Related Experiment Video
Updated: May 15, 2025
Analyzing Long-Term Electrocardiography Recordings to Detect Arrhythmias in Mice
Published on: May 23, 2021
Cardiotocography data analysis for foetal health classification using Spatial Bayesian Neural Network Optimized with
P Solainayagi1, G Sivagaminathan2, Sabenabanu Abdulkadhar3
1Department of Computer Science and Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences (SIMATS), Chennai, Tamil Nadu, India.
Abstract:
Pregnancy complications require early detection, but traditional Cardiotocography (CTG) analysis is labor-intensive and error-prone. This manuscript presents Cardiotocography Data Analysis for Foetal Health Classification using Spatial Bayesian Neural Network Optimized with Dwarf Mongoose Optimizer (CDA-FHC-SBNN-DMO). The process involves collecting CTG data, optimizing feature selection with Humboldt Squid Optimization Algorithm (HSOA) and classification using Spatial Bayesian Neural Network (SBNN) to categorize foetal health. Dwarf Mongoose Optimizer (DMO) is used to optimize SBNN. The CDA-FHC-SBNN-DMO method was implemented in Python, outperforms existing methods, achieving improvements of 20.89%, 31.45%, and 28.32% in accuracy, and significant increases in precision and recall.
