cover
Contact Name
Fitrianingsih
Contact Email
infokom@gunadarma.ac.id
Phone
+6221-78881112 ext. 516
Journal Mail Official
infokom@gunadarma.ac.id
Editorial Address
Jalan Margonda Raya 100
Location
Kota depok,
Jawa barat
INDONESIA
Jurnal Ilmiah Informatika Komputer
Published by Universitas Gunadarma
ISSN : 08538638     EISSN : 20898045     DOI : http://dx.doi.org/10.35760/ik
Core Subject : Science,
This journal is published periodically three times a year, April, August, and December. It publishes a broad range of research articles on Information Technology and Communication, whether in Indonesian Language or English.
Articles 8 Documents
Search results for , issue "Vol. 30 No. 3 (2025)" : 8 Documents clear
Implementasi Metode CNN Berbasis Transfer Learning dengan Arsitektur MobileNetV2 dalam Klasifikasi dan Pemetaan Tempat Wisata Mira; Cahyaningtyas, Christian; Sari, Maya; Yuliana
Jurnal Ilmiah Informatika Komputer Vol. 30 No. 3 (2025)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/ik.2025.v30i3.56

Abstract

The growth of tourism in the digital era encourages the use of social media as a source of visual data for destination analysis. This study aims to classify and map tourist attractions in West Kalimantan using a transfer learning-based Convolutional Neural Network (CNN) method with the MobileNetV2 architecture. A total of 454 images were collected through web scraping from the Instagram account @enjoykalbar, then through a process of elimination, augmentation, normalization, and manual labeling based on the West Kalimantan Disporapar tourism categories, namely Hills, Beaches, Cascades, Culture, Lakes, Rivers, Caves, and Forests. The dataset was divided into training data (70%), validation (20%), and test (10%). The model was built by freezing the initial layers of MobileNetV2 and adding a classification head, then drilled for 20 epochs using the Adam Optimizer and EarlyStopping and ReduceLROnPlateau callbacks. The training results showed a training accuracy of 95.8%, validation accuracy of 88.1%, and test accuracy of 80%. Further evaluation using the classification report yielded an overall accuracy of 89%, with an average precision of 0.93, a recall of 0.86, and an F1-score of 0.88. The model was then integrated into a category- and coordinate-based interactive mapping system to display the distribution of tourist attractions across 12 districts and 2 cities. The results demonstrate that the CNN transfer learning approach is effective for tourism image classification and supports spatial visualization in tourism promotion and planning.
BISINDO Sign Letters Recognition Through HOG Features and Bagging Decision Tree Indra, Dolly; Alwi, Erick Irawadi; Anwar, Faudiah; Prihandani, St. Nadya Kurnia
Jurnal Ilmiah Informatika Komputer Vol. 30 No. 3 (2025)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/ik.2025.v30i3.57

Abstract

Sign language is one of the primary means of communication for people with hearing disabilities. BISINDO (Indonesian sign language) communicates using hand movements, among other things. One solution to this problem is to use image processing to recognize BISINDO letters A-Z based on hand movements. This study aims to create a BISINDO letter recognition system based on image processing using several stages, namely, preprocessing such as converting RGB images to grayscale images, then improving image quality by adjusting image contrast and removing noise with a median filter, HOG (Histogram of Oriented Gradients) feature extraction, and Bagging Decision Tree classification. A total of 156 images were used in the dataset, consisting of 104 letter images for training data and 52 letter images for test data. The data will be processed in the system as training data, and the dataset will then be stored in ‘mat’ format. Based on the results of testing Classification using Bagging Decision Tree, which produced an average accuracy rate of 86.5%. Thus, this research is expected to contribute to the development of BISINDO character recognition technology based on digital image processing.
Implementasi Data Mining Naïve Bayes untuk Sistem Peringatan Dini Hasil Belajar Siswa Sekolah Dasar S, Adyatma Ramadhani; Hilda, Atiqah Meutia; Elly, Muhammad Jafar; Mintarsih, Nani
Jurnal Ilmiah Informatika Komputer Vol. 30 No. 3 (2025)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/ik.2025.v30i3.58

Abstract

This study aims to apply data mining techniques using the Naïve Bayes algorithm to classify student learning outcomes as an early warning system. The classification model was developed using 90 student score records and grouped into two categories, namely “Good” and “Poor”. The experimental results show that the Naïve Bayes model achieved 100% accuracy, precision, and recall. These findings indicate that the proposed model is capable of consistently classifying student learning outcomes and has the potential to serve as a decision support tool for teachers and school administrators.
Identifikasi Tingkat Kepatuhan Wajib Pajak Bumi dan Bangunan di Jakarta dengan Pendekatan Algoritma K-Means Umam, Muhammad Taufiqul; Basyah, Baby Lolita
Jurnal Ilmiah Informatika Komputer Vol. 30 No. 3 (2025)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/ik.2025.v30i3.59

Abstract

The Rural and Urban Land and Building Tax (PBB-P2) serves as a regional fiscal mechanism levied on the ownership, control, or utilization of property assets by both individuals and corporate entities. As a cornerstone of regional fiscal policy, PBB-P2 is instrumental in bolstering Local Own-Source Revenue (PAD). Given Jakarta's status as the nation’s administrative and commercial epicenter characterized by high population density and intense economic momentum, the city holds a strategic and vast potential for PBB-P2 collection. This study aims to categorize the compliance behavior of PBB-P2 taxpayers within the Jakarta region by utilizing the K-Means algorithm. The research methodology is guided by the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework, which involves six systematic phases: business understanding, data understanding, data preparation, modeling, evaluation, and deployment. The dataset consists of 28,125 PBB-P2 taxpayer records collected from 2020 to 2024. The findings reveal that taxpayer compliance is classified into four distinct clusters. Cluster 0 indicates very high compliance, Cluster 1 reflects low compliance, Cluster 2 denotes moderate compliance, and Cluster 3 corresponds to high compliance. An average silhouette coefficient value of 0.742 demonstrates that the resulting clusters are well-defined, showing strong internal similarity and clear separation from one another.
Implementasi Algoritma AES-256 Berbasis Web untuk Pengamanan Dokumen Digital di CV. Karya Eksklusif Nusantara Naqiyah, Ainun; Hayati, Lilis Nur; Faradibah, Amaliah
Jurnal Ilmiah Informatika Komputer Vol. 30 No. 3 (2025)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/ik.2025.v30i3.60

Abstract

In the digital era, corporate document security has become a major challenge due to the increasing risk of data breaches and cyberattacks. CV. Karya Eksklusif Nusantara, a company that provides goods and services, still stores important documents in digital formats such as .pdf, .docx, and .xlsx without a special protection system, making them vulnerable to illegal access or data corruption. This study aims to implement the AES-256 algorithm in CBC mode on a web-based system to encrypt and decrypt digital documents, as well as to test its performance based on different file sizes. This research uses the Waterfall method, which includes stages of data collection through interviews and literature review, system requirement analysis, design using UML, implementation with the Laravel framework, and black-box testing. The result of the study is a web-based application capable of securely encrypting and decrypting digital documents. Performance testing shows that the encryption and decryption operations are very fast, with an average encryption time of 0.2924 seconds and a decryption time of 0.3309 seconds, while functional testing ensures that all functions work according to requirements.
Rancang Bangun Aplikasi Walking Log dalam Penghitungan Jumlah Langkah untuk Pembakaran Kalori Tubuh Raharja, Wahyu Kusuma; Azhari, M. Fajar; Alfitra, Zidan
Jurnal Ilmiah Informatika Komputer Vol. 30 No. 3 (2025)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/ik.2025.v30i3.68

Abstract

Walking is a light physical activity that has a positive impact on health. A pedometer can be used to count the number of steps taken while walking. However, these devices usually have limited features and seem impractical to use. Current mobile technology developments, especially smartphones, can be used as an alternative to using a pedometer. The Walking Log application was created as an application to count the number of steps walked and the body's calorie burn. This application was created through several stages including planning, design, coding, and testing. In the planning stage, information will be collected regarding the number of steps, calorie burn, the sensors used, and the process of creating an Android application. At the design stage, a navigation structure, display design and file structure for storing historical data will be created.. In the coding stage, the application will be created using Android Studio. This research produced an Android application file named walking-log.apk with a size of 3,023 kilobytes. The walking log application consists of six menus: the main screen, track menu, settings menu, history menu, and about menu. Based on the results of the trial process, the application can run well on several devices that have met the minimum requirements to be able to run this application, namely Android smartphones with a minimum Android operating system. In the accuracy and error percentage tests, this application has an error percentage of ±2.12%. This error value shows that the application that has been built has good accuracy
Pengembangan Aplikasi Berbasis Web untuk Skrining Tingkat Depresi Ibu Pasca Melahirkan Menggunakan Skala EPDS dan PHQ-9 Pangestu, Primanita; Widowati, Henny; Pernadi, Dody
Jurnal Ilmiah Informatika Komputer Vol. 30 No. 3 (2025)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/ik.2025.v30i3.69

Abstract

Anxiety and depression are mental health issues that are common in mothers during pregnancy and after childbirth. The prevalence of anxiety and depression among pregnant women is 12.6%, and among postpartum women, it is 10.1%. However, mental health screening is still not an integral part of comprehensive antenatal or postnatal care. This research aims to develop a website-based application for screening postpartum maternal depression levels using the EPDS and PHQ-9 scales. The method used involves application development using the PHP programming language and implementing the EPDS and PHQ-9 scales as assessment instruments. The research findings are a screening application that can help postpartum mothers self-assess their level of depression. The website has been successfully implemented and can be accessed online via the link https://postnatalcare.my.id/. The application is expected to serve as a screening tool for determining the level of postpartum depression in mothers and to assist midwives in monitoring patients' mental health conditions, enabling them to provide appropriate care.
Segmentasi Konsumen E-Commerce Menggunakan Algoritma K-Means Berbasis Dashboard Interaktif Rasyid, Aru Chevy; Fauziah
Jurnal Ilmiah Informatika Komputer Vol. 30 No. 3 (2025)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/ik.2025.v30i3.70

Abstract

The rapid expansion of the e-commerce industry in Indonesia has led to a substantial increase in consumer behavioral data. This condition highlights the need for analytical approaches capable of identifying transaction patterns and supporting meaningful customer segmentation. This study aims to segment e-commerce customers using the K-Means clustering method and to present the results through an interactive dashboard. The research process includes data cleaning and standardization, followed by the construction of derived variables such as average basket, spend per month, and paylater share to represent customer transaction behavior. The optimal number of clusters was determined by evaluating several metrics, including the Sum of Squared Errors (SSE) graph, Silhouette Score, Calinski–Harabasz Index, and Davies–Bouldin Index. Although the custest Silhouette Score and Calinski–Harabasz Index were obtained at k = 2, the overall evaluation indicated that k = 3 produced a more balanced and interpretable clustering structure. Consequently, three customer segments were identified: customers with moderate shopping activity, high-value customers with a tendency to use Paylater services, and customers with high transaction frequency but relatively low purchase value. The analytical results were subsequently implemented in a Streamlit-based interactive dashboard to support data-driven decision making.

Page 1 of 1 | Total Record : 8