cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Med Irzal
Contact Email
medirzal@unj.ac.id
Phone
-
Journal Mail Official
prosilkom@unj.ac.id
Editorial Address
-
Location
Kota adm. jakarta timur,
Dki jakarta
INDONESIA
J-KOMA : Jurnal Ilmu Komputer dan Aplikasi
Published by Universitas Negeri Jakarta
ISSN : 26204827     EISSN : 26204827     DOI : -
Core Subject : Science,
Computer Science & IT
J-KOMA is an open access journal, with core focus in two aspect: computer science general and information technology. All copyrights are retained by each respective author, but we hold publishing right. Currently, this journal has E-ISSN :2620-4827 published by LIPI which made it as a national journal.
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 68 Documents
 3   4   5   6   7 
Analysis of the Relationship Between Taxes and Indonesia's Economic Growth Using the Vector Error Correction Model (VECM) Muhammad Arib Alwansyah Arib; Vitaria Ronauli Silalahi Vitaria; Winalia Agwil Winalia; Nurul Hidayati Nurul
J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 9 No 01 (2026): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi
Publisher : Universitas Negeri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/JKOMA.091.01

Abstract

The Vector Error Correction Model (VECM) is a simultaneous modeling approach designed for variables that are stationary at the same order and exhibit cointegration relationships. This study aims to model the variables of Gross Domestic Product (GDP), Value Added Tax (VAT), Land and Building Tax (LBT), Income Tax (IT), and Import Duties using VECM, as well as to analyze the factors influencing the relationship between taxation and economic growth. The data used are annual data from 1990 to 2023, sourced from the Central Statistics Agency (BPS) and the World Bank. The analysis results indicate that the constructed model is a VECM with an optimal lag of 3 and a cointegration rank of 3. The long-term relationships in the VECM show that Income Tax and Import Duties affect Land and Building Tax and Value Added Tax. Meanwhile, short-term relationships reveal that GDP from the previous period influences Land and Building Tax, Income Tax, and current-period GDP. VAT from the previous period affects Land and Building Tax, Import Duties, and current-period VAT. Land and Building Tax from the previous period influences Income Tax, Import Duties, and current-period Land and Building Tax. Additionally, Import Duties from the previous period affect current-period VAT and Income Tax.
Analisis Sentimen terhadap Kebijakan Pengembalian Penjurusan di Sekolah Menengah Atas Menggunakan Algoritma Random Forest Saire Fernando; Mulyono; Ari Hendarno; Ersa Resita; Carli Apriansyah Hutagalung
J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 9 No 01 (2026): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi
Publisher : Universitas Negeri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/JKOMA.091.02

Abstract

In the 2025/2026 academic year, the Minister of Education, Culture, Research, and Technology (Permendikbudristek) planned to reinstate majors in high schools. This policy quickly sparked public debate, generating a variety of responses from the public, particularly on YouTube. This study was conducted to analyze public sentiment towards this policy using the Random Forest algorithm. Data was obtained through YouTube comment collection between April 2025 and June 2025, which yielded 4,181 comments. The analysis showed that YouTube comments on videos regarding the policy of reinstating majors in the high school curriculum had a more positive response than negative, with a ratio of 18.3% compared to 5%, with a total of 76.7% neutral. The model's performance in classifying sentiment achieved an overall accuracy of 83.16%, with a precision of 77.56%, indicating a fairly reliable model prediction. However, recall was at 57.25%, indicating that the model still had difficulty detecting all data in small classes such as positive and negative. Overall, the model's performance is represented by an F1-score of 61.26%. This research is expected to serve as a consideration for education leaders or the Minister of Education, Culture, Research, and Technology in determining whether a policy needs to be enacted or changed.
Lung Disease Diagnosis Based on MRI Data Using CNN Transfer Learning Method with MobileNetV2 and DenseNet121 Dinar Munggaran Akhmad; Dimas Ramadhan; Eneng Tita Tosida
J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 9 No 01 (2026): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi
Publisher : Universitas Negeri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/JKOMA.091.03

Abstract

Accurate lung disease diagnosis plays a critical role in medical treatment and improving patient outcomes. Conventional diagnostic methods often require experienced radiologists and are time-consuming. This study develops a lung disease diagnosis system based on Magnetic Resonance Imaging (MRI) data using the Convolutional Neural Network (CNN) method with Transfer Learning, specifically utilizing MobileNetV2 and DenseNet121 architectures. The dataset comprises 7,141 MRI images collected from Kaggle and RS Islam Aysha Bogor, classified into nine categories: Bacterial Pneumonia, Covid-19, Normal, Tuberculosis, Pneumothorax, Viral Infection, Asthma, Bronchitis, and Bronchopneumonia. Images were preprocessed to 224×224 pixels with pixel normalization to [0,1]. Four experimental scenarios were evaluated, varying optimizer, learning rate, batch size, and number of epochs. Results showed that MobileNetV2 achieved the best accuracy of 92.14%using RMSprop optimizer, learning rate 0.001, batch size 32, and 40 epochs. DenseNet121 achieved 87.82% accuracy with Adam optimizer under the same configuration. Validation using the confusion matrix yielded an overall accuracy of 91%, precision of 91.37%, recall of 92.25%, and F1-score of 91.79%. The best model was deployed as a web-based application built with Python Flask, enabling automatic image normalization and real-time classification without manual preprocessing. This research demonstrates that CNN-based Transfer Learning is effective for automated lung disease diagnosis with limited datasets
Comparing Linear and Quadratic Discriminant Analysis for Cervical Cancer Risk Prediction Using Behavioral Attributes Mochammad Anshori; Nindynar Rikatsih
J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 9 No 01 (2026): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi
Publisher : Universitas Negeri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/JKOMA.091.04

Abstract

Cervical cancer remains a critical global health challenge, yet early prediction using non-medical determinants is underexplored. This study aims to compare linear and quadratic discriminant analysis for early cervical cancer risk assessment based on behavioral and psychosocial factors. A quantitative experimental approach was utilized, analyzing a publicly available behavioral dataset of seventy-two instances and eighteen psychosocial features. Following rigorous statistical validation, feature normalization, and stratified data splitting, both discriminant models were trained and evaluated using accuracy and area under the receiver operating characteristic curve metrics. The empirical findings reveal a striking performance disparity between the classifiers. Linear discriminant analysis emerged as the superior model, achieving an exceptional accuracy of 93.33% and an area under the curve of 0.9464, demonstrating robust discriminative capability. Crucially, it attained perfect sensitivity with zero false negatives, eliminating the most dangerous diagnostic errors. Conversely, quadratic discriminant analysis exhibited complete predictive failure, performing no better than random guessing. This extreme divergence indicates that the underlying behavioral data possesses linearly separable characteristics. The additional complexity of estimating class-specific covariance matrices in the quadratic model resulted in severe overfitting and numerical instability given the limited sample size, proving that simpler, assumption-aligned models outperform complex alternatives. Ultimately, linear discriminant analysis provides an accurate, interpretable, and cost-effective decision support tool for identifying cervical cancer vulnerability. These findings validate that integrating social psychology with machine learning offers a robust framework for early disease screening in resource-constrained environments.
Lexicon-Based and Machine Learning Approaches for Sentiment Classification of Telemedicine Reviews in Indonesia Ahsanun Naseh Khudori; Fauzih
J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 9 No 01 (2026): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi
Publisher : Universitas Negeri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/JKOMA.091.05

Abstract

The rapid growth of telemedicine services in Indonesia has generated a substantial volume of user reviews, an important source for evaluating service quality. This study compares the effectiveness of lexicon-based and machine learning approaches in classifying review sentiment, using the three largest telemedicine applications in Indonesia, Alodokter, Halodoc, and KlikDokter as a case study. A publicly available dataset of 19,389 reviews, manually labelled by two annotators under the guidance of a psychologist, served as the gold standard and was preprocessed through case folding, normalisation, stopword removal, and stemming. The lexicon-based approach employs the InSet dictionary, while the machine learning approach applies Support Vector Machine (SVM), Naïve Bayes (NB), and Random Forest (RF) with TF-IDF features, evaluated via stratified 10-fold cross-validation. Given the highly imbalanced class distribution (positive 74.77%, negative 21.69%, neutral 3.54%), macro-F1 is adopted as the primary metric alongside accuracy. Machine learning approaches substantially outperformed the lexicon-based approach: SVM achieved the highest macro-F1 of 70.43% (88.68% accuracy), far exceeding the InSet dictionary's macro-F1 of 27.67% (34.92% accuracy). A further key finding is an evaluation paradox: although Naïve Bayes attained the highest accuracy (89.91%), its macro-F1 was comparatively low (60.11%) due to bias toward the majority class, demonstrating how accuracy alone can mislead on imbalanced data. The InSet dictionary also performed poorly in the telemedicine domain, frequently misclassifying positive reviews as negative. Finally, comparing three imbalance-handling strategies (no handling, class-weight, and random oversampling) showed that cost-sensitive learning (class-weight) was most effective, raising the neutral-class F1-score from 26.56% to 35.8% without compromising majority-class performance.
OPTIMISASI SISTEM INFORMASI MANAJEMEN RUANGAN PADA WEBSITE SIPERAD MENGGUNAKAN METODE WATERFALL Aqil Aswangga Anggaraksa; Ria Arafiyah; Carli Apriansyah Hutagalung
J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 9 No 01 (2026): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi
Publisher : Universitas Negeri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/JKOMA.091.06

Abstract

Room reservation management at Universitas Negeri Jakarta's Dewi Sartika Building faced persistent inefficiencies in the existing SIPERAD (Sistem Informasi Peminjaman Ruangan dan Presensi Perkuliahan) platform, including manual one-by-one data entry, the absence of a data export feature, and uncertainty about whether scheduled classes were actually held, which caused rooms to remain marked as occupied although they were in fact vacant. This study aims to develop and implement a web-based room management system with an integrated automatic notification feature to confirm classroom usage and improve room utilization efficiency. The system was developed using the Waterfall method, covering requirements analysis, system design with UML and Entity Relationship Diagram modeling, backend and frontend implementation using the Laravel framework, and system testing. The developed features include automatic web push notifications sent one day before scheduled classes, a course-in-charge confirmation mechanism, bulk data import via CSV, and report export in Excel and PDF formats. Testing was carried out using Black Box Testing to verify functional requirements and User Acceptance Testing (UAT) to assess user acceptance. Black Box Testing results showed that all 31 test scenarios for the Admin role and all 5 test scenarios for the Student role produced valid outputs, indicating 100% functional validity. UAT results indicated a very high acceptance level, with satisfaction percentages of 95.79% from Admin users and 89.69% from Student users, both categorized as "Very Good". These results demonstrate that the developed system successfully addresses the identified limitations of the existing SIPERAD platform and effectively supports real-time, transparent, and efficient room management at Universitas Negeri Jakarta.
Integrity-Audited Intrusion Detection under Withheld IoT Traffic Contexts Zainab Abbas Fadhil
J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 9 No 01 (2026): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi
Publisher : Universitas Negeri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/JKOMA.091.07

Abstract

Row-by-row examination of flow-based IoT intrusion detection would allow exact predictor replicas to exist in both train and test datasets. This research conducted auditing on RT-IoT2022 prior to modelling and focused on fixed baseline detectors under withheld traffic situations. The raw data consisted of 5,202 replicate rows besides the first replica and six predictor replicas with inconsistent labels in 128 rows. Data cleansing resulted in 117,909 flows. There were 6.59-6.90% of rows having an exact replica in training in the fixed five-fold raw split. Macro-F1 diagnostic random forest score for raw rows and cleansed rows were 0.9965 and 0.9968 respectively. On clean data, random forest scored 0.9968 with all 83 predictors and 0.9963 after ports and service were removed. Complete-service holdouts gave macro-F1 of 0.660–0.994. With disjoint normal pools, recall for an attack family absent from training ranged from 0.354 to 1.000. At an assumed attack prevalence of 1%, projected positive predictive value was 0.565. The benchmark supports strong interpolation inside one capture, but context changes still exposed failures.
Early Plant Disease Classification System Based on Deep Neural Network Techniques Wasan Ahmed Ali
J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 9 No 01 (2026): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi
Publisher : Universitas Negeri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/JKOMA.091.08

Abstract

Plant diseases pose a significant challenge to agricultural productivity because they can reduce crop yield and quality. Accurate and automated disease identification can support early diagnosis and improve crop management. This study presents a deep learning-based approach for classifying plant diseases from leaf images using the PlantVillage dataset. The dataset contains plant leaf images representing healthy and diseased conditions, which were preprocessed by resizing the images to 224 × 224 pixels, normalizing pixel values, and applying data augmentation to improve model robustness. Two deep learning approaches were evaluated: a custom Convolutional Neural Network (CNN) and DenseNet121 using transfer learning with ImageNet-pretrained weights. The models were trained using 70% of the dataset, while 10% and 20% were used for validation and testing, respectively. Experimental results show that the custom CNN achieved a validation accuracy of 98%, with a training accuracy of 97.36%, while DenseNet121 achieved a validation accuracy of 96.85% and a training accuracy of 98.23%. The results demonstrate that the custom CNN achieved higher validation accuracy than the DenseNet121-based transfer learning approach for the evaluated plant disease classification task. These findings indicate that a relatively compact CNN architecture can provide competitive performance for automated plant disease classification

Page 7 of 7 | Total Record : 68

 3   4   5   6   7 

Filter by Year

2017 2026


Reset
Filter By Issues
All Issue Vol 9 No 01 (2026): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 8 No 02 (2025): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 8 No 1 (2025): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 7 No 2 (2024): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 7 No 1 (2024): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 6 No 2 (2023): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 6 No 1 (2023): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 5 No 1 (2022): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 4 No 1 (2021): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 3 No 1 (2020): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 2 No 1 (2018): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi Vol 1 No 1 (2017): J-KOMA : Jurnal Ilmu Komputer dan Aplikasi More Issue