Internet of Medical Things (IoMT) and Reflective Belief Design-Based Big Data Analytics with Convolution Neural Network-Metaheuristic Optimization Procedure (CNN-MOP)

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18470%2F22%3A50019637" target="_blank" >RIV/62690094:18470/22:50019637 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.hindawi.com/journals/cin/2022/2898061/" target="_blank" >https://www.hindawi.com/journals/cin/2022/2898061/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1155/2022/2898061" target="_blank" >10.1155/2022/2898061</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Internet of Medical Things (IoMT) and Reflective Belief Design-Based Big Data Analytics with Convolution Neural Network-Metaheuristic Optimization Procedure (CNN-MOP)

Popis výsledku v původním jazyce

In recent times, the Internet of Medical Things (IoMT) is a new loomed technology, which has been deliberated as a promising technology designed for various and broadly connected networks. In an intelligent healthcare system, the framework of IoMT observes the health circumstances of the patients dynamically and responds to backings their needs, which helps detect the symptoms of critical rare body conditions based on the data collected. Metaheuristic algorithms have proven effective, robust, and efficient in deciphering real-world optimization, clustering, forecasting, classification, and other engineering problems. The emergence of extraordinary, very large-scale data being generated from various sources such as the web, sensors, and social media has led the world to the era of big data. Big data poses a new contest to metaheuristic algorithms. So, this research work presents the metaheuristic optimization algorithm for big data analysis in the IoMT using gravitational search optimization algorithm (GSOA) and reflective belief network with convolutional neural networks (DBN-CNNs). Here the data optimization has been carried out using GSOA for the collected input data. The input data were collected for the diabetes prediction with cardiac risk prediction based on the damage in blood vessels and cardiac nerves. Collected data have been classified to predict abnormal and normal diabetes range, and based on this range, the risk for a cardiac attack has been predicted using SVM. The performance analysis is made to reveal that GSOA-DBN_CNN performs well in predicting diseases. The simulation results illustrate that the GSOA-DBN_CNN model used for prediction improves accuracy, precision, recall, F1-score, and PSNR.

Název v anglickém jazyce

Internet of Medical Things (IoMT) and Reflective Belief Design-Based Big Data Analytics with Convolution Neural Network-Metaheuristic Optimization Procedure (CNN-MOP)

Popis výsledku anglicky

In recent times, the Internet of Medical Things (IoMT) is a new loomed technology, which has been deliberated as a promising technology designed for various and broadly connected networks. In an intelligent healthcare system, the framework of IoMT observes the health circumstances of the patients dynamically and responds to backings their needs, which helps detect the symptoms of critical rare body conditions based on the data collected. Metaheuristic algorithms have proven effective, robust, and efficient in deciphering real-world optimization, clustering, forecasting, classification, and other engineering problems. The emergence of extraordinary, very large-scale data being generated from various sources such as the web, sensors, and social media has led the world to the era of big data. Big data poses a new contest to metaheuristic algorithms. So, this research work presents the metaheuristic optimization algorithm for big data analysis in the IoMT using gravitational search optimization algorithm (GSOA) and reflective belief network with convolutional neural networks (DBN-CNNs). Here the data optimization has been carried out using GSOA for the collected input data. The input data were collected for the diabetes prediction with cardiac risk prediction based on the damage in blood vessels and cardiac nerves. Collected data have been classified to predict abnormal and normal diabetes range, and based on this range, the risk for a cardiac attack has been predicted using SVM. The performance analysis is made to reveal that GSOA-DBN_CNN performs well in predicting diseases. The simulation results illustrate that the GSOA-DBN_CNN model used for prediction improves accuracy, precision, recall, F1-score, and PSNR.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE

ISSN

1687-5265

e-ISSN

1687-5273

Svazek periodika

2022

Číslo periodika v rámci svazku

MAR 18

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

14

Strana od-do

"Article Number: 2898061"

Kód UT WoS článku

000783742700008

EID výsledku v databázi Scopus

2-s2.0-85127750826