Differential Evolution based Hyperparameters Tuned Deep Learning Models for Disease Diagnosis and Classification

Abstract

With recent advancements in medical filed, the quantity of healthcare care data is increasing at a faster rate. Medical data classification is considered as a major research topic and numerous research works have been already existed in the literature. Presently, deep learning (DL) models offers an efficient method for developing a dedicated model to determine the class labels of the respective medical data. But the performance of the DL is mainly based on the hyperparameters such as, learning rate, batch size, momentum, and weight decay, which need expertise and wide-ranging trial and error. Therefore, the process of identifying the optimal configuration of the hyper parameters of a DL is still remains a major issue. To resolve this issue, this paper presents a new hyperparameters tuned DL models for intelligent medical diagnosis and classification. The proposed model is mainly based on four major processes namely pre-processing, feature extraction, classification and parameter tuning. The proposed method makes use of simulated annealing (SA) based feature selection. Then, a set of DL models namely recurrent neural network (RNN), gated recurrent units (GRU) and long short term memory (LSTM) are used for classification. To further increase the classification performance, differential evolution (DE) algorithm is applied to tune the hyperparameters of the DL models. A detailed simulation analysis takes place using three benchmark medical dataset namely Diabetes, EEG Eye State and Sleep stage dataset. The simulation outcome indicated that the DE-LSTM model have shown better performance with the maximum accuracy of 97.59%, 88.52% and 93.18% on the applied diabetes, EEG Eye State and Sleep Stage dataset.

Optimal multiple key‐based homomorphic encryption with deep neural networks to secure medical data transmission and diagnosis

“…A detailed comparative analysis of the PPEDL‐MDTC method with recent techniques on UCD Sleep Stage dataset is given in Table 7 and Figure 11 (Kaliyapillai & Krishnamurthy, 2020). The experimental outcome portrayed that the CNN and RNN approaches have showcased minimum performance with the accuracy of 0.7823 and 0.8219 correspondingly.…”

“…Figure 11(Kaliyapillai & Krishnamurthy, 2020). The experimental outcome portrayed that the CNN and RNN approaches have showcased…”

A Framework for Text Classification Using Evolutionary Contiguous Convolutional Neural Network and Swarm Based Deep Neural Network

“…The feature selection for text and image data using DE with support vector machines and Naïve Bayesian classifiers was done by Dixit and Bansal ( 2020 ), and DE was used for fine tuning Naïve Bayesian classifiers with its applications for text classification implemented by Diab and El Hindi ( 2017 ). The DE based hyperparameters tuned deep learning models for disease diagnosis and classification were done in Kaliyapillai and Krishnamurthy ( 2020 ). The DE based feature selection and classifier ensemble for named entity recognition was done by Sikdar et al ( 2012 ) and evolutionary optimization of ensemble learning to determine sentiment polarity in an unbalanced multiclass corpus was done by Gracia-mendoza et al ( 2020 ).…”