Cargando…

A comparative recognition research on excretory organism in medical applications using artificial neural networks

Purpose: In the contemporary era, a significant number of individuals encounter various health issues, including digestive system ailments, even during their advanced years. The major purpose of this study is based on certain observations that are made in internal digestive systems in order to preve...

Descripción completa

Detalles Bibliográficos
Autores principales: Selvarajan, Shitharth, Manoharan, Hariprasath, Iwendi, Celestine, Alsowail, Rakan A., Pandiaraj, Saravanan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10312079/
https://www.ncbi.nlm.nih.gov/pubmed/37397968
http://dx.doi.org/10.3389/fbioe.2023.1211143
Descripción
Sumario:Purpose: In the contemporary era, a significant number of individuals encounter various health issues, including digestive system ailments, even during their advanced years. The major purpose of this study is based on certain observations that are made in internal digestive systems in order to prevent severe cause that usually occurs in elderly people. Approach: To solve the purpose of the proposed method the proposed system is introduced with advanced features and parametric monitoring system that are based on wireless sensor setups. The parametric monitoring system is integrated with neural network where certain control actions are taken to prevent gastrointestinal activities at reduced data loss. Results: The outcome of the combined process is examined based on four different cases that is designed based on analytical model where control parameters and weight establishments are also determined. As the internal digestive system is monitored the data loss that is present with wireless sensor network must be reduced and proposed approach prevents such data loss with an optimized value of 1.39%. Conclusion: Parametric cases were conducted to evaluate the efficacy of neural networks. The findings indicate a significantly higher effectiveness rate of approximately 68% when compared to the control cases.