Image Reconstruction Algorithm Based on PSO-Tuned Fuzzy Inference System for Electrical Capacitance Tomography

Deabes, Wael; Amin, Hesham H.

doi:10.1109/access.2020.3033185

Cited by 17 publications

(10 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They are, however, computationally very expensive, thus, more useful for offline processing. The need for tools that can compromise the trade-off between high quality reconstructed images and computational efficiency, is currently the main interest of machine learning (ML) [17,18], more specifically, deep neural network (DNN) methods [19]. DNN methods have been utilized in many fields due to their ability to map complex nonlinear functions [20,21].…”

Section: Introductionmentioning

confidence: 99%

Adversarial Resolution Enhancement for Electrical Capacitance Tomography Image Reconstruction

Deabes

Abdel-Hakim

Bouazza

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

High-quality image reconstruction is essential for many electrical capacitance tomography (CT) applications. Raw capacitance measurements are used in the literature to generate low-resolution images. However, such low-resolution images are not sufficient for proper functionality of most systems. In this paper, we propose a novel adversarial resolution enhancement (ARE-ECT) model to reconstruct high-resolution images of inner distributions based on low-quality initial images, which are generated from the capacitance measurements. The proposed model uses a UNet as the generator of a conditional generative adversarial network (CGAN). The generator’s input is set to the low-resolution image rather than the typical random input signal. Additionally, the CGAN is conditioned by the input low-resolution image itself. For evaluation purposes, a massive ECT dataset of 320 K synthetic image–measurement pairs was created. This dataset is used for training, validating, and testing the proposed model. New flow patterns, which are not exposed to the model during the training phase, are used to evaluate the feasibility and generalization ability of the ARE-ECT model. The superiority of ARE-ECT, in the efficient generation of more accurate ECT images than traditional and other deep learning-based image reconstruction algorithms, is proved by the evaluation results. The ARE-ECT model achieved an average image correlation coefficient of more than 98.8% and an average relative image error about 0.1%.

show abstract

Section: Introductionmentioning

confidence: 99%

Adversarial Resolution Enhancement for Electrical Capacitance Tomography Image Reconstruction

Deabes

Abdel-Hakim

Bouazza

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Researchers from the ECT area tried to use machine learning-based approaches to solve the problem of image reconstruction. Deabes et al solved the forward problem using NN system, and they proposed a Multi-Fuzzy System (MFS) to generate images of conductive materials in a Lost Foam Casting (LFC) process [20,21].…”

Section: Introductionmentioning

confidence: 99%

Residual Autoencoder Deep Neural Network for Electrical Capacitance燭omography

Deabes¹,

Bouazza²

2022

Computers, Materials &Amp; Continua

Self Cite

View full text Add to dashboard Cite

Great achievements have been made during the last decades in the field of Electrical Capacitance Tomography (ECT) image reconstruction. However, there is still a need to make these image reconstruction results faster and of better quality. Recently, Deep Learning (DL) is flourishing and is adopted in many fields. The DL is very good at dealing with complex nonlinear functions and it is built using several series of Artificial Neural Networks (ANNs). An ECT image reconstruction model using DNN is proposed in this paper. The proposed model mainly uses Residual Autoencoder called (ECT_ResAE). A large-scale dataset of 320 k instances have been generated to train and test the proposed ECT_ResAE model. Each instance contains two vectors; a distinct permittivity distribution and its corresponding capacitance measurements. The capacitance vector has been modulated to generate a 66×66 image, and represented to the ECT_ResAE as an input. The scalability and practicability of the ECT_ResAE network are tested using noisy data, new samples, and experimental data. The experimental results show that the proposed ECT_ResAE image reconstruction model provides accurate reconstructed images. It achieved an average image Correlation Coefficient (CC) of more than 99% and an average Relative Image Error (IE) around 8.5%.

show abstract

“…Intelligent algorithms have steadily been used to the field of ECT image reconstruction, with the particle swarm optimization method, in particular, being frequently employed to address illposed issues due to its simple algorithm implementation and high robustness [3] . Many better algorithms for ECT image reconstruction based on particle swarm optimization have been presented [4][5][6][7] . K Luu et al adopted a competitive Particle Swarm Optimization (PSO) to assist particles in escaping from local minima, with a simple implementation that promotes diversity of particle swarm [4] .…”

Section: Introductionmentioning

confidence: 99%

Image Reconstruction Algorithm for Electrical Capacitance Tomography Based on Constrained Particle Swarm Optimization

Chen

Kan

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

When the particle swarm is active, the robustness of the system is quite great, which is very useful for solving ill-conditioned problems like picture reconstruction. In the reconstructed image, however, the large number of pixels results in the large dimension of particles, making it harder for particles to attain the ideal solution during the optimization process. A constraint condition is applied to the position of particles to solve this problem. The image reconstruction algorithm regularized by Tikhonov is used as the particle position reference to constrain the particles to search within a certain range of the algorithm, and the penalty function is used to solve the problem to improve the particle search speed. For the inertia weight of particle swarm, this paper uses linear decreasing weight to realize its adaptive dynamic adjustment, which improves the flexibility of the algorithm. When chaos operator is added to the particle swarm location search process, if the particle is trapped in a local optimum, the chaos variable will fluctuate within a certain range, thus reducing the error rate of the optimal solution. The experimental comparison results illustrate that the modified particle swarm optimization technique for the image reconstruction of Electrical Capacitance Tomography outperforms the classic LBP and Tikhonov algorithms in terms of accuracy and efficiency.

show abstract

Image Reconstruction Algorithm Based on PSO-Tuned Fuzzy Inference System for Electrical Capacitance Tomography

Cited by 17 publications

References 25 publications

Adversarial Resolution Enhancement for Electrical Capacitance Tomography Image Reconstruction

Adversarial Resolution Enhancement for Electrical Capacitance Tomography Image Reconstruction

Residual Autoencoder Deep Neural Network for Electrical Capacitance燭omography

Image Reconstruction Algorithm for Electrical Capacitance Tomography Based on Constrained Particle Swarm Optimization

Contact Info

Product

Resources

About