Anzeige
Erschienen in:
2019 | OriginalPaper | Buchkapitel
Fuzzy Deep Learning for Diabetes Detection
verfasst von : Tushar Deshmukh, H. S. Fadewar
Erschienen in: Computing, Communication and Signal Processing
Verlag: Springer Singapore
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
The use of science for the betterment of society is the main cause for research for years. That is the reason the framework of diabetes diagnosis is always changing with new dimensions. The new and advance algorithms on the horizons are tried in hope of getting better accuracy and speed. Apart from normal algorithms researchers have tried the possible hybrid combinations. In recent times, the Convolution Neural Network (CNN) has outperformed most of the application areas of traditional prediction algorithms. Here is an attempt to use the deep convolutional neural network for diagnosis of diabetes. This work has two major contributions, first is the application of CNN for diabetes detection and second is data fuzzification in matrix form to suit needs of CNN. In the experiments, the comparison is made between classical NN and CNN for diabetes detection. Results prove that fuzzification of data significantly improves the accuracy of CNN and CNN outperforms classical NN.