Hybrid Optimized Imperialist Competitive Algorithm with Ensemble Learning for Cancer Subtypes Diagnosis
Main Article Content
Cancer disease diagnosis and treatment now place a high priority on categorization of cancer subtypes. Pathological cancer subgroups have proven difficult to accurately identify molecularly. Numerous supervised learning techniques have been used to classify cancer subtypes in recent years in order to address these demands. For the categorization of cancer subtypes, the prior system used Deep Fuzzy Flexible Neural Forest (DFFNForest) with Binomial Probability Distribution-based Principal Component Analysis (BDPCA).BDPCA is used in this study to conduct dimensional reductions. The Imperialist Competitive Algorithm (ICA) algorithm will next be used to execute the feature selection in order to lower the classifier's miss rate. The DFFNForest is used to classify cancer subtypes in accordance with the chosen characteristic. However, the single classifier does not always produce better results. In order to enhance prediction performance, ensemble learning is necessary. A Hybrid Optimized Imperialist Competitive Algorithm (HOICA) with Ensemble Learning (EL) for Cancer Subtypes Diagnosis was developed by the suggested approach to address this issue. Dimensional reduction, feature choice, and classification processes make up the proposed cancer diagnostic system. Utilizing Improved Independent Component Analysis (IICA), dimensional reductions are carried out in the first step. To reduce the classifier's miss rate in the second stage, features are chosen using HOICA. Finally, the categorization is carried out using EL, which combines methodologies from the Support Vector Machine (SVM), Weighted Activation Function based Convolutional Neural Network (WAFCNN), and DFFN Forest. In terms of accuracy, precision, recall, f-measure, and error, the experimental findings demonstrate that the suggested system outperforms the current system.
Kourou, K., Exarchos, T. P., Exarchos, K. P., Karamouzis, M. V., & Fotiadis, D. I. (2015). Machine learning applications in cancer prognosis and prediction. Computational and structural biotechnology journal, 13, pp. 8-17.
Fu, L. M., & Fu-Liu, C. S. (2004). Multi-class cancer subtype classification based ongene expression signatures with reliability analysis. FEBS SXEFR65TJNUHREGBTHBGTssssswederletters, 561(1-3), pp.186-190.
Rhee, S., Seo, S., & Kim, S. (2017). Hybrid approach of relation network and localized graph convolutional filtering for breast cancer subtype classification. arXiv preprint arXiv:1711.05859.
Tung, W. L., & Quek, C. (2005). GenSo-FDSS: a neural-fuzzy decision support system for pediatric ALL cancer subtype identification using gene expression data. Artificial intelligence in medicine, 33(1), pp.61-88.
Franks, J. M., Cai, G., & Whitfield, M. L. (2018). Feature specific quantile normalization enables cross-platform classification of molecular subtypes using gene expression data. Bioinformatics, 34(11), pp.1868-1874.
Joshi, P., Jeong, S., & Park, T. (2019, November). Cancer subtype classification based on superlayered neural network. In 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 1988-1992). IEEE.
Hung, F. H., & Chiu, H. W. (2017). Cancer subtype prediction from a pathway-level perspective by using a support vector machine based on integrated gene expression and protein network. Computer methods and programs in biomedicine, 141, pp.27-34.
Guo, Y., Qi, Y., Li, Z., & Shang, X. (2018). Improvement of cancer subtype prediction by incorporating transcriptome expression data and heterogeneous biological networks. BMC medical genomics, 11(6), pp.87-98.
Xu, J., Wu, P., Chen, Y., Meng, Q., Dawood, H., & Khan, M. M. (2019). A novel deep flexible neural forest model for classification of cancer subtypes based on gene expression data. IEEE Access, 7, pp.22086-22095.
Halder, A., Dey, S., & Kumar, A. (2015). Active learning using fuzzy k-NN for cancer classification from microarray gene expression data. In Advances in Communication and Computing (pp. 103-113). Springer, New Delhi.
Guo, Y., Liu, S., Li, Z., & Shang, X. (2018). BCDForest: a boosting cascade deep forest model towards the classification of cancer subtypes based on gene expression data. BMC bioinformatics, 19(5), 118.
Kar, S., Sharma, K. D., & Maitra, M. (2015). Gene selection from microarray gene expression data for classification of cancer subgroups employing PSO and adaptive K-nearest neighborhood technique. Expert Systems with Applications, 42(1),pp. 612-627.
Xia, C. Q., Han, K., Qi, Y., Zhang, Y., & Yu, D. J. (2017). A self-training subspace clustering algorithm under low-rank representation for cancer classification on gene expression data. IEEE/ACM transactions on computational biology and bioinformatics, 15(4), pp.1315-1324.
Spurek, P., Tabor, J., &Śmieja, M. (2018). Fast independent component analysis algorithm with a simple closed-form solution. Knowledge-Based Systems, 161, pp.26-34.
Nordhausen, K., &Oja, H. (2018). Independent component analysis: A statistical perspective. Wiley Interdisciplinary Reviews: Computational Statistics, 10(5), e1440.
Yamashita, R., Nishio, M., Do, R. K. G., &Togashi, K. (2018). Convolutional neural networks: an overview and application in radiology. Insights into imaging, 9(4), pp.611-629.
Zhou, D. X. (2020). Universality of deep convolutional neural networks. Applied and computational harmonic analysis, 48(2), pp.787-794.