Search

Hepatitis is a disease originating from a viral bacterium that can be avoided by the earlier identification of the disease and also with the proper classification. The proposed methodology is split into two phases: pre-processing technique and classification method. The pre-processing methods are incorporated to improve the accuracy and reduce the complexity of data. In the first phase, the pre-processing method such as (i) First, label encoder with one hot encoder (LE-OHE), is adopted to convert all the categorical data into a numerical column (ii) Then, Fuzzy logic with may fly (FL-MF) is developed to fill the missing values and (iii) Finally, inter-quartile range (IQR) technique is used to detect the outliers. In the second phase, the classification method is refined by following three steps (i) A correlationbased decision tree (CDT) is constructed to interpret the data as simple, (ii) A reduced error pruning tree (REPT) technique is employed to split the data using grid search algorithm and (iii) The different combination of REPT is given as input to the ensemble stacking method that enhances the predictive performance. According to the results, our proposed method outperforms with an average accuracy rate of 96.1%, and time complexity in both datasets (hepatitis and indian liver patient record (ILPR)) when compared with the existing algorithms such as min max scalarsupport vector machine (MMS-SVM), mean imputation-random forest (MI-RF), gradient boosting (GB), random forest (RF), ensemble-stacking (ES), extreme gradient boosting (XGBoost), and radial basis function-extreme learning machine (RBF-ELM). Moreover, the proposed method also reduces the mean absolute error (MAE) error rate. [ABSTRACT FROM AUTHOR]

In the modern era, the number of diseases is increasing and it is very crucial to diagnose them. One among them is the hepatitis virus in which the proper identification of symptoms is tedious. Machine learning algorithms are essential in recognizing the disease in the earlier stages. In this paper, a novel pre-processing technique and feature selection (FS) method are proposed to achieve improved accuracy with less time complexity. The proposed methodology is divided into three phases: In the first phase, the pre-processing technique such as Multiple Imputation with weight based fuzzy logic (MI-WFL) is applied to decrease the classification error. In the second phase, the correlation-based hybridized bat and particle swarm optimization (CHBPSO) FS algorithm is used to minimize the time complexity and maximize the accuracy rate. In the third phase, the poly kernel support vector machine (PK-SVM) classifier is implemented to avoid overfitting issues. According to the results of the experiments, the CHBPSO algorithm outperforms in the accuracy rate of 96.15%, and classification error for the following metrics mean absolute error (MAE) is 0.17, root mean squared error (RMSE) is 0.23, relative absolute error (RAE) is 49.66, and root relative squared error (RRSE) is 54.62 are lower than the existing algorithms. Furthermore, the proposed solution has attained less processing time of 1.6 sec due to the reduced optimal features. [ABSTRACT FROM AUTHOR]