Article Per Year (5 Year)
p-Index From 2021 - 2026
2.811
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi dan Ilmu Komputer Journal of Information Technology and Computer Science JIEET (Journal of Information Engineering and Educational Technology) Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Indonesian Journal of Electrical Engineering and Computer Science Indonesian Journal of Engineering and Technology (INAJET) Journal of Informatics and Computer Science (JINACS) Jurnal Ilmiah Edutic : Pendidikan dan Informatika J-Icon : Jurnal Komputer dan Informatika Repeater: Publikasi Teknik Informatika dan Jaringan JURNAL LINTAS KARSA
Ervin Yohannes
Universitas Negeri Surabaya
Arts Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Mechanical Engineering Social Sciences

Published : 24 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 24 Documents
Search

 1   2   3 
Fatigue Detection Based on Facial Expressions Using ResNet50 with Grad-CAM Visualization Wike Septiana Vidya Utami; Ervin Yohannes
Journal of Informatics and Computer Science (JINACS) Article In Press
Publisher : Universitas Negeri Surabaya

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

Abstract

Abstract—Fatigue is a condition that can affect a person's performance and concentration, making an automatic system necessary for its rapid and accurate detection. This study applies a Convolutional Neural Network (CNN) architecture based on the pretrained ResNet50 model to classify facial images into two categories, fatigued and non-fatigued, using the Driver Drowsiness Dataset, which consists of approximately 41,700 images. The model was trained and validated using five data-split scenarios, namely 50:50, 60:40, 70:30, 80:20, and 90:10, with varying learning rates, batch sizes, and numbers of epochs. Performance was evaluated using accuracy, precision, recall, and F1-score metrics. The results show that the best performance of the ResNet50 model was obtained with a 60:40 data split, a learning rate of 0.0001, a batch size of 16, and 30 epochs, achieving an accuracy of 99.22%, a precision of 99.67%, a recall of 99.86%, and an F1-score of 99.26%. Visual analysis using Grad-CAM showed that the model focused attention on the eyes, eyelids, cheeks, and forehead during the classification decision, improving the interpretability of the predictions. The ResNet50 model was also implemented in a camera-based system to provide real-time fatigue predictions. These results indicate that ResNet50 is effective and has the potential to be applied in a practical and efficient facial-image-based fatigue detection system. Keywords—ResNet50, Convolutional Neural Network (CNN), Fatigue Detection, Grad-CAM, Facial Image Classification.
Evaluation Of The Buku Pokok Pemakaman Application In Supporting Smart Governance Using The System Usability Scale (SUS) (A Case Study At The Department Of Population And Civil Registration Of Magetan Regency) Yulinda Seven Ningtyas; Ervin Yohannes
Journal of Informatics and Computer Science (JINACS) Article In Press
Publisher : Universitas Negeri Surabaya

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

Abstract

Abstract—Buku Pokok Pemakaman Application is a web-based system developed by the Population and Civil Registration Office of Magetan Regency to support the management of death data. This study aims to evaluate the usability of the application using the System Usability Scale (SUS) method and to provide improvement recommendations based on the evaluation results. The study involved 112 respondents, who are village and sub-district (desa and kelurahan) operators acting as active users of the application. Data were collected through task-scenario testing to measure effectiveness and efficiency, distribution of the SUS questionnaire to measure user satisfaction, and interviews to identify problems in using the application. The data were analyzed using the effectiveness, efficiency, and System Usability Scale (SUS) metrics. The results show an effectiveness level of 98.98%, categorized as very effective. An efficiency value of 0.121 goals/sec indicates that users were able to complete tasks well. Meanwhile, the SUS evaluation obtained an average score of 68.59, which falls into Grade C, with a High Marginal acceptance level and an OK adjective rating. These results indicate that the application has met the aspects of effectiveness and efficiency but still requires improvement to increase user satisfaction. Based on the evaluation results, this study produced five interface improvement recommendations, realized in the form of mockups referring to the Google Material Design guidelines. Kata Kunci— usability, System Usability Scale (SUS), buku pokok pemakaman, smart governance, information system evaluation.
Machine Learning-Based Land Cover Change Analysis in Surabaya Using Google Earth Engine Devika Setyaningrum; Ervin Yohannes
Journal of Informatics and Computer Science (JINACS) Article In Press
Publisher : Universitas Negeri Surabaya

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

Abstract

Abstrak—Penyebaran hoaks di kalangan pelajar Sekolah Menengah Atas (SMA) terus meningkat seiring tingginya intensitas penggunaan media digital yang tidak diimbangi kemampuan literasi digital memadai, sementara metode edukasi konvensional dinilai kurang mampu melibatkan generasi muda secara aktif. Penelitian ini bertujuan mengembangkan aplikasi edukasi mobile bergamifikasi bernama “Detektif Hoaks” yang mengintegrasikan kerangka evaluasi informasi CRAAP (Currency, Relevance, Authority, Accuracy, Purpose) guna meningkatkan kewaspadaan siswa SMA terhadap hoaks. Aplikasi dikembangkan menggunakan model ADDIE (Analysis, Design, Development, Implementation, Evaluation) dengan Flutter sebagai kerangka kerja front-end dan Supabase sebagai backend. Mekanisme gamifikasi yang diterapkan meliputi tiga level berjenjang, bank soal dinamis, sistem poin dan bintang, serta fitur ulasan jawaban. Pengujian fungsionalitas melalui black box testing menunjukkan tingkat keberhasilan 100% pada 17 skenario uji. Validasi ahli materi memperoleh persentase kelayakan 98,29% dan ahli media 96,7%, keduanya berkategori “Sangat Layak”. Uji coba kepada 24 siswa SMA menghasilkan tingkat penerimaan pengguna sebesar 98,83%, juga berkategori “Sangat Layak”, dengan 90,48% responden menyatakan merasa lebih mampu mengidentifikasi hoaks setelah menggunakan aplikasi. Temuan ini menunjukkan bahwa integrasi kerangka CRAAP ke dalam mekanika gamifikasi berbasis mobile merupakan pendekatan yang valid dan diterima baik sebagai media literasi digital preventif bagi siswa SMA. Kata Kunci—Gamifikasi, Literasi Digital, Hoaks, Kerangka CRAAP, Model ADDIE, Aplikasi Mobile, Flutter.
Detection of Potholes and Speed Bumps Using One-Stage and Two-Stage Detectors Sinta Ayu Dwi Ardita; Ervin Yohannes
Journal of Informatics and Computer Science (JINACS) Article In Press(1)
Publisher : Universitas Negeri Surabaya

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

Abstract

Abstract – Road damage and road-control objects, particularly potholes and speed bumps, can affect driving comfort and traffic safety. Conventional inspection depends on direct observation and can require substantial time and human resources. This study evaluates object detection approaches based on one-stage and two-stage detectors for automatically identifying potholes and speed bumps. YOLOv11 and Single Shot Detector (SSD) are evaluated as one-stage detectors, while Faster R-CNN is evaluated using ResNet50, ResNet101, MobileNetV2, and MobileNetV3 backbones. A conventional image-processing approach is also included as a baseline. The dataset consists of 790 images containing two object classes, pothole and speedbump, and is divided into training, validation, and testing subsets. Evaluation uses mAP@0.5:0.95, mAP@0.5, mAP@0.75, recall, confusion matrix, and qualitative testing on images and video. The results show that YOLOv11 achieves the highest overall performance with mAP@0.5:0.95 of 49.30%, mAP@0.5 of 85.90%, mAP@0.75 of 47.40%, and recall of 84.30%. Among Faster R-CNN backbones, MobileNetV3 provides the best performance with mAP@0.5:0.95 of 45.37%, mAP@0.5 of 83.74%, mAP@0.75 of 40.85%, and recall of 53.34%. The conventional image-processing approach obtains substantially lower results. Overall, YOLOv11 provides the best balance of detection performance and real-time capability for the dataset used in this study. Keywords – pothole, speedbump, object detection, YOLOv11, SSD, Faster R-CNN, deep learning.
Co-Authors Ahmad Fikri Hanafi Asyrofa Rahmi, Asyrofa Avirmed Enkhbat Devika Setyaningrum Esti, Esti Yogiyanti Febriansyah, Aldin Liswardana Gostafi Arifin Muhammad Dzaki Salman Muhammad Farrell Saifulloh Mulyono, Alfito Nafisah, Nurun Paramitha Nerisafitra Putri, Windy Chikita Cornia Ramadhany, Sinta Dhea Rayyan Nur Fauzan Reza Pahlevi Ricky Eka Putra Ronggo Alit Shih, Timothy K. Sinta Ayu Dwi Ardita Titis Dila Fajari Utaminingrum, Fitri Wayan Firdaus Mahmudy Wike Septiana Vidya Utami Windy Chikita Cornia Putri Wiyli Yustanti Wiyli Yustanti Yoyok Prastyo Yulinda Seven Ningtyas Yuni Yamasari