Computational Models-Based Detection of Peripheral Malarial Parasites in Blood Smears

Table 2

Convolution neural network model.

Layer	Output	Parameter
i_1	[(N, 125, 125, io1)]	P0
c2d	(N, 125, 125, co1)	P1
mp2d	(N, 62, 62, mpo2)	p01
c2d_1	(N, 62, 62, c2do1)	P2
mp2d _1	(N, 31, 31, mp2o1)	p02
c2d2	(N, 31, 31, c2o2)	P3
m2d_2	(N, 15, 15, m2do)	p03
Fl	(N, flo)	P4
Dl	(N, det5)	14746112
Dt	(N, dot5)	p05
dns_1	(N, dnst5)	262656
Dot	(N, dot5)	d05
dense_2	(N, 1)	513
Total	—	15,102,529
Trainable	—	15,102,529
Non-trainable	—	0

Note: _1 = “input1”, c2d = “convolutional2d”, mp2d = “ max_poolint2d”, c2d_1 = “convolutional2d1”, mp2d _1 = “max_poolint2d1”, c2d2 = “convolutional2d2 “, m2d_2 = “max_poolint2d2 “, f1 = “Flatten Layers”, d1 = “ dropout”, dt = “ dense1”, dns_1 = “dense2”, dot = “dropout1”. io1 = “3”, co1 = “ “, mpo2 = “ 32”, c2do1 = “64 “, mp2o1 = “64 “, c2o2 = “128 “, m2do = “ 128”,flo = “ 28800”, det5 = “512 “, dot5 = “512 “, dnst5 = “ 512”, p0 = “0”, p1 = “ 896”, p01 = “0”, p2 = “ 18496”, p02 = “0”, p3 = “ 73856”, p03 = “0”, p4 = “ 0”, p05 = “0”, d05 = “0”.