| Autor: |
Pethuraj, Mohamed Shakeel, Burhanuddin, M. A., Dzakiyullah, Nur Rachman |
| Předmět: |
|
| Zdroj: |
Neural Computing & Applications; Nov2024, Vol. 36 Issue 31, p19777-19793, 17p |
| Abstrakt: |
Psychological vital assessments are required for monitoring health conditions and observing body reactions toward diseases and medications. Wearable sensors play a vital role in sensing body vitals and presenting them as signals for computer-based analysis. The problem relies on the signal decoding due to its input stream that turns out to be discrete/ continuous. Therefore for addressing the above specific issue, this article introduces MV-DUO (Multi-Variate Discrete Unified Optimization) method. This method addresses the above problem from a multi-variate perspective by sensing differential signals across healthy and unhealthy conditions. The healthy and unhealthy conditions are trained using neural learning by augmenting/ ceasing external vital data. The unification is performed using single-point artificial ecosystem-based optimization for identifying discrete sequences collaborated with continuous signals. The single-point reference is grouped based on the maximum continuity fitness observed under various sensing intervals. In this process, the non-grouped sequences are identified as unhealthy or discrete for which additional detection training and classification are required. Considerably the changes between successive sensing intervals are used for variations detection from unified high-fitness groups. Those grouped instances are used for training new vital changes observed at distinct intervals. This improves detection accuracy under controlled errors. For the varying sensing intervals, the proposed method achieves 14.13% high accuracy, 8.29% high grouping rate, 10.77% less error, and 10.07% less detection time. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
Full text from SpringerLink