Article
Engineering, Electrical & Electronic
Zhou Chen, Yunjie Yang, Pierre-Olivier Bagnaninchi
Summary: This study proposes a hybrid algorithm based on deep learning and group sparsity regularization for cell imaging using mEIT. By combining deep neural networks with CS regularization, the method achieves superior performance and generalization ability in image reconstruction.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Engineering, Electrical & Electronic
Lu Yang, Hongtao Wu, Kai Liu, Bai Chen, Shan Huang, Jiafeng Yao
Summary: This article proposes a multicircle planar electrical impedance tomography (EIT) sensor for three-dimensional (3-D) miniature imaging. The sensor addresses the low spatial resolution and severe influence of contact impedance in 3-D miniature EIT imaging. The proposed EIT sensor adopts a multicircle structure to reduce contact impedance and improve spatial resolution. Furthermore, a new driven-measurement pattern is proposed to enhance image reconstruction quality. Simulation and experiment demonstrate the effectiveness of the proposed EIT sensor, achieving high image correlation coefficients (ICC) in both cases.
IEEE SENSORS JOURNAL
(2023)
Article
Materials Science, Multidisciplinary
Ryoma Ogawa, Amelia Hallas-Potts, Hancong Wu, Jiabin Jia, Pierre O. Bagnaninchi
Summary: This study demonstrates a method combining 3D cell culture and impedance imaging technology to simultaneously perform 3D impedance imaging and viability measurements. Utilizing low-resistance 3D printed scaffolds, real-time monitoring of large-scale 3D cell cultures is achieved, paving the way for quantitative, non-invasive evaluation of tissue engineering products.
ADVANCED ENGINEERING MATERIALS
(2021)
Article
Engineering, Electrical & Electronic
Zhou Chen, Yunjie Yang
Summary: This article introduces a structure-aware dual-branch deep-learning method for addressing the reconstruction of multilevel continuous conductivity distributions in electrical impedance tomography. By encoding structure and conductivity features, the proposed method has demonstrated superior performance in dealing with this challenging problem.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Engineering, Electrical & Electronic
Zhe Liu, Yunjie Yang
Summary: The study integrates optical imaging into Electrical Impedance Tomography (EIT) and proposes a dual-modal image reconstruction algorithm based on optical image-guided group sparsity (IGGS) to improve image quality. Experimental results demonstrate the superiority of the proposed algorithm over traditional image reconstruction methods.
IEEE SENSORS JOURNAL
(2021)
Article
Computer Science, Interdisciplinary Applications
Zhe Liu, Pierre Bagnaninchi, Yunjie Yang
Summary: This paper presents an impedance-optical dual-modal imaging framework for high-quality 3D cell culture imaging and other tissue engineering applications. The framework includes a dual-modal sensor, a guidance image processing algorithm, and a deep learning model for information fusion. The proposed method significantly improves image quality and has the potential to reveal both structural and functional information of tissue-level targets simultaneously.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Computer Science, Artificial Intelligence
Talha A. Khan, Sai Ho Ling, Arslan A. Rizvi
Summary: Preventing direct exposure to ionising radiation has led to advancements in medical imaging and e-health. Electrical Impedance Tomography (EIT) is a non-invasive, low-cost, and safe imaging method that addresses the health issues associated with ionising radiation. This study proposes three population-based optimisation techniques for optimizing EIT image reconstruction, improving solution quality and stability. Results demonstrate the superiority of the HGSPSO algorithm in terms of solution quality and stability.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Environmental Sciences
Rinku Basak, Khan A. Wahid
Summary: Plant phenotyping is crucial for enhancing crop yields by evaluating plant traits through image reconstruction. In this study, an electrical impedance tomography (EIT) system is developed to non-destructively reconstruct and evaluate plant inhomogeneities. The system utilizes a high-precision electrode array sensor and impedance imaging technique to assess and calibrate the reconstructed results. The performance and accuracy of the EIT system are evaluated using low-cost impedance spectroscopy tools and a finite element method (FEM) modeling.
Article
Engineering, Electrical & Electronic
Zhe Liu, Yunjie Yang
Summary: This article presents a kernel method-based multimodal EIT image reconstruction approach that incorporates the structural information of an auxiliary high-resolution image into the EIT inversion process. It performs image-level segmentation-free information fusion and generates superior EIT images on challenging simulation and experimental phantoms.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Engineering, Electrical & Electronic
Ming Ye, Tong Zhou, Xiaocheng Li, Lu Yang, Kai Liu, Jiafeng Yao
Summary: A flexible EIT sensor with combined electrodes is proposed to reconstruct 3D image, and an innovative U-2-Net neural network structure is implemented to solve the inverse problem of 3D EIT. Simulation and experiment verify the proposed 3D EIT sensor, and the image reconstruction quality is evaluated.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Yu Wang, Feng Dong, Shangjie Ren
Summary: This paper proposes a method to improve the spatial resolution of Electrical Impedance Tomography (EIT) by optimizing the sensor array to enhance sensitivity and accuracy within the region of interest (ROI). Experimental results show that the optimized sensor can more accurately reconstruct inclusions in the ROI, and has higher recognition ability for small size and closely located inclusions in the ROI.
IEEE SENSORS JOURNAL
(2021)
Article
Engineering, Electrical & Electronic
Yanyan Shi, Yuehui Wu, Meng Wang, Zuguang Rao, Bin Yang, Feng Fu, Yajun Lou
Summary: This article proposes a novel approach for image reconstruction of conductivity distribution in electrical impedance tomography (EIT). The approach introduces a fidelity term based on L-1 norm to stabilize the problem and enforce sparsity in the solution. It also introduces a hybrid penalty term combining first-order and high-order total variation to preserve sharp profiles and suppress the staircase effect.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Engineering, Electrical & Electronic
Zheng Wang, Yandan Jiang, Junchao Huang, Baoliang Wang, Haifeng Ji, Zhiyao Huang
Summary: This paper proposes a new image reconstruction algorithm for capacitively coupled electrical resistance tomography (CCERT) based on density peaks clustering (DPC) and K-means. DPC is improved by automatically selecting the cluster centers, and K-means is improved by introducing a post-processing to consider the non-uniform sensitivity characteristic in the sensing area. Experimental results verify the effectiveness of the proposed algorithm and indicate the successful improvements of DPC and K-means. Compared with conventional algorithms, the proposed algorithm achieves better image reconstruction results with less manual intervention.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Qi Wang, Zinan Guo, Jie Wang, Ronghua Zhang, Xiuyan Li, Xiaojie Duan, Yukuan Sun, Wen Sun, Jianming Wang
Summary: This study proposes a new online membrane fouling monitoring method that uses electrical impedance tomography to monitor the development of membrane fouling in UF membrane processes in real-time. The conductivity distribution of membrane fouling is reconstructed by a group sparse-based EIT imaging algorithm, allowing for visualization of membrane fouling accumulation under different filtering conditions.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Engineering, Electrical & Electronic
Mehmood Nawaz, Russell W. Chan, Anju Malik, Tariq Khan, Peng Cao
Summary: Human-computer interaction using hand gestures has always been challenging, but advancements in machine learning have made it possible to recognize and classify gestures more accurately. In this study, a technique using a wearable low-cost device to generate EIT images was proposed to recover the inner impedance structure of a user's wrist, enabling real-time monitoring and classification of gestures.
IEEE SENSORS JOURNAL
(2022)
Article
Biophysics
Eva Gonzalez-Fernandez, Matteo Staderini, Jamie R. K. Marland, Mark E. Gray, Ahmet Ucar, Camelia Dunare, Ewen O. Blair, Paul Sullivan, Andreas Tsiamis, Stephen N. Greenhalgh, Rachael Gregson, Richard Eddie Clutton, Stewart Smith, Jonathan G. Terry, David J. Argyle, Anthony J. Walton, Andrew R. Mount, Mark Bradley, Alan F. Murray
Summary: The study introduced a miniaturised, self-contained electrochemical pH sensor system using a methylene blue redox reporter, which demonstrated remarkable robustness, accuracy, and sensitivity. The sensor effectively tracked real-time intratumoral tissue pH changes in vivo, correlating well with laboratory blood tests.
BIOSENSORS & BIOELECTRONICS
(2022)
Article
Computer Science, Interdisciplinary Applications
Zhe Liu, Pierre Bagnaninchi, Yunjie Yang
Summary: This paper presents an impedance-optical dual-modal imaging framework for high-quality 3D cell culture imaging and other tissue engineering applications. The framework includes a dual-modal sensor, a guidance image processing algorithm, and a deep learning model for information fusion. The proposed method significantly improves image quality and has the potential to reveal both structural and functional information of tissue-level targets simultaneously.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Biochemistry & Molecular Biology
Jiwon Park, Siyang Jia, Donald Salter, Pierre Bagnaninchi, Carsten G. Hansen
Summary: In this study, the cellular response to hydrostatic pressure was investigated using quantitative label-free digital holographic imaging. It was found that cells respond to elevated hydrostatic pressure by rapidly changing their volume, which is regulated by the co-transcriptional regulators YAP and TAZ of the Hippo signaling pathway. Additionally, YAP/TAZ activation induced transcription and expression of cellular components involved in regulating cell volume and extracellular matrix.
Article
Engineering, Electrical & Electronic
Zhe Liu, Renjie Zhao, Graham Anderson, Pierre-Olivier Bagnaninchi, Yunjie Yang
Summary: This article proposes an enhanced deep neural network, En-MSFCF-Net, for automatically improving the mask image obtained from an auxiliary imaging modality and conducting information fusion and image reconstruction. Compared with the original MSFCF-Net, En-MSFCF-Net demonstrates a more accurate conductivity estimation, as well as superior shape preservation and conductivity prediction accuracy. Both qualitative and quantitative results indicate that En-MSFCF-Net can make dual-modal imaging more robust in real-world situations.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Delin Hu, Haotian Li, Francesco Giorgio-Serchi, Yunjie Yang
Summary: Simulation is a standard tool for robot design, control, and performance analysis. Most existing models for soft robotics systems focus on the dynamics of soft bodies during actuation and do not consider the sensory system. This article proposes a pipeline to implement coupling field simulation (CFS) of capacitive sensors deployed on soft arm and pneumatic manipulator, which can seamlessly integrate mechanical and sensing components and provide valuable insights into sensor behavior.
IEEE SENSORS JOURNAL
(2023)
Article
Chemistry, Analytical
Yinhuan Dong, Guoxiong He, Tughrul Arslan, Yunjie Yang, Yingda Ma
Summary: This paper proposes a scalable WiFi fingerprint augmentation method, which includes virtual reference point generation and spatial WiFi signal modeling modules. The potential unsurveyed reference points are determined using a globally self-adaptive and a locally self-adaptive approach, and a multivariate Gaussian process regression model is used to predict signals and generate more fingerprints. The results show that combining the proposed approaches can improve positioning accuracy by 5% to 20% while reducing computation complexity compared to traditional methods.
Article
Chemistry, Analytical
Andreas Tsiamis, Anthony Buchoux, Stephen T. Mahon, Anthony J. Walton, Stewart Smith, David J. Clarke, Adam A. Stokes
Summary: The lab-on-a-chip concept, enabled by microfluidic technology, integrates multiple discrete laboratory techniques into a miniaturised system. However, previous research has focused on developing individual elements without fully optimising and miniaturising the complete system. This paper presents a demonstrator platform that fully integrates multiple technologies into a single device, enabling breakthroughs in research by incorporating all physical requirements into one device.
Article
Computer Science, Artificial Intelligence
Delin Hu, Francesco Giorgio-Serchi, Shiming Zhang, Yunjie Yang
Summary: Researchers have developed a stretchable e-skin combined with deep learning for high-resolution 3D geometry reconstruction of soft robots, which can be used in various scenarios like human-robot interaction.
NATURE MACHINE INTELLIGENCE
(2023)
Article
Engineering, Biomedical
Zhe Liu, Hengjia Gu, Zhou Chen, Pierre Bagnaninchi, Yunjie Yang
Summary: This paper proposes a segmentation-free dual-modal EIT image reconstruction algorithm based on Overlapping Group Lasso and Laplacian regularization. The algorithm utilizes structural images obtained from an auxiliary imaging modality to construct an overlapping group lasso penalty based on conductivity change properties. Laplacian regularization is introduced to alleviate artifacts caused by group overlapping. Experimental results demonstrate the superiority of the proposed method in terms of structure preservation, background artifact suppression, and conductivity contrast differentiation.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Zhou Chen, Jinxi Xiang, Pierre-Olivier Bagnaninchi, Yunjie Yang
Summary: This article presents a learning algorithm called MMV-Net based on a multiple measurement vector (MMV) model to solve the mfEIT image reconstruction problem. MMV-Net considers the correlations between mfEIT images and uses a cascade of a Spatial Self-Attention module and a ConvLSTM module to capture intrafrequency and interfrequency dependencies. The experimental results demonstrate that MMV-Net outperforms traditional methods and state-of-the-art deep learning methods in terms of image quality, convergence performance, noise robustness, and computational efficiency.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Zhenlei Chen, Qing Guo, Tieshan Li, Yao Yan, Dan Jiang
Summary: A deep-Gaussian-process (DGP)-based method for operator's gait prediction is proposed to estimate real-time motion intention and compensate for the measurement delay. A variable admittance controller is designed based on the quantified gait prediction uncertainties, and an extend-state observer (ESO) is used to compensate unmeasured system state, model uncertainties, and unmodeled dynamics.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Proceedings Paper
Engineering, Electrical & Electronic
Alan W. S. Ross, Coinneach M. Dover, Stewart Smith, Jonathan G. Terry, Andrew R. Mount, Anthony J. Walton
Summary: This paper presents a previously documented full wafer test structure to evaluate the effect of seed layer thickness and conductivity on the plating uniformity of patterned electroplated structures. The results demonstrate that by adjusting the current distribution structures, significant improvement in wafer plating uniformity can be achieved when using seed layer thicknesses of a few nanometers.
2022 IEEE 34TH INTERNATIONAL CONFERENCE ON MICROELECTRONIC TEST STRUCTURES (ICMTS)
(2022)
Proceedings Paper
Engineering, Electrical & Electronic
Camelia Dunare, Shan Zhang, Jamie R. K. Marland, Andreas Tsiamis, Paul Sullivan, Ian Underwood, Jonathan G. Terry, Anthony J. Walton, Stewart Smith
Summary: In order to produce robust and reliable micro-scale integrated electrochemical sensors, a stable reference electrode such as a silver/silver chloride (Ag/AgCl) electrode is needed. The preparation process of the Ag/AgCl electrode requires a good understanding and controlled processes to ensure stability.
2022 IEEE 34TH INTERNATIONAL CONFERENCE ON MICROELECTRONIC TEST STRUCTURES (ICMTS)
(2022)
