Abstract

Despite the numerous fish classification systems developed over the years, they often suffer from poor prediction accuracy, necessitating further improvement. This study addresses this issue by comparing the performance of different classifiers on fish landing datasets (2005-2019) obtained from the Department of Fisheries Malaysia (DOFM). The focus is on the East Coast of Peninsular Malaysia. The classifiers evaluated include Sequential minimal optimization (SMO), naïve Bayes (NB), multi-layer perception (MLP), instance-based for k-nearest neighbor (IBK), and random forest (RF). The performance of each classifier is assessed using classification accuracy and confusion matrix metrics, employing a 10-fold cross-validation method. Additionally, a multi-classification technique is applied to enhance the accuracy of individual classifiers and determine the most effective approach for generating an accurate dataset. The study reveals that the combinations RF+SMO+NB+MLP and SMO+RF+NB+MLP outperform single classifiers and other fusion methods, achieving the highest accuracy at 80.95%. This indicates that a multi-classifier approach can significantly enhance the performance of individual classifiers. The findings highlight the effectiveness of the multi-classifier approach in improving prediction accuracy for fish classification. The identified combinations, RF+SMO+NB+MLP and SMO+RF+NB+MLP, demonstrate superior performance and can serve as a robust methodology for fish landing classification in the context of the East Coast of Peninsular Malaysia. Further research and implementation of such multi-classifier approaches could contribute to more accurate and reliable fish classification systems.

Keyword

Fish landing dataset, Feature selection, Classification performance, Multi-classifier.

Cite this article

Rosly R, Man M, Ngah A, Manan NS.Multi-classifier models to improve the accuracy of fish landing application. International Journal of Advanced Technology and Engineering Exploration. 2024;11(111):145-159. DOI:10.19101/IJATEE.2023.10102060

Refference

[1]Fathoni S, Rachman MA, Arasy AK. Analysis determinant supply & demand fisheries. In IOP conference series: earth and environmental science 2019 (pp. 1-7). IOP Publishing.

[2]Alhatali A, Soosaimanickam A. A comparative study of the efficient data mining algorithm to find the most influenced factor on price variation in Oman fish markets. Sakarya University Journal of Computer and Information Sciences. 2018; 1(2):1-6.

[3]Islam MM, Chuenpagdee R. Towards a classification of vulnerability of small-scale fisheries. Environmental Science & Policy. 2022; 134:1-2.

[4]Andrews N, Bennett NJ, Le BP, Green SJ, Cisneros-montemayor AM, Amongin S, et al. Oil, fisheries and coastal communities: a review of impacts on the environment, livelihoods, space and governance. Energy Research & Social Science. 2021; 75:102009.

[5]Sheth V, Tripathi U, Sharma A. A comparative analysis of machine learning algorithms for classification purpose. Procedia Computer Science. 2022; 215:422-31.

[6]Phyu TN. Survey of classification techniques in data mining. In proceedings of the international multiconference of engineers and computer scientists 2009 (pp. 727-31).

[7]Seliya N, Abdollah ZA, Khoshgoftaar TM. A literature review on one-class classification and its potential applications in big data. Journal of Big Data. 2021; 8(1):1-31.

[8]Chen P, Fan R, Lin C. A study on SMO-type decomposition methods for support vector machines. IEEE Transactions on Neural Networks. 2006; 17(4): 893-908.

[9]https://aiml.com/what-is-a-multilayer-perceptron-mlp/. Accessed 19 December 2023.

[10]David SK, Rafiullah M, Siddiqui K. Comparison of different machine learning techniques to predict diabetic kidney disease. Journal of Healthcare Engineering. 2022; 2022:1-9.

[11]Rodriguez-galiano VF, Ghimire B, Rogan J, Chica-olmo M, Rigol-sanchez JP. An assessment of the effectiveness of a random forest classifier for land-cover classification. ISPRS Journal of Photogrammetry and Remote Sensing. 2012; 67:93-104.

[12]Riccio V, Jahangirova G, Stocco A, Humbatova N, Weiss M, Tonella P. Testing machine learning based systems: a systematic mapping. Empirical Software Engineering. 2020; 25:5193-254.

[13]Ribeiro VH, Reynoso-meza G. Ensemble learning by means of a multi-objective optimization design approach for dealing with imbalanced data sets. Expert Systems with Applications. 2020; 147:113232.

[14]Rosly R, Makhtar M, Awang MK, Awang MI, Rahman MN, Mahdin H. Comprehensive study on ensemble classification for medical applications. International Journal of Engineering & Technology. 2018; 7(2.14):186-90.

[15]Mahfouz A, Abuhussein A, Venugopal D, Shiva S. Ensemble classifiers for network intrusion detection using a novel network attack dataset. Future Internet. 2020; 12(11):1-19.

[16]Saputra S, Yudhana A, Umar R. Implementation of naïve bayes for fish freshness identification based on image processing. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi). 2022; 6(3):412-20.

[17]Rohani A, Taki M, Bahrami G. Application of artificial intelligence for separation of live and dead rainbow trout fish eggs. Artificial Intelligence in Agriculture. 2019; 1:27-34.

[18]Maniriho P, Mahoro LJ, Niyigaba E, Bizimana Z, Ahmad T. Detecting intrusions in computer network traffic with machine learning approaches. International Journal of Intelligent Engineering & Systems. 2020; 13(3):433-45.

[19]Snapir B, Waine TW, Biermann L. Maritime vessel classification to monitor fisheries with SAR: demonstration in the North Sea. Remote Sensing. 2019; 11(3):1-16.

[20]Lastanto JA, Djatna T. A predictive analytics of production planning model for yield performance in organic broiler industry using ensemble learning. In IOP conference series: earth and environmental science 2022 (pp. 1-9). IOP Publishing.

[21]Jany Arman R, Hossain M, Hossain S. Fish classification using saliency detection depending on shape and texture. Computación y Sistemas. 2022; 26(1):303-10.

[22]Ogunlana SO, Olabode O, Oluwadare SA, Iwasokun GB. Fish classification using support vector machine. African Journal of Computing & ICT. 2015; 8(2):75-82.

[23]Deep BV, Dash R. Underwater fish species recognition using deep learning techniques. In 6th international conference on signal processing and integrated networks 2019 (pp. 665-9). IEEE.

[24]Rahman LF, Marufuzzaman M, Alam L, Bari MA, Sumaila UR, Sidek LM. Developing an ensembled machine learning prediction model for marine fish and aquaculture production. Sustainability. 2021; 13(16):1-14.

[25]Amini F, Hu G. A two-layer feature selection method using genetic algorithm and elastic net. Expert Systems with Applications. 2021; 166:114072.

[26]Hou D. Determine the impact on fisheries by predicting the migration of fish near Scotland. In IOP conference series: earth and environmental science 2021 (pp. 1-7). IOP Publishing.

[27]Agarwal AK, Tiwari RG, Khullar V, Kaushal RK. Transfer learning inspired fish species classification. In 8th international conference on signal processing and integrated networks 2021 (pp. 1154-9). IEEE.

[28]Little LR, Kuikka S, Punt AE, Pantus F, Davies CR, Mapstone BD. Information flow among fishing vessels modelled using a Bayesian network. Environmental Modelling & Software. 2004; 19(1):27-34.

[29]Fitrianah D, Fahmi H, Hidayanto AN, Arymurthy AM. A data mining based approach for determining the potential fishing zones. International Journal of Information and Education Technology. 2016; 6(3):187-91.

[30]Boettiger C, Mangel M, Munch S. Avoiding tipping points in fisheries management through gaussian process dynamic programming. Proceedings of the Royal Society B: Biological Sciences. 2015; 282(1801):1-9.

[31]Kamakshi V, Krishnan NC. Explainable image classification: the journey so far and the road ahead. AI. 2023; 4(3):620-51.

[32]Badger JJ, Large SI, Thorson JT. Spatio-temporal species distribution models reveal dynamic indicators for ecosystem-based fisheries management. ICES Journal of Marine Science. 2023; 80(7):1949-62.

[33]Zhang H, Chen Q, Zhou A, Wang Y. Beyond deep learning: an evolutionary feature engineering approach to tabular data classification. ICLR conference 2023 (pp.1-23).

[34]Li D, Yang Y, Song YZ, Hospedales T. Learning to generalize: meta-learning for domain generalization. In proceedings of the AAAI conference on artificial intelligence 2018 (pp.3490-7).

[35]Chhabra HS, Srivastava AK, Nijhawan R. A hybrid deep learning approach for automatic fish classification. In proceedings of ICETIT: emerging trends in information technology 2020 (pp. 427-36). Springer International Publishing.

[36]Alfatinah A, Chu HJ, Tatas, Patra SR. Fishing area prediction using scene-based ensemble models. Journal of Marine Science and Engineering. 2023; 11(7):1-16.

[37]Saleh A, Sheaves M, Jerry D, Azghadi MR. Transformer-based self-supervised fish segmentation in underwater videos. arXiv preprint arXiv:2206.05390. 2022.

[38]Zainuddin M, Safruddin S, Selamat MB, Farhum A, Hidayat S. Prediction of potential fishing zones for skipjack tuna during the northwest monsoon using remotely sensed satellite data. Marine Science. 2017; 22(2):59-66.

[39]Mugo R, Saitoh SI. Ensemble modelling of Skipjack tuna (Katsuwonus pelamis) habitats in the western North Pacific using satellite remotely sensed data; a comparative analysis using machine-learning models. Remote Sensing. 2020; 12(16):1-15.

[40]Alaba S, Shah C, Nabi MM, Ball J, Moorhead R, Han D, et al. Semi-supervised learning for fish species recognition. In ocean sensing and monitoring XV 2023 (pp. 248-55). SPIE.

[41]Saleh A, Sheaves M, Jerry D, Azghadi MR. Applications of deep learning in fish habitat monitoring: a tutorial and survey. Expert Systems with Applications. 2023:121841.

[42]Malik H, Naeem A, Hassan S, Ali F, Naqvi RA, Yon DK. Multi-classification deep neural networks for identification of fish species using camera captured images. Plos One. 2023; 18(4):1-32.

[43]Alkhulaifi A, Alsahli F, Ahmad I. Knowledge distillation in deep learning and its applications. PeerJ Computer Science. 2021; 14:1-24.

[44]Masuda H, Jukei T, Hasegawa T. Fish species identification using a CNN-based multimodal learning method. In proceedings of the 2nd international conference on image, video and signal processing 2020 (pp. 15-9). ACM.

[45]Edmondson E, Fanning L. Implementing adaptive management within a fisheries management context: a systematic literature review revealing gaps, challenges, and ways forward. Sustainability. 2022; 14(12):1-16.

[46]Palaniappan S, Hameed NA, Mustapha A, Samsudin NA. Classification of alcohol consumption among secondary school students. JOIV: International Journal on Informatics Visualization. 2017; 1(4-2):224-6.

[47]Amarnath B, Balamurugan SAA. Conditional probability based feature selector for effective data classification. Revista Tecnica De La Facultad De Ingenieria Universidad Del Zulia. 2016; 39(7): 1-8.

[48]https://machinelearningmastery.com/failure-of-accuracy-for-imbalanced-class-distributions/. Accessed 14 June 2023.