Detection of Lungs Status Using Morphological Complexities of Respiratory Sounds

Table 1

Performance of ELM and SVM classifier for different sets of the proposed feature vectors.

Type of classifier	Feature set	Feature vector	SEN (%)	SPE (%)	CA (%)	Training time (ms)	Testing time (ms)
ELM	Set-1	[𝜒,𝜉]	52.94	69.38	62.82	0.75	0.57
SVM	Set-1	[𝜒,𝜉]	61.56	59.71	60.71	6.50	2.10
ELM	Set-2	[𝜒,𝜉,𝜁]	85.71	87.50	90.47	0.83	0.65
SVM	Set-2	[𝜒,𝜉,𝜁]	85.71	77.38	85.71	17.00	5.70
ELM	Set-3	[𝜒,𝜉,𝜁,𝛼]	86.30	86.90	92.86	4.20	3.70
SVM	Set-3	[𝜒,𝜉,𝜁,𝛼]	86.30	85.70	91.60	23.60	8.10

𝜒: Kurtosis; 𝜉: Skewness; 𝜁: Lacunarity; 𝛼: Sample Entropy.