Open AccessResearch on improving ERT reconstruction precision based on combined algorithm
Author(s) -
Shihan Li,
Hua Yan
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1754/1/012238
Subject(s) - particle swarm optimization , algorithm , computation , computer science , iterative reconstruction , field (mathematics) , reconstruction algorithm , population , mathematical optimization , artificial intelligence , mathematics , demography , sociology , pure mathematics
Among the traditional image reconstruction algorithm for ERT (Electrical Resistance Tomography) system, the Landweber algorithm is the most commonly used iterative algorithm, with moderate computation and good reconstruction quality. However, because "soft field" error is usually ignored in reconstruction, there is still much room for improvement in the quality of reconstructed images. Aiming this problem, a combined algorithm is proposed. The Landweber reconstruction results were taken as the initial population position of the particle swarm optimization (PSO). Through the random forest regression model, the "soft field" error prior condition is obtained, and used in the construction of the PSO objective function to eliminate the influence of ignoring the "soft field" error. The simulation experiment results show that the proposed algorithm effectively improves the accuracy of the reconstructed image.