A Support Vector Learning-Based Particle Filter Scheme for Target Localization in Communication-Constrained Underwater Acoustic Sensor Networks

. 2017 Dec 21;18(1):8. doi: 10.3390/s18010008

Algorithm 1 LSSVR-based observation function

1:
Initialization:Train LSSVR model with training dataset D and acquire $α$ and b by solving matrix Equation (17)
2:
Input: Raw data $R_{k}$
3:
Diagnosis of excessive sensing noise
4:
for all $l = 1, \dots, M$ do
5:
if There exists $T_{I L} - R_{I L} \geq \hat{p} τ (R_{k} [l])$ and $τ (R_{k} [l]) = 20 \log R_{k} [l] + β R_{k} [l] \cdot 10^{- 3}$ in (25) then
6:
Corresponding parameter which the excessive sensing occurs is set based on (26): $δ_{(l, l)} = \frac{| R_{k} [l] - {\bar{S}}_{l} |}{R_{k} [l]}$
7:
else
8:
Corresponding parameter which the excessive sensing does not occur is set based on (26): $δ_{(l, l)} = 1$
9:
end if
10:
end for
11:
All corresponding parameters are determined and the diagonal matrix $δ$ is obtained
12:
Iteration: calculate the observations
13:
while Termination condition: $|Z_{k}^{(ν + 1)} - b| \geq ϵ$ and $|Z_{k}^{(ν + 1)} - Z_{k}^{(ν)}| \leq ε$ do
14:
The iterative equation: $Z_{k}^{(ν + 1)} = Z_{k}^{(ν)} (δ R_{k}) = Q (Z_{k}^{(ν)})$ , $ν = 0, 1, 2 \dots$
15:
end while
16:
Output: Observation of $Z_{k} = Z_{k}^{(ν + 1)}$