Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering Journal of Information Technology and Computer Science (JOINTECS)
Widya Silfianti
Gunadarma University
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Library & Information Science Mathematics

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Accelerating Compression Time of the standard JPEG by Employing The Quantized YCbCr Color Space Algorithm Trini Saptariani; Sarifudin Madenda; Ernastuti Ernastuti; Widya Silfianti
International Journal of Electrical and Computer Engineering (IJECE) Vol 8, No 6: December 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (772.335 KB) | DOI: 10.11591/ijece.v8i6.pp4343-4351

Abstract

In this paper, we propose a quantized YCbCr color space (QYCbCr) technique which is employed in standard JPEG. The objective of this work is to accelerate computational time of the standard JPEG image compression algorithm. This is a development of the standard JPEG which is named QYCBCr algorithm. It merges two processes i.e., YCbCr color space conversion and Q quantization in which in the standar JPEG they were performed separately. The merger forms a new single integrated process of color conversion which is employed prior to DCT process by subsequently eliminating the quantization process. The equation formula of QYCbCr color coversion is built based on the chrominance and luminance properties of the human visual system which derived from quatization matrices. Experiment results performed on images of different sizes show that the computational running time of QYCbCr algorithm gives 4 up to 8 times faster than JPEG standard, and also provides higher compression ratio and better image quality.
Prediksi Gerakan secara Real-Time untuk Pengenalan Bahasa Isyarat menggunakan LSTM Vira Yolanda; Widya Silfianti
JOINTECS (Journal of Information Technology and Computer Science) Vol 8, No 3 (2023)
Publisher : Universitas Widyagama Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31328/jointecs.v8i3.4607

Abstract

Bahasa Isyarat merupakan bahasa yang digunakan untuk berkomunikasi khususnya bagi penyandang tunarungu dan tuna wicara agar dapat saling berkomunikasi dengan baik. Namun karena minimnya pendidikan di masyarakat, bahasa isyarat jarang digunakan, bahkan banyak yang tidak mengetahui bahasa isyarat. Maka diperlukan suatu sistem untuk mengenali bahasa isyarat agar lebih banyak orang yang memahami bahasa isyarat. Dalam penelitian ini, kami mengembangkan deteksi gerakan dinamis untuk pengenalan 6 kata dalam bahasa isyarat Indonesia (SIBI) dengan memanfaatkan perubahan koordinat secara real-time yang dideteksi menggunakan MediaPipe Holistic dan model klasifikasi LSTM Neural Network. Dari hasil pengujian yang telah dilakukan dapat disimpulkan bahwa hasil implementasi Sistem Pengenalan Bahasa Isyarat secara real-time dengan memanfaatkan perubahan koordinat menggunakan metode MediaPipe Holistic dan Long Short Term Memory (LSTM) diperoleh sebuah model dengan nilai akurasi 96%. Akurasi yang diperoleh sebesar 96% artinya model tersebut akurat dalam mengklasifikasikan kelas-kelas gerakan. Setiap kelas memiliki nilai presisi, recall, f1-score dan support yang sangat baik dengan rata-rata 96%.
Co-Authors Ernastuti Ernastuti Sarifudin Madenda Trini Saptariani Vira Yolanda