Comparison of Accuracy Rate for Soybean Type Using Backpropagation

Article Sidebar

PDF (Indonesian) Untitled (Indonesian)
Published: Oct 31, 2021
DOI: https://doi.org/10.56873/jpkm.v6i2.2910
Dimensions
Altmetrics
Statistics
Read Counter : 279
Download : 257
Crossmark/ Data Version

Main Article Content

Novan Wijaya
Universitas Multi Data Palembang

Abstract

Abstract – Soybean is a pods plants that were use a base component to make food such as tempe and tofu. Soybean has a few kind of shapes, circle, circle and flat, oval, oval and flat. Soybean also has a few kinds which is white soybean, black soybean and green soybean (edamame). On this article the accuration level from recognation of those 3 kinds will be compared based on the portrait distance. There were three distance, 10 cm, 15 cm and 20 cm. Feature extraction that used is GLCM and recognation using backpropagation algorithm. The result after preprocessing, feature extraction with GLCM and recognation with backpropagation algorithm with the portrait distance of 10 cm accuration level is 100%, 15 cm accuration level is 99.07% and 20 cm accuration level is 77.22%

Keywords: Soybean, GLCM, Backpropagation

Article Details

Issue
Vol. 6 No. 2 (2021): October 2021
Section
Informatics
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

The proposed policy for journals that offer open access

Authors who publish with this journal agree to the following terms:

  1. Copyright on any article is retained by the author(s).
  2. Author grant the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work’s authorship and initial publication in this journal.
  3. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
  4. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
  5. The article and any associated published material is distributed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License