Deep Layer Kernel Sparse Representation Network for the Detection of Heart Valve Ailments from the Time-Frequency Representation of PCG Recordings

Table 4

Overall accuracy values obtained using the DLKSRN classifier for various number of neurons in the 1st and 2nd hidden layer of validation and test sets for N vs. MS vs. MR vs. AS vs. MVP classification scheme.

Number of neurons		Overall accuracy (%)
1^st hidden layer	2^nd hidden layer	Validation set	Test set
200	100	94.60	95.86
400	200	96.00	96.26
600	400	96.20	96.66
800	600	97.80	99.23
1000	800	95.80	97.33