More Web Proxy on the site http://driver.im/

research-article

Minimax bilevel fractional optimization for imaging in electrical capacitance tomography

Authors:

Qibin LiuAuthors Info & Claims

Volume 169, Issue C

https://doi.org/10.1016/j.asoc.2024.112598

Published: 18 February 2025 Publication History

Abstract

Electrical capacitance tomography shows great promise in measuring multiphase flow parameters, but its effectiveness is hampered by poor image reconstruction quality. To unlock the technique’s full potential, the image reconstruction problem is reformulated as a minimax bilevel fractional optimization problem. This innovative model accommodates uncertainties in both the reconstruction model and measurement data, while enabling automatic parameter adjustment. It leverages priors related to measurement physics, collected data, and reconstruction objects, and effectively bridges the gap between machine learning and the physical mechanisms underlying the measurement process. A potent nested optimizer that merges the proposed fractional optimization solver with the differential evolution algorithm is proposed to solve the minimax bilevel fractional optimization imaging model. The minimax bilevel physics-informed random vector functional link network is proposed to infer the supervised learning prior. To maintain predictions in line with core physical significances, the training process incorporates measurement physics through a newly devised minimax bilevel optimization training model. Comparative analysis demonstrates that this novel reconstruction approach significantly outperforms leading imaging algorithms in terms of reconstruction quality and noise robustness. This research presents a comprehensive solution to imaging challenges, and the insights and methodologies contribute to the advancement of computational imaging and electrical capacitance tomography.

Highlights

•

A new minimax bilevel fractional optimization model is introduced for imaging.

•

Measurement physics and machine learning are bridged.

•

Uncertainties in model are considered and model parameters are learned adaptively.

•

A new solver with two optimization loops is proposed to solve the imaging model.

•

The effectiveness of the proposed imaging algorithm is verified.

References

[1]

C. Kang, H. Zhou, The extensions of convergence rates of Kaczmarz-type methods, J. Comput. Appl. Math. 382 (2021),.

[2]

W.T. Wang, K.Y. Zhao, P. Zhang, J.W. Bao, S.B. Xue, Investigation of water ingress into uncracked and cracked cement-based materials using electrical capacitance volume tomography, Mater. Des. 220 (2022),.

[3]

X.Y. Dong, Z.Y. Ye, M. Soleimani, Image reconstruction for electrical capacitance tomography by using soft-thresholding iterative method with adaptive regulation parameter, Meas. Sci. Technol. 24 (2013) 1–8,.

[4]

P. Suo, J. Sun, X. Zhang, X. Li, S. Sun, L. Xu, Adaptive group-based sparse representation for image reconstruction in electrical capacitance tomography, IEEE Trans. Instrum. Meas. 72 (2023) 4504509,.

[5]

H.B. Guo, S. Liu, H.Y. Cheng, S.X. Sun, J.Q. Ding, H.Q. Guo, Iterative computational imaging method for flow pattern reconstruction based on electrical capacitance tomography, Chem. Eng. Sci. 214 (2020),.

[6]

Y.Y. Shi, J.J. Liao, M. Wang, Y.T. Li, F. Fu, M. Soleimani, Total fractional-order variation regularization based image reconstruction method for capacitively coupled electrical resistance tomography, Flow. Meas. Instrum. 82 (2021),.

[7]

J. Chen, M. Zhang, Y. Liu, J. Chen, Y. Li, Image reconstruction algorithms for electrical capacitance tomography based on ROF model using new numerical techniques, Meas. Sci. Technol. 28 (2017) 1–11,.

[8]

G.W. Tong, S. Liu, H.Y. Chen, X.Y. Wang, Regularization iteration imaging algorithm for electrical capacitance tomography, Meas. Sci. Technol. 29 (2017),.

[9]

J. Dutta, S. Ahn, C. Li, S.R. Cherry, R.M. Leahy, Joint L1 and total variation regularization for fluorescence molecular tomography, Phys. Med. Biol. 57 (2015) 1459–1476,.

[10]

W.S. Xie, Y.F. Yang, B. Zhou, An ADMM algorithm for second-order TV-based MR image reconstruction, Numer. Algorithms 67 (2014) 827–843,.

Digital Library

[11]

X. Cai, R. Chan, T. Zeng, A two-stage images segmentation method using a convex variant of the Mumford-Shah model and thresholding, SIAM J. Imaging Sci. 6 (2013) 368–390,.

Digital Library

[12]

A. Padcharoen, P. Kumam, J. Martínez-Moreno, Augmented Lagrangian method for TV-l1-l2 based colour image restoration, J. Comput. Appl. Math. 354 (2019) 507–519,.

Digital Library

[13]

X.J. Chen, Z.Q. Jiang, X. Han, X.L. Wang, X.Y. Tang, Research of magnetic particle imaging reconstruction based on the elastic net regularization, Biomed. Signal Process. Control 69 (2021),.

[14]

W. Guo, J. Qin, W. Yin, A new detail-preserving regularization scheme, SIAM J. Imaging Sci. 7 (2014) 1309–1334,.

Digital Library

[15]

X. Liu, Total generalized variation and wavelet frame-based adaptive image restoration algorithm, Vis. Comput. 35 (2018) 1883–1894,.

Digital Library

[16]

G. Guo, G.W. Tong, L. Lu, S. Liu, Iterative reconstruction algorithm for the inverse problems in electrical capacitance tomography, Flow. Meas. Instrum. 64 (2018) 204–212,.

[17]

D.O. Acero, Q.M. Marahsdeh, F.L. Teixeira, Relevance vector machine image reconstruction algorithm for electrical capacitance tomography with explicit uncertainty estimates, IEEE Sens. J. 99 (2020) 1–15,.

[18]

B. Zhang, L. Zhang, Z. Wang, Z. Cui, Y. Sun, H. Hua, Image reconstruction of planar electrical capacitance tomography based on DBSCAN and self-adaptive ADMM algorithm, IEEE Trans. Instrum. Meas. 72 (2023) 4504711,.

[19]

J. Lei, S. Liu, X.Y. Wang, Q.B. Liu, An image reconstruction algorithm for electrical capacitance tomography based on robust principle component analysis, Sensors 13 (2013) 2076–2092,.

[20]

Y. Sun, Y. Zhang, Y. Wen, Image reconstruction based on fractional Tikhonov framework for planar array capacitance sensor, IEEE Trans. Comput. Imaging 8 (2022) 109–120,.

[21]

H.J. Xie, T. Xia, Z.N. Tian, X.D. Zheng, X.B. Zhang, A least squares support vector regression coupled linear reconstruction algorithm for ECT, Flow. Meas. Instrum. 77 (2021),.

[22]

J. Lei, H.P. Mu, Q.B. Liu, X.Y. Wang, S. Liu, Data-driven reconstruction method for electrical capacitance tomography, Neurocomputing 273 (2018) 333–345,.

Digital Library

[23]

X.H. Wu, M.Y. Gao, S.R. Xu, S.W. Liu, H. Yan, Y. Wang, Research on ECT image reconstruction method based on long short-term memory network (LSTM), Flow. Meas. Instrum. 95 (2024),.

[24]

H. Zhu, J. Sun, L.J. Xu, W.B. Tian, S. Sun, Permittivity reconstruction in electrical capacitance tomography based on visual representation of deep neural network, IEEE Sens. J. 20 (2020) 4803–4815,.

[25]

J. Zheng, L. Peng, A deep learning compensated back projection for image reconstruction of electrical capacitance tomography, IEEE Sens. J. 20 (2020) 4879–4890,.

[26]

G. Wang, J.C. Ye, B.D. Man, Deep learning for tomographic image reconstruction, Nat. Mach. Intell. 2 (2020) 737–748,.

[27]

Y.N. Bai, W. Chen, J. Chen, W.S. Guo, Deep learning methods for solving linear inverse problems: research directions and paradigms, Signal Process. 177 (2020),.

[28]

W.N. Niu, X.H. Liao, S.P. Huang, Y.D. Li, X.S. Zhang, B.B. Li, A robust wide & deep learning framework for log-based anomaly detection, Appl. Soft Comput. 153 (2024),.

Digital Library

[29]

S. Halder, K.H. Lim, J.F. Chan, X.Z. Zhang, A survey on personalized itinerary recommendation: from optimisation to deep learning, Appl. Soft Comput. 152 (2024),.

Digital Library

[30]

N.J. Szymanski, B. Rendy, Y. Fei, R.E. Kumar, T. He, D. Milsted, M.J. McDermott, M. Gallant, E.D. Cubuk, A. Merchant, H. Kim, A. Jain, C.J. Bartel, K. Persson, Y. Zeng, G. Ceder, An autonomous laboratory for the accelerated synthesis of novel materials, Nature (2023),.

[31]

T. Xu, P. Xu, C.X. Yang, Z.X. Li, A. Wang, W.N. Guo, An LSTM-stacked autoencoder multisource response prediction and constraint optimization for scaled expansion tubes, Appl. Soft Comput. 153 (2024),.

Digital Library

[32]

Q. Zhu, A. Shankar, C. Maple, Grey wolf optimizer based deep learning mechanism for music composition with data analysis, Appl. Soft Comput. 153 (2024),.

Digital Library

[33]

J.L. Kim, B.S. Won, J.H. Yoon, A convolutional neural network based classification for fuzzy datasets using 2-D transformation, Appl. Soft Comput. 147 (2023),.

Digital Library

[34]

Y. LeCun, Y. Bengio, G. Hinton, Deep learning, Nature 521 (2015) 436–444,.

[35]

D.G. Wang, L.R. Gao, Y. Qu, X. Sun, W.Z. Liao, Frequency-to-spectrum mapping GAN for semisupervised hyperspectral anomaly detection, CAAI Trans. Intell. Technol. 8 (2023) 1258–1273,.

Digital Library

[36]

Q. Zhang, Y.S. Dong, Y.M. Zheng, H.Y. Yu, M.P. Song, L.F. Zhang, Q.Q. Yuan, Three-dimension spatial-spectral attention transformer for hyperspectral image denoising, IEEE Transactions on Geoscience and Remote Sensing. https://10.1109/TGRS.2024.3458174.

[37]

D. Wang, L. Zhuang, L. Gao, X. Sun, X. Zhao, A. Plaza, Sliding dual-window-inspired reconstruction network for hyperspectral anomaly detection, IEEE Trans. Geosci. Remote Sens. 62 (2024) 5504115,.

[38]

D. Wang, L. Zhuang, L. Gao, X. Sun, M. Huang, A.J. Plaza, PDBSNet: pixel-shuffle downsampling blind-spot reconstruction network for hyperspectral anomaly detection, IEEE Trans. Geosci. Remote Sens. 61 (2023) 5511914,.

[39]

V. Antun, F. Renna, C. Poon, B. Adcock, A.C. Hansen, On instabilities of deep learning in image reconstruction and the potential costs of AI, Proc. Natl. Acad. Sci. 117 (2020) 1–8,.

[40]

V. Monga, Y. Li, Y.C. Eldar, Algorithm unrolling: interpretable, efficient deep learning for signal and image processing, IEEE Signal Process. Mag. 38 (2021) 18–44,.

[41]

S.V. Venkatakrishnan, C.A. Bouman, B. Wohlberg, Plug-and-play priors for model based reconstruction, IEEE Glob. Conf. Signal Inf. Process. (2013) 945–948,.

[42]

Y. Romano, M. Elad, P. Milanfar, The little engine that could: regularization by denoising (RED), SIAM J. Imaging Sci. 10 (2017) 1804–1844,.

Digital Library

[43]

A. Qayyum, I. Ilahi, F. Shamshad, F. Boussaid, M. Bennamoun, J. Qadir, Untrained neural network priors for inverse imaging problems: a survey, IEEE Trans. Pattern Anal. Mach. Intell. 45 (2023) 6511–6536,.

Digital Library

[44]

D.O. Baguer, J. Leuschner, M. Schmidt, Computed tomography reconstruction using deep image prior and learned reconstruction methods, Inverse Probl. 36 (2020),.

[45]

T.A. Khan, S.H. Ling, A.A. Rizvi, Optimisation of electrical impedance tomography image reconstruction error using heuristic algorithms, Artif. Intell. Rev. 56 (2023) 15079–15099,.

Digital Library

[46]

Q.Z. Lin, B.S. Hu, Y. Tang, L.Y. Zhang, J.Y. Chen, X.M. Wang, Z. Ming, A local search enhanced differential evolutionary algorithm for sparse recovery, Appl. Soft Comput. 57 (2017) 144–163,.

Digital Library

[47]

M.E. Erkoc, N. Karaboga, Evolutionary algorithms for sparse signal reconstruction, Signal, Image Video Process. 13 (2019) 1293–1301,.

[48]

M.E. Erkoc, N. Karaboga, A novel sparse reconstruction method based on multi-objective artificial bee colony algorithm, Signal Process. 189 (2021),.

Digital Library

[49]

Y. Zhou, S. Kwong, H.N. Guo, X. Zhang, Q.F. Zhang, A two-phase evolutionary approach for compressive sensing reconstruction, IEEE Trans. Cybern. 47 (2017) 2651–2663,.

[50]

M.G. Gong, H. Li, X.M. Jiang, A multi-objective optimization framework for ill-posed inverse problems, CAAI Trans. Intell. Technol. 1 (2016) 225–240,.

[51]

M.E. Erkoc, N. Karaboga, A comparative study of multi-objective optimization algorithms for sparse signal reconstruction, Artif. Intell. Rev. 55 (2022) 3153–3181,.

Digital Library

[52]

Z. Lv, Z.R. Liao, Y. Liu, J. Zhao, Meta-learning-based multi-objective PSO model for dynamic scheduling optimization, Energy Rep. 9 (2023) 1227–1236,.

[53]

H. Tanabe, E.H. Fukuda, N. Yamashita, Proximal gradient methods for multiobjective optimization and their applications, Comput. Optim. Appl. 72 (2019) 339–361,.

Digital Library

[54]

M. Iglesias, Y.C. Yang, Adaptive regularisation for ensemble Kalman inversion, Inverse Probl. 37 (2021),.

[55]

S. Liu, P.Y. Chen, B. Kailkhura, G. Zhang, A.O. Hero, P.K. Varshney, A primer on zeroth-order optimization in signal processing and machine learning: principals, recent advances, and applications, IEEE Signal Process. Mag. 37 (2020) 43–54,.

[56]

H.Q. Cai, D. McKenzie, W.T. Yin, Z.L. Zhang, Zeroth-order regularized optimization (ZORO): approximately sparse gradients and adaptive sampling, SIAM J. Optim. (2022),.

Digital Library

[57]

G.X. Huang, Y.Y. Liu, F. Yin, Tikhonov regularization with MTRSVD method for solving large-scale discrete ill-posed problems, J. Comput. Appl. Math. 405 (2022),.

Digital Library

[58]

D.J. Urwin, A.N. Alexandrova, Regularization of least squares problems in CHARMM parameter optimization by truncated singular value decompositions, J. Chem. Phys. 154 (2021),.

[59]

A. Beck, A. Ben-Tal, On the solution of the Tikhonov regularization of the total least squares problem, SIAM J. Optim. 17 (2006) 98–118,.

Digital Library

[60]

S. Xu, Smoothing method for minimax problems, Comput. Optim. Appl. 20 (2001) 267–279,.

Digital Library

[61]

A.M. Cramer, S.D. Sudhoff, E.L. Zivi, Evolutionary algorithms for minimax problems in robust design, IEEE Trans. Evolut. Comput. 13 (2009) 444–453,.

Digital Library

[62]

J.K. Liu, L. Zheng, A smoothing iterative method for the finite minimax problem, J. Comput. Appl. Math. 374 (2020),.

Digital Library

[63]

Q.S. Shi, R. Katuwal, P.N. Suganthan, M. Tanveer, Random vector functional link neural network based ensemble deep learning, Pattern Recognit. 117 (2021),.

[64]

Q.S. Shi, P.N. Suganthan, J.D. Ser, Jointly optimized ensemble deep random vector functional link network for semi-supervised classification, Eng. Appl. Artif. Intell. 115 (2022),.

Digital Library

[65]

A.K. Malik, R.B. Gao, M.A. Ganaie, M. Tanveer, P.N. Suganthan, Random vector functional link network: recent developments, applications, and future directions, Appl. Soft Comput. 143 (2023),.

Digital Library

[66]

A.K. Malik, M.A. Ganaie, M. Tanveer, P.N. Suganthan, Alzheimer’s disease diagnosis via intuitionistic fuzzy random vector functional link network, IEEE Trans. Comput. Soc. Syst. 11 (2024) 4754–4765,.

[67]

S. Shiva, M.H. Hu, P.N. Suganthan, Online learning using deep random vector functional link network, Eng. Appl. Artif. Intell. 125 (2023),.

Digital Library

[68]

K.H. Cheng, J. Du, H.X. Zhou, D. Zhao, H.L. Qin, Image super-resolution based on half quadratic splitting, Infrared Phys. Technol. 105 (2020),.

[69]

Y. Sun, Y. Yang, Q. Liu, J. Chen, X.T. Yuan, G. Guo, Learning non-locally regularized compressed sensing network with half-quadratic splitting, IEEE Trans. Multimed. 22 (2020) 3236–3248,.

Digital Library

[70]

A. Beck, M. Tebouule, A fast iteration shrinkage thresholding algorithm for linear inverse problems, SIAM J. Imaging Sci. 2 (2009) 183–202,.

Digital Library

[71]

Y. Sun, G. Pan, Y.S. Li, Y.Y. Yang, Differential evolution with nearest density clustering for multimodal optimization problems, Inf. Sci. 637 (2023),.

Digital Library

[72]

M.P. Bilal, H. Zaheer, L. García-Hernández, A. Abraham, Differential evolution: a review of more than two decades of research, Eng. Appl. Artif. Intell. 90 (2020),.

Digital Library

[73]

H.K. Singh, M.M. Islam, T. Ray, M.J. Ryan, Nested evolutionary algorithms for computationally expensive bilevel optimization problems: variants and their systematic analysis, Swarm Evolut. Comput. 48 (2019) 329–344,.

[74]

M.M. Islam, H.K. Singh, T. Ray, A. Sinha, An enhanced memetic algorithm for single-objective bilevel optimization problems, Evolut. Comput. 25 (2017) 607–642,.

Digital Library

[75]

J.A. Mejía-De-Dios, A. Rodríguez-Molina, E. Mezura-Montes, Multiobjective bilevel optimization: a survey of the state-of-the-art, IEEE Trans. Syst. Man Cybern. Syst. 53 (2023) 5478–5490,.

[76]

A. Sinha, P. Malo, K. Deb, A review on bilevel optimization: from classical to evolutionary approaches and applications, IEEE Trans. Evolut. Comput. 22 (2018) 276–295,.

[77]

W. Dinkelbach, On nonlinear fractional programming, Manag. Sci. 133 (1957) 492–498,.

Digital Library

[78]

A. Zappone, E. Jorswieck, Energy efficiency in wireless networks via fractional programming theory, Found. Trends® Commun. Inf. Theory 11 (2015) 185–396,.

Digital Library

[79]

K. Shen, W. Yu, Fractional programming for communication systems—part i: power control and beamforming, IEEE Trans. Signal Process. 66 (2018) 2616–2630,.

[80]

Y. Bello-Cruz, G.Y. Li, T.T.A. Nghia, On the linear convergence of forward-backward splitting method: part i—convergence analysis, J. Optim. Theory Appl. 188 (2021) 378–401,.

Digital Library

[81]

B.B. Hao, J.G. Zhu, Fast L1 regularized iterative forward backward splitting with adaptive parameter selection for image restoration, J. Vis. Commun. Image Represent. 44 (2017) 139–147,.

Digital Library

[82]

G. Yuan, Z. Wei, Y. Yang, The global convergence of the Polak-Ribière-Polyak conjugate gradient algorithm under inexact line search for nonconvex functions, J. Comput. Appl. Math. 362 (2019) 262–275,.

Digital Library

[83]

D.A. Lorenz, S. Wenger, F. Schöpfer, M. Magnor, A sparse Kaczmarz solver and a linearized Bregman method for online compressed sensing, IEEE Int. Conf. Image Process. ICIP (2014) 1347–1351,.

[84]

F. Schöpfer, D.A. Lorenz, Linear convergence of the randomized sparse Kaczmarz method, Math. Program. 173 (2019) 509–536,.

Digital Library

[85]

W.L. Guo, Y.F. Lou, J. Qin, M. Yan, A new regularization based on the error function for sparse recovery, J. Sci. Comput. 87 (2021) 1–22,.

Digital Library

[86]

S. Zhang, J. Xin, Minimization of transformed L1 penalty: closed form representation and iterative thresholding algorithms, Commun. Math. Sci. 15 (2017) 511–537,.

[87]

K. Yang, Y. Liu, Z. Yu, C.L.P. Chen, Extracting and composing robust features with broad learning system, IEEE Trans. Knowl. Data Eng. (2021),.

Digital Library

[88]

Z.X. Hu, F.P. Nie, R. Wang, X.L. Li, Low rank regularization: a review, Neural Netw. 136 (2021) 218–232,.

[89]

C.Y. Ao, B.J. Qiao, L. Chen, J.H. Xu, M.R. Liu, X.F. Chen, Blade dynamic strain non-intrusive measurement using L1/2-norm regularization and transmissibility, Measurement 190 (2022),.

[90]

T. Goldstein, S. Osher, The split Bregman method for L1-regularized problems, SIAM J. Imaging Sci. 2 (2009) 323–343,.

Digital Library

[91]

J. Lei, W.Y. Liu, Q.B. Liu, X.Y. Wang, S. Liu, Robust dynamic inversion algorithm for the visualization in electrical capacitance tomography, Measurement 50 (2014) 305–318,.

Index Terms

Minimax bilevel fractional optimization for imaging in electrical capacitance tomography

Index terms have been assigned to the content through auto-classification.

Recommendations

Learnable bilevel optimization method for electrical capacitance tomography
Highlights
- A new learnable bilevel optimization model is proposed for imaging.
- Physics-constrained extreme learning machine is developed to infer image priors.
- A nested optimizer is proposed to solve the bilevel optimization imaging model.
Abstract
The positive role of electrical capacitance tomography technology depends on high-precision tomographic images. Despite its success, one of the main barriers is the low-quality tomogram. A new learnable bilevel optimization imaging method is ...
Multitasking optimization for the imaging problem in electrical capacitance tomography
Abstract
Electrical capacitance tomography excels in measuring multiphase flows, but it faces challenges in reconstructing high-accuracy images. To tap into the potential of this measurement technique, we model the image reconstruction problem as a ...
An Image Reconstruction Algorithm Based on the Regularized Minimax Estimation for Electrical Capacitance Tomography

Electrical capacitance tomography (ECT) is considered as a promising process tomography (PT) technology. Image reconstruction algorithms play an important role in the successful applications of ECT. In this paper, a generalized objective functional, ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Applied Soft Computing

Applied Soft Computing Volume 169, Issue C

Jan 2025

1583 pages

Issue’s Table of Contents

Elsevier B.V.

Publisher

Elsevier Science Publishers B. V.

Netherlands

Publication History

Published: 18 February 2025

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

0
Total Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 05 Mar 2025

Other Metrics

View Author Metrics

Citations

View Options

View options

Figures

Tables

Media

View Issue’s Table of Contents