cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Tri A. Sundara
Contact Email
tri.sundara@stmikindonesia.ac.id
Phone
+628116606456
Journal Mail Official
ijcs@stmikindonesia.ac.id
Editorial Address
Jalan Khatib Sulaiman Dalam 1, Padang, Indonesia
Location
Kota padang,
Sumatera barat
INDONESIA
The Indonesian Journal of Computer Science
Published by STMIK Indonesia Padang
ISSN : 25497286     EISSN : 25497286     DOI : https://doi.org/10.33022
Core Subject : Science, Engineering,
Computer Science & IT Electrical & Electronics Engineering Engineering
The Indonesian Journal of Computer Science (IJCS) is a bimonthly peer-reviewed journal published by AI Society and STMIK Indonesia. IJCS editions will be published at the end of February, April, June, August, October and December. The scope of IJCS includes general computer science, information system, information technology, artificial intelligence, big data, industrial revolution 4.0, and general engineering. The articles will be published in English and Bahasa Indonesia.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 38 Documents
 1   2   3   4 
Search results for , issue "Vol. 14 No. 3 (2025): The Indonesian Journal of Computer Science" : 38 Documents clear
Klasifikasi Jenis Peralatan Gym Menggunakan Convolutional Neural Network Andika, Farid; Yunarti, Sry; Baharuddin, Suardi Hi
The Indonesian Journal of Computer Science Vol. 14 No. 3 (2025): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i3.4065

Abstract

The use of artificial intelligence, especially Convolutional Neural Networks (CNN), has shown significant progress in image classification and object recognition. This research aims to develop an effective CNN model for automatically classifying gym equipment types, with the potential to improve the operational efficiency of fitness centers. The CNN model was trained using TensorFlow and Keras with the Adam optimizer and categorical cross-entropy loss function for 10 epochs, with data augmentation using ImageDataGenerator. The model evaluation shows satisfactory accuracy with a precision value of 0.9760, recall of 0.9772, and F1-score of 0.9766. The model successfully identified image samples from test data with a high level of confidence. The results of this study show that the use of CNNs in gym equipment classification has great potential to improve the efficiency of equipment recognition and contribute to the development of more advanced fitness technologies.
Klasifikasi User Review pada Aplikasi Online Travel Booking Menggunakan Multinomial Naïve Bayes Pratama, Mohammad Yoga; Cahyo Crysdian
The Indonesian Journal of Computer Science Vol. 14 No. 3 (2025): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i3.4199

Abstract

Perkembangan teknologi yang pesat telah membawa perubahan dalam berbagai aspek kehidupan, termasuk dalam sektor pariwisata. Aplikasi tiket travel online seperti Traveloka, pegipegi dan Tiket.com merupakan aplikasi travel yang sangat populer di Indonesia. penelitian ini bertujuan untuk mengukur performa dari metode Multinomial Naïve Bayes dalam mengklasifikasikan ulasan pengguna aplikasi tersebut menjadi kelas “satisfied” dan “unhappy”. Dataset berjumlah 1339 ulasan pengguna yang diambil dari Google Play Store. Uji coba dilakukan dengan tiga skenario rasio pembagian dataset (7:3, 8:2, 9:1) dan dievaluasi menggunakan confusion matrix dan K-Fold Cross Validation. Hasil uji coba menunjukkan skenario pembagian data 9:1 menghasilkan akurasi model tertinggi sebesar 81.34% dengan precision 81.47%, recall 81.44% dan F1-Score 81.34%. Analisa kata menggunakan TF-IDF menunjukkan bahwa kata-kata seperti “good”, “nice” dan “nice” mendominasi pada kelas “satisfied”, sedangkan kata seperti “price”, “cant”, dan “app” merupakan 3 kata yang paling mendominasi pada kelas “unhappy”. Dapat disimpulkan bahwa metode Multinomial Naïve Bayes memiliki performa yang baik untuk klasifikasi ulasan pengguna aplikasi travel online, dan semakin banyak dataset yang digunakan makan semakin bagus pula model yang dihasilkan.
Prediction Of Alzheimer Patients with Machine Learning Algorithms Priyono, Eko
The Indonesian Journal of Computer Science Vol. 14 No. 3 (2025): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i3.4364

Abstract

Alzheimer's disease is a neurological illness that impacts mental and emotional functions functions, has become a global concern due to its increasing prevalence. While age is the primary risk factor, other factors such as the APOE ε4 gene, family history, and brain injury also play a role. To date, there is no effective treatment for Alzheimer's, making early detection crucial. This study aims to explore early detection methods for Alzheimer's using machine learning algorithms, including transformer techniques. The results indicate that the Random Forest algorithm with Transformer methods achieved the highest accuracy of 98.9%. These findings are expected to contribute to the development of more accurate and efficient early detection strategies and improve the management of developing Alzheimer's later on.
Pengembangan Game Android Pada Anak Menggunakan Pendekatan User Centered Design Dan Evaluasi Usability Think Aloud Alvico, Alvico; Kurniawan, Dedy; Meiriza, Allsela; Syahbani, Muhammad Husni; Firnando, Ricy
The Indonesian Journal of Computer Science Vol. 14 No. 3 (2025): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i3.4396

Abstract

Technology, especially handheld devices, has become an integral part of modern life. The use of handheld devices among children aged 12-15 years reaches 99.61%. Despite the potential to cause dependency, these devices can be utilized positively, for example through learning with educational games. One of them is a titungan game that aims to increase user motivation and skills. However, the development of this game must also consider user needs. This research applies the User Centered Design method to improve the experience and comfort of playing, and the Think Aloud method as an evaluation. This study involved 8 participants consisting of children with an age range of 10-14 years. The results showed that the developed application has met the needs of users, with only two problems identified from 64 total evaluation scenarios with a percentage of 96.87% using the Think Aloud method.
PENGGUNAAN MIXED METHOD USABILITY TESTING (EYE TRACKING METHOD DAN COGNITIVE WALKTHROUGH (STUDI KASUS: WEBSITE JURUSAN SISTEM INFORMASI FAKULTAS ILMU KOMPUTER UNIVERSITAS SRIWIJAYA): Case Study: Website of The Department of Information Systems, Faculty of Computer Science, Sriwijaya University Putra, Pacu; Oktadini, Nabila Rizky; Hardiyanti, Dinna Yunika; Larasati, Salsabila; Putri, Nyayu Dwi Tarisa
The Indonesian Journal of Computer Science Vol. 14 No. 3 (2025): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i2.4516

Abstract

Universitas Sriwijaya is one of the state universities in Indonesia. Universitas Sriwijaya has 10 faculties, one of which is the Faculty of Computer Science. Information Systems is one of the departments in the Faculty of Computer Science, Sriwijaya University. Based on the observation results, the Department of Information Systems has just updated the appearance of its website. To determine the level of usability of the website, this research uses two methods, namely eye-tracking method and cognitive walkthrough. The activities that are the research material in this research include searching for lecturers' schedules, downloading final project guidelines and searching for course codes. As a result of the cognitive walkthrough method, the activity of searching for lecturers' timetables has the lowest success rate of 0%, followed by the activity of searching for course codes with 40% and the activity of downloading final project guidelines with 80%. In addition, the research continued using the eye-tracking method to identify areas of confusion for the respondents and to understand the emotional level of the respondents when carrying out these activities. It can be seen that the average respondent is still confused or unfocused when working on the pre-defined activities.
The Effects of Data Sampling and Feature Selection on Public Service Satisfaction Using an Ensemble Classifier Algorithm Priatna, Wowon
The Indonesian Journal of Computer Science Vol. 14 No. 3 (2025): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i3.4533

Abstract

Customer satisfaction is an important factor that determines quality. User satisfaction analysis can identify the service quality and measure quality through an evaluation process to improve services. This research aims to measure the performance of services provided by the village government. Villages and sub-districts offer services based on the community's specific needs. Nevertheless, by delivering impeccable service, it is possible to satisfy the community without causing physical or material harm. An essential requirement is the development of a service user classification methodology to enhance service quality, efficiently address service user grievances, detect recurring trends, and promptly offer feedback to enhance the offerings of products and services. Machine learning approaches can be used to quantify public service satisfaction in the analytical process. Machine learning is an algorithmic approach used to assess and prioritize satisfaction with public services offered by service providers. The main approach for machine learning is an ensemble classifier. The data was analyzed using Excel; then, the data was processed first to create a classification model. At the preprocessing stage, the data is grouped to obtain labels/targets to be processed based on algorithmic classification. The classification uses the Classifier aggregation algorithm. Type improvements using optimization features using the Particle Swarm Optimization (PSO) sampling algorithm and random subsampling techniques. This research produced an accuracy value before adding sampling techniques and a PSO accuracy value of 92.68. After adding sampling techniques and PSO optimization, an accuracy value of 100% was obtained
Polinomial Jacobi dan T-Design untuk Kode Linear Susanto, Agnes Indarwati; Santika, Aditya Purwa
The Indonesian Journal of Computer Science Vol. 14 No. 3 (2025): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i3.4614

Abstract

This thesis explores the use of Jacobi polynomials and t-design properties in linear codes. The primary goal of the research is to develop a Python and SageMath program to compute the Jacobi polynomial for linear codes with multiple reference vectors. The methodology involves analyzing self-dual codes over various f ields to derive Jacobi polynomials under specific conditions. The results indicate that the analyzed codes do not satisfy the t-design criteria, as different random reference vectors yield varying Jacobi polynomials. The study offers insights into the relationship between linear codes and Jacobi polynomials, with suggestions for further exploration of more complex codes to meet the t-design criteria.
Optimizing the Performance of the PSHS CARC Knowledge Hub: A Mixed-Method Evaluation of a Moodle-Based LMS Cuyasen, Graceson
The Indonesian Journal of Computer Science Vol. 14 No. 3 (2025): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i3.4617

Abstract

Abstract—This study focuses on optimizing the performance of the Philippine Science High School – Cordillera Administrative Region Campus Knowledge Hub (PSHS-CARC KHub), a Moodle-based Learning Management System (LMS), by addressing key performance issues such as slow response times. A mixed-method approach, including a comprehensive literature review and experimental testing, was used to identify effective strategies for hardware, software, and front-end optimization. The study examined the impact of server configurations, memory upgrades, and Apache module optimizations on system performance. Results indicate that hardware optimizations (such as SSD deployment), software improvements (including database indexing and caching), and front-end enhancements (such as minimizing HTTP requests and optimizing images) led to measurable improvements in system scalability and responsiveness. While performance tests showed reduced response times and stable throughput, occasional delays for high-latency transactions were observed. These findings provide actionable insights for optimizing Moodle-based LMS platforms, improving both user experience and system efficiency.
Variability in Makeup and Expressions: Impacts on Deep Learning Classifiers for Face Recognition: Assessing the Performance of Deep Learning Models in Diverse Facial Scenarios Egwali, Annie; Winifred, Sule
The Indonesian Journal of Computer Science Vol. 14 No. 3 (2025): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i3.4636

Abstract

Facial recognition technology serves as an integral component of security, access management, and identification systems. This study addresses the challenges this technology faces due to makeup and varying facial expressions, which can lead to misidentification. We investigate the effectiveness of five deep learning models—ResNet, InceptionV3, EfficientNet, Xception, and SENet—in recognizing faces with makeup and diverse emotional expressions. Using five publicly accessible datasets, including KDEF, CelebA, and UTKFace, we measure performance with metrics such as accuracy, precision, recall, F1 score, and ROC-AUC. Our analysis evaluates the benefits of transfer learning with pre-trained models and their robustness against new data. We find that InceptionV3 achieves peak accuracy of 85.2% on CelebA with high performance across all datasets, with an average accuracy of 79.8%. These results highlight how makeup and emotional expressions affect recognition accuracy and emphasize the need for improving facial recognition technologies for security and accessibility applications.
Klasifikasi Sentimen Tweet dengan Arsitektur Hybrid Transformers-CNN pada Platform Twitter Safrizal Ardana Ardiyansa; Abdi Negara Guci; Jemmy Febryan; Dian Alhusari; Haidar Ahmad Fajri
The Indonesian Journal of Computer Science Vol. 14 No. 3 (2025): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i3.4653

Abstract

Twitter, now known as X, is a popular platform used to express opinions on the latest trends, making it a valuable source of data for sentiment analysis research. The huge volume of data makes manual analysis impractical because it requires a long time and human resources, so it is necessary to automate the sentiment classification process through machine learning. Machine learning can be used to classify sentiment on a large scale quickly and accurately by utilising patterns. Machine learning models such as Transformers-CNN show the most superior performance with accuracy reaching 85.71% on test data and 99.90% on training data. The accuracy on the test data was better than other architectures namely LSTM, CNN, BERT, Transformers-LSTM, and LSTM-CNN with accuracies of 84.73%; 82.27%; 77.34%; 85.71%; 84.24% respectively. Transformers-CNN also has a training time of 30.17 minutes which is shorter than Transformers-LSTM, but longer than the other architectures.

Page 1 of 4 | Total Record : 38

 1   2   3   4 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol. 14 No. 5 (2025): The Indonesian Journal of Computer Science Vol. 14 No. 4 (2025): The Indonesian Journal of Computer Science Vol. 14 No. 3 (2025): The Indonesian Journal of Computer Science Vol. 14 No. 2 (2025): The Indonesian Journal of Computer Science Vol. 14 No. 1 (2025): The Indonesian Journal of Computer Science (IJCS) Vol. 13 No. 6 (2024): The Indonesian Journal of Computer Science (IJCS) Vol. 13 No. 5 (2024): The Indonesian Journal of Computer Science (IJCS) Vol. 13 No. 4 (2024): The Indonesian Journal of Computer Science (IJCS) Vol. 13 No. 3 (2024): The Indonesian Journal of Computer Science (IJCS) Vol. 13 No. 2 (2024): The Indonesian Journal of Computer Science (IJCS) Vol. 13 No. 1 (2024): The Indonesian Journal of Computer Science (IJCS) Vol. 12 No. 6 (2023): The Indonesian Journal of Computer Science (IJCS) Vol. 12 No. 5 (2023): The Indonesian Journal of Computer Science (IJCS) Vol. 12 No. 4 (2023): The Indonesian Journal of Computer Science (IJCS) Vol. 12 No. 3 (2023): The Indonesian Journal of Computer Science Vol. 12 No. 2 (2023): The Indonesian Journal of Computer Science Vol. 12 No. 1 (2023): The Indonesian Journal of Computer Science Vol. 11 No. 3 (2022): The Indonesian Journal of Computer Science Vol. 11 No. 2 (2022): The Indonesian Journal of Computer Science Vol. 11 No. 1 (2022): The Indonesian Journal of Computer Science Vol. 10 No. 2 (2021): The Indonesian Journal of Computer Science More Issue