Simulation and Analysis of Fetal Distress Using PCG and ECG Signals
Title:- Fully Automated Hybrid Deep Learning based Continuous Remote Monitoring for Fetal Distress Level Classification & Preterm Labor Prediction Using PCG and EHG Signals
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Installl the required software ------- 1) Matlab-R2022b
Copy the zip file and paste to the D or E drive and Extract the zip file.
Copy the "Propsed - Fully Automated Hybrid Deep Learning based Continuous Remote Monitoring" and "Existing - Automated labour detection framework" folders and Paste into any Drive.
Note: Don't Delete any file or folders project contains...
Then Launch matlab IDE.
Next copy the source code location (Note: Use the source code location avoids space). Then paste the source code location into matlab address location. After paste, press the enter key.
Dataset Download Links:
https://physionet.org/content/sufhsdb...
https://physionet.org/content/ehgdb/1...
Existing Work -- https://physionet.org/content/tpehgdb...
Implementation Plan:
---------------------
Step 1: Initially we load signals data from two datasets such as etal Heart Sound Database (SUFHSG), and Icelandic EHG database (IEHG).
Step 2: Next we perform the Dual Way Pre-Processing, In this step the signals from the PCG sensors and EHG sensor are digitized using Analog to Digital Converter (ADC). The pre-processing module consists of two sub-modules (i.e., PCG sub module and EHG sub module) for processing the digitalized PCG and EHG signals respectively.
2.1: The PCG sub-module, initially removes the unwanted noises and artifacts in the incoming PCG signals using Weight based Savitzky-Golay Filter (WSGF).
2.2: The proposed work adopts blind source separation method named Runner Game Optimizer based Independent Component Analysis (RGO-ICA). (i.e., The average MHR is ranging between 70bpm-90bpm, and the average FHR is between 60bpm-110bpm and above).
2.3: For both the FHR and MHR, the unwanted signal spikes (i.e., unwanted amplitudes) are removed by Enhanced Median Filter (EMF). (At last, the preprocessed FHR and MHR PCG signals are provided to
Least Square Support Vector Machine (LSSVM) algorithm for quality analysis which classifies the preprocessed signals).
Step 3: Next Deep Markov Model based Segmentation & Collaborative Signal Analysis, The segmentation is performed for three signals in separate manner using agents such as FHR, MHR, and EHG agents respectively. The proposed DMM is composed of a learning and physical model to capture the uncertain states of the incoming FHR, MHR, and EHG signals and effectively segments them. The classification, we reconstruct the 2D correlation graph to 3D correlation graph using General Adversarial Neural Network (GAN) with less complexity.
Step 4: Then we perform the Hybrid Deep Learning based Automated Fetal Distress Level Detection & Prediction Process, In this process the fetal distress detection and prediction using hybrid deep learning algorithm named Contextual Axial Reverse Attention Network - Long Short Term Memory (CARANet-LSTM).
Step 5: Next Secure Storage process, In this process the results are then stored in the cloud server database in an encrypted manner using Boosted ChaCha (B-ChaCha) Algorithm.
Step 6: Finally, The proposed work is evaluated in terms of metrics such as,
• Accuracy
• Sensitivity
• F1-Score
• True Positive Rate
• Security Strength
• Prediction Accuracy
• Complexity
===========================================================================================================================================================
Software Requirement:
----------------------
1. Tool: Matlab-R2022b
2. Operating System: Windows 10 (64-bit)
===========================================================================================================================================================
Note:-
-------
We make a simulation based process only.
We perform the EXISTING process based on the REFERENCE 3 Title: - Automated labour detection framework to monitor pregnant women with a high risk of premature labour using machine learning and deep learning
