Article Per Year (5 Year)
p-Index From 2019 - 2024
0.92
P-Index
This Author published in this journals
All Journal Jurnal Pendidikan Teknologi dan Kejuruan Jupiter Jurnal Sains dan Teknologi Jurnal Matematika Sains dan Teknologi Jurnal Pendidikan Terbuka Dan Jarak Jauh Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI) International Journal of Global Operations Research
Dwi Astuti Aprijani
Universitas Terbuka
Agriculture, Biological Sciences & Forestry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Library & Information Science Mathematics Other

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Jurnal Matematika Sains dan Teknologi

 1 
APLIKASI JARINGAN SYARAF TIRUAN UNTUK MENGENALI TULISAN TANGAN HURUF A, B, C, DAN D PADA JAWABAN SOAL PILIHAN GANDA (Studi Eksplorasi Pengembangan Pengolahan Lembar Jawaban Ujian Soal Pilihan Ganda Di Universitas Terbuka) Dwi Astuti Aprijani; Unggul Utan Sufandi
Jurnal Matematika Sains dan Teknologi Vol. 12 No. 1 (2011)
Publisher : LPPM Universitas Terbuka

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

Abstract

Artificial Neural Network (ANN) can be applied to recognice pattern, particularly at the stage of data classification. This study used a multilayer perceptron backpropagation ANN, an unsupervised learning algorithm, to recognize the pattern of uppercase handwriting on the answer sheet of multiple-choice exams. The application of this network involves mapping a set of input against a reference set of outputs. In this research, ANN was trained using 8000 handwritten uppercase characters (A, B, C, and D) consisting of 6000 training data characters (1500 characters for each letter) and 2000 testing data characters (500 characters for each letter). The result showed that for the most optimal performance, the architecture and network parameters were 10 neurons in hidden layer, learning rate of 0.1 and 3000 iteration times. The accuracies of the result using the optimal network architecture and parameters were 90.28% for training data and 87.35% for testing data.
Co-Authors Adhi Susilo Andri Suryadi Bagus Arif Wicaksono Denisha Trihapningsari Dian Nurdiana Laksono Trisnantoro Mochamad Priono Paken Pandiangan Sri Kurniati Unggul Utan Sufandi