Article Per Year (5 Year)
p-Index From 2020 - 2025
2.501
P-Index
This Author published in this journals
All Journal Bianglala Informatika : Jurnal Komputer dan Informatika Akademi Bina Sarana Informatika Yogyakarta INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi Jurnal Sisfokom (Sistem Informasi dan Komputer) RESEARCH : Computer, Information System & Technology Management Buletin Ilmiah Sarjana Teknik Elektro Generation Journal Indonesian Journal of Networking and Security - IJNS SPEED - Sentra Penelitian Engineering dan Edukasi Kontribusi: Jurnal Penelitian dan Pengabdian Kepada Masyarakat Joutica : Journal of Informatic Unisla Nusantara of Engineering (NOE) Prosiding SEMNAS INOTEK (Seminar Nasional Inovasi Teknologi)
Made Ayu Dusea Widyadara - Universitas Nusantara Kediri, Made Ayu Dusea Widyadara
Teknik Informatika, Fakultas Teknik, Universitas Nusantara PGRI Kediri
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Energy Engineering Health Professions Industrial & Manufacturing Engineering Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Mechanical Engineering Transportation

Published : 22 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 22 Documents
Search

 1   2   3 
A Generalized Deep Learning Approach for Multi Braille Character (MBC) Recognition Widyadara, Made Ayu Dusea; Handayani, Anik Nur; Herwanto, Heru Wahyu; Yu, Tony
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 3 (2025): September
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i3.13891

Abstract

Automated visual recognition of Multi Braille Characters (MBC) poses significant challenges for assistive reading technologies for the visually impaired. The intricate dot configurations and compact layouts of Braille complicate MBC classification. This study introduces a deep learning approach utilizing Convolutional Neural Networks (CNN) and compares four leading architectures: ResNet-50, ResNet-101, MobileNetV2, and VGG-16. A dataset comprising 105 MBC classes was developed from printed Braille materials and underwent preprocessing that included image cropping, brightness enhancement, character position labeling, and resizing to 89×89 pixels. A 70:20:10 data partitioning strategy was applied for training and evaluation, with variations in batch sizes (8–128) and epochs (50–500). The results demonstrate that ResNet-101 achieved superior performance, attaining an accuracy of 91.46%, an F1-score of 89.48%, and a minimum error rate of 8.5%. ResNet-50 and MobileNetV2 performed competitively under specific conditions, whereas VGG-16 consistently exhibited lower accuracy and training stability. Standard deviation assessments corroborated the stability of residual architectures throughout the training process. These results endorse ResNet-101 as the most effective architecture for Multi Braille Character classification, highlighting its potential for incorporation into automated Braille reading systems, a tool for translating braille into text or sound for future needs.
Implementation and Evaluation of the K – Nearest Neighbors Algorithm in Badminton Movement Classification Adiba, Fera Hidayatul; Kasih, Patmi; Dara, Made Ayu Dusea Widya
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 14 No. 4 (2025): NOVEMBER
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v14i4.2441

Abstract

To meet the needs of automated sports analysys, this study will develop and evaluated a bandminton motion analysis system that uses the K-nearest Neighbors (KNN) algorithm. This system will detect netting, smash, and serve motions and assess whether the labels are correct and inccprrect. The system uses MediaPipe Pose to extrac keypoints from 3-5 second videos, with data normalized using StandartScaler. Evaluation result show an eccuracy of 0.8438 for netting, 0.8276 for smashes, and 0.7778 for serves. Keypoints extraction time ranges from 4.53 to 25.44 seconds, influaced by lighting conditions, while prediction time is efficient at 0.03-0.05 second. Although this system can be used for sport training, additional data and features are needed to improve performance in low-ligh conditions.
Co-Authors - Universitas Nusantara PGRI Kediri, Mochamad Bilal - Universitas Nusantara PGRI Kediri, Roni Heri Irawan Abraham Dimas Bayu Aji Adiba, Fera Hidayatul Agus Muji Santoso Ahmad Bagus Setiawan Alfiana Hidayati Angga Yuanisyak Anik Nur Handayani Anisa Fatimatul Firdhausi Bella Putri Damayanti Daniel Swanjaya Dini Haris Suryaningtias Dwi Lianawati Febri Nurcahyo Dwiyantoko Frans Rega Agista Hana Agustina Hanif Al Fatta - STMIK AMIKOM Yogyakarta Hari Setiawan Heru Wahyu Herwanto Intan Nur Farida Irma Setiawan Kusuma Islamiati Rachmah Julian Sahertian Moh. Febby Ulil Albab Moh. Zakariya Yahya Mohamad Marjuni Mohammad Ahsin Febrianto Mohammad Askar Dipa Perwira Muhamad Sholafudin Mukhammad Annafinurika Nia Talia Salsabela D.M. Oktafiyan Pratama, Yana Patmi Kasih Risa Helilintar Roni Heri Irawan Sari, Kartika Rahayu Tri Prasetyo Tutus Lusni Pratama Vingki Dewi Aristina Violyna Sofiananda Wahyu Efendy Yu, Tony Zidane Chesa Wardana