Evolution of Deep Neural Network Architecture Using Particle Swarm Optimization to Improve the Performance in Determining the Friction Angle of Soil

Algorithm 1

Algorithm 1

	FOR each particle i in swarm
	Initialize parameters: , _damp, c1, c2.
	FOR each dimension j
	Initialize position xij randomly within permissible range
	Initialize velocity randomly within permissible range
	End FOR
	End FOR
	Iteration k = 1
	WHILE k < maximum_Iteration
	FOR each particle i in swarm
	Calculate fitness value
	IF fitness value > P_best[i] THEN
	P_best[i] = fitness value
	END IF
	IF fitness value > G_best THEN
	G_best = fitness value
	END IF
	END FOR
	FOR each particle i in swarm
	FOR each dimension j
	Calculate new velocity:
	(k + 1) = wvij(k) + c1random (0,1) (P_best[i] − xij[i]) + c2random (0,1) (G_best − xij[i])
	Update particle positon:
	xij(k + 1) = xij(k) + (k + 1)
	END FOR
	END FOR
	= ._damp
	k = k + 1
	END WHILE