{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T13:35:59Z","timestamp":1785418559195,"version":"3.56.0"},"reference-count":28,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T00:00:00Z","timestamp":1776729600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100018789","name":"Kajima Foundation","doi-asserted-by":"publisher","award":["None"],"award-info":[{"award-number":["None"]}],"id":[{"id":"10.13039\/501100018789","id-type":"DOI","asserted-by":"publisher"}]},{"award":["None"],"award-info":[{"award-number":["None"]}],"id":[{"id":"https:\/\/ror.org\/043ga8x09","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Top Researcher Development Program of Tokyo University of Science","award":["NA"],"award-info":[{"award-number":["NA"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Electrical Impedance Tomography (EIT) is a promising non-invasive sensing technique, yet its practical application in resource-constrained environments is often limited by the high computational cost of inverse image reconstruction. To address this challenge, we focus on specific sensing objectives rather than full image recovery. In this study, we propose a lightweight, task-oriented inference framework for object localization in EIT that bypasses the need to solve computationally expensive inverse reconstruction problems. This approach addresses the high computational demands and hardware complexity of conventional iterative methods, which often hinder real-time monitoring in resource-constrained edge computing environments. Training datasets were generated via finite element method (FEM) simulations for Opposite and Adjacent current injection configurations. A feedforward neural network was developed to independently estimate the radial and angular object positions as probability distributions. Our systematic evaluation revealed that the localization performance depends on the injection configuration and model depth; notably, the Opposite method achieved perfect classification accuracy (1.00) for radial estimation with an optimized architecture of four hidden layers, whereas the Adjacent method exhibited higher ambiguity. Results quantitatively evaluated using the Wasserstein distance show that the Opposite configuration produces more localized, unimodal probability distributions than the Adjacent configuration by utilizing current fields that traverse the entire domain. Compared with existing image-based reconstruction methods, including the conventional electrical impedance tomography and diffuse optical tomography reconstruction software (EIDORS ver.3.12), the proposed framework reduced energy consumption from 3.09 to 0.96 Wh, demonstrating an approximately 70% improvement in energy efficiency while maintaining a high localization accuracy without the need for iterative Jacobian updates. This task-oriented framework enables reliable, high-speed, and energy-efficient localization, making it well-suited for low-power EIT applications in mobile and embedded sensor systems.<\/jats:p>","DOI":"10.3390\/s26082570","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T16:10:44Z","timestamp":1776787844000},"page":"2570","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Task-Oriented Inference Framework for Lightweight and Energy-Efficient Object Localization in Electrical Impedance Tomography"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5322-9373","authenticated-orcid":false,"given":"Takashi","family":"Ikuno","sequence":"first","affiliation":[{"name":"Department of Applied Electronics, Graduate School of Advanced Engineering, Tokyo University of Science, Tokyo 125-8585, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reiji","family":"Kaneko","sequence":"additional","affiliation":[{"name":"Department of Applied Electronics, Graduate School of Advanced Engineering, Tokyo University of Science, Tokyo 125-8585, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"S25","DOI":"10.1088\/0967-3334\/27\/5\/S03","article-title":"Uses and abuses of EIDORS: An extensible software base for EIT","volume":"27","author":"Adler","year":"2006","journal-title":"Physiol. Meas."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1067","DOI":"10.1088\/0967-3334\/36\/6\/1067","article-title":"Why is EIT so hard, and what are we doing about it?","volume":"36","author":"Adler","year":"2015","journal-title":"Physiol. Meas."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"21870","DOI":"10.1109\/ACCESS.2019.2898091","article-title":"Frequency Difference EIT with Localization: A Potential Medical Imaging Tool During Cancer Treatment","volume":"7","author":"Wu","year":"2019","journal-title":"IEEE Access"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"7509610","DOI":"10.1109\/TIM.2024.3481564","article-title":"Measurement of Gas Fraction in Gas\u2013Liquid Dispersed Bubbly Flow with EMAT Array and EIT Sensor","volume":"73","author":"Xie","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Krol, K., Klosowski, G., Rymarczyk, T., Gauda, K., Kulisz, M., Golec, E., and Surowiec, A. (2025). Process Control via Electrical Impedance Tomography for Energy-Aware Industrial Systems. Energies, 18.","DOI":"10.3390\/en18225956"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Kulisz, M., Klosowski, G., Rymarczyk, T., Sloniec, J., Gauda, K., and Cwynar, W. (2024). Optimizing the Neural Network Loss Function in Electrical Tomography to Increase Energy Efficiency in Industrial Reactors. Energies, 17.","DOI":"10.3390\/en17030681"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"110874","DOI":"10.1016\/j.measurement.2022.110874","article-title":"Evaluation of electrical impedance tomography sensor using internal-external electrodes for small-scale cylindrical root zones","volume":"192","author":"Zhao","year":"2022","journal-title":"Measurement"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"114432","DOI":"10.1016\/j.bios.2022.114432","article-title":"Non-invasive imaging of ion concentration distribution around cell spheroids by electrical impedance tomographic sensor printed on circuit board under temporal compensation by ion transport impedance model","volume":"212","author":"Kawashima","year":"2022","journal-title":"Biosens. Bioelectron."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"015210","DOI":"10.1063\/5.0185371","article-title":"A hybrid of iterative Gauss\u2013Newton and one-dimensional convolutional neural network for high-resolution electrical impedance tomography","volume":"14","author":"Minakawa","year":"2024","journal-title":"AIP Adv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Wanta, D., Ivanenko, M., Smolik, W.T., Wr\u00f3blewski, P., and Midura, M. (2024). Real-Time Nonlinear Image Reconstruction in Electrical Capacitance Tomography Using the Generative Adversarial Network. Information, 15.","DOI":"10.3390\/info15100617"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Pennati, F., Angelucci, L., Morelli, L., Bardini, S., Barzanti, E., Cavallini, F., Conelli, A., Federico, G.D., Paganelli, C., and Aliverti, A. (2023). Electrical Impedance Tomography: From the Traditional Design to the Novel Frontier of Wearables. Sensors, 23.","DOI":"10.3390\/s23031182"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zamora-Arellano, F., Lopez-Bonilla, O.R., Garcia-Guerrero, E.E., Olgu\u00edn-Tiznado, J.E., Inzunza-Gonzalez, E., Lopez-Mancilla, D., and Tlelo-Cuautle, E. (2021). Development of a Portable, Reliable and Low-Cost Electrical Impedance Tomography System Using an Embedded System. Electronics, 10.","DOI":"10.3390\/electronics10010015"},{"key":"ref_13","first-page":"1","article-title":"Development of a Portable and Low-Cost Data Acquisition System with Edge Intelligence for Electrical Impedance Tomography-Based Spatial Damage Detection","volume":"73","author":"Li","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1088\/0967-3334\/32\/5\/007","article-title":"An optimized strategy for real-time hemorrhage monitoring with electrical impedance tomography","volume":"32","author":"Xu","year":"2011","journal-title":"Physiol. Meas."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"117986","DOI":"10.1016\/j.measurement.2025.117986","article-title":"Feasibility analysis of EIT-guided lung tumor tracking with prior information for robotic arm-assisted radiotherapy","volume":"256","author":"Yu","year":"2025","journal-title":"Measurement"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"104116","DOI":"10.1016\/j.autcon.2021.104116","article-title":"High-accuracy rebar position detection using deep learning\u2013based frequency-difference electrical resistance tomography","volume":"135","author":"Jeon","year":"2022","journal-title":"Autom. Constr."},{"key":"ref_17","first-page":"300","article-title":"Multimodal CNN for Improving Spatial Resolution of Electrical Impedance Tomography Method","volume":"33","author":"Kaneko","year":"2025","journal-title":"J. Jpn. Soc. Appl. Electromagn. Mech."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"126032","DOI":"10.1016\/j.envpol.2025.126032","article-title":"Evaluating the reliability of geophysical methods for investigating the migration of a hydrocarbon plume: Validation by sample analysis","volume":"372","author":"Yu","year":"2025","journal-title":"Environ. Pollut."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Neumayer, M., Suppan, T., Bretterklieber, H., Wegleiter, H., and Fox, C. (2024). Efficient Jacobian Computations for Complex ECT\/EIT Imaging. Mathematics, 12.","DOI":"10.3390\/math12071023"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Khan, T.A., and Ling, S.H. (2019). Review on Electrical Impedance Tomography: Artificial Intelligence Methods and its Applications. Algorithms, 12.","DOI":"10.3390\/a12050088"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"085007","DOI":"10.1088\/1361-6420\/ac7743","article-title":"Machine learning enhanced electrical impedance tomography for 2D materials","volume":"38","author":"Coxson","year":"2022","journal-title":"Inverse Probl."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1137\/0152060","article-title":"Existence and Uniqueness for Electrode Models for Electric Current Computed Tomography","volume":"52","author":"Somersalo","year":"1992","journal-title":"SIAM J. Appl. Math."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"41856","DOI":"10.1109\/JSEN.2024.3484468","article-title":"Fast 3-D Electrical Impedance Tomography Imaging of Tumor Boundary Based on Plane Extension Layer and Deep Learning","volume":"24","author":"Zou","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_24","first-page":"4501414","article-title":"Model-Based Deep Unrolling Framework for Electrical Impedance Tomography Image Reconstruction","volume":"74","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1109\/JSSC.2024.3434638","article-title":"A 1.76 mW, 355-fps, Electrical Impedance Tomography System with a Simple Time-to-Digital Impedance Readout for Fast Neonatal Lung Imaging","volume":"60","author":"Li","year":"2025","journal-title":"IEEE J. Solid-State Circuits"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"851","DOI":"10.1109\/TBME.2025.3594249","article-title":"Graph Convolutional Networks Enable Fast Hemorrhagic Stroke Monitoring with Electrical Impedance Tomography","volume":"73","author":"Toivanen","year":"2026","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1109\/TCI.2026.3664753","article-title":"Fast Electrical Impedance Tomography with Hybrid Priors","volume":"12","author":"Shi","year":"2026","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Wang, L., Peng, G., and Li, S. (2021). WDA.: An Improved Wasserstein Distance-Based Transfer Learning Fault Diagnosis Method. Sensors, 21.","DOI":"10.3390\/s21134394"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/8\/2570\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T04:16:18Z","timestamp":1777090578000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/8\/2570"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,21]]},"references-count":28,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["s26082570"],"URL":"https:\/\/doi.org\/10.3390\/s26082570","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,21]]}}}