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

Table 4

LBP Feature based classification results.

Methods	Prediction speed (obs/sec)	Training time (sec)	Accuracy (%)
Bagged ensemble	240	26.813	90.8
Subspace discriminant	140	34.813	87.5
Subspace KNN	110	34.081	93.4
RUSBoost	320	37.822	84.2
Fine tree	610	39.573	84.2
Medium tree	640	30.62	84.2
Coarse tree	3300	66.487	86.2
Linear SVM	1200	11.318	90.8
Quadratic SVM	1300	9.416	92.1
Cubic SVM	2500	11.899	92.1
Fine Gaussian SVM	2600	11.64	90.8
Medium Gaussian SVM	2400	11.51	92.1
Fine KNN	540	6.581	92.1
Medium KNN	740	4.525	87.5
Cubic KNN	820	8.64	86.2
Cosine KNN	910	8.94	91.4
Weighted KNN	1900	7.164	91.4