Statistical Analysis of Normalization Impact on GLCM-Based Coral Classification
Keywords:
Statistical Analysis, Data Normalization, Gray Level Co-occurrence Matrix (GLCM), Coral Image ClassificationAbstract
To the best of the authors’ knowledge, this research provides part of the first statistically validated and comprehensive comparison of multiple normalization methods for GLCM-based coral image classification across different classical classifiers using ANOVA and Tukey’s HSD tests. The process addresses the lack of evidence-based normalization analyses in previous studies and offers practical guidance for preprocessing design in coral reef monitoring systems. The research investigates the statistical impact of five normalization methods including MinMax Scaling, Z-Score Standardization, Robust Scaler, Power Transformer, and L2 Normalization on the performance of GLCM-based coral image classification using Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Random Forest (RF) classifiers. A dataset of 2,511 coral images, with healthy, unhealthy, and dead classes, is analyzed using 8 GLCM texture features. Five-fold cross-validation is applied, and classification performance is evaluated using accuracy, precision, recall, and F1-score metrics. One-way Analysis of Variance (ANOVA) and Tukey’s Honestly Significant Difference (HSD) tests assess performance differences among normalization methods. Results show that normalization significantly impacts classification performance across all classifiers (p < 0.05). L2 Normalization produces the lowest accuracy and F1-score particularly for SVM (≈ 0.397) due to the suppression of essential magnitude information in GLCM features. Z-Score Standardization, Robust Scaler, and Power Transformer achieve the highest and statistically comparable performance. ZScore Standardization has the best results for SVM with an estimated accuracy of 0.913, and MinMax Scaling performs competitively for KNN. The results confirm normalization as a critical preprocessing step in texturebased coral image classification.
References
[1] S. Najeeb, R. A. A. Khan, X. Deng, and C. Wu, “Drivers and consequences of degradation in tropical reef island ecosystems: Strategies for restoration and conservation,” Frontiers in Marine Science, vol. 12, pp. 1–15, 2025.
[2] M. H. Yuan, K. T. Lin, S. Y. Pan, and C. K. Yang, “Exploring coral reef benefits: A systematic SEEA-driven review,” Science of the Total Environment, vol. 950, pp. 1–14, 2024.
[3] A. Apprill et al., “Toward a new era of coral reef monitoring,” Environmental Science & Technology, vol. 57, no. 13, pp. 5117–5124, 2023.
[4] A. Pourzangbar, M. Jalali, and M. Brocchini, “Machine learning application in modelling marine and coastal phenomena: A critical review,” Frontiers in Environmental Engineering, vol. 2, pp. 1–27, 2023.
[5] A. P. R. Nababan, T. Haryanto, and S. H. Wijaya, “Classification of coral images using support vector machine with gray level co-occurrence matrix feature extraction,” JOIV: International Journal on Informatics Visualization, vol. 9, no. 3, pp. 936–946, 2025.
[6] S. Anwarul and R. Tanwar, “CoralClassify: Advancing coral health monitoring using deep learning,” Procedia Computer Science, vol. 259, pp. 88–97, 2025.
[7] D. Menaga, S. L. Deborah, and M. Makizhna, “Deep learning models for coral reef health classification: MobileNetV2, VGG16 and ResNet,” in International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024). Chennai, India: Atlantis Press, Dec. 30–31, 2025, pp. 1241–1251.
[8] Y. S. Kim, M. K. Kim, N. Fu, J. Liu, J. Wang, and J. Srebric, “Investigating the impact of data normalization methods on predicting electricity consumption in a building using different artificial neural network models,” Sustainable Cities and Society, vol. 118, pp. 1–12, 2025.
[9] J. M. H. Pinheiro et al., “The impact of feature scaling in machine learning: Effects on regression and classification tasks,” IEEE Access, vol. 13, pp. 199 903–199 931, 2025.
[10] L. B. V. De Amorim, G. D. C. Cavalcanti, and R. M. O. Cruz, “The choice of scaling technique matters for classification performance,” Applied Soft Computing, vol. 133, 2023.
[11] A. Demircio˘glu, “The effect of feature normalization methods in radiomics,” Insights Into Imaging, vol. 15, pp. 1–11, 2024.
[12] U. Sta´nczyk, B. Zielosko, and G. Baron, “Importance of characteristic features and their form for data exploration,” Entropy, vol. 26, no. 5, pp. 1–32, 2024.
[13] G. Kotronoulas et al., “An overview of the fundamentals of data management, analysis, and interpretation in quantitative research,” Seminars in Oncology Nursing, vol. 39, no. 2, pp. 1–9, 2023.
[14] T. N. Abebe and A. T. Goshu, “Asymmetric generalized error distribution with its properties and applications,” Frontiers in Applied Mathematics and Statistics, vol. 10, pp. 1–14, 2024.
[15] T. Burger, “Controlling for false discoveries subsequently to large scale one-way ANOVA testing in proteomics: Practical considerations,” Proteomics, vol. 23, no. 18, pp. 1–12, 2023.
[16] Z. Li, J. Smith-Colin, and J. Wang, “A unified multi-criteria equity metric for data-driven decision-making: Application to tract-level electric vehicle charging station planning,” Engineering Applications of Artificial Intelligence, vol. 144, pp. 1–19, 2025.
[17] B. H. Liu, L. W. Zhang, Y. Q. Wei, and C. Chen, “Dual power transformation and yeo–johnson techniques for static and dynamic reliability assessments,” Buildings, vol. 14, no. 11, pp. 1–21, 2024.
[18] R. Guido, S. Ferrisi, D. Lofaro, and D. Conforti, “An overview on the advancements of support vector machine models in healthcare applications: A review,” Information, vol. 15, no. 4, pp. 1–36, 2024.
[19] N. Amaya-Tejera, M. Gamarra, J. I. V´elez, and E. Zurek, “A distance-based kernel for classification via support vector machines,” Frontiers in Artificial Intelligence, vol. 7, pp. 1–15, 2024.
[20] R. Yang, H. Li, and H. Huang, “A Gaussian kernel similarity approach to multisource information fusion considering the weight of focal element beliefs,” 2023. [Online]. Available: https://www.qeios.com/read/N4DNZI
[21] J. Zhang, C. L. Liu, and X. Jiang, “Polynomial kernel learning for interpolation kernel machines with application to graph classification,” Pattern Recognition Letters, vol. 186, pp. 7–13, 2024.
[22] B. Ahmadi, M. Gholamalifard, S. M. Ghasempouri, and T. Kutser, “Comparative analysis of k-nearest neighbors distance metrics for retrieving coastal water quality based on concurrent in situ and satellite observations,” Marine Pollution Bulletin, vol. 214, 2025.
[23] R. K. Halder, M. N. Uddin, M. A. Uddin, S. Aryal, and A. Khraisat, “Enhancing k-nearest neighbor algorithm: A comprehensive review and performance analysis of modifications,” Journal of Big Data, vol. 11, pp. 1–55, 2024.
[24] Z. Sun, G. Wang, P. Li, H. Wang, M. Zhang, and X. Liang, “An improved random forest based on the classification accuracy and correlation measurement of decision trees,” Expert Systems with Applications, vol. 237, Part B, 2024.
[25] H. N. Noura, Z. Allal, O. Salman, and K. Chahine, “An optimized tree-based model with feature selection for efficient fault detection and diagnosis in diesel engine systems,” Results in Engineering, vol. 27, pp. 1–20, 2025.
[26] C. P. J. Chen, R. R. White, and R. Wright, “Common pitfalls in evaluating model performance and strategies for avoidance in agricultural studies,” Computers and Electronics in Agriculture, vol. 234, pp. 1–21, 2025.
[27] S. A. Hicks et al., “On evaluation metrics formedical applications of artificial intelligence,” Scientific Reports, vol. 12, pp. 1–9, 2022.
[28] S. Farhadpour, T. A. Warner, and A. E. Maxwell, “Selecting and interpreting multiclass loss and accuracy assessment metrics for classifications with class imbalance: Guidance and best practices,” Remote Sensing, vol. 16, no. 3, pp. 1–22, 2024.
[29] J. Kozak, B. Probierz, K. Kania, and P. Juszczuk, “Preference-driven classification measure,” Entropy, vol. 24, no. 4, pp. 1–24, 2022.
[30] M. C. Hinojosa Lee, J. Braet, and J. Springael, “Performance metrics for multilabel emotion classification: Comparing micro, macro, and weighted F1-scores,” Applied Sciences, vol. 14, no. 21, pp. 1–21, 2024.
[31] X. Sun, Y. Zhang, C. Liu, X. Zheng, and F. Zou, “Evaluating cross-platform normalization methods for integrated microarray and RNA-seq data analysis,” 2026. [Online]. Available: https://www.biorxiv.org/content/10.1101/2024.09.30.615938v2
[32] N. A. Rozaini and Z. M. Khalid, “One-way and two-way Analysis of Variance (ANOVA) using parametric and non-parametric methods,” Proceedings of Science and Mathematics, vol. 22, pp. 53–65, 2024.
[33] J. Rahnenf¨uhrer et al., “Statistical analysis of high-dimensional biomedical data: A gentle introduction to analytical goals, common approaches and challenges,” BMC Medicine, vol. 21, pp. 1–54, 2023.
[34] C. E. Agbangba, E. S. Aide, H. Honfo, and R. G. Kakai, “On the use of post-hoc tests in environmental and biological sciences: Acritical review,” Heliyon, vol. 10, no. 3, pp. 1–12, 2024.
[35] F. Strale Jr, “Partitioning for enhanced statistical power and noise reduction: Comparing oneway and repeated measures Analysis of Variance (ANOVA),” Cureus, vol. 16, no. 12, pp. 1–10, 2024.
[36] S. Kwak, “Are only p-values less than 0.05 significant? A p-value greater than 0.05 is also significant!” Journal of Lipid and Atherosclerosis, vol. 12, no. 2, pp. 89–95, 2023.
[37] M. H. Kabir et al., “Exploring feature selection and classification techniques to improve the performance of an electroencephalography-based motor imagery brain–computer interface system,” Sensors, vol. 24, no. 15, pp. 1–27, 2024.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Adi Pandu Rahmat Nababan, Stendy Budi Hartono Sakur, Miske Silangen, Toto Haryanto, Sony Hartono Wijaya
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
a. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License - Share Alike that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
b. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
c. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
Â
USER RIGHTS
All articles published Open Access will be immediately and permanently free for everyone to read and download. We are continuously working with our author communities to select the best choice of license options, currently being defined for this journal as follows: Creative Commons Attribution-Share Alike (CC BY-SA)
