Attention-Based Sequence-to-Sequence Model for Time Series Imputation

. 2022 Dec 9;24(12):1798. doi: 10.3390/e24121798

Algorithm 2 Missing Time Series Imputation Algorithm.

Input:

T_{l}

T_{r}

of the time series,

Ψ

Encoder related parameters,

θ

Decoder related parameters, n number of iterations,

ξ

overall model optimizable parameters.
Output: P imputation all the samples
for i = 1 to n do
E←

E_{Ψ} (T_{l}, T_{r})

H←

H = E_{K}

C←

{S (\frac{E H^{T}}{\sqrt{d_{k}}}) \cdot E} \cup H

Q←

η_{θ} (T_{l}, T_{r})

O←

C \cup Q

D←

G_{θ} (O, H) \cup Q \cup C

P←

M_{ξ} (E, D)

end for
return P