Key result
The proposed 1DCNN-ABC-Tabu optimized algorithm demonstrated superior performance in terms of error rate and accuracy for cardiac classification in an IoT-based edge computing environment.
Why the study?
Transferring healthcare data consumes substantial energy and time, causing high energy and latency issues that edge computing combined with IoT can address.
An optimized CNN model utilizing edge computing and IoT paradigms can provide accurate and low-latency cardiac classification for health monitoring.
Background: The current environment of modern computation can offer a smart healthcare monitoring for the early prediction of disease detection. For the domain of healthcare services, the Internet of Things (IoT) has a vital role, and also aids in the enhancement of the data’s processing as well as predictions. The transfer of data or reports from one location to another will consume a lot of energy as well as time, and also does result in issues of high energy as well as latency. With edge computing, the disadvantages can be easily resolved. Objectives: This work presents a Convolutional Neural Network (CNN)-based model of prediction which employs edge computing as well as IoT paradigms. The term edge computing will refer to a distributed environment framework that facilitates swift resource accessibility and response times by means of the local edge servers for processing at the end of the IoT devices. With this model, there can be an analysis of the health data which has been gathered by the IoT devices. Additionally, the edge devices will employ the edge servers for offering the patients as well as the doctors health-prediction reports in a timely manner. Methods: This work has proposals of an optimized CNN with Tabu Search (TS), Artificial Bee Colony (ABC) as well as the hybrid TS-ABC algorithms. Results: Analysis of these proposed algorithms is done with the parameters of performance such as the rate of error and the accuracy. Also, these algorithms’ simulated outcomes have been able to demonstrate their superior performance in comparison to the other technologically advanced approaches.
No takes yet. Share an insight, caveat, or question.
Stephen et al. (2023) studied Cardiac classification. 1DCNN-ABC-Tabu optimized model vs. Standard CNN and other optimization algorithms was evaluated on Error rate and accuracy. The proposed 1DCNN-ABC-Tabu optimized algorithm demonstrated superior performance in terms of error rate and accuracy for cardiac classification in an IoT-based edge computing environment.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: