Title: An efficient oppositional crow search optimisation-based deep neural network classifier for chronic kidney disease identification

Authors: Pramila Arulanthu; Eswaran Perumal

Addresses: Department of Computer Applications, Alagappa University, Karaikudi, India ' Department of Computer Applications, Alagappa University, Karaikudi, India

Abstract: Internet of things (IoT) enables gathering the patient data that can incite logically exact and tiny prosperity events. Distributed computing along with the IoT is another example of gainful regulating and treatment of sensor data. This paper presents IoT and cloud-based capable choice emotionally supportive network for identification of chronic kidney disease (CKD). Additionally, deep neural network (DNN) classifier is utilised for the assurance of CKD. Oppositional crow search (OCS) optimisation approach selects the necessary features and takes out the undesirable features and also it enhances the process of DNN. This model gathers the patient information by utilising the IoT gadgets with cloud and related therapeutic records from the UCI vault. The proposed OCS-DNN measured by the accuracy, specificity, execution time and sensitivity which produces 97.71% accuracy, 98.88% sensitivity and 93.44% of specificity when contrasted with other classifiers and results exhibit that the proposed OCS-DNN is much better.

Keywords: OCS; deep neural network; DNN; optimisation; cloud; internet of things; IoT; chronic kidney disease; CKD.

DOI: 10.1504/IJICA.2021.116671

International Journal of Innovative Computing and Applications, 2021 Vol.12 No.4, pp.206 - 215

Received: 02 Mar 2020
Accepted: 31 May 2020
Published online: 29 Jul 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article