| Autor: |
Prasad Reddy, Tatiparti B., Venkata Srinivasa Rao, Cheruku Poorna, Reddy, T. Suhasini, Ghate, Sukhaveerji |
| Předmět: |
|
| Zdroj: |
AIP Conference Proceedings; 2024, Vol. 2971 Issue 1, p1-16, 16p |
| Abstrakt: |
Nowadays, Internet of Medical Things (IoMT) and cloud computing (CC) is typically used in various healthcare requests by the amalgamation of intensive care objects like medical strategies and sensors to observe distant patients. To avail enhanced medical services, the massive amount of data produced by IoMT devices from the healthcare sector is inspected in the cloud ambience in its place depending on limited processing and storage sources. Parallelly, previous recognition of chronic kidney disease (CKD) is necessary for diminishing the death rates. This article develops a Modified Arithmetic Optimization with fusion based Deep Learning based Chronic Kidney Disease Classification (MAOFDL-CKDC) model for IoMT environment. The proposed MOAFDL-CKDC technique encompasses data acquisition at the preliminary stage to collect patient data. Followed by, data is pre-processed to make it compatible with further processes. For CKD detection and classification, fusion-based DL models namely gated recurrent unit (GRU), deep belief network (DBN), and bidirectional long short-term memory (BiLSTM) model is practical in this study. To improve the detection efficacy of the MOAFDL-CKDC technique, the MAO algorithm is designed by the combination of Levy flight with the traditional AOA. The performance assessment of the MOAFDL-CKDC technique is tested on standard CKD dataset from UCI source. The comparison study demonstrates the promising performance of the MOAFDL-CKDC technique over other existing approaches. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
