Diabetes prediction based on the fusion of deep neural network, support vector machine and particle swarm optimization algorithm

Fuente: Zenodo
Salvato in:
Dettagli Bibliografici
Autore principale: Yu, Jing
Natura: Recurso digital
Lingua:inglese
Pubblicazione: Zenodo 2025
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866902272640811008
author Yu, Jing
author_facet Yu, Jing
contents <p><strong><span lang="EN-US">Figure. 1</span></strong> <span lang="EN-US">Content Framework Diagram of Model Construction</span><span lang="EN-US">.</span> <span lang="EN-US">[Utilizing the Kaggle diabetes dataset, high-dimensional features were extracted and optimally selected through deep neural networks, integrated with support vector machines for classification prediction, while employing particle swarm optimization algorithms for parameter tuning].</span></p> <p><span lang="EN-US"><strong><span lang="EN-US">Figure. 2 </span></strong><span lang="EN-US">Network Structure of the DNN Model.</span> <span lang="EN-US">[The DNN consists of an input layer, two hidden layers, and an output layer, with each layer comprising neurons equipped with activation functions. The dimensionality of the input layer is dictated by the dimension of the feature space, whereas the configuration of the output layer is determined by the specific requirements of the classification task].</span></span></p> <p><span lang="EN-US"><span lang="EN-US"><strong><span lang="EN-US">Figure. 3</span></strong><span lang="EN-US"> PSO training process.</span> <span lang="EN-US">[The PSO algorithm is integrated with the SVM model to automatically identify the optimal parameter configuration for the SVM]</span></span></span></p> <p><span lang="EN-US"><span lang="EN-US"><span lang="EN-US"><a name="OLE_LINK45"></a><a name="OLE_LINK27"></a><strong><span lang="EN-US">Figure</span></strong><strong><span lang="EN-US">.4</span></strong><span lang="EN-US"> Comparison of accuracy rates of each model</span><span lang="EN-US">.</span> <span lang="EN-US">[The bar chart visually compares the accuracy performance of various models on the identical dataset, with percentage values clearly demonstrating the performance disparities among the models]. </span></span></span></span></p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_16986875
institution Zenodo
language eng
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle Diabetes prediction based on the fusion of deep neural network, support vector machine and particle swarm optimization algorithm
Yu, Jing
<p><strong><span lang="EN-US">Figure. 1</span></strong> <span lang="EN-US">Content Framework Diagram of Model Construction</span><span lang="EN-US">.</span> <span lang="EN-US">[Utilizing the Kaggle diabetes dataset, high-dimensional features were extracted and optimally selected through deep neural networks, integrated with support vector machines for classification prediction, while employing particle swarm optimization algorithms for parameter tuning].</span></p> <p><span lang="EN-US"><strong><span lang="EN-US">Figure. 2 </span></strong><span lang="EN-US">Network Structure of the DNN Model.</span> <span lang="EN-US">[The DNN consists of an input layer, two hidden layers, and an output layer, with each layer comprising neurons equipped with activation functions. The dimensionality of the input layer is dictated by the dimension of the feature space, whereas the configuration of the output layer is determined by the specific requirements of the classification task].</span></span></p> <p><span lang="EN-US"><span lang="EN-US"><strong><span lang="EN-US">Figure. 3</span></strong><span lang="EN-US"> PSO training process.</span> <span lang="EN-US">[The PSO algorithm is integrated with the SVM model to automatically identify the optimal parameter configuration for the SVM]</span></span></span></p> <p><span lang="EN-US"><span lang="EN-US"><span lang="EN-US"><a name="OLE_LINK45"></a><a name="OLE_LINK27"></a><strong><span lang="EN-US">Figure</span></strong><strong><span lang="EN-US">.4</span></strong><span lang="EN-US"> Comparison of accuracy rates of each model</span><span lang="EN-US">.</span> <span lang="EN-US">[The bar chart visually compares the accuracy performance of various models on the identical dataset, with percentage values clearly demonstrating the performance disparities among the models]. </span></span></span></span></p>
title Diabetes prediction based on the fusion of deep neural network, support vector machine and particle swarm optimization algorithm
url https://doi.org/10.5281/zenodo.16986875