Table 1.

Proposed fuzzy logic-empowered opposite learning mutant particle swarm optimization (FL-OLMPSO) algorithm.

S. no.	Steps
Level 1
1	Start
2	2.1. Initialization of data populaces Dp = { Dp1, Dp2, .................. Dpa} and velocity Wd
	2.2. Initialization of channel populaces Dk = { Dk1, Dk2, .................. Dka} and velocity Wk
3	Compute the wellness of population utilizing the cost work given in (14)
4	Compute lower bound value (MBp, MBi) and upper bound value (HBp, HBi) from Dp and Dk separately
	Calculate the opposite populace
5	For FL-TOLMPSO	For FL-POLMPSO
	5.1. Opposite data population	5.1. Opposite data population
	OD p = {ODp1, ODp2, .................. ODpa}	OD p = {ODp1, ODp2, .................. ODpa/2}
	OD pi = {ODpi,1, ODpi,2, .................. ODpi,M}	OD pi = {ODpi,1, ODpi,2, .................. ODpi,M}
	ODpi,j = MBp + HBa − Dpi,j	ODpi,j = MBp + HBa − Dpi,j
	5.2. Opposite channel population	5.2. Opposite channel population
	OD k = {ODk1,ODk2, .................. ODka}	OD k = {ODk1,ODk2, .................. ODka/2}
	OD ki = {ODki,1, ODki,2, .................. ODki,M}	OD ki = {ODki,1, ODki,2, .................. ODki,M}
	ODki,j = MBi + HBi − Dki,j	ODki,j = MB + HBi − Dki,j
6	Compute the fitness of both opposite populations (ODp and ODk) using the cost function given in equation (16)
7	Select the local best particle of the following: 7.1. Data population Mbdp from Dp and ODp 7.2. Channel population Lbdk from Dk and ODk
8	Select the global best particle of the following: 8.1. Data population Nbdp = min(Mbdp) 8.2. Channel population Nbdp = min(Lbdp)
Level 2: global best data vector is fixed and continuous FL-OLMPSO algorithm works on the channel population
9	Update velocities of each particle of channel population using FIS: Whim(n) = Whim(n−1) + FLC (LI, GI, Whim(n−1))
10	Update the position of each particle channel population Calculate the mutant operator (MO) Moh(i) = ∑j=1k(whij/k) Dkim(n) = Dkim(n−1) + Moh(i) ∗ rand()
11	Compute the fitness of mutated particles of channel population using equation (16)
12	Update the channel population Dk
13	If (number of cycles > required NoC) go to step 14 Else go to step 9
Level 3: in this level, the discrete FL-OLMPSO algorithm is used for estimating the data symbols
14	The global best particle of the data population is chosen and update the velocity: Whim(n) = FLC (LI, GI, Whim(n−1))
15	Update position of each particle of data population Compute the mutant operator (MO) Mod(i) = ∑j=1kWdij/k Dpim(n) = Dpim(n−1) + Mod(i) ∗ rand()
16	Compute the fitness of particles of data population using (16)
17	Update the data population Dp
18	If (number of cycles > required NoC) go to step 20 Else go to step 14
Level 4: next sample of the received signal is taken and execution goes to level 2
19	Stop