OPTIMIZING LANTANA CLASSIFICATION: HIGH-ACCURACY MODEL UTILIZING FEATURE EXTRACTION

Authors

  • Adri Gabriel Sooai Universitas Katolik Widya Mandira Kupang, Indonesia
  • Sisilia Daeng Bakka Mau Universitas Katolik Widya Mandira Kupang, Indonesia
  • Yovinia Carmeneja Hoar Siki Universitas Katolik Widya Mandira Kupang, Indonesia
  • Donatus Joseph Manehat Universitas Katolik Widya Mandira Kupang, Indonesia
  • Shine Crossifixio Sianturi Universitas Sanata Dharma Yogyakarta, Indonesia
  • Alicia Herlin Mondolang Universitas Negeri Malang, Indonesia

DOI:

https://doi.org/10.21107/kursor.v12i2.347

Keywords:

Machine Learning, classification, Feature Extraction, image processing, lantana

Abstract

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.

Downloads

Download data is not yet available.

References

T. Samarajeewa et al., “Identification of Lantana Camara Distribution Using Convolutional Neural Networks,” 2018 18th International Conference on Advances in ICT for Emerging Regions (ICTer), pp. 221–228, 2018, doi: 10.1109/ICTER.2018.8615559.

M. Ntalo, K. E. Ravhuhali, B. Moyo, O. Hawu, and N. H. Msiza, “Lantana camara: Poisonous Species and a Potential Browse Species for Goats in Southern Africa—A Review,” Sustainability, vol. 14, no. 2, p. 751, Jan. 2022, doi: 10.3390/su14020751.

S. S. Mukherjee, M. T. Ahmed, and A. Hossain, “Role of a Global Invasive Species (GIS), Lantana camara in conservation and sustenance of local butterfly community,” Acta Ecologica Sinica, Mar. 2021, doi: 10.1016/j.chnaes.2021.02.008.

R. Gupta, D. Niyogi, R. Nayan, S. Singh, A. Mishra, and V. Varun, “Clinico-pathological study of Lantana camara toxicity in a sheep farm,” Journal of Pharmacognosy and Phytochemistry, vol. 8, no. 4, p. 3, 2019.

A. Tarugara, B. W. Clegg, and R. Matuvhunye, “Mapping the spatial distribution and canopy cover of Lantana camara in the Zaka district of Zimbabwe,” Scientific African, vol. 17, p. e01339, Sep. 2022, doi: 10.1016/j.sciaf.2022.e01339.

G. C. S. Negi et al., “Ecology and Use of Lantana camara in India,” Bot. Rev., vol. 85, no. 2, pp. 109–130, Jun. 2019, doi: 10.1007/s12229-019-09209-8.

N. Z. Fanani et al., “Two Stages Outlier Removal as Pre-processing Digitizer Data on Fine Motor Skills (FMS) Classification Using Covariance Estimator and Isolation Forest,” IJIES, vol. 14, no. 4, pp. 571–582, Aug. 2021, doi: 10.22266/ijies2021.0831.50.

N. Z. Fanani, A. G. Sooai, S. Sumpeno, and M. H. Purnomo, “Penentuan Kemampuan Motorik Halus Anak dari Proses Menulis Hanacaraka Menggunakan Random Forest,” JNTETI, vol. 9, no. 2, Art. no. 2, May 2020, doi: 10.22146/jnteti.v9i2.153.

A. J. Lado et al., “Comparison of Neural Network and Random Forest Classifier Performance on Dragon Fruit Disease,” in 2021 International Electronics Symposium (IES), Sep. 2021, pp. 287–291. doi: 10.1109/IES53407.2021.9593992.

A. G. Sooai, K. Yoshimoto, H. Takahashi, S. Sumpeno, and M. H. Purnomo, “Dynamic Hand Gesture Recognition on 3D Virtual Cultural Heritage Ancient Collection Objects Using k-Nearest Neighbor,” Engineering Letters, vol. 26, no. 3, pp. 356–363, 2018.

A. G. Sooai, A. N. Rumaksari, K. Khamid, N. Z. Fanani, S. Sumpeno, and M. H. Purnomo, “Deteksi Gestur Lengan Dinamis pada Lingkungan Virtual Tiga Dimensi Koleksi Warisan Budaya,” Jurnal Nasional Teknik Elektro dan Teknologi Informasi (JNTETI), vol. 7, no. 4, 2018, doi: 10.22146/jnteti.v7i4.457.

A. G. Sooai et al., “Comparison of Recognition Accuracy on Dynamic Hand Gesture Using Feature Selection,” in 2018 International Conference on Computer Engineering, Network and Intelligent Multimedia (CENIM), Surabaya: Institut Teknologi Sepuluh Nopember, Nov. 2018, pp. 270–274. doi: 10.1109/CENIM.2018.8711397.

A. B. Gumelar, E. M. Yuniarno, D. P. Adi, A. G. Sooai, I. Sugiarto, and M. H. Purnomo, “BiLSTM-CNN Hyperparameter Optimization for Speech Emotion and Stress Recognition,” in Wireless Technologies and Intelligent Systems for Better Human Lives, Surabaya, Indonesia: IEEE, Sep. 2021, pp. 220–225. doi: 10.1109/IES53407.2021.9594024.

A. B. Gumelar et al., “Human Voice Emotion Identification Using Prosodic and Spectral Feature Extraction Based on Deep Neural Networks,” in 2019 IEEE 7th International Conference on Serious Games and Applications for Health (SeGAH), Kyoto, Japan: IEEE, Aug. 2019, pp. 1–8. doi: 10.1109/SeGAH.2019.8882461.

E. Talahaturuson et al., “Exploring Indonesian Netizen’s Emotional Behavior Through Investment Sentiment Analysis Using TextBlob-NLTK (Natural Language Toolkit),” in Technology 4.0 for Smart Ecosystem: A New Way of Doing DIgital Business, Semarang, Indonesia: IEEE, Sep. 2022.

H. A. Roysid, A. Maulana, and U. Pujianto, “CAN K-NEAREST NEIGHBOR METHOD BE USED TO PREDICT SUCCESS IN INDONESIA STATE UNIVERSITY STUDENT SELECTION,” Jurnal Ilmiah Kursor, vol. 9, no. 4, Art. no. 4, Dec. 2018, doi: 10.28961/kursor.v9i4.186.

A. Z. Nur, H. Suyono, and M. Aswin, “APPLICATION OF HYBRID GA-PSO TO IMPROVE THE PERFORMANCE OF DECISION TREE C5.0,” Jurnal Ilmiah Kursor, vol. 10, no. 4, Art. no. 4, Dec. 2020, doi: 10.21107/kursor.v10i4.248.

M. R. Siki, N. H. Harani, and C. Prianto, “Electronic Data Interchange (EDI) Applications Use the Decision Tree Method to Determine Vendor Recommendations,” Jurnal Ilmiah Kursor, vol. 10, no. 2, Art. no. 2, Dec. 2019, doi: 10.21107/kursor.v10i2.217.

A. A. Omeer and R. R. Deshmukh, “Deep Learning-Based Models for Classification of Invasive Plant Species from Hyperspectral Remotely Sensed Data,” in Proceedings of the International Conference on Data Science, Machine Learning and Artificial Intelligence, in DSMLAI “21.” New York, NY, USA: Association for Computing Machinery, Aug. 2021, pp. 222–230. doi: 10.1145/3484824.3484884.

S. Hidayat, A. Y. Rahman, and Istiadi, “Betta Fish Image Classification Using Artificial Neural Networks with Gabor Extraction Features,” in 2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom), Malang, Indonesia: IEEE, Jun. 2022, pp. 270–273. doi: 10.1109/CyberneticsCom55287.2022.9865509.

O. Loyola-González, M. A. Medina-Pérez, and K.-K. R. Choo, “A Review of Supervised Classification based on Contrast Patterns: Applications, Trends, and Challenges,” J Grid Computing, vol. 18, no. 4, pp. 797–845, Dec. 2020, doi: 10.1007/s10723-020-09526-y.

A. Y. Rahman, “Image Classification of Starlings Using Artificial Neural Network and Decision Tree,” in 2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom), Malang, Indonesia: IEEE, Jun. 2022, pp. 286–291. doi: 10.1109/CyberneticsCom55287.2022.9865465.

M. Piernik and T. Morzy, “A study on using data clustering for feature extraction to improve the quality of classification,” Knowl Inf Syst, vol. 63, no. 7, pp. 1771–1805, Jul. 2021, doi: 10.1007/s10115-021-01572-6.

M. Rzanny, P. Mäder, A. Deggelmann, M. Chen, and J. Wäldchen, “Flowers, leaves or both? How to obtain suitable images for automated plant identification,” Plant Methods, vol. 15, no. 1, p. 77, Jul. 2019, doi: 10.1186/s13007-019-0462-4.

R. Zhang et al., “Metric learning for image-based flower cultivars identification,” Plant Methods, vol. 17, no. 1, p. 65, Jun. 2021, doi: 10.1186/s13007-021-00767-w.

G. Kumar and V. Kumar, “Herbal Plants Leaf Image Classification Using Deep Learning Models Based On Augmentation Approach.” Rochester, NY, Jul. 31, 2022. doi: 10.2139/ssrn.4292344.

G. Batchuluun, S. H. Nam, and K. R. Park, “Deep Learning-Based Plant-Image Classification Using a Small Training Dataset,” Mathematics, vol. 10, no. 17, Art. no. 17, Jan. 2022, doi: 10.3390/math10173091.

A. G. Sooai, “Seleksi Fitur untuk Pengenalan Gestur Tangan 3D secara Dinamis pada Interaksi Benda Virtual Menggunakan Hybrid GMM,” doctoral, Institut Teknologi Sepuluh Nopember, Surabaya, 2020. Accessed: Jul. 04, 2023. [Online]. Available: https://repository.its.ac.id/81786/

Downloads

Published

2023-12-10

Issue

Section

Articles

Citation Check