Cover Image

Detecting beef and pork adulteration using principal component analysis

Principal Component Analysis (PCA) is proposed for the automatic detection of beef and pork adulteration images in this paper. The method is used for the feature extraction phase. Two database resources are used in the research. They are Kaggle database to obtain the beef and pork images and previou...

Full description

Saved in:
Bibliographic Details
Main Authors: Siti, Nur Avivah, Ku Muhammad Naim, Ku Khalif, Noryanti, Muhammad
Format: Conference or Workshop Item
Language:English
Published: 2022
Subjects:
Q Science (General)
QA Mathematics
Online Access:http://umpir.ump.edu.my/id/eprint/37031/1/Detecting%20beef%20and%20pork%20adulteration%20using%20principal%20component%20analysis.pdf
http://umpir.ump.edu.my/id/eprint/37031/
https://ncon-pgr.ump.edu.my/index.php/en/?option=com_fileman&view=file&routed=1&name=E-BOOK%20NCON%202022%20.pdf&folder=E-BOOK%20NCON%202022&container=fileman-files
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.ump.umpir.37031
record_format eprints
spelling my.ump.umpir.370312023-03-14T08:46:45Z http://umpir.ump.edu.my/id/eprint/37031/ Detecting beef and pork adulteration using principal component analysis Siti, Nur Avivah Ku Muhammad Naim, Ku Khalif Noryanti, Muhammad Q Science (General) QA Mathematics Principal Component Analysis (PCA) is proposed for the automatic detection of beef and pork adulteration images in this paper. The method is used for the feature extraction phase. Two database resources are used in the research. They are Kaggle database to obtain the beef and pork images and previous research by L. Handayani et al. to get the adulteration images. The images are divided into two processes that are training and testing. For the training process, this experiment was conducted on 100 images of beef, 100 images of pork, and 50 images of adulteration. Whereas for testing, this study used 25 images for each category. The proposed research requires three phases to obtain the detection result, i.e., the first phase is resizing images to 300x300 pixels for both the training and testing dataset. The second is implementing the proposed method to obtain the featured images. The last is the detection process of testing images using Mean Squared Error (MSE). The results of this research show that the PCA method is very effective for detecting beef and pork adulteration, reaching average accuracy values up to 96%. 2022-11-15 Conference or Workshop Item PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/37031/1/Detecting%20beef%20and%20pork%20adulteration%20using%20principal%20component%20analysis.pdf Siti, Nur Avivah and Ku Muhammad Naim, Ku Khalif and Noryanti, Muhammad (2022) Detecting beef and pork adulteration using principal component analysis. In: The 6th National Conference for Postgraduate Research (NCON-PGR 2022), 15 November 2022 , Virtual Conference, Universiti Malaysia Pahang, Malaysia. p. 147.. https://ncon-pgr.ump.edu.my/index.php/en/?option=com_fileman&view=file&routed=1&name=E-BOOK%20NCON%202022%20.pdf&folder=E-BOOK%20NCON%202022&container=fileman-files
institution Universiti Malaysia Pahang
building UMP Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Pahang
content_source UMP Institutional Repository
url_provider http://umpir.ump.edu.my/
language English
topic Q Science (General)
QA Mathematics
spellingShingle Q Science (General)
QA Mathematics
Siti, Nur Avivah
Ku Muhammad Naim, Ku Khalif
Noryanti, Muhammad
Detecting beef and pork adulteration using principal component analysis
description Principal Component Analysis (PCA) is proposed for the automatic detection of beef and pork adulteration images in this paper. The method is used for the feature extraction phase. Two database resources are used in the research. They are Kaggle database to obtain the beef and pork images and previous research by L. Handayani et al. to get the adulteration images. The images are divided into two processes that are training and testing. For the training process, this experiment was conducted on 100 images of beef, 100 images of pork, and 50 images of adulteration. Whereas for testing, this study used 25 images for each category. The proposed research requires three phases to obtain the detection result, i.e., the first phase is resizing images to 300x300 pixels for both the training and testing dataset. The second is implementing the proposed method to obtain the featured images. The last is the detection process of testing images using Mean Squared Error (MSE). The results of this research show that the PCA method is very effective for detecting beef and pork adulteration, reaching average accuracy values up to 96%.
format Conference or Workshop Item
author Siti, Nur Avivah
Ku Muhammad Naim, Ku Khalif
Noryanti, Muhammad
author_facet Siti, Nur Avivah
Ku Muhammad Naim, Ku Khalif
Noryanti, Muhammad
author_sort Siti, Nur Avivah
title Detecting beef and pork adulteration using principal component analysis
title_short Detecting beef and pork adulteration using principal component analysis
title_full Detecting beef and pork adulteration using principal component analysis
title_fullStr Detecting beef and pork adulteration using principal component analysis
title_full_unstemmed Detecting beef and pork adulteration using principal component analysis
title_sort detecting beef and pork adulteration using principal component analysis
publishDate 2022
url http://umpir.ump.edu.my/id/eprint/37031/1/Detecting%20beef%20and%20pork%20adulteration%20using%20principal%20component%20analysis.pdf
http://umpir.ump.edu.my/id/eprint/37031/
https://ncon-pgr.ump.edu.my/index.php/en/?option=com_fileman&view=file&routed=1&name=E-BOOK%20NCON%202022%20.pdf&folder=E-BOOK%20NCON%202022&container=fileman-files
_version_ 1761616604204892160
score 13.211869

Similar Items