Comparison of algorithm Support Vector Machine and C4.5 for identification of pests and diseases in chili plants
Data from the Central Bureau of Statistics of the population working in the agricultural sector continued to decline from 39.22 million in 2013 to 38.97 million in 2014, the number dropped back to 37.75 million in 2015. According to the MIT G-Lab Team (global entrepreneurship program) concludes five...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2019
|
Subjects: | |
Online Access: | http://ur.aeu.edu.my/698/1/Comparison%20of%20algorithm%20Support%20Vector%20Machine_J._Phys.__Conf._Ser._1402_066104-2-10.pdf http://ur.aeu.edu.my/698/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my-aeu-eprints.698 |
---|---|
record_format |
eprints |
spelling |
my-aeu-eprints.6982020-03-27T06:49:42Z http://ur.aeu.edu.my/698/ Comparison of algorithm Support Vector Machine and C4.5 for identification of pests and diseases in chili plants M, Irfan N, Lukman A. A, Alfauzi J, Jumadi TA Engineering (General). Civil engineering (General) Data from the Central Bureau of Statistics of the population working in the agricultural sector continued to decline from 39.22 million in 2013 to 38.97 million in 2014, the number dropped back to 37.75 million in 2015. According to the MIT G-Lab Team (global entrepreneurship program) concludes five factors that make it difficult to raise agricultural productivity to compete in the domestic market, namely the low education of farmers in dealing with pests, the difficulty of access to finance for rural areas, lack of skills, lack of access to information and lack of application of agricultural technology. Chili plants are plants that are very susceptible to pests so BPS noted a decrease in chili production reaching 25%. Information about chili pests is collected so that it becomes a database that can be used to identify disease pests using the data mining method. The use of data mining algorithms is expected to help in the identification of pests and diseases in chili plants. In this study comparing the performance classification techniques of Support Vector Machine (SVM) and C4.5 algorithms. The attributes used consist of Leaves, Stems, and Fruits. By using each training data and testing data as many as 30 data. The results of the study were conducted, based on the accuracy of SVM, which was 82.33% and C4.5 89.29 %%. The final result of this study was that the accuracy of the C4.5 method was better. 2019 Conference or Workshop Item PeerReviewed text en http://ur.aeu.edu.my/698/1/Comparison%20of%20algorithm%20Support%20Vector%20Machine_J._Phys.__Conf._Ser._1402_066104-2-10.pdf M, Irfan and N, Lukman and A. A, Alfauzi and J, Jumadi (2019) Comparison of algorithm Support Vector Machine and C4.5 for identification of pests and diseases in chili plants. In: 4th Annual Applied Science and Engineering Conference. |
institution |
Asia e University |
building |
AEU Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Asia e University |
content_source |
AEU University Repository |
url_provider |
http://ur.aeu.edu.my/ |
language |
English |
topic |
TA Engineering (General). Civil engineering (General) |
spellingShingle |
TA Engineering (General). Civil engineering (General) M, Irfan N, Lukman A. A, Alfauzi J, Jumadi Comparison of algorithm Support Vector Machine and C4.5 for identification of pests and diseases in chili plants |
description |
Data from the Central Bureau of Statistics of the population working in the agricultural sector continued to decline from 39.22 million in 2013 to 38.97 million in 2014, the number dropped back to 37.75 million in 2015. According to the MIT G-Lab Team (global entrepreneurship program) concludes five factors that make it difficult to raise agricultural productivity to compete in the domestic market, namely the low education of farmers in dealing with pests, the difficulty of access to finance for rural areas, lack of skills, lack of access to information and lack of application of agricultural technology. Chili plants are plants that are very susceptible to pests so BPS noted a decrease in chili production reaching 25%. Information about chili pests is collected so that it becomes a database that can be used to identify disease pests using the data mining method. The use of data mining algorithms is expected to help in the identification of pests and diseases in chili plants. In this study comparing the performance classification techniques of Support Vector Machine (SVM) and C4.5 algorithms. The attributes used consist of Leaves, Stems, and Fruits. By using each training data and testing data as many as 30 data. The results of the study were conducted, based on the accuracy of SVM, which was 82.33% and C4.5 89.29 %%. The final result of this study was that the accuracy of the C4.5 method was better. |
format |
Conference or Workshop Item |
author |
M, Irfan N, Lukman A. A, Alfauzi J, Jumadi |
author_facet |
M, Irfan N, Lukman A. A, Alfauzi J, Jumadi |
author_sort |
M, Irfan |
title |
Comparison of algorithm Support Vector Machine and C4.5 for identification of pests and diseases in chili plants |
title_short |
Comparison of algorithm Support Vector Machine and C4.5 for identification of pests and diseases in chili plants |
title_full |
Comparison of algorithm Support Vector Machine and C4.5 for identification of pests and diseases in chili plants |
title_fullStr |
Comparison of algorithm Support Vector Machine and C4.5 for identification of pests and diseases in chili plants |
title_full_unstemmed |
Comparison of algorithm Support Vector Machine and C4.5 for identification of pests and diseases in chili plants |
title_sort |
comparison of algorithm support vector machine and c4.5 for identification of pests and diseases in chili plants |
publishDate |
2019 |
url |
http://ur.aeu.edu.my/698/1/Comparison%20of%20algorithm%20Support%20Vector%20Machine_J._Phys.__Conf._Ser._1402_066104-2-10.pdf http://ur.aeu.edu.my/698/ |
_version_ |
1662760041911943168 |
score |
13.18916 |