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
jurikom.stmikbd@gmail.com
Editorial Address
STMIK Budi Darma Jalan Sisingamangaraja No. 338 Simpang Limun Medan - Sumatera Utara
Location
Kota medan,
Sumatera utara
INDONESIA
JURIKOM (Jurnal Riset Komputer)
Published by Sekolah Tinggi Manajemen Informatika dan Komputer Budi Darma
ISSN : 2407389X     EISSN : 27157393     DOI : http://dx.doi.org/10.30865/jurikom.v7i1.1927
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering
JURIKOM (Jurnal Riset Komputer) membahas ilmu dibidang Informatika, Sistem Informasi, Manajemen Informatika, DSS, AI, ES, Jaringan, sebagai wadah dalam menuangkan hasil penelitian baik secara konseptual maupun teknis yang berkaitan dengan Teknologi Informatika dan Komputer. Topik utama yang diterbitkan mencakup: 1. Teknik Informatika 2. Sistem Informasi 3. Sistem Pendukung Keputusan 4. Sistem Pakar 5. Kecerdasan Buatan 6. Manajemen Informasi 7. Data Mining 8. Big Data 9. Jaringan Komputer 10. Dan lain-lain (topik lainnya yang berhubungan dengan Teknologi Informati dan komputer)
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 1,069 Documents
 103   104   105   106   107 
Evaluasi Pengaruh RFE Terhadap Kinerja Random Forest dengan SVM pada Klasifikasi Kemiskinan Kabupaten/Kota Indonesia Shafa Kirana Aralia; Mula Agung Barata; Ita Aristia Sa'ida
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 1 (2026): Februari 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i1.9527

Abstract

Poverty is a socio-economic issue that remains a concern in Indonesia, with differences in development characteristics between districts/cities causing wide variations in indicators that are intercorrelated. Feature redundancy and the existence of extreme values have the potential to reduce the generalization ability of classification models and reduce the interpretability of results. Therefore, an approach is needed that not only produces high accuracy but is also capable of identifying the most relevant indicators. Therefore, an approach is needed that not only produces high accuracy but is also capable of identifying the most relevant indicators. This study aims to evaluate the effect of Recursive Feature Elimination (RFE) on the performance of Support Vector Machine (SVM) and Random Forest in classifying the poverty status of districts/cities in Indonesia. The dataset used consists of 514 observations with two target classes, namely non-poor and poor. The preprocessing stage included data cleaning and outlier handling using the IQR capping method, then the data was divided into 80% training data and 20% test data. Testing was conducted on four scenarios: SVM, SVM+RFE, Random Forest, and Random Forest+RFE. Evaluation used a confusion matrix, accuracy, precision, recall, and F1-score. The results show that RFE does not change the accuracy of SVM (0.971), but improves the performance of Random Forest from 0.981 to 0.99 and improves the precision of the minority class. The Random Forest+RFE combination is the most effective and efficient configuration for regional poverty classification.
Klasifikasi Model Konten Kuliner Viral UMKM di TikTok Menggunakan Algoritma Naive Bayes Mikraj, Ziyad Habibul; Putri, Raissa Amanda
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 1 (2026): Februari 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i1.9537

Abstract

This study examines the development of a classification model for viral culinary content of Micro, Small, and Medium Enterprises on the TikTok platform based on video caption text. The main problem lies in the high variation of promotional language, the use of trending terms, and unstructured text formats, which make the identification of viral culinary categories difficult to perform manually and inconsistently. This study aims to design a systematic classification model to automatically and measurably group TikTok captions of enterprises into viral culinary categories. The dataset consists of 800 captions collected through scraping using the Apify API. The model development process includes preprocessing stages such as cleaning, case folding, tokenizing, normalization, stopword removal, stemming, and detokenization to produce standardized text. Feature weighting is then performed using TF-IDF, followed by model construction using the Naïve Bayes algorithm. The resulting model classifies data into ten viral culinary categories, namely Donat Mochi, Cireng, Risol, Kentang Curly, Lukchup, Dimsum Mentai, Es Teh Jumbo, Indomie Telur, Mochi Daifuku, and Dessert Box. Evaluation using a confusion matrix and classification report shows an accuracy of 0.74 or 74 percent. These results indicate the model supports automated analysis of viral culinary trends.
Perbandingan Kinerja Identifikasi Model VGG-19 Dengan Inception V3 Dalam Klasifikasi Penyakit Appendicitis Dwi Prapita Sari; Ilka Zufria
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 1 (2026): Februari 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i1.9540

Abstract

Appendicitis is a surgical emergency that requires rapid and accurate diagnosis. However, limitations in ultrasound (USG) image interpretation often pose a risk of misdiagnosis, particularly in scenarios with limited medical data. This study aims to determine the most effective classification model for a clinical decision support system by comparing two transfer learning-based Convolutional Neural Network (CNN) architectures: VGG-19 and InceptionV3. Utilizing a dataset of 2,168 images split into 70% training, 10% validation, and 20% testing data, the models were evaluated using metrics such as accuracy, precision, recall, F1-score, and Area Under Curve (AUC). The results demonstrate that InceptionV3 delivered significantly superior performance, achieving an accuracy of 0.9033%, an F1-score of 0.8946% for the appendicitis class, and an AUC of 0.9502%. In contrast, VGG-19 only reached an accuracy of 0.8255%, with a recall for the appendicitis class as low as 0.8019%. The poor recall performance of VGG-19 indicates a high risk of missed diagnosis. This research contributes by recommending a more reliable and effective model to support AI-based appendicitis identification, specifically in limited data scenarios.
Optimasi IndoBERT untuk Pengenalan Entitas Bernama Bahasa Indonesia pada Data Media Sosial dengan Penalaan Hiperparameter Optuna Siswanto, Bambang; M. Hanafi
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 1 (2026): Februari 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i1.9545

Abstract

Named Entity Recognition (NER) merupakan salah satu tugas fundamental dalam pemrosesan bahasa alami yang berperan penting dalam ekstraksi informasi terstruktur dari teks tidak terstruktur. Pada Bahasa Indonesia, kinerja model NER berbasis pre-trained BERT sangat dipengaruhi oleh konfigurasi hiperparameter pada tahap fine-tuning. Namun, banyak penelitian masih menggunakan konfigurasi bawaan atau penyesuaian terbatas, sehingga potensi peningkatan kinerja dan stabilitas model belum sepenuhnya dimanfaatkan. Penelitian ini bertujuan untuk mengevaluasi dampak optimasi hiperparameter berbasis Optuna terhadap kinerja dan stabilitas pelatihan model pre-trained BERT untuk tugas NER Bahasa Indonesia. Model yang digunakan adalah IndoBERT (indobenchmark/indobert-base-p1) yang difine-tune untuk mengenali entitas Person (PER), Organization (ORG), dan Location (LOC) dengan skema pelabelan BIO. Metode optimasi hiperparameter dilakukan menggunakan pendekatan Bayesian berbasis Named Entity Recognition (NER) is a fundamental task in natural language processing for extracting structured information from unstructured text. In Indonesian, particularly for informal and diverse social media text, the performance of NER models based on Bidirectional Encoder Representations from Transformers (BERT) is strongly influenced by hyperparameter configurations during fine-tuning. However, many studies still rely on default settings or limited adjustments, so the potential improvements in performance and training stability have not been fully exploited. This study evaluates the impact of hyperparameter tuning using Optuna with a Tree-structured Parzen Estimator (TPE) on the performance and training stability of IndoBERT (indobenchmark/indobert-base-p1) on Twitter/X data. The main contribution of this work is an empirical evaluation of how hyperparameter tuning improves IndoBERT’s performance and training stability, and the resulting recommendations of reliable configurations for reproducible experiments and practical deployment of Indonesian NER. The dataset is annotated using the Begin–Inside–Outside (BIO) labeling scheme for three entity types: person (PER), organization (ORG), and location (LOC). The optimization objective is defined as the F1-score on the validation set. The results show that the Optuna configuration achieves a precision of 0.9338, recall of 0.9312, F1-score of 0.9325, and accuracy of 0.9854 on the test set, outperforming the baseline with an F1-score of 0.9253 and accuracy of 0.9837. Multi-seed evaluation indicates consistent improvements, with an average F1 of 0.9302 ± 0.0016 compared to 0.9238 ± 0.0009 for the baseline. These findings confirm that Optuna-based hyperparameter tuning improves both the performance and reliability of IndoBERT for Indonesian NER on social media text.
Analisis Komparasi Algoritma KNN dan Naive Bayes untuk Klasifikasi Pasien Rehabilitasi Narkoba di XYZ Putri Khairunnisa Nabilah; Triase, Triase
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 1 (2026): Februari 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i1.9553

Abstract

The development of information technology in the field of data mining opens up significant opportunities to optimize data classification in the healthcare and rehabilitation sectors. LRPPN BI Medan currently faces challenges in determining rehabilitation programs because the decision-making process is still subjective and has not yet systematically utilized historical data. Inaccuracies in determining these programs can reduce recovery effectiveness and increase the potential for patient relapse. This study aims to apply and test the effectiveness of the KNN and Naïve Bayes algorithms in classifying rehabilitation programs based on patient criteria, such as duration of drug use, URICA test results, medical history, and addiction level. This study uses a quantitative approach with the Waterfall development method. This solution is proposed to overcome subjectivity through a data-based classification system that complements each other in accuracy and processing speed. The results of this study show that the Naive Bayes algorithm has a higher accuracy rate of 96.43%, while KNN has an accuracy of 94.29%.
Perbandingan CNN Dan ResNet50 Dalam Klasifikasi Tuberkulosis Pada Citra X-Ray Paru Aulia, Muhammad Fathir; Ikhsan, Muhammad
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 1 (2026): Februari 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i1.9554

Abstract

Tuberculosis (TB) remains a global health problem and requires rapid and consistent early screening. Chest X-rays are widely used because they are practical and economical, but manual interpretation is highly dependent on experts, which can lead to subjectivity, fatigue, and delayed diagnosis. This study aims to compare the performance of a basic Convolutional Neural Network (CNN) and a transfer learning-based ResNet50 in classifying lung X-ray images into two classes, namely TB and Normal, as well as to assess the trade-off between accuracy and computational efficiency. The dataset used is a balanced subset of 1,000 images (500 TB and 500 Normal) divided into 70% training data, 15% validation, and 15% testing with a fixed seed to ensure reproducible experiments. Preprocessing was performed by resizing the images to 224×224 pixels and normalizing the pixel values. ResNet50 used a preprocessing scheme in accordance with the pretrained model. Evaluation was performed using a confusion matrix and accuracy, precision, recall, and F1-score metrics. The test results show that CNN achieved an accuracy of 98.00% with three classification errors, while ResNet50 achieved an accuracy of 99.33% with one classification error and average precision, recall, and F1-score metrics above 0.99. In terms of efficiency, the CNN training time was approximately 40.46 seconds, while ResNet50 took a total of approximately 226.99 seconds. In the robustness test, the CNN inference time was approximately ±100 ms/image and ResNet50 was approximately ±1,900 ms/image. These findings indicate that ResNet50 excels in accuracy and generalization stability, while CNN is more efficient for fast response and limited resource requirements.
Sistem Informasi Prediksi Penjualan Bubuk Teh PT XYZ Menggunakan Metode ARIMA Sebagai Pendukung Pengambilan Keputusan Asisura, Lili; Samsudin, Samsudin
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 1 (2026): Februari 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i1.9556

Abstract

Sales of tea powder experience significant fluctuations influenced by consumption trends, seasonal factors, and changes in market demand, which may lead to overstock and understock problems. These conditions highlight the need for an accurate and practical forecasting tool that can directly support managerial decision-making. This study aims to develop a web-based sales and revenue forecasting information system by integrating the Autoregressive Integrated Moving Average (ARIMA) method. The dataset consists of historical tea powder sales from May 2023 to March 2025, aggregated into monthly time series data. The research stages include data preprocessing, visualization, stationarity testing using the Augmented Dickey-Fuller (ADF) test, differencing, ARIMA model identification and parameter estimation, forecasting, and model evaluation using MAE, MSE, and MAPE. The evaluation results indicate that ARIMA(1,1,2) is the best-performing model, achieving an MAE of 4.07, an MSE of 3.15, and a MAPE of 147.34%. The forecasting results show fluctuating patterns in future sales and revenue. The main contribution of this research lies in the integration of the ARIMA forecasting model into a web-based information system that enables automatic and real-time prediction, providing practical support for inventory planning and data-driven managerial decision-making.
Aplikasi Monitoring Aset Berbasis QR Code Dengan Rule-Based Alert Engine Sebagai Peringatan Dini Sibarani, Gitarosalina; Santa, Kristofel; Tinambunan, Medi Hermanto
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 1 (2026): Februari 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i1.9561

Abstract

Asset management at PT PLN Nusantara Power Unit Pembangkitan Minahasa is still carried out manually, which has the potential to cause recording errors and delays in data updates. In addition, most QR Code-based asset management systems that have been developed generally only focus on the process of recording and identifying assets, without being equipped with an early warning mechanism. This study aims to develop a web-based asset monitoring application that integrates QR Code technology with a rule-based alert engine using the Extreme Programming (XP) method. The research methods include iterative software development, functional testing using black box testing, system response time analysis, and user satisfaction evaluation through questionnaires. Testing results show that all system functions run according to user requirements with an average response time of less than 5 seconds, thus supporting real-time use. The rule-based alert engine is capable of automatically detecting asset conditions that require attention and generating notifications as a form of early warning. User evaluation shows a high level of satisfaction with the ease of use and functionality of the system. Based on these results, the developed application has been proven to improve the accuracy of recording and efficiency of asset management compared to manual methods, and has the potential to become an adaptive digital solution in office asset management.
Analisis Perbandingan Algoritma SVM, Logistic Regression, Naive Bayes, dan XGBoost Untuk Deteksi Fake News Umar Farid Al Faqihi; Afril Efan Pajri; Muhammad Jauhar Vikri
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 1 (2026): Februari 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i1.9492

Abstract

The rapid growth of digital technology and internet access has completely changed how information is shared, enabling content to spread quickly across various online platforms. However, these advancements have also made it easier for misleading or entirely fabricated news to circulate, posing serious risks to social stability, political environments, and public health. This study tackles this problem by employing several machine learning-based classification methods for analyzing textual data. Four algorithms Support Vector Machine (SVM), Logistic Regression (LR), Naive Bayes (NB), and Extreme Gradient Boosting (XGBoost) were applied to detect linguistic patterns that differentiate genuine news from fake content. A major contribution of this research is the creation of a custom dataset gathered directly from Indonesian online news portals, comprising a total of 4,909 entries. The evaluation results demonstrate exceptionally high accuracy across the models: 99.69% for SVM, 99.39% for LR, 99.29% for NB, and 99.19% for XGBoost. To verify reliability, each model was further evaluated using cross-validation, yielding average accuracy scores of 99.57% (SVM), 99.52% (LR), 99.44% (NB), and 99.49% (XGBoost). These findings confirm that all four classifiers are highly effective and well-suited for identifying fake news in text-based data.

Page 107 of 107 | Total Record : 1069

 103   104   105   106   107 

Filter by Year

2015 2026


Reset
Filter By Issues
All Issue Vol. 13 No. 1 (2026): Februari 2026 Vol. 12 No. 6 (2025): Desember 2025 Vol. 12 No. 5 (2025): Oktober 2025 Vol. 12 No. 4 (2025): Agustus 2025 Vol 12, No 3 (2025): Juni 2025 Vol. 12 No. 3 (2025): Juni 2025 Vol 12, No 2 (2025): April 2025 Vol. 12 No. 2 (2025): April 2025 Vol 12, No 1 (2025): Februari 2025 Vol. 12 No. 1 (2025): Februari 2025 Vol 11, No 6 (2024): Desember 2024 Vol. 11 No. 6 (2024): Desember 2024 Vol. 11 No. 5 (2024): Oktober 2024 Vol 11, No 5 (2024): Oktober 2024 Vol 11, No 4 (2024): Augustus 2024 Vol. 11 No. 4 (2024): Augustus 2024 Vol. 11 No. 3 (2024): Juni 2024 Vol 11, No 3 (2024): Juni 2024 Vol 11, No 2 (2024): April 2024 Vol. 11 No. 2 (2024): April 2024 Vol 10, No 3 (2023): Juni 2023 Vol 10, No 2 (2023): April 2023 Vol 10, No 1 (2023): Februari 2023 Vol 9, No 6 (2022): Desember 2022 Vol 9, No 5 (2022): Oktober 2022 Vol 9, No 4 (2022): Agustus 2022 Vol 9, No 3 (2022): Juni 2022 Vol 9, No 2 (2022): April 2022 Vol 9, No 1 (2022): Februari 2022 Vol 8, No 6 (2021): Desember 2021 Vol 8, No 5 (2021): Oktober 2021 Vol 8, No 4 (2021): Agustus 2021 Vol 8, No 3 (2021): Juni 2021 Vol 8, No 2 (2021): April 2021 Vol 8, No 1 (2021): Februari 2021 Vol 7, No 6 (2020): Desember 2020 Vol. 7 No. 5 (2020): Oktober 2020 Vol 7, No 5 (2020): Oktober 2020 Vol 7, No 4 (2020): Agustus 2020 Vol 7, No 3 (2020): Juni 2020 Vol 7, No 2 (2020): April 2020 Vol 7, No 1 (2020): Februari 2020 Vol 6, No 6 (2019): Desember 2019 Vol 6, No 5 (2019): Oktober 2019 Vol 6, No 4 (2019): Agustus 2019 Vol 6, No 3 (2019): Juni 2019 Vol 6, No 2 (2019): April 2019 Vol 6, No 1 (2019): Februari 2019 Vol 5, No 6 (2018): Desember 2018 Vol 5, No 5 (2018): Oktober 2018 Vol 5, No 4 (2018): Agustus 2018 Vol 5, No 3 (2018): Juni 2018 Vol 5, No 2 (2018): April 2018 Vol 5, No 1 (2018): Februari 2018 Vol 4, No 5 (2017): Oktober 2017 Vol 4, No 4 (2017): Agustus 2017 Vol 3, No 6 (2016): Desember 2016 Vol 3, No 5 (2016): Oktober 2016 Vol 3, No 4 (2016): Agustus 2016 Vol 3, No 1 (2016): Februari 2016 Vol 2, No 6 (2015): Desember 2015 More Issue