IoT based cloud network for smart health care using optimization algorithm
In recent years, the Internet of Things (IoT) technology has drawn significant interest as it can decrease the liability on healthcare services on account of an expansion in notable illnesses and the population's growing age. The best decision of virtualized resources in cloud computing plays a...
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Elsevier
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/b1f8b091bde349d49ca9dee8beb6e7fa |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | In recent years, the Internet of Things (IoT) technology has drawn significant interest as it can decrease the liability on healthcare services on account of an expansion in notable illnesses and the population's growing age. The best decision of virtualized resources in cloud computing plays a prominent role in improving the efficiency of cloud computing, reducing the overall time required to complete patient demands by turnaround time, and maximizing CPU use and waiting times. An improved PSO approach for improving physiological sensor-data fusion calculation accuracy in the Internet of Things (IoT) framework has been introduced in this paper. This approach helps in automatically diagnosing natural epilepsy and brain fatalities from detected EEG signals received by the health center. There is also an application of discrete wavelet transform for featuring abolition. Neurological disability diagnosis using particle swarm computation helps in optimizing the propagation of neural networks and EEG. A device that is more effective in terms of result precision requires complicated signals like EEG for input. While the primary ANN model diagnoses signals from the patient, it does not optimize the parameters. It, therefore, implies that the PSO-ANNs have a perfect number of cells in the secret layer to provide better performance than the basic EEG-Signal ANN-Model. The proposed model effectively improved about 4.6% reciprocal to the Genetic Algorithm optimum selection model in execution times. Moreover, the test result determines the sensitivity and accuracy metrics for different neurological disorders of the patient. |
|---|