Garuda - Garba Rujukan Digital

The Effect of Resampling on Classifier Performance: an Empirical Study Utomo Pujianto; Muhammad Iqbal Akbar; Niendhitta Tamia Lassela; Deni Sutaji
Knowledge Engineering and Data Science Vol 5, No 1 (2022)
Publisher : Universitas Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17977/um018v5i12022p87-100

An imbalanced class on a dataset is a common classification problem. The effect of using imbalanced class datasets can cause a decrease in the performance of the classifier. Resampling is one of the solutions to this problem. This study used 100 datasets from 3 websites: UCI Machine Learning, Kaggle, and OpenML. Each dataset will go through 3 processing stages: the resampling process, the classification process, and the significance testing process between performance evaluation values of the combination of classifier and the resampling using paired t-test. The resampling used in the process is Random Undersampling, Random Oversampling, and SMOTE. The classifier used in the classification process is Naïve Bayes Classifier, Decision Tree, and Neural Network. The classification results in accuracy, precision, recall, and f-measure values are tested using paired t-tests to determine the significance of the classifier's performance from datasets that were not resampled and those that had applied the resampling. The paired t-test is also used to find a combination between the classifier and the resampling that gives significant results. This study obtained two results. The first result is that resampling on imbalanced class datasets can substantially affect the classifier's performance more than the classifier's performance from datasets that are not applied the resampling technique. The second result is that combining the Neural Network Algorithm without the resampling provides significance based on the accuracy value. Combining the Neural Network Algorithm with the SMOTE technique provides significant performance based on the amount of precision, recall, and f-measure.

The Identification of Covid-19 Fake News Factors on Social Media in Indonesia Chotijah, Umi; Husenti , Nadya; Sutaji, Deni; Mahditya Indra Pratama, Angga
Indonesian Journal of Information Systems Vol. 6 No. 1 (2023): August 2023
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/ijis.v6i1.6613

Social media is a protocol for people’s interaction and disseminating new ideas. The spread of fake information can occur on social media because there is no control and verification from the legal account. During the COVID-19 corona virus outbreak, the government issued a self-isolation policy. However, people use social media to find information about COVID-19 and spread news about COVID-19 greedily, especially in Indonesia. Therefore, this study explores the factors influencing the spread of fake news related to COVID-19. The sampling used in this study was non-random/non-probability sampling with the Convenience Sampling technique, including two hundred and twenty-two respondences from several regions in Indonesia. These phenomenons are studied using the Uses and Gratification framework by eliminating entertainment variables, adding altruism motivation, and adding moderating variables for demographic factors of individual psychological well-being, including age, education, income, and gender. Data were analyzed using Smart Partial Least Squares (PLS) to determine the effect of five variables. The analysis results show that all the variables, e.g., altruism, socialization, time elapsed, information sharing, and information seeking, as well as moderating variables and demographic factors of individual psychological well-being have no positive and significant effect on the spread of fake COVID-19—news on social media in Indonesia.

Pengembangan Software Penilaian Pegawai Berbasis Web di Perumda Giri Tirta Gresik Al Husain, Gymnastiar Ishaq; Sutaji, Deni; Ilmi, Rifqy Rosyidah
Jurnal Inovatif Vol. 3 No. 3 (2024): Desember 2024
Publisher : Jurnal Inovatif

Show Abstract | Download Original | Original Source | Check in Google Scholar

Perumda Giri Tirta Gresik adalah perusahaan yang bergerak di bidang penyediaan air bersih bagi masyarakat Kabupaten Gresik. Salah satu tantangan utama yang dihadapi adalah penilaian kinerja pegawai yang selama ini dilakukan secara manual, menggunakan formulir fisik yang rentan terhadap kesalahan dan kurang efisien. Untuk mengatasi masalah ini, dikembangkan software penilaian pegawai berbasis web menggunakan metode System Development Life Cycle (SDLC). Software ini dirancang untuk meningkatkan efisiensi, akurasi, dan transparansi dalam proses penilaian kinerja, serta memungkinkan akses pegawai terhadap hasil penilaian secara real-time. Hasil implementasi menunjukkan bahwa penggunaan software ini mampu mempermudah proses penilaian kinerja, mempercepat pengambilan keputusan, dan mendukung peningkatan kualitas manajemen sumber daya manusia. Dengan demikian, software ini menjadi solusi yang efektif dalam mendukung visi Perumda Giri Tirta Gresik untuk memberikan pelayanan air bersih yang prima dan berkelanjutan.

Optimasi Sistem Pengelolaan Surat Masuk dan Keluar Berbasis Website di Perumda Giri Tirta Gresik Abdillah, Hanif; Sutaji, Deni; Ilmi, Rifqy Rosyidah
Jurnal Inovatif Vol. 3 No. 3 (2024): Desember 2024
Publisher : Jurnal Inovatif

Show Abstract | Download Original | Original Source | Check in Google Scholar

Studi ini bertujuan untuk membangun sistem manajemen surat masuk dan keluar yang dapat diakses melalui internet untuk Perumda Giri Tirta Gresik, dengan tujuan meningkatkan efisiensi serta kemudahan akses dalam pengelolaan surat. Penelitian ini menggunakan metode Waterfall untuk melakukan identifikasi kebutuhan, perancangan sistem, penerapan, pengujian, dan pemeliharaan. Hasilnya menunjukkan bahwa sistem yang baru dibangun dapat mengurangi kesalahan administrasi., memperkuat kolaborasi antar divisi, dan memudahkan pengguna dalam mengelola surat secara real-time. Semua fungsi aplikasi beroperasi sesuai dengan spesifikasi yang diharapkan, seperti yang ditunjukkan oleh pengujian sistem dengan metode black-box. Kesimpulan dari penelitian ini adalah bahwa sistem yang dikembangkan mampu memenuhi kebutuhan operasional Perumda Giri Tirta dengan efektif dan berkelanjutan, serta memberikan kontribusi positif terhadap pengelolaan administrasi surat di instansi tersebut.

Rancang Bangun Sistem Informasi Pengaduan Masyarakat Berbasis Web di Desa Gapurosukolilo Rifki, Achmad; Sutaji, Deni
Jurnal Multimedia dan Teknologi Informasi (Jatilima) Vol. 6 No. 03 (2024): Jatilima : Jurnal Multimedia Dan Teknologi Informasi
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jatilima.v6i03.834

Desa Gapurosukolilo menghadapi kendala dalam pengelolaan pengaduan masyarakat yang masih dilakukan secara manual. Hal ini menyebabkan lambatnya proses penanganan pengaduan, kurangnya efisiensi, serta minimnya transparansi dalam penyelesaian keluhan warga. Untuk mengatasi permasalahan tersebut, penelitian ini bertujuan untuk merancang dan membangun Sistem Informasi Pengaduan Masyarakat berbasis web yang dapat mempermudah masyarakat dalam menyampaikan pengaduan, memantau statusnya, dan memperoleh respon dari pemerintah desa secara lebih cepat dan terstruktur. Pengembangan sistem dilakukan menggunakan metode Waterfall, yang meliputi tahapan analisis kebutuhan, desain sistem, implementasi, pengujian, dan pemeliharaan. Sistem ini dibangun menggunakan bahasa pemrograman PHP dan basis data MySQL. Fitur-fitur utama yang disediakan meliputi pembuatan pengaduan oleh masyarakat, pengelolaan pengaduan oleh petugas, pelacakan status pengaduan, serta pencetakan laporan oleh admin. Pengujian sistem dilakukan dengan metode BlackBox, yang berfokus pada pengujian fungsionalitas fitur-fitur utama untuk memastikan bahwa sistem beroperasi sesuai dengan spesifikasi yang telah ditentukan. Hasil pengujian menunjukkan bahwa sistem ini mampu menangani pengaduan masyarakat secara efektif dan efisien, di mana pengguna dapat mengajukan pengaduan, melihat respon dari petugas, dan melacak perkembangan pengaduan dengan mudah. Selain itu, sistem juga memfasilitasi petugas dan admin dalam mengelola serta merespon pengaduan secara lebih terstruktur. Dengan adanya sistem ini, diharapkan pengelolaan pengaduan di Desa Gapurosukolilo menjadi lebih cepat, transparan, dan akuntabel, sehingga dapat meningkatkan kepercayaan masyarakat terhadap pelayanan publik yang diberikan oleh pemerintah desa.

Perancangan Dan Implementasi Sistem Inventaris Aset Kantor Berbasis Web Dinas Kominfo Lamongan Mubarok, Bina Kharik Ervin; Sutaji, Deni
Bianglala Informatika Vol 13, No 1 (2025): Bianglala Informatika 2025
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/bi.v13i1.25238

Penggunaan sistem informasi dalam berbagai instansi saat ini menjadi kebutuhan penting untuk meningkatkan akurasi, relevansi, dan efisiensi dalam pengelolaan data. Salah satu aspek yang memerlukan sistem informasi yang terstruktur adalah inventarisasi aset kantor, yang berfungsi untuk mencatat, mengelola, serta melaporkan aset yang dimiliki suatu instansi. Pada Dinas Komunikasi dan Informatika (Kominfo) Kabupaten Lamongan, pengelolaan aset kantor masih dilakukan secara manual, yang menyebabkan berbagai kendala seperti kesulitan dalam pencarian data aset, kurangnya kelengkapan informasi, dan keterlambatan pelaporan. Oleh karena itu, penelitian ini bertujuan untuk merancang dan mengimplementasikan Sistem Aset Kantor Berbasis Web guna meningkatkan efisiensi dan akurasi dalam pengelolaan aset. Dengan adanya sistem ini, pencatatan dan pemantauan aset dapat dilakukan secara lebih efektif, sehingga membantu instansi dalam pengambilan keputusan yang lebih tepat berdasarkan data yang terorganisir dengan baik.

Integrasi Sistem Presensi Pegawai Berbasis Web dengan Geolokasi dan Swafoto di PT Gresik Migas Muhammad Romadhon; Deni Sutaji
Repeater : Publikasi Teknik Informatika dan Jaringan Vol. 3 No. 2 (2025): Repeater : Publikasi Teknik Informatika dan Jaringan
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/repeater.v3i2.402

The manual attendance system using paper at work locations other than offices at PT Gresik Migas creates challenges in the effectiveness and efficiency of employee attendance records. This study implements a web-based attendance system that integrates geolocation and selfie features to improve the accuracy and efficiency of attendance recording. The system was developed using native PHP for backend, jQuery for frontend, MySQL as database, and Leaflet JS for geolocation implementation. Implementation results show the system was successfully implemented in 5 different locations with a 50-meter validation radius and used by 40 employees. This system enables real-time attendance monitoring through an admin dashboard and produces more efficient attendance records compared to the previous manual system.

Perancangan Company Profile Berbasis Web Untuk Roemahkita Modern Retail Menggunakan Framework Codeigniter Nurdianto, Afrinda; Sutaji, Deni
Jurnal Sosial Teknologi Vol. 5 No. 7 (2025): Jurnal Sosial dan Teknologi
Publisher : CV. Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/jurnalsostech.v5i7.32334

RoemahKita Modern Retail is a retail business that requires a digital promotional medium to enhance branding and expand customer reach. This project aims to design an informative, interactive, and responsive company profile website using the CodeIgniter framework. CodeIgniter was chosen due to its ease of development, organized structure, and robust security features. The system development methodology includes needs analysis, design, implementation, and testing. The outcome of this project is a company profile website that displays company information, products, galleries, and contact details. The website is designed with a user-friendly interface and is optimized for accessibility across various devices. The use of CodeIgniter enables efficient development with its MVC (Model-View-Controller) architecture, which separates business logic and presentation layers. This website is expected to serve as an effective promotional tool for RoemahKita Modern Retail in introducing its business to potential customers. For future development, additional features such as e-commerce integration, SEO optimization, and enhanced system security can be implemented.

Implementasi YOLOv8 dan Local Binary Pattern Histogram (LBPH) untuk Simulasi Presensi Muhammad Romadhon; Deni Sutaji
Router : Jurnal Teknik Informatika dan Terapan Vol. 3 No. 3 (2025): Router : Jurnal Teknik Informatika dan Terapan
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/router.v3i3.622

Attendance is an essential activity in both educational institutions and companies, serving as an indicator of discipline, presence, and individual responsibility. Conventional attendance systems that still rely on manual journals often face several problems, such as vulnerability to manipulation, data loss, and physical damage. Meanwhile, modern methods such as fingerprint, QR code, RFID, and GPS are not entirely ideal since each has its own limitations in terms of cost, accuracy, user convenience, and potential misuse. For instance, fingerprint systems raise hygiene concerns due to shared use, while QR code and GPS methods are prone to fraud and location spoofing. To address these challenges, this study proposes a face-based attendance simulation system by integrating the YOLOv8 algorithm for face detection and Local Binary Pattern Histogram (LBPH) for face recognition. YOLOv8 was chosen for its ability to detect faces in real time with high speed and accuracy, while LBPH is employed for face recognition due to its robustness in handling variations in facial features and its relatively low computational requirements. This makes the system efficient even when implemented on medium-specification devices. The system was tested on 25 participants with a total of 250 attendance attempts. Based on the confusion matrix analysis, the system achieved outstanding performance with 98.4% accuracy, 98.4% precision, 100% recall, and a 99.2% F1-score. Furthermore, the system automatically recorded attendance dates and times with an average latency of 69.185 ms, proving its capability to operate quickly and reliably in real-world scenarios. Nevertheless, several limitations were observed, such as decreased accuracy when the face moved too quickly during image capture, as well as potential performance degradation under extreme lighting conditions. Despite these challenges, the proposed system demonstrates excellent performance and offers a promising solution for efficient, hygienic, and fraud-resistant attendance management applicable to both educational and professional environments.

The Identification of Covid-19 Fake News Factors on Social Media in Indonesia Chotijah, Umi; Husenti , Nadya; Sutaji, Deni; Mahditya Indra Pratama, Angga
Indonesian Journal of Information Systems Vol. 6 No. 1 (2023): August 2023
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/ijis.v6i1.6613

Social media is a protocol for people’s interaction and disseminating new ideas. The spread of fake information can occur on social media because there is no control and verification from the legal account. During the COVID-19 corona virus outbreak, the government issued a self-isolation policy. However, people use social media to find information about COVID-19 and spread news about COVID-19 greedily, especially in Indonesia. Therefore, this study explores the factors influencing the spread of fake news related to COVID-19. The sampling used in this study was non-random/non-probability sampling with the Convenience Sampling technique, including two hundred and twenty-two respondences from several regions in Indonesia. These phenomenons are studied using the Uses and Gratification framework by eliminating entertainment variables, adding altruism motivation, and adding moderating variables for demographic factors of individual psychological well-being, including age, education, income, and gender. Data were analyzed using Smart Partial Least Squares (PLS) to determine the effect of five variables. The analysis results show that all the variables, e.g., altruism, socialization, time elapsed, information sharing, and information seeking, as well as moderating variables and demographic factors of individual psychological well-being have no positive and significant effect on the spread of fake COVID-19—news on social media in Indonesia.

Title

Found 22 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 22 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 22 Documents
Search