PERFORMANCE COMPARISON OF EXTREME LEARNING MACHINE AND ITS VARIANTS IN IMAGE CLASSIFICATION

Year 2025, Volume: 13 Issue: 3, 856 - 871, 30.09.2025

Kübra Bozoğlan , Uğur Yüzgeç

https://doi.org/10.21923/jesd.1670485

Abstract

Image classification is a critical technology in various fields such as medicine, agriculture, security, and more. Machine learning algorithms, particularly Extreme Learning Machines (ELM), have gained attention due to their fast learning capabilities and high accuracy rates. However, the performance of ELM can vary depending on the dataset and application scenario. This study aims to evaluate and compare the performance of the ELM model and its improved variants—namely, the incremental extreme learning machine (IELM), online sequential extreme learning machine (OSELM), regularized extreme learning machine (RELM), and constrained extreme learning machine (CELM)—in the context of image classification. These models were tested on four distinct datasets: MNIST, brain MRI images, rice images, and images of vehicle drivers. The models' performances were evaluated based on success rates, precision, recall, and F1 scores. The results indicate that the CELM model achieved the highest success rate, while the IELM model demonstrated the lowest performance. These findings provide valuable insights into how the unique structural features of each model influence classification success. Furthermore, the differences in performance across the datasets offer important clues for selecting the most effective model based on dataset characteristics. By understanding the strengths and limitations of each model, researchers and practitioners can make informed decisions when addressing image classification challenges.

Keywords

Extreme Learning Machines , Image Classification , Machine Learning

GÖRÜNTÜ SINIFLANDIRMADA AŞIRI ÖĞRENME MAKİNESİ VE VARYANTLARININ PERFORMANS KARŞILAŞTIRMASI

Abstract

Görüntü sınıflandırma tıp, tarım, güvenlik ve daha fazlası gibi çeşitli alanlarda kritik bir teknolojidir. Makine öğrenmesi algoritmaları, özellikle de Aşırı Öğrenme Makineleri (ELM), hızlı öğrenme yetenekleri ve yüksek doğruluk oranları nedeniyle dikkat çekmiştir. Bununla birlikte, ELM'nin performansı veri kümesine ve uygulama senaryosuna bağlı olarak değişebilir. Bu çalışma, ELM modelinin ve geliştirilmiş varyantlarının (artımlı aşırı öğrenme makinesi (IELM), çevrimiçi sıralı aşırı öğrenme makinesi (OSELM), düzenli aşırı öğrenme makinesi (RELM) ve kısıtlı aşırı öğrenme makinesi (CELM)) performansını görüntü sınıflandırma bağlamında değerlendirmeyi ve karşılaştırmayı amaçlamaktadır. Bu modeller dört farklı veri kümesi üzerinde test edilmiştir: MNIST, beyin MRI görüntüleri, pirinç görüntüleri ve araç sürücülerinin görüntüleri. Modellerin performansları başarı oranları, kesinlik, geri çağırma ve F1 puanlarına göre değerlendirilmiştir. Sonuçlar, CELM modelinin en yüksek başarı oranını elde ettiğini, IELM modelinin ise en düşük performansı gösterdiğini ortaya koymuştur. Bu bulgular, her modelin kendine özgü yapısal özelliklerinin sınıflandırma başarısını nasıl etkilediğine dair değerli bilgiler sağlamaktadır. Ayrıca, veri kümeleri arasındaki performans farklılıkları, veri kümesi özelliklerine göre en etkili modelin seçilmesi için önemli ipuçları sunmaktadır. Araştırmacılar ve uygulayıcılar, her modelin güçlü yönlerini ve sınırlamalarını anlayarak, görüntü sınıflandırma zorluklarını ele alırken bilinçli kararlar verebilirler.

Keywords

Aşırı Öğrenme Makineleri , Görüntü Sınıflandırma , Makine Öğrenmesi

References

• Albadr, M. A. A., AL-Dhief, F. T., Man, L., Arram, A., Abbas, A. H., & Homod, R. Z. (2024). Online sequential extreme learning machine approach for breast cancer diagnosis. Neural Computing and Applications, 1-17.
• Al-Yaseen, W. L., Idrees, A. K., & Almasoudy, F. H. (2022). Wrapper feature selection method based differential evolution and extreme learning machine for intrusion detection system. Pattern Recognition, 132, 108912.
• Anam, K., & Al-Jumaily, A. (2015, August). A robust myoelectric pattern recognition using online sequential extreme learning machine for finger movement classification. In 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 7266-7269). IEEE.
• Baran, B. (2019). Sınır Değerler Arasında Kalan Evsel Atık Su Numune Analizi Sonucunun Aşırı Öğrenme Makineleri ile Sınıflandırılması. Mühendislik Bilimleri ve Tasarım Dergisi, 7(1), 18-25.
• Chacko, B. P., Vimal Krishnan, V. R., Raju, G., & Babu Anto, P. (2012). Handwritten character recognition using wavelet energy and extreme learning machine. International Journal of Machine Learning and Cybernetics, 3, 149-161.
• Chen, K., Li, J., Liu, K., Bai, C., Zhu, J., Gao, G., ... & Laghrouche, S. (2024). State of health estimation for lithium-ion battery based on particle swarm optimization algorithm and extreme learning machine. Green Energy and Intelligent Transportation, 3(1), 100151.
• Coşkun, C., & Baykal, A. (2011). Veri madenciliğinde sınıflandırma algoritmalarının bir örnek üzerinde karşılaştırılması. Akademik Bilişim, 2011, 1-8.
• Deng, W., Zheng, Q., & Chen, L. (2009, March). Regularized extreme learning machine. In 2009 IEEE symposium on computational intelligence and data mining (pp. 389-395). IEEE.
• Ding, S., Xu, X., & Nie, R. (2014). Extreme learning machine and its applications. Neural Computing and Applications, 25, 549 556.
• GeeksforGeeks. (2025). Extreme Learning Machine . https://www.geeksforgeeks.org/extreme-learning-machine/
• Goutte, C., & Gaussier, E. (2005, March). A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. In European conference on information retrieval (pp. 345-359). Berlin, Heidelberg: Springer Berlin Heidelberg.
• Guangyu, X., Shaoping, S., & Jietao, S. (2017, July). Wind speed forecast for the stratospheric airship by incremental extreme learning machine. In 2017 36th Chinese Control Conference (CCC) (pp. 4088-4092). IEEE.
• Gumaei, A., Hassan, M. M., Hassan, M. R., Alelaiwi, A., & Fortino, G. (2019). A hybrid feature extraction method with regularized extreme learning machine for brain tumor classification. IEEE Access, 7, 36266-36273.
• Hameed, M. M., Razali, S. F. M., Mohtar, W. H. M. W., Alsaydalani, M. O. A., & Yaseen, Z. M. (2024). Deep learning versus hybrid regularized extreme learning machine for multi-month drought forecasting: A comparative study and trend analysis in tropical region. Heliyon, 10(1).
• He, C., Kang, H., Yao, T., & Li, X. (2019). An effective classifier based on convolutional neural network and regularized extreme learning machine. Mathematical biosciences and engineering, 16(6), 8309-8321.
• Huang, G. B., Liang, N. Y., Rong, H. J., Saratchandran, P., & Sundararajan, N. (2005). On-line sequential extreme learning machine. Computational Intelligence, 2005, 232-237.
• Huang, G. B., Zhu, Q. Y., & Siew, C. K. (2004, July). Extreme learning machine: a new learning scheme of feedforward neural networks. In 2004 IEEE international joint conference on neural networks (IEEE Cat. No. 04CH37541) (Vol. 2, pp. 985 990). IEEE.
• Huang, G. B., & Chen, L. (2007). Convex incremental extreme learning machine. Neurocomputing, 70(16-18), 3056-3062.
• Huang, X., Lei, Q., Xie, T., Zhang, Y., Hu, Z., & Zhou, Q. (2020). Deep transfer convolutional neural network and extreme learning machine for lung nodule diagnosis on CT images. Knowledge-Based Systems, 204, 106230.
• Iosifidis, A., Tefas, A., & Pitas, I. (2015). Regularized Extreme Learning Machine for large-scale media content analysis. Procedia Computer Science, 53, 420-427.
• Ismail Nasri. (2023). Driver Drowsiness Dataset (DDD). https://www.kaggle.com/datasets/ismailnasri20/driver-drowsiness dataset-ddd.
• Kaynar, O., Görmez, Y., Yıldız, M., & Albayrak, A. (2016, September). Makine öğrenmesi yöntemleri ile Duygu Analizi. In International Artificial Intelligence and Data Processing Symposium (IDAP'16) (Vol. 17, No. 18, pp. 17-18).
• Lama, R. K., Gwak, J., Park, J. S., & Lee, S. W. (2017). Diagnosis of Alzheimer’s disease based on structural MRI images using a regularized extreme learning machine and PCA features. Journal of healthcare engineering, 2017(1), 5485080.
• Lazarevska, E. (2016). Wind speed prediction based on incremental extreme learning machine. In Proceedings of The 9th EUROSIM Congress on Modelling and Simulation, EUROSIM (pp. 544-550).
• Liang, N. Y., Saratchandran, P., Huang, G. B., & Sundararajan, N. (2006). Classification of mental tasks from EEG signals using extreme learning machine. International journal of neural systems, 16(01), 29-38.
• Lu, D., & Weng, Q. (2007). A survey of image classification methods and techniques for improving classification performance. International journal of Remote sensing, 28(5), 823-870.
• Lu, S., Wang, H., Wu, X., & Wang, S. (2016, December). Pathological brain detection based on online sequential extreme learning machine. In 2016 International Conference on Progress in Informatics and Computing (PIC) (pp. 219-223). IEEE.
• Malik, H., Anees, T., Naeem, A., Naqvi, R. A., & Loh, W. K. (2023). Blockchain-federated and deep-learning-based ensembling of capsule network with incremental extreme learning machines for classification of COVID-19 using CT scans. Bioengineering, 10(2), 203.
• Masoudnickparvar. (2023). Brain Tumor MRI Dataset. https://www.kaggle.com/datasets/masoudnickparvar/brain-tumor mri-dataset.
• Maurya, R., Mahapatra, S., Dutta, M. K., Singh, V. P., Karnati, M., Sahu, G., & Pandey, N. N. (2024). Skin cancer detection through attention guided dual autoencoder approach with extreme learning machine. Scientific Reports, 14(1), 17785.
• Ouyang, Q., Chen, Q., Zhao, J., & Lin, H. (2013). Determination of amino acid nitrogen in soy sauce using near infrared spectroscopy combined with characteristic variables selection and extreme learning machine. Food and Bioprocess Technology, 6(9), 2486-2493.
• Prakash, S. B., Chandan, K., Karthik, K., Devanathan, S., Kumar, R. V., Nagaraja, K. V., & Prasannakumara, B. C. (2023). Investigation of the thermal analysis of a wavy fin with radiation impact: an application of extreme learning machine. Physica Scripta, 99(1), 015225.
• Serin, Z., Karakuzu, C., & Yüzgeç, U. (2024). Meta-Constrained Extreme Learning Machines: A Novel Approach For Classification Problems. Available at SSRN 5061376.
• Sezgin, N. (2016). Epileptik EG İşaretlerin Aşırı Öğrenme Makineleri ile Sınıflandırılması. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 7(3), 481-490.
• Vani, G., Savitha, R., & Sundararajan, N. (2010, December). Classification of abnormalities in digitized mammograms using extreme learning machine. In 2010 11th International Conference on Control Automation Robotics & Vision (pp. 2114-2117). IEEE.
• Walid, M. A. A., Mallick, S. P., Rastogi, R., Chauhan, A., & Vidya, A. (2023, March). Melanoma skin cancer detection using a CNN regularized extreme learning machine (RELM) based Model. In 2023 Second International Conference on Electronics and Renewable Systems (ICEARS) (pp. 1239-1245). IEEE.
• Wang, D., & Huang, G. B. (2005, July). Protein sequence classification using extreme learning machine. In Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005 (Vol. 3, pp. 1406-1411). IEEE.
• Wang, Y., Li, Q., Zhang, J., Yin, C., Zhang, Q., Shi, Y., & Men, H. (2025). A gas detection system combined with a global extension extreme learning machine for early warning of electrical fires. Sensors and Actuators B: Chemical, 423, 136801.
• Wong, S. Y., Yap, K. S., & Li, X. C. (2020). A new probabilistic output constrained optimization extreme learning machine. IEEE Access, 8, 28934-28946.
• Xiao, H., Rasul, K., & Vollgraf, R. (2017). Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747.
• Zhao, Y. P., & Chen, Y. B. (2022). Extreme learning machine based transfer learning for aero engine fault diagnosis. Aerospace science and technology, 121, 107311.
• Zhu, W., Miao, J., & Qing, L. (2014, July). Constrained extreme learning machine: a novel highly discriminative random feedforward neural network. In 2014 International Joint Conference on Neural Networks (IJCNN) (pp. 800-807). IEEE.