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.
Sleep stage performs a vital role in people's daily lives in the detection of sleep-related diseases. Conventional automated sleep stage classifier models are not efficient due to the complexity linked to the design of mathematical models and extraction of hand-engineering features. Further, quick oscillations amongst sleep stages frequently lead to indistinct feature extraction, which might result in the imprecise classification of sleep stages. To resolve these issues, deep learning (DL) models are applied, which make use of many layers of linear and nonlinear processing components for learning the hierarchical representation or feature from input data and have been used for sleep stage classification (SSC). Therefore, this paper proposes an ensemble of voting-based DL models, namely the recurrent neural network (RNN), long short-term memory (LSTM) and gated recurrent unit (GRU), with activation Regularization (AR) functions for SSC. The penalty addition of L1, L1_L2, and L2 on the layers of the model fine-tunes it in proportion to the magnitude of the activation function in the model by reducing overfitting. Subsequently, the presented model integrates the results of every classification model to the max voting combination rule. Finally, experimental results of the proposed approach using the benchmark Sleep Stage dataset are evaluated using various metrics. The experimental results illustrates that the Ensemble RNN, Ensemble GRU, and Ensemble LSTM models have achieved an accuracy of 85.57%, 87.41%, and 89.01%, respectively.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.