Boosting Performance of SVM in Koi Classification Using Direct Methods-Based Optimization

Muhammad Hafizh Arkananta - Telkom University, Jl. Telekomunikasi. 1, Bandung, 40257, Indonesia
Wikky Fawwaz Al Maki - Telkom University, Jl. Telekomunikasi. 1, Bandung, 40257, Indonesia


Citation Format:



DOI: http://dx.doi.org/10.62527/joiv.8.4.2474

Abstract


Many koi fish enthusiasts keep or buy them just for their attractive colors without knowing what type of koi fish they are. The manual classification of koi fish species is still frequently incorrect. As a result, it is critical to apply a machine learning technique to identify various koi fish species. This research implemented a computer vision algorithm to classify koi fish species using the Support Vector Machine (SVM) as the classifier. However, the maximum accuracy SVM can achieve in our koi fish classification system is 79%.  To achieve better performance, the SVM was optimized by applying various optimization methods from the Direct Method group, i.e., the Generalized Pattern Search (GPS), the Powell method, and the Nelder-Mead method. Three optimization methods from the Direct Method group have successfully improved the performance of SVM in this task. Experimental results demonstrated that using the Generalized Pattern Search (GPS) in our classification system can increase the accuracy to 98%. Also, implementing the Powell and the Nelder-Mead method can make the koi classification system obtain a better accuracy of 99%. These results indicate that the proposed approach is a viable solution to overcome the limitations of the SVM algorithm.


Keywords


Koi fish; support vector machine; direct method; powell; nelder-mead; generalized pattern search

Full Text:

PDF

References


M. S. Cueto, J. M. B. Diangkinay, K. W. B. Melencion, T. P. Senerado, H. L. P. Taytay, and E. R. E. Tolentino, “Classification of different types of koi fish using convolutional neural network,” in Proceedings - 5th International Conference on Intelligent Computing and Control Systems, ICICCS 2021, Institute of Electrical and Electronics Engineers Inc., May 2021, pp. 1135–1142. doi: 10.1109/ICICCS51141.2021.9432358.

Y. Zheng, L. Deng, Q. Lin, W. Xu, F. Wang, and J. Li, “KRS-Net: A Classification Approach Based on Deep Learning for Koi with High Similarity,” Biology, vol. 11, p. 1727, 2022. doi: 10.3390/biology11121727.

U. Andayani, A. Wijaya, R. F. Rahmat, B. Siregar, and M. F. Syahputra, “Fish Species Classification Using Probabilistic Neural Network,” in Journal of Physics: Conference Series, Institute of Physics Publishing, Jul. 2019. doi: 10.1088/1742-6596/1235/1/012094.

I. Sharmin, N. F. Islam, I. Jahan, T. Ahmed Joye, M. R. Rahman, and M. T. Habib, “Machine vision based local fish recognition,” SN Appl Sci, vol. 1, no. 12, Dec. 2019, doi: 10.1007/s42452-019-1568-z.

A. Anushya, “ASSESSMENT OF SUPPORT VECTOR MACHINE FOR CLASSIFICATION OF SARDINE IMAGES,” ICTACT JOURNAL ON IMAGE AND VIDEO PROCESSING, no. 10, p. 3, 2020, doi: 10.21917/ijivp.2020.0306.

M. S. Ahmed, T. T. Aurpa, and M. A. K. Azad, “Fish Disease Detection Using Image Based Machine Learning Technique in Aquaculture,” Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 8, pp. 5170–5182, Sep. 2022, doi: 10.1016/j.jksuci.2021.05.003.

R. R. Pineda and P. Naval, “A Comparison of SVM and K-NN in the Classification of Jewel Damselfish Activity Automated Epileptic Seizure Detection in Intracranial EEGs Using Wavelet Transform and SVM Classifier View project Autoencoders in Autoencoder Models for Certain Computer Vision Tasks View project A Comparison of SVM and K-NN in the Classification of Jewel Damselfish Activity,” 2019. [Online]. Available: https://www.researchgate.net/publication/339497440

M. J. Mia, R. Bin Mahmud, M. S. Sadad, H. Al Asad, and R. Hossain, “An in-depth automated approach for fish disease recognition,” Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 9, pp. 7174–7183, Oct. 2022, doi: 10.1016/j.jksuci.2022.02.023.

U. A. Badawi, “Fish classification using extraction of appropriate feature set,” International Journal of Electrical and Computer Engineering, vol. 12, no. 3, pp. 2488–2500, Jun. 2022, doi: 10.11591/ijece.v12i3.pp2488-2500.

M. A. Iqbal, Z. Wang, Z. A. Ali, and S. Riaz, “Automatic Fish Species Classification Using Deep Convolutional Neural Networks,” Wirel Pers Commun, vol. 116, no. 2, pp. 1043–1053, Jan. 2021, doi: 10.1007/s11277-019-06634-1.

M. Mathur and N. Goel, “FishResNet: Automatic Fish Classification Approach in Underwater Scenario,” SN Comput Sci, vol. 2, no. 4, Jul. 2021, doi: 10.1007/s42979-021-00614-8.

A. Tharwat, A. E. Hassanien, and B. E. Elnaghi, “A BA-based algorithm for parameter optimization of Support Vector Machine,” Pattern Recognit Lett, vol. 93, pp. 13–22, Jul. 2017, doi: 10.1016/j.patrec.2016.10.007.

D. S. Y. Kartika and D. Herumurti, Koi Fish Classification based on HSV Color Space. IEEE, 2016. doi: 10.1109/ICTS.2016.7910280.

M. B. Akçay and K. Oğuz, “Speech emotion recognition: Emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers,” Speech Communication, vol. 116. Elsevier B.V., pp. 56–76, Jan. 01, 2020. doi: 10.1016/j.specom.2019.12.001.

S. Avidan and A. Shamir, “Seam carving for content-aware image resizing,” ACM Trans Graph, vol. 26, no. 99, p. 10, Jul. 2007, doi: 10.1145/1239451.1239461.

X. Liu, L. Song, S. Liu, and Y. Zhang, “A review of deep-learning-based medical image segmentation methods,” Sustainability (Switzerland), vol. 13, no. 3, pp. 1–29, Feb. 2021, doi: 10.3390/su13031224.

A. Ahmad Fauzi and A. Adisuputra, “Implementation of ColorSpace, GrabCut, and Watershed Methods on Digital Image Segmentation of Coral and Fish Objects,” Journal of Computer Networks, Architecture and High Performance Computing, vol. 5, no. 1, pp. 87–99, Jan. 2023, doi: 10.47709/cnahpc.v5i1.2012.

J. Ye, Z. Shen, P. Behrani, F. Ding, and Y. Q. Shi, “Detecting USM image sharpening by using CNN,” Signal Process Image Commun, vol. 68, pp. 258–264, Oct. 2018, doi: 10.1016/j.image.2018.04.016.

W. Castro, J. Oblitas, M. De-La-Torre, C. Cotrina, K. Bazan, and H. Avila-George, “Classification of Cape Gooseberry Fruit According to its Level of Ripeness Using Machine Learning Techniques and Different Color Spaces,” IEEE Access, vol. 7, pp. 27389–27400, 2019, doi: 10.1109/ACCESS.2019.2898223.

R. Zebari, A. Abdulazeez, D. Zeebaree, D. Zebari, and J. Saeed, “A Comprehensive Review of Dimensionality Reduction Techniques for Feature Selection and Feature Extraction,” Journal of Applied Science and Technology Trends, vol. 1, no. 2, pp. 56–70, May 2020, doi: 10.38094/jastt1224.

H. Gao, K. Xu, M. Cao, J. Xiao, Q. Xu, and Y. Yin, “The Deep Features and Attention Mechanism-Based Method to Dish Healthcare under Social IoT Systems: An Empirical Study with a Hand-Deep Local-Global Net,” IEEE Trans Comput Soc Syst, vol. 9, no. 1, pp. 336–347, Feb. 2022, doi: 10.1109/TCSS.2021.3102591.

G. F. Laxmi and F. S. F. Kusumah, “Region of interest and color moment method for freshwater fish identification,” Telkomnika (Telecommunication Computing Electronics and Control), vol. 17, no. 3, pp. 1432–1438, 2019, doi: 10.12928/TELKOMNIKA.V17I3.11749.

X. Chen, S. Xu, S. Li, H. He, Y. Han, and X. Qu, “Identification of architectural elements based on SVM with PCA: A case study of sandy braided river reservoir in the Lamadian Oilfield, Songliao Basin, NE China,” J Pet Sci Eng, vol. 198, Mar. 2021, doi: 10.1016/j.petrol.2020.108247.

N. Baygin, M. Baygin, and M. Karakose, “A SVM-PSO Classifier for Robot Motion in Environment with Obstacles,” 2019. doi: 10.1109/IDAP.2019.8875921.

E. Wang, P. Yan, and J. Liu, “A Hybrid Chatter Detection Method Based on WPD, SSA, and SVM-PSO,” Shock and Vibration, vol. 2020, 2020, doi: 10.1155/2020/7943807.

Y. Ozaki, M. Yano, and M. Onishi, “Effective hyperparameter optimization using Nelder-Mead method in deep learning,” IPSJ Transactions on Computer Vision and Applications, vol. 9, 2017, doi: 10.1186/s41074-017-0030-7.

G. Cohen, P. Ruch, and M. Hilario, “Model Selection for Support Vector Classifiers via Direct Simplex Search,” 2005. [Online]. Available: www.aaai.org

M. Kishihara, K. Yamane, dan I. Ohta, "Parallel Processing of Powell’s Optimization Algorithm and its Application to Design of Multi-Way Power Dividers," in 2005 Asia-Pacific Microwave Conference Proceedings, doi: 10.1109/apmc.2005.1606817.

Y. Zhuang, K. Gao, X. Miu, L. Han, and X. Gong, “Infrared and visual image registration based on mutual information with a combined particle swarm optimization - Powell search algorithm,” Optik (Stuttg), vol. 127, no. 1, pp. 188–191, Jan. 2016, doi: 10.1016/j.ijleo.2015.09.199.

K. Haghdar and H. A. Shayanfar, “Selective Harmonic Elimination with Optimal DC Sources in Multilevel Inverters Using Generalized Pattern Search,” IEEE Trans Industr Inform, vol. 14, no. 7, pp. 3124–3131, Jul. 2018, doi: 10.1109/TII.2018.2790931.

A. Zaouche, I. Dayoub, and J. M. Rouvaen, “Baud-spaced constant modulus blind equalization via hybrid genetic algorithm and generalized pattern search optimization,” AEU - International Journal of Electronics and Communications, vol. 62, no. 2, pp. 122–131, Feb. 2008, doi: 10.1016/j.aeue.2007.03.011.

W. M. Li, Z. H. Jiang, T. L. Wang, and H. P. Zhu, “Optimization method based on Generalized Pattern Search Algorithm to identify bridge parameters indirectly by a passing vehicle,” J Sound Vib, vol. 333, no. 2, pp. 364–380, Jan. 2014, doi: 10.1016/j.jsv.2013.08.021.