IMPLEMENTASI METODE BACKPROPAGATION DALAM KLASTERISASI OBJEK

Authors

  • Diaz D Santika Jurusan Teknik Informatika, Fakultas Ilmu Komputer, Universitas Bina Nusantara, Jl. K.H. Syahdan No. 9, Kemanggisan/Palmerah, Jakarta Barat 11480
  • Betsy Susanti Jurusan Teknik Informatika, Fakultas Ilmu Komputer, Universitas Bina Nusantara, Jl. K.H. Syahdan No. 9, Kemanggisan/Palmerah, Jakarta Barat 11480
  • Willy Anderson Jurusan Teknik Informatika, Fakultas Ilmu Komputer, Universitas Bina Nusantara, Jl. K.H. Syahdan No. 9, Kemanggisan/Palmerah, Jakarta Barat 11480
  • Kanisius Wongso Jurusan Teknik Informatika, Fakultas Ilmu Komputer, Universitas Bina Nusantara, Jl. K.H. Syahdan No. 9, Kemanggisan/Palmerah, Jakarta Barat 11480

DOI:

https://doi.org/10.21512/commit.v1i1.465

Abstract

Aim of the research was to prove that backpropagation method could be implemented for image recognition
while doing object classification. Observational method done was to do library research by reading and searching for
information from various sources, then conduct analysis upon data, and last, design the application from analysis
results. From the evaluation that has been done, the result for accuration and speed are high enough (above 95%). After
analyzing evaluation result, it is concluded that backpropagation method could be implemented for object classification.
Dimensions

Plum Analytics

Downloads

Published

2007-05-31

Issue

Vol. 1 No. 1 (2007): CommIT Journal

Section

Articles

License

Authors who publish with this journal agree to the following terms:
a. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License - Share Alike that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.

b. 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 acknowledgment of its initial publication in this journal.

c. 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.

 

USER RIGHTS

All articles published Open Access will be immediately and permanently free for everyone to read and download.  We are continuously working with our author communities to select the best choice of license options, currently being defined for this journal as follows: Creative Commons Attribution-Share Alike (CC BY-SA)

Abstract 398  .
PDF downloaded 731  .