ordikhan Goto Github PK

2d_

2d_genetic

all-machinelearning-hospital

A number of machine learning models for hospital data

calibration

The output of previous steps was introduced to a modifier function. The modifier function calculated the ratio of people who had a positive class label to the total number of people covered in each cell of the chromosome matrix. To maintain the chart order and chromosome validity, the gene was increased if this ratio was higher than 50% and was decreased otherwise.

coxmodel-pars

This repository contains the implementation of the PARSproject using the Cox model.

data-cleansing

Dataste cleaning parts in machine learning

deep-learning-for-hertdataset

deep learning 3 laye cnn

exam-in-quora

exam

feature_selection

feature_selection

framingham

Calculating the risk of Framingham cardiovascular disease with Python coding language.

gcs

In this project, we have used a machine learning model for the prediction of cancers in the dataset of the Golestan cohort; the dataset is unavailable. The code of this project is written in python and implemented in the notebook.

heart-disease-site-jango

Thesis site

imbalanced-dataset

Imbalanced

procam

Calculating the risk of PROCAM cardiovascular disease with Python coding language.

raha_

Initial and install the labrary sphonix

reynolds

Calculating the risk of Reynolds cardiovascular disease with Python coding language.

simple-genetic-algorithm

supervised-learning

A few classic machine learning methods

supervised-learning-ann

ANN

unsupervised-learning

A few classic methods of machine learning unsupervised learning

version-machine-for-hertdataset-

version-machine-for-hertdataset-and-cancer

xpars-1d-representation

This repository contains the genetic code of the Chart-base one-dimensional representation of the CVD risk score part of the published article project ("An evolutionary machine learning algorithm for cardiovascular disease risk prediction"). The method is the non-cholesterol approach, in which each block is a 4×1 matrix representing the assessed risk at different BP intervals, thus is called the one-dimensional (1D) representation.

xpars-2d-representation

This repository contains the genetic code of the Chart-base two-dimensional representation of the CVD risk score part of the published article project ("An evolutionary machine learning algorithm for cardiovascular disease risk prediction"). The method is more widely used, which combines BP and cholesterol levels. The chart was composed of same-sized blocks, each representing four categories for BP and five for cholesterol, making each block a 4×5 matrix. This is the code that uses only 5 risk factor ('blood_preMIure;, 'sex', 'whr', 'cholesterol', 'age').