OPTIMIZING LANTANA CLASSIFICATION: HIGH-ACCURACY MODEL UTILIZING FEATURE EXTRACTION
As an invasive and poisonous plant, Lantana has become a pest in the agricultural world. Still, on the other hand, it becomes an ornamental plant with different positive potentials. Lantana flower datasets are not yet widely available for open image classification research, given that the research...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Informatics Department, Engineering Faculty
2023-12-01
|
Series: | Jurnal Ilmiah Kursor: Menuju Solusi Teknologi Informasi |
Subjects: | |
Online Access: | https://kursorjournal.org/index.php/kursor/article/view/347 |
_version_ | 1797392384515899392 |
---|---|
author | Adri Gabriel Sooai Sisilia Daeng Bakka Mau Yovinia Carmeneja Hoar Siki Donatus Joseph Manehat Shine Crossifixio Sianturi Alicia Herlin Mondolang |
author_facet | Adri Gabriel Sooai Sisilia Daeng Bakka Mau Yovinia Carmeneja Hoar Siki Donatus Joseph Manehat Shine Crossifixio Sianturi Alicia Herlin Mondolang |
author_sort | Adri Gabriel Sooai |
collection | DOAJ |
description |
As an invasive and poisonous plant, Lantana has become a pest in the agricultural world. Still, on the other hand, it becomes an ornamental plant with different positive potentials. Lantana flower datasets are not yet widely available for open image classification research, given that the research needs are still broad in remote sensing. This study aims to provide a model with classifier accuracy that outperforms similar studies and Lantana datasets for classification needs using several algorithms that can be run on small source computers. This study used five types of lantana colors, red, white, yellow, purple, and orange, as the primary dataset, which had 411 instances. VGG16 assisted feature extraction in preparing datasets for the data training using three classifiers: decision tree, AdaBoost, and k-NN. 2-fold cross-validation, 5-fold cross-validation, and a self-organizing map are used to help validate each process. The experiment to measure the classifier's performance resulted in a good figure of 99.8% accuracy for 2-fold cross-validation, 100% for 5-fold cross-validation, and a primary dataset of lantana interest that can be accessed freely on the IEEE Data port. This study outperformed other related studies in terms of classifier accuracy.
|
first_indexed | 2024-03-08T23:46:27Z |
format | Article |
id | doaj.art-3b8a902a974441dab74776b51e835afa |
institution | Directory Open Access Journal |
issn | 0216-0544 2301-6914 |
language | English |
last_indexed | 2024-03-08T23:46:27Z |
publishDate | 2023-12-01 |
publisher | Informatics Department, Engineering Faculty |
record_format | Article |
series | Jurnal Ilmiah Kursor: Menuju Solusi Teknologi Informasi |
spelling | doaj.art-3b8a902a974441dab74776b51e835afa2023-12-13T18:43:17ZengInformatics Department, Engineering FacultyJurnal Ilmiah Kursor: Menuju Solusi Teknologi Informasi0216-05442301-69142023-12-0112210.21107/kursor.v12i2.347OPTIMIZING LANTANA CLASSIFICATION: HIGH-ACCURACY MODEL UTILIZING FEATURE EXTRACTIONAdri Gabriel Sooai0Sisilia Daeng Bakka Mau1Yovinia Carmeneja Hoar Siki2Donatus Joseph Manehat3Shine Crossifixio Sianturi4Alicia Herlin Mondolang5Universitas Katolik Widya Mandira KupangUniversitas Katolik Widya Mandira KupangUniversitas Katolik Widya Mandira KupangUniversitas Katolik Widya Mandira KupangUniversitas Sanata Dharma YogyakartaUniversitas Negeri Malang As an invasive and poisonous plant, Lantana has become a pest in the agricultural world. Still, on the other hand, it becomes an ornamental plant with different positive potentials. Lantana flower datasets are not yet widely available for open image classification research, given that the research needs are still broad in remote sensing. This study aims to provide a model with classifier accuracy that outperforms similar studies and Lantana datasets for classification needs using several algorithms that can be run on small source computers. This study used five types of lantana colors, red, white, yellow, purple, and orange, as the primary dataset, which had 411 instances. VGG16 assisted feature extraction in preparing datasets for the data training using three classifiers: decision tree, AdaBoost, and k-NN. 2-fold cross-validation, 5-fold cross-validation, and a self-organizing map are used to help validate each process. The experiment to measure the classifier's performance resulted in a good figure of 99.8% accuracy for 2-fold cross-validation, 100% for 5-fold cross-validation, and a primary dataset of lantana interest that can be accessed freely on the IEEE Data port. This study outperformed other related studies in terms of classifier accuracy. https://kursorjournal.org/index.php/kursor/article/view/347Machine LearningclassificationFeature Extractionimage processinglantana |
spellingShingle | Adri Gabriel Sooai Sisilia Daeng Bakka Mau Yovinia Carmeneja Hoar Siki Donatus Joseph Manehat Shine Crossifixio Sianturi Alicia Herlin Mondolang OPTIMIZING LANTANA CLASSIFICATION: HIGH-ACCURACY MODEL UTILIZING FEATURE EXTRACTION Jurnal Ilmiah Kursor: Menuju Solusi Teknologi Informasi Machine Learning classification Feature Extraction image processing lantana |
title | OPTIMIZING LANTANA CLASSIFICATION: HIGH-ACCURACY MODEL UTILIZING FEATURE EXTRACTION |
title_full | OPTIMIZING LANTANA CLASSIFICATION: HIGH-ACCURACY MODEL UTILIZING FEATURE EXTRACTION |
title_fullStr | OPTIMIZING LANTANA CLASSIFICATION: HIGH-ACCURACY MODEL UTILIZING FEATURE EXTRACTION |
title_full_unstemmed | OPTIMIZING LANTANA CLASSIFICATION: HIGH-ACCURACY MODEL UTILIZING FEATURE EXTRACTION |
title_short | OPTIMIZING LANTANA CLASSIFICATION: HIGH-ACCURACY MODEL UTILIZING FEATURE EXTRACTION |
title_sort | optimizing lantana classification high accuracy model utilizing feature extraction |
topic | Machine Learning classification Feature Extraction image processing lantana |
url | https://kursorjournal.org/index.php/kursor/article/view/347 |
work_keys_str_mv | AT adrigabrielsooai optimizinglantanaclassificationhighaccuracymodelutilizingfeatureextraction AT sisiliadaengbakkamau optimizinglantanaclassificationhighaccuracymodelutilizingfeatureextraction AT yoviniacarmenejahoarsiki optimizinglantanaclassificationhighaccuracymodelutilizingfeatureextraction AT donatusjosephmanehat optimizinglantanaclassificationhighaccuracymodelutilizingfeatureextraction AT shinecrossifixiosianturi optimizinglantanaclassificationhighaccuracymodelutilizingfeatureextraction AT aliciaherlinmondolang optimizinglantanaclassificationhighaccuracymodelutilizingfeatureextraction |