental conditions and freshness indicators of post-harvest fish storage. The system integrates an ESP32 microcontroller with a DHT22 temperature-humidity sensor, an MQ-137 ammonia sensor, and an analog pH probe. Sensor measurements are sampled every five seconds, transmitted through Wi-Fi using the MQTT publish-subscribe protocol, stored in a MySQL database through a Node.js backend, and visualized on a React.js web dashboard. A research-and-development design with iterative prototyping was applied, followed by sensor calibration, integration testing, transmission-performance testing, and a 72-hour storage experiment using tuna and snapper samples. The system achieved average accuracies of 97.3% for temperature, 96.8% for relative humidity, 94.2% for ammonia, and 95.1% for pH. Average end-to-end latency was 0.856 s on a local network, 1.230 s on a 10 Mbps Internet connection, and 2.145 s on a 5 Mbps connection. Continuous operation for seven days produced 99.2% uptime. During the storage test, ammonia increased from below 2 ppm to 28.4 ppm while pH decreased from 6.8 to 5.2. The dashboard issued warning and critical alerts when predefined ammonia thresholds were exceeded, demonstrating its capability for timely quality-risk detection.

Page 80 of 80 | Total Record : 800

 76   77   78   79   80 

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