cover
Contact Name
Soeb Aripin
Contact Email
suefarifin@gmail.com
Phone
+6282370070808
Journal Mail Official
mesran.skom.mkom@gmail.com
Editorial Address
Jalan sisingamangaraja No 338 Medan, Indonesia
Location
Kota medan,
Sumatera utara
INDONESIA
Jurnal Sains dan Teknologi Informasi
ISSN : -     EISSN : 2809610X     DOI : https://doi.org/10.47065/jussi.v3i2.4883
Bidang kajian dari Jurnal Sains dan Teknologi Informasi, yaitu: Teknik Informatika, Manajemen Informatika, Sistem Informasi, Teknik Komputer, Kecerdasan Buatan, dan Computer Science.
Articles 96 Documents
Analisis Sentimen Komentar YouTube Kualifikasi Piala Dunia 2026 Ronde 4 Timnas Indonesia menggunakan Naïve Bayes Rasyid Iskandar Prayogi; Azhari Ali Ridha; Ade Andri Hendriadi; Nina Sulistyowati; Taufik Ridwan
Jurnal Sains dan Teknologi Informasi Vol 5 No 4 (2026): September 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jussi.v5i4.11226

Abstract

Public interest in the Indonesian National Team’s 2026 World Cup Qualifiers is evident from the diverse responses expressed in YouTube comments. The diversity of these responses indicates a range of sentiments toward the Indonesian National Team’s performance, making it necessary to cluster the comments to identify emerging sentiment trends. This study aims to analyze the sentiment of YouTube comments regarding the Indonesian National Team during Round 4 of the 2026 World Cup Qualifiers using the Multinomial Naïve Bayes algorithm. A total of 17,404 comments were collected via the YouTube Data API v3 from the Indonesian National Team and RCTI Sports channels. The data then underwent preprocessing, labeling using the InSet Lexicon verified by linguists, weighting using Term Frequency-Inverse Document Frequency (TF-IDF), and classification with the Multinomial Naïve Bayes algorithm. Testing was conducted using three data split scenarios 80:20, 75:25, and 70:30 with the metrics of accuracy, precision, recall, and F1-score. The test results showed that the 70:30 data split yielded the highest accuracy of 79.09%. In that scenario, the negative class achieved a precision of 0.81, a recall of 0.93, and an F1-score of 0.87. The negative class was also the most dominant sentiment, while the number of data points in the neutral and positive classes was lower. These results indicate that Multinomial Naïve Bayes can be used to classify YouTube comments.
Rancang Bangun Sistem Enterprise Resource Planning (ERP) Berbasis Web Menggunakan Metode Scrum untuk Integrasi Proses Bisnis Fakhri Akmal Fadillah; Jenie Sundari; Endah Wiji Lestari
Jurnal Sains dan Teknologi Informasi Vol 5 No 4 (2026): September 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jussi.v5i4.10573

Abstract

The development of information technology encourages companies to improve data management efficiency and business process integration. Procurement, sales, inventory management, payment, and transaction recording processes that are not optimally integrated may lead to data redundancy and errors in information management. This study aims to design and develop a web-based Enterprise Resource Planning (ERP) application that integrates various business processes into a centralized system. The system was developed using the Scrum method, which supports an incremental and flexible development process according to user requirements. Data collection methods included observation, interviews, and literature review. The development process involved preparing the product backlog, system implementation, and testing using the Black Box Testing method. The result of this study is a web-based ERP application named Synchro, which integrates product, customer, and vendor management, Sales Order, Purchase Order, Delivery Order, Goods Receipt, invoice and payment management, General Journal, and General Ledger. This integration enables data related to procurement, sales, inventory, and transaction recording to be managed within a single system. The developed features include purchase and sales transaction management, goods receipt and delivery recording, inventory monitoring, invoice and payment management, and accounting journal recording. Black Box Testing was conducted to examine whether the system functions met the specified functional requirements. Based on the test results, the tested features operated according to their expected functions. Therefore, the Synchro ERP application provides a centralized system that supports business process integration and more structured information management.
Penerapan Convolutional Neural Network Berbasis Computer Vision untuk Identifikasi Varietas Padi Berdasarkan Citra Bulir Gabah Fachriel A. Pomalingo; Syahrial Syahrial; Mohamad Ilyas Abas; Irawan Ibrahim
Jurnal Sains dan Teknologi Informasi Vol 5 No 4 (2026): September 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jussi.v5i4.11227

Abstract

Rice variety identification based on paddy grain images faces a challenge because several varieties have relatively similar visual characteristics, particularly in shape, size, and color, which may lead to inconsistent manual identification. This condition indicates the need for a computer vision approach that can automatically learn the visual characteristics of paddy grains. This study aimed to develop a Convolutional Neural Network (CNN) model to identify five rice varieties available at the Agricultural Research and Modernization Center of Gorontalo (BRMP Gorontalo), namely Ciherang, Inpari 30, Inpari 42, Inpari IR Nutri Zinc, and Mekongga. The dataset was obtained through direct image acquisition, consisting of 28 RAW photographs for each variety and nine cropped images from each photograph, resulting in 1,260 images. The research stages included preprocessing, Custom CNN development, evaluation of image size, learning rate, number of convolutional layers, and data splitting, as well as comparison with MobileNetV2, ResNet50, DenseNet121, and InceptionV3. The best configuration used an input size of 224×224 pixels, a learning rate of 0.0005, four convolutional layers, and an 80:20 data split. Testing on 135 final testing images achieved 93.33% accuracy, 93.44% precision, 93.33% recall, and 93.32% F1-score. These results indicate that the Custom CNN effectively identified the five rice varieties under the dataset and experimental conditions used in this study.
Penerapan Algoritma C4.5 untuk Klasifikasi Tingkat Pemahaman Mahasiswa pada Mata Kuliah Pemrograman Berdasarkan Hasil Evaluasi Akademik Aldian A. Surbakti; Teuku Amanda Rivaldi; Seri Ninta Br Bangun; M. Agustian; David JM Sembiring; Raheliya Br Ginting
Jurnal Sains dan Teknologi Informasi Vol 5 No 4 (2026): September 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jussi.v5i4.11338

Abstract

The use of academic data through data mining techniques can help identify patterns in student learning outcomes systematically. This study aims to apply the C4.5 algorithm to classify students’ levels of understanding in a programming course based on academic evaluation results. The attributes include attendance percentage, assignment scores, practical scores, midterm examination scores, and final examination scores, with target classes categorized as low, medium, and high. The research employs a classification approach using the C4.5 algorithm through the calculation of Entropy, Information Gain, and Gain Ratio to construct a decision tree. A simulated dataset consisting of 250 records was divided into 200 training records (80%) and 50 testing records (20%). Model performance was evaluated using a confusion matrix, accuracy, precision, recall, and F1-score. The reported test results indicate an accuracy of 78.00%, a macro-average precision of 75.83%, a macro-average recall of 80.61%, and a macro-average F1-score of 77.50%. Of the 50 testing records, 39 were correctly classified, while 11 were misclassified. The low category achieved a recall of 87.50%, the medium category 73.08%, and the high category 81.25%. These findings indicate that C4.5 has the potential to produce an interpretable classification model through decision rules. However, because the study uses a simulated dataset and the target labels are derived from the same evaluation attributes used as predictors, the results cannot yet be generalized to measure students’ actual understanding. Further testing using real academic data and validated class definitions is required to strengthen the validity of the findings.
Optimasi Kinerja XGBoost Dan Random Forest Dalam Klasifikasi Penyakit Hati Berdasarkan Data Klinis Pasien Pada Imbalance Dataset Sri Novida Sari; Julham Julham; Michael Stevano Sinurat; Dito Putro Utomo
Jurnal Sains dan Teknologi Informasi Vol 5 No 4 (2026): September 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jussi.v5i4.11347

Abstract

Liver disease is a major health concern that requires early detection through accurate clinical data analysis. Machine learning can support liver disease classification; however, an imbalanced dataset may cause a model to favor the majority class. This study aims to optimize and compare the performance of Random Forest and Extreme Gradient Boosting (XGBoost) algorithms for liver disease classification using clinical patient data. The dataset is the Liver Patient Dataset, comprising 27,158 records and 11 attributes, including the target variable Result. The research methodology includes data preprocessing, an 80:20 training-test split, the application of the Synthetic Minority Over-sampling Technique (SMOTE) to the training data, and hyperparameter optimization. Six experimental scenarios are designed to compare both algorithms before and after SMOTE and parameter optimization. Model performance is evaluated using accuracy, precision, recall, F1-score, ROC-AUC, and confusion matrices. Based on the reported simulation results, XGBoost combined with SMOTE and hyperparameter tuning achieves an accuracy of 89.12%, precision of 88.45%, recall of 88.21%, an F1-score of 88.33%, and an ROC-AUC of 91.27%. These results indicate the potential of combining data balancing and parameter optimization to improve classification performance. Nevertheless, these figures require verification through actual computational experiments before they can be considered empirical findings. This study is expected to provide a basis for evaluating clinical-data-based liver disease classification models and for further research into reliable machine learning approaches for healthcare applications.
Keamanan Multimedia untuk Menjamin Keaslian Konten menggunakan Digital Signature Berbasis Algoritma RSA Dito Putro Utomo; Bister Purba; Sri Novida Sari; Alyiza Dwi Ningtyas
Jurnal Sains dan Teknologi Informasi Vol 5 No 4 (2026): September 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jussi.v5i4.11358

Abstract

Multimedia content security has become a challenge as the distribution and manipulation of digital files become increasingly easy. This study aims to implement a digital signature based on the Rivest–Shamir–Adleman (RSA) algorithm to support the verification of multimedia content authenticity and integrity. The methods include problem identification, model design, implementation of the SHA-256 hash function, signature generation using a private RSA key, and verification using a public key. Testing was designed for six multimedia formats, namely JPEG, PNG, MP3, WAV, MP4, and AVI, using parameters including file size, hash value changes, verification status, signing time, verification time, and verification success rate. Based on the testing scenario, file sizes ranged from 2.50 to 82.70 MB. Signing time ranged from 0.012 to 0.038 seconds, with an average of 0.0218 seconds, while verification time ranged from 0.004 to 0.010 seconds, with an average of 0.0063 seconds. Testing across 12 conditions, consisting of six original files and six modified files, yielded a verification success rate of 100%, based on the assumption that all results matched the expected conditions. Hash value changes were used to identify changes in file content after manipulation. These results illustrate the potential of RSA for supporting multimedia integrity verification. However, empirical testing is still required to validate all values and objectively assess system performance.

Page 10 of 10 | Total Record : 96