The week's pick
Reseach Article
The Comparison of Classification Accuracy on the Teak Wood Image Processing using Support Vector Machine (SVM) and Artificial Neural Network (ANN)
| International Journal of Applied Information Systems |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 12 - Number 38 |
| Year of Publication: 2021 |
| Authors: Mussalimun Mussalimun, Rahmat Robi Waliyansyah |
10.5120/ijais2021451922
|
Mussalimun Mussalimun, Rahmat Robi Waliyansyah . The Comparison of Classification Accuracy on the Teak Wood Image Processing using Support Vector Machine (SVM) and Artificial Neural Network (ANN). International Journal of Applied Information Systems. 12, 38 ( December 2021), 21-27. DOI=10.5120/ijais2021451922
Abstract
Tropical climate in Indonesia resulted this country having the largest and most tropical rainforests. Numerous types or varieties of tress grow, however not all types have sale value. Teak wood among other types of wood is the top commodities due to its high-value. In general, the identification of wood types in Indonesia depends on the subjectivity of human’s eyes thus the process is slow and inaccurate. Therefore, technology is used to overcome human limitations in observing or analyzing the classification or grouping according to the wood types. This study aims to compare Classification Accuracy on Teak Wood Image Processing using Support Vector Machine (SVM) and Artificial Neural Network (ANN) with 3 data varieties namely semarangan, blora, and Sulawesi. Based on the results of tests and analyses carried out, it can be concluded that classification method ANN obtained higher accuracy with 76.0% accuracy value compared to SVM with 72.0% accuracy value.
References
- Eleyan, A., and Demirel, H. 2011. Co-Occurrence matrix and its statistical features as a new approach for face recognition, Turkish Journal of Electrical and Computer Science, Vol 19, 2011.
- Kadir, A., and Susanto, A. 2014. Teori dan Aplikasi Pengolahan Citra. Yogyakarta, 2014.
- Martawijaya, A. 1990. Sifat dasar beberapa jenis kayu yang berasal dari hutan alam dan hutam tanaman. Proceeding Diskusi Hutan Tanaman Industri. Jakarta: Badan Litbang Kehutanan, 1990.
- Nello, C., and Taylor, J. S. 2000. An Introduction to Support Vector Machines and Other Kernel Based Learning Methods. Cambridge University Press, 2000.
- Effendi, D. A. N. and Astuti, E. Z. 2017. Pengelompokanjenisteksturkayumenggunakan k-nearest neighbor dan ekstraksifitur histogram”, Jurnal Voice of Informatics, Vol. 6, pp. 37-46, 2017.
- Prasetyo, E. 2012. Data Mining Konsep dan Aplikasi Menggunakan Matlab. Yogyakarta: Andi, 2012.
- Peluso, N. L. 1992. Rich Forests, Poor People : Resource Control and Resistance in Java. Barkeley, USA: University of California Press, 1992.
- Asogwa, O. C. 2015. Of Students Academic Perfomance Rates Using Artificial Neural Networks (ANNs), Am. J. Appl. Math. Stat., Vol. 3, 2015.
- Achmaliadi, R. and Mahaadi, I. G. 2001. Keadaan Hutan di Indonesia. Bogor: FWI, 2001.
- Waliyansyah, R. R.,andFitriyah, C. 2019. Perbandinganakurasiklasifikasicitrakayujatimenggunakanmetode Naive Bayes dan k-Nearest Neighbor (k-NN), JurnalEdukasi dan PenelitianInformatika, Vol. 5, No. 2, 2019.
- Novianto, T. D., and Erawan, I. M. S. 2020. Perbandinganmetodeklasifikasi pada pengolahancitramata ikan tuna, Prosiding SNFA (Seminar Nasional Fisika dan Aplikasinya, 2020.
- Herawan, T. and Rina, L. H. 1996. Petunjuk Teknis Kegiatan Kultur Jaringan. Yogyakarta: Badan Litbang Kehutanan, Balai Penelitian dan Pengembangan Pemuliaan Benih Tanaman Hutan, 1996.
- Pullaperuma, P. P., and Dharmaratne, A. 2013. Taxonomy of file fragments using gray-level co-occurrence matrices, Proceedings Conference: Digital Image Computing: Techniques and Applications (DICTA), 2013
Index Terms
Keywords