Self-Regulated Particle Swarm Multi-Task Optimization

. 2021 Nov 11;21(22):7499. doi: 10.3390/s21227499

Algorithm 3 VelocityUpdate_V2.

1:
for individual $p_{i}, i = 1$ to n do
2:
Get the index $j_{b}$ of the biggest in $ϕ_{i} = {ϕ_{i, j}}_{j = 1}^{k}$ .
3:
$t e m p_{d} = 0, n o r m_{a f} = 0$ .
4:
for task $T_{j}, j = 1$ to k do
5:
if $j = j_{b}$ or $r a n d < ϕ_{i, j}$ then
6:
$r_{2} = r a n d$
7:
$t e m p_{d} = t e m p_{d} + r_{2} * ϕ_{i, j} * (g b e s t_{j, d} - x_{i, d}^{g})$ .
8:
$n o r m_{a f} = n o r m_{a f} + ϕ_{i, j}$ .
9:
end if
10:
$v_{i, d}^{g + 1} = w v_{i, d}^{g} + c_{1} r_{1} (p b e s t_{i, d} - x_{i, d}^{g}) + c_{2} (t e m p_{d} / n o r m_{a f})$ .
11:
end for
12:
end for