The paper performs with CS-RC, three classification costs are used in the rotational classifier which effectively trade-off between the Design Engineering ISSN: 0011-9342 | Year 2021 Issue: 9 | Pages: 4652-4673 classification accuracy and classification cost. In order to solve this problem and to further improve the cancer prediction accuracy, a Cost-Sensitive Rotational classifier (CS-RC) is proposed in this paper.
Even though the prediction accuracy of ANN is high, it has problems such as high time-consumption and slow learning. The selected features and samples are processed in ANN for cancer prediction. It reduced the computational complexity of classifiers. So, Simultaneous Feature and Sample Selection using Ensemble of Multi-objectiveSearch space enhancedModified Whale Optimization Algorithm (SFSS-EMSMWOA) was proposed to simultaneously select the most important features and samples from the microarray data. This particular property of microarray data makes most of the traditional classifiers such as Artificial Neural Network (ANN) face difficulty in producing accurate and stable classification result. Generally, the number of features can be a hundred time larger than the number of samples. The microarray data is known as large-scale, highly redundant and imbalanced data. The classification of microarray data represents a crucial component in next generation cancer diagnosis technology.
The proposed model refers to an ensemble model (PEM) for the organization of cancer disease by reducing the feature subsets, which results show improvements in the success rate.RESULTS: The proposed ensemble model obtains the accuracy of 94.58%, 96.56% and 97.04% for PEM-1 to PEM-3, respectively.CONCLUSION: Our proposed MGA-PEM model gives satisfactory results for cancer identification and classification. The MGA feature selection procedure is applied to microarray information for cancer patients that minimize a high dimension feature subset into low dimension feature subsets.METHODS: The various data mining methods for classifying the various kinds of cancer disease patients are presented. Gene expression microarray information contains a high extent feature set, which minimizes the performance and the accuracy of classifiers.OBJECTIVES: This paper proposes a Modified Genetic Algorithm (MGA) that is based on Classifier Subset Evaluators – Genetic Search (Eval-CSE_GS) for selecting the relevant feature subsets. INTRODUCTION: Gene expression levels are important for identifying and diagnosing diseases like cancer. The proposed approach addresses a data scarcity problem, is flexible to the choice of heterogeneous base classifiers, and is able to produce HAHR models comparable to the established MAQC-II results. The successful soldiers are combined through heterogeneous ensembles for optimal results. Every soldier of the ITO army is a base model with its own independently chosen Subset selection method, pre-processing, and validation methods and classifier. The algorithm produces results in two phases: (i) Lightweight Infantry Group (LIG) converges quickly to find non-local maxima and produces comparable results (i.e., 70 to 88% accuracy) (ii) Followup Team (FT) uses advanced tuning to enhance the baseline performance (i.e., 75 to 99%). The proposed ITO algorithm combines parameter-free and parameter-based classifiers to produce a high-accuracy-high-reliability (HAHR) binary classifier. This paper presents a warzone inspired “infiltration tactics” based optimization algorithm (ITO)-not to be confused with the ITO algorithm based on the Itõ Process in the field of Stochastic calculus. Thus, generalized optimization is still a challenge open for further research. However, higher accuracy may not necessarily mean higher reliability of the model. The former are quick but may result in local maxima while the latter use dataset-specific parameter-tuning for higher accuracy. A number of different feature selection and classification techniques have been proposed in literature including parameter-free and parameter-based algorithms.