Evolutionary optimisation with outlier detection-based deep learning model for biomedical data classification. (2nd December 2022)

• Record Type: Journal Article
• Authors: Raja, R.; Ashok, B.
• Is Part Of: International journal of networking and virtual organisations. Volume 27:Number 2(2022)
• Page Start: 143
• Page End: 162
• Publication Date: 2022-12-02
• Subjects: classification -- medical data -- data mining -- outlier detection -- class imbalance -- deep learning -- parameter tuning; Computer networks -- Periodicals; Information networks -- Periodicals; Virtual corporations -- Periodicals; Electronic commerce -- Periodicals; Management information systems -- Periodicals; Management -- Data processing -- Periodicals; 004.65
• Languages: English
• ISSNs: 1470-9503

Abstract

In recent times, large amount of medical data is being generated by various sources such as test reports, medications, etc. Due to the recent advances of machine learning (ML) and deep learning (DL) models, medical data classification (MDC) remains a crucial process in the healthcare sector. This study introduces a new hyperparameter tuned convolutional neural network-recurrent neural network (HPT-CNN-RNN) model for medical data classification. The proposed HPT-CNN-RNN model includes pre-processing step to transform the actual healthcare data into useful format. Besides, SVM-SMOTE approach was executed to handle the class imbalance problems. In addition, outlier detection process is performed using extreme gradient boosting (XGBoost) model. Moreover, bacterial foraging optimisation algorithm (BFOA) with CNNRNN model is employed to categorise medical data. Furthermore, the BFOA is utilised to optimally choose the hyperparameter values of the CNNRNN model. The experimental outcomes designated the better performance of the HPT-CNN-RNN model over the other methods.