Research on Improved Depth Belief Network-Based Prediction of Cardiovascular Diseases

Table 1

Data set attributes.

Features	Description	Data types	Normalization	Value
Age	Age	Continuous data	Min-max scaling	16–80; 0∼1
Sex	Gender	Text-based data	Direct mapping	0: female
				1: male
Cp	Chest pain type	Text-based data	Direct mapping	0: typical angina
				1: typical type angina
				2: nonangina pain
				3: asymptomatic
Trestbps	Trest blood pressure	Range data	Improved min-max scaling	MmHg on admission to the hospital
Chol	Serum cholesterol	Range data	Improved min-max scaling	(mg/dl)
Fbs	Fasting blood sugar	Hierarchical data	Hierarchical mapping	0: <120 mg/dl
				1: >120 mg/dl
Restecg	Resting electrographic results	Text-based data	Direct mapping	0: normal
				1: having ST-T wave abnormality
				2: showing probable or definite left ventricular hypertrophy
Thalach	Maximum heart rate achieved	Range data	Improved min-max scaling	—
Exang	Exercise-induced angina	Text-based data	Direct mapping	0 = no
				1 = yes
Oldpeak	ST depression induced by exercise relative to rest	Range data	Improved min-max scaling
Slope	Slope of the peak exercise ST segment	Text-based data	Direct mapping	0: unsloping
				1: flat
				2: downsloping
Ca	Number of major vessels colored by fluoroscopy	Text-based data	Direct mapping	0–3
Thal		Text-based data	Direct mapping	0: normal
	1: fixed defect
	2: reversible defect
Num	Predicted attribute	—	—	0, 1, 2, 3, 4