HYBRID LEARNING FOR BOTTLENOSE DOLPHIN MOTION APPROXIMATION USING WEIGHTED POLLING KNN AND BAYES MECHANISM
DOI:
https://doi.org/10.15282/Keywords:
Probability classification, Supervised learning, Clustering, KNN, Machine LearningAbstract
Artificial intelligence has been extensively employed to examine social animal behaviours, such as feeding habits, reproduction, swarm structures, and hibernation. For marine biologists, grasping essential habitat characteristics like swimming depth and temperature preferences is vital for evaluating ecological boundaries, habitat deterioration, and conservation initiatives. Machine learning has been used to help identify bottlenose dolphins and their cohabitation patterns, as computer vision and deep learning are often used in studies of fish habitats involving predation, feeding habits, breeding, and other fish. Existing techniques do not provide sufficient variety in estimating classification characteristics for assigning unique animals to their corresponding subclasses, particularly for differentiating various marine species along with their respective groups. The objective for this proposed research framework is aimed at integrating supervised clustering and probabilistic classifiers such as K-Nearest Neighbors (KNN) or Bayes classifying with weighted voting to classify dolphin types, apart from consolidated behavioral patterns. The study further integrated the use of oxygen usage into the dataset for monitoring movement activity after pup pre-feeding intervals in addition to metabolic rates of other animals. Data was cross verified, encompassing trial laps, dolphin identifiers, timing, segment length, and carbon dioxide emission rates, for the purpose of classification. Findings showed an average classification accuracy of 97% for weighted KNN types and 91% for weighted Bayes classifiers, emphasizing their effectiveness in differentiating dolphin classes in swarming settings. These machine learning methods provide essential tools for enhancing marine research and aiding conservation and habitat preservation through improved identification of ecological traits.
References
[1] N. Suryani and A. S. Fitrani, “Prediction Of Election Participant With Malang City Demographic Data Using The K-Nn Algorithm,” J. Mantik, vol. 6, no. 36, pp. 2369–2376, 2022, [Online]. Available: https://ejournal.iocscience.org/index.php/mantik/article/view/2802%0Ahttps://ejournal.iocscience.org/index.php/mantik/article/download/2802/2223
[2] K. Kaharuddin and E. W. Sholeha, “Classification of Fish Species with Image Data Using K-Nearest Neighbor,” Int. J. Comput. Inf. Syst., vol. 2, no. 2, pp. 54–58, 2021, doi: 10.29040/ijcis.v2i2.33.
[3] R. Taylor, “Machine Learning Techniques for Fish Breeding Decision Making,” 2023 Wellingt. Fac. Eng. Symp., pp. 1–12, 2023, [Online]. Available: https://ojs.victoria.ac.nz/wfes/article/view/8422
[4] S. Winiarti, F. I. Indikawati, A. Oktaviana, and H. Yuliansyah, “Consumable Fish Classification Using k-Nearest Neighbor,” IOP Conf. Ser. Mater. Sci. Eng., vol. 821, no. 1, 2020, doi: 10.1088/1757-899X/821/1/012039.
[5] I. F. Dehkordi, K. Manochehri, and V. Aghazarian, “Internet of Things ( IoT ) Intrusion Detection by Machine Learning ( ML ): A Review,” Asia-Pacific J. Inf. Technol. Multimed., vol. 12, no. 1, pp. 13–38, 2023, doi: dx.doi.org/10.17576/apjitm-2023-1201-02.
[6] J. K. C. Revanna and N. Y. B. Al-Nakash, “Metaheuristic link prediction (MLP) using AI based ACO-GA optimization model for solving vehicle routing problem,” Int. J. Inf. Technol., vol. 15, no. 7, pp. 3425–3439, 2023, doi: 10.1007/s41870-023-01378-5.
[7] M. K. Alsmadi and I. Almarashdeh, “A survey on fish classification techniques,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 5, pp. 1625–1638, 2022, doi: 10.1016/j.jksuci.2020.07.005.
[8] R. Rosly, M. Man, A. Ngah, and N. S. A. Manan, “Multi-classifier models to improve the accuracy of fish landing application,” Int. J. Adv. Technol. Eng. Explor., vol. 11, no. 111, pp. 145–159, 2024, doi: 10.19101/IJATEE.2023.10102060.
[9] S. S. Latt and M. Myint, “Classification of Fish based on Naive Bayesian Classifier,” in LISS 2013, Berlin, Heidelberg: Springer Berlin Heidelberg, 2015, pp. 585–589. doi: 10.1007/978-3-642-40660-7_86.
[10] A. Fix and V. Efix, “Comparison between the KNN, W-KNN, Wc-KNN and Wk-KNN models on a CDC heart disease dataset,” no. April, 2024, doi: 10.21203/rs.3.rs-4505140/v1.
[11] M. H. Alobaidi, M. A. Meguid, and T. Zayed, “Semi-supervised learning framework for oil and gas pipeline failure detection,” Sci. Rep., vol. 12, no. 1, pp. 1–11, 2022, doi: 10.1038/s41598-022-16830-y.
[12] S. Sulaiman, R. A. Wahid, and F. Morsidi, “Feature extraction using regular expression in detecting proper noun for Malay news articles based on KNN algorithm,” J. Fundam. Appl. Sci., vol. 9, no. 5S, p. 210, Jan. 2018, doi: 10.4314/jfas.v9i5s.16.
[13] R. R. Rani and D. Ramyachitra, “Krill Herd Optimization algorithm for cancer feature selection and random forest technique for classification,” in Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS, 2018, pp. 109–113. doi: 10.1109/ICSESS.2017.8342875.
[14] M. Çakir, M. Yilmaz, M. A. Oral, H. Ö. Kazanci, and O. Oral, “Accuracy assessment of RFerns, NB, SVM, and kNN machine learning classifiers in aquaculture,” J. King Saud Univ. - Sci., vol. 35, no. 6, 2023, doi: 10.1016/j.jksus.2023.102754.
[15] A. S. Allen et al., “Dynamic body acceleration as a proxy to predict the cost of locomotion in bottlenose dolphins,” J. Exp. Biol., vol. 225, no. 4, pp. 1–13, 2022, doi: 10.1242/jeb.243121.
[16] A. Saleh, M. Sheaves, and M. Rahimi Azghadi, “Computer vision and deep learning for fish classification in underwater habitats: A survey,” Fish Fish., vol. 23, no. 4, pp. 977–999, 2022, doi: 10.1111/faf.12666.
[17] Y. Baidai, L. Dagorn, M. J. Amande, D. Gaertner, and M. Capello, “Machine learning for characterizing tropical tuna aggregations under Drifting Fish Aggregating Devices (DFADs) from commercial echosounder buoys data,” Fish. Res., vol. 229, no. September, 2020, doi: 10.1016/j.fishres.2020.105613.
[18] S. M. M. Islam, S. I. Bani, and R. Ghosh, “Content-based Fish Classification Using Combination of Machine Learning Methods,” Int. J. Inf. Technol. Comput. Sci., vol. 13, no. 1, pp. 62–68, 2021, doi: 10.5815/ijitcs.2021.01.05.
[19] Y. Gültepe, “Analysis of Alburnus tarichi population by machine learning classification methods for sustainable fisheries,” SLAS Technol., vol. 27, no. 4, pp. 261–266, 2022, doi: 10.1016/j.slast.2022.03.005.
[20] J. Gou, T. Xiong, and Y. Kuang, “A novel weighted voting for K-nearest neighbor rule,” J. Comput., vol. 6, no. 5, pp. 833–840, 2011, doi: 10.4304/jcp.6.5.833-840.
[21] S. Saputra, A. Yudhana, and R. Umar, “Implementation of Naïve Bayes for Fish Freshness Identification Based on Image Processing,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 6, no. 3, pp. 412–420, 2022, doi: 10.29207/resti.v6i3.4062.
[22] X. Wu et al., “Top 10 algorithms in data mining,” Knowl. Inf. Syst., vol. 14, no. 1, pp. 1–37, Jan. 2008, doi: 10.1007/s10115-007-0114-2.
[23] I. Fondón et al., “Automatic classification of tissue malignancy for breast carcinoma diagnosis,” Comput. Biol. Med., vol. 96, no. December 2017, pp. 41–51, 2018, doi: 10.1016/j.compbiomed.2018.03.003.
[24] M. Açıkkar and S. Tokgöz, “An improved KNN classifier based on a novel weighted voting function and adaptive k-value selection,” Neural Comput. Appl., vol. 36, no. 8, pp. 4027–4045, 2024, doi: 10.1007/s00521-023-09272-8.
[25] W. L. Buntine, “A Theory Of Learning Classification Rules,” 1992. doi: 10.1.1.49.5614.
[26] K. Demir and O. Yaman, “A HOG Feature Extractor and KNN-Based Method for Underwater Image Classification,” Firat Univ. J. Exp. Comput. Eng., vol. 3, no. 1, pp. 1–10, 2024, doi: 10.62520/fujece.1443818.
[27] Tavish Srivastava, “Guide to K-Nearest Neighbors Algorithm in Machine Learning,” Https://Www.Analyticsvidhya.Com/Blog/2018/03/Introduction-K-Neighbours-Algorithm-Clustering/, pp. 1–20, 2024.
[28] D. S. Pedroche, D. Amigo, J. García, and J. M. Molina, “Architecture for trajectory-based fishing ship classification with AIS data,” Sensors (Switzerland), vol. 20, no. 13, pp. 1–21, 2020, doi: 10.3390/s20133782.
[29] F. Idachaba and O. Tomomewo, “Surface pipeline leak detection using realtime sensor data analysis,” J. Pipeline Sci. Eng., vol. 3, no. 2, p. 100108, 2023, doi: 10.1016/j.jpse.2022.100108.
[30] T. De Kerf, J. Gladines, S. Sels, and S. Vanlanduit, “Oil spill detection using machine learning and infrared images,” Remote Sens., vol. 12, no. 24, pp. 1–13, 2020, doi: 10.3390/rs12244090.
[31] I. Md Jelas, M. A. Zulkifley, M. Abdullah, and M. Spraggon, “Deforestation detection using deep learning-based semantic segmentation techniques: a systematic review,” Front. For. Glob. Chang., vol. 7, no. February, 2024, doi: 10.3389/ffgc.2024.1300060.
[32] Y. Xu, W. Yang, and J. Wang, “Air quality early-warning system for cities in China,” Atmos. Environ., vol. 148, pp. 239–257, 2017, doi: 10.1016/j.atmosenv.2016.10.046.
[33] D. R. Tobergte and S. Curtis, “The 54th Annual Meeting of the Association for Computational Linguistics,” in Climate Change 2013 – The Physical Science Basis, vol. 53, no. 9, Cambridge University Press, 2016, pp. 1–30. doi: 10.18653/v1/P16-2
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Farid Morsidi

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.