Internet of Things Enabled Disease Diagnosis Model for Smart Healthcare Systems

Authors

  • Ms. A. Priyanka, Dr. P. Devabalan, Shubhashish Jena, Subhashree Jena

DOI:

https://doi.org/10.17762/msea.v71i4.1124

Abstract

Recent advances in the Internet of Things (IoT), cloud computing, and Artificial Intelligence (AI) have turned the traditional healthcare system into an intelligent healthcare system. Adding important technologies like IoT and AI could make medical care better. Putting IoT and AI together gives the healthcare business new ways to do things. In this way, the current work presents a new way for AI and IoT to work together to help intelligent healthcare systems find sickness. In this paper, AI and IoT convergence methods are used to try to build a model that can find heart disease and diabetes. The provided model has several steps, such as collecting data, preprocessing it, classifying it, and adjusting the parameters. IoT devices, like wearables and sensors, make it easy to collect data, which can then be used by AI to figure out what's wrong with someone. Cascaded Long Short Term Memory (CSO-CLSTM), which is based on the Crowd Search Optimization algorithm, is used in the proposed method for finding diseases. CSO is used to fine-tune the "weights" and "bias" parameters of the CLSTM model to improve the classification of medical data. The isolation Forest (iForest) method is also used to leave outliers from this study. The CLSTM model is much better at making diagnoses when CSO is used. Healthcare data were used to prove that the CSO-LSTM model works. A new version of LSTM, called Convolution 2D Neural Network (CNN2D), has been added to the CNN2D algorithm, along with a CSO features selection technique. Experiments using data from the Heart and Diabetes show that the extension strategy is the most accurate.

Downloads

Published

2022-10-18

How to Cite

Ms. A. Priyanka, Dr. P. Devabalan, Shubhashish Jena, Subhashree Jena. (2022). Internet of Things Enabled Disease Diagnosis Model for Smart Healthcare Systems. Mathematical Statistician and Engineering Applications, 71(4), 5398–5411. https://doi.org/10.17762/msea.v71i4.1124

Issue

Section

Articles