Header menu link for other important links
X
Time Series Classification-Based Correlational Neural Network with Bidirectional LSTM for Automated Detection of Kidney Disease
N. Bhaskar, , N.Y. Philip
Published in Institute of Electrical and Electronics Engineers Inc.
2021
Volume: 21
   
Issue: 4
Pages: 4811 - 4818
Abstract
In this paper, we aim to explore the feasibility of salivary analysis for Chronic Kidney Disease (CKD) detection and thereby design an automated mechanism to detect CKD through analysis of human saliva samples. We have implemented an improved deep learning model that combines both a one-dimensional Correlational Neural Network (1-D CorrNN) and bidirectional Long Short-Term Memory (LSTM) network for making accurate predictions. The LSTM network is integrated with the neural model to utilize the capabilities of both these networks to analyze the time-series data. The proposed model is trained and tested with a CKD sensing module. The application of deep learning algorithms helps to improve the detection accuracy as they are capable of discovering the best features from the input data. The proposed method achieved an average accuracy rate of 98.08% for the testing dataset. The results show that the proposed detection module and classification algorithm substantially advance the current methodologies, and provides more accurate predictions compared to conventional methods. © 2001-2012 IEEE.
About the journal
JournalData powered by TypesetIEEE Sensors Journal
PublisherData powered by TypesetInstitute of Electrical and Electronics Engineers Inc.
ISSN1530437X