Table 3 Performance comparison of features derived from different techniques.

From: Enhancing parkinson disease detection through feature based deep learning with autoencoders and neural networks

Feature Source

Accuracy (%)

Precision (%)

Recall (%)

F1 Score (%)

Raw Audio Data

83.25

84.1

82.8

83.45

PCA-Extracted Features

89.45

90.1

88.95

89.52

SAE-Extracted Features

96.15

98

98

98

Back to article page