Home > Archive > 2017 > Volume 7 Number 5 (Oct. 2017) >
IJMLC 2017 Vol.7(5): 110-113 ISSN: 2010-3700
DOI: 10.18178/ijmlc.2017.7.5.630

Android Based Automated Scoring of Multiple-Choice Test

Hendra Tjahyadi,Yoga G. Budijono, Samuel Lukas, and Dion Krisnadi

Abstract—In this paper design and implementation of an Android based automated scoring of multiple-choice test is reported. This application is designed as a more affordable alternative for more popular solutions which usually composed of a software and Optical Mark Recognition Scanner. Two main parts are involved in the design process, namely the answer sheets design and the image processing procedure. Moreover, there are 4 main stages in the image processing procedure: (i) input taking stage, (ii) early processing stage, (iii) identifying stage, and (iv) evaluating stage. After those stages are implemented, tests are conducted to find the best distance and angle of the smart phone to the answer sheet in taking the answer sheet’s images and to evaluate the accuracy in identifying right answers and gives valid scoring. The experiment results show that the best distance and angle with 95% of identification success rate is between 20 to 50 centimetres with 45 to 90 degrees angle, and when the answer sheet’s image is correctly identified, the identification of valid scoring success rate is 100%.

Index Terms—Multiple-choice test, Android, image processing, automated scoring.

Hendra Tjahyadi is with Department of Computer System, Faculty of Computer Science, Universitas Pelita Harapan, Indonesia (e-mail: hendra.tjahyadi@uph.edu).
Yoga G. Budijono is with Bank Central Asia, Indonesia (e-mail:yoga.gb@live.com). Samuel Lukas and Dion Krisnadi are with Department of Information Technology, Faculty of Computer Science, Universitas Pelita Harapan, Indonesia (e-mail: samuel.lukas@uph.edu, dion.krisnadi@uph.edu).

[PDF]

Cite: Hendra Tjahyadi,Yoga G. Budijono, Samuel Lukas, and Dion Krisnadi, "Android Based Automated Scoring of Multiple-Choice Test," International Journal of Machine Learning and Computing vol. 7, no. 5, pp. 110-113, 2017.

General Information

  • ISSN: 2010-3700 (Online)
  • Abbreviated Title: Int. J. Mach. Learn. Comput.
  • Frequency: Bimonthly
  • DOI: 10.18178/IJMLC
  • Editor-in-Chief: Dr. Lin Huang
  • Executive Editor:  Ms. Cherry L. Chen
  • Abstracing/Indexing: Inspec (IET), Google Scholar, Crossref, ProQuest, Electronic Journals Library.
  • E-mail: ijmlc@ejournal.net


Article Metrics