This codes correspond to the paper called "A Learning-Based Image Processing Approach for Pulse Wave Velocity Estimation using spectrogram from Peripheral Pulse Wave Signals: An in-silico Study", and have the following uses:
-
Spectrogram_selection.m : This file containts the code to select the parameters for the histogram computing the Q-metrics.
-
SCSA_tune.m and SCSA_noise_tune.m : This files contains the codes to selects the SCSA parameters for the noisy-free cases and the noisy cases.
-
Laws_features.m, SCSA_features.m and Statistical_features.m : This files contains the codes to compute the different features used in this project.
-
ML_hyptun.py : This files contains the code to train the different machine learning models and obtain the prediction.
-
Functions : This folder contains the different functions used in the project
-
Data: The dataset used is this project can be downloaded in : https://peterhcharlton.github.io/pwdb/index.html
-
Results: Every time you run the algorithms the result will be saved in this folder