Optimal progressive classification study using SMOTE-SVM for stages of lung disease

Abstract

Data used in big data applications are typically kept in decentralized computing resources in the real world, which has an impact on the design of artificial intelligence algorithms. When there are significantly more observations from one class than from another, the dataset is said to be imbalanced. Therefore, in this work, the study elaborates the model as SMOTE-SVM which resolves imbalance issues in sampling the data and improves overall accuracy to 94%. The model deploys K-nearest neighbours to compute the difference between samples and to balance the samples, it computes the kernel space. Further, to optimize the classification, GWO optimizer merges with SMOTE-SVM to achieve enhanced performance. GWO (Grey Wolf Optimizer) induces greedy selection to perform optimization among classification. It is important to remember that grey wolves have a flexible social structure that might change the hierarchy. As the mobilization continues, the grey wolves are reconstructed with the distance between them and their prey, or more specifically, in accordance with the resultant value of the fitness. In addition, to prove the efficiency, the following performance metrics are measured-Overall Accuracy, Classification Accuracy, AUC and ROC.