An Efficient SMOTE-Based Deep Learning Model for Heart Attack Prediction

Table 2

Parameters tunning of classification models.

Classification models	Parameter tunning
AdaBoost	n_estimators = 30, learning rate = 1, algorithm = SAMME.R, base estimator = decisionclassifier
Bagging	Base estimator = decisionclassifier, n_estimators = 100, bootstrap = true
Random forest	n_estimators = 100, max_depth = 16, bootstrap = true, min_samples_leaf = 0.1, min_samples_split = 2, min_leaf_nodes = 10
KNN	n_neighbors = 10, , weights = “uniform,” algorithm = “auto”, leaf_size = 30
Logistic regression	Stopping criteria-1e − 9, bias = true, maximum iteration for convergence = 100
Naïve Bayes	Prior = default, smoothing = 1e − 9, class count = 2
Support vector machine	Regularization = 1, kernel = rbf, kernel coefficient = gamma
Vote	Voting = “hard,” estimators = logistic regression, decision tree,
Artificial neural network	Activation function = “relu” for input layers, activation function = “sigmoid” for output layer, dropout = “0.1 ,” batch size = “10,” num_hidden_layers = “1,” loss = “binary_cross-entropy,” optimizer = “Adam,” epoch = “150”