Identification and Classification of Lungs Focal Opacity Using CNN Segmentation and Optimal Feature Selection

Table 5

LBP-HOG features based classification results.

Methods	Prediction speed (obs/sec)	Training time (sec)	Accuracy (%)
Bagged ensemble	260	38.98	88.2
Subspace discriminant	140	15.307	90.1
Subspace KNN	110	11.841	78.9
RUSBoost	2800	22.179	87.5
Fine tree	740	2.997	82.2
Medium tree	760	2.155	82.2
Coarse tree	1000	7.058	85.5
Linear SVM	520	5.95	86.8
Quadratic SVM	520	4.90	88.8
Cubic SVM	690	6.77	87.5
Fine Gaussian SVM	780	6.59	82.2
Medium Gaussian SVM	700	7.503	83.6
Fine KNN	560	3.87	80.9
Medium KNN	610	2.11	71.1
Cubic KNN	280	4.81	76.3
Cosine KNN	600	4.49	79.6
Weighted KNN	620	4.699	82.9