Transformative Advancements in Fetal Cardiac Health through BILSTM Networks for FPCG Classification

Abstract

This article unveils a cutting-edge methodology for Fetal Phonocardiogram
(FPCG) classification employing Bidirectional Long Short-Term Memory (BILSTM)
networks. Acknowledging the pivotal role of fetal heart monitoring in
early anomaly detection, the research delves into the profound insights offered
by FPCG signals concerning fetal cardiac activity. The innovative approach
encompasses preprocessing FPCG signals using Mel-frequency cepstral coefficients
(MFCC) and spectrogram features, coupled with the strategic application
of BI-LSTM networks, ensuring a resilient classification framework. The bidirectional
nature of the LSTM architecture elevates the model’s ability to capture
temporal dependencies in both forward and backward directions, facilitating the
discernment of intricate patterns in fetal heart sounds. Remarkably, experimental
findings demonstrate a remarkable 98% accuracy, reaffirming the effectiveness
and precision of the BILSTM approach in fetal PCG classification. This pioneering
research significantly advances automated methods for evaluating fetal
cardiac health, promising transformative enhancements in prenatal care.