检索结果-内蒙古大学图书馆

IEEE International conference on Big data

作者： Anika Tabassum Nikhil Muralidhar Ramakrishnan Kannan Srikanth Allu Oak Ridge National Laboratory Department of Computer Science Stevens Institute of Technology

ISBN: (纸本)9781665480468

Li-ion Batteries (LIB), one of the most efficient energy storage devices, are used extensively in many industrial applications. These batteries consist of electrodes that are put together with heterogeneous material compositions. Imaging data of these battery electrodes obtained from X-ray tomography can explain the distribution of material constituents and allow reconstructions to study electron transport pathways. Such reconstructions of material constituents help quantify various associated properties of electrodes (e.g., volume-specific surface area, porosity) which determine the performance of batteries. These images often suffer from low image contrast between multiple material constituents, hence making it difficult for humans to distinguish and characterize these constituents through visual inspection. A minor error in detecting distributions of the material constituents can lead to magnified errors in the calculated parameters of material properties (e.g., porosity). We present MatPhase, a novel hierarchical curriculum learning technique to address the complex task of estimating material constituent distribution in battery electrodes. MatPhase comprises three modules: (i) an uncertainty-aware global model trained to yield inferences conditioned upon global knowledge of material distribution, (ii) a local model to capture relatively more fine-grained (local) distributional signals, (iii) an aggregator model to appropriately fuse the local and global effects towards obtaining the final distribution. On average, MatPhase improves prediction up to 8.5% relative to other sophisticated modeling pipelines and state-of-the-arts (SOTA) object detection models employed in the performance comparison.

关键词： Electrodes Lithium-ion batteries Surface reconstruction Pipelines Object detection Predictive models Big data

来源：评论

学校读者我要写书评

暂无评论

Super-resolution GANs of randomly-seeded fields

arXiv

引用

arXiv 2022年

作者： Güemes, Alejandro Vila, Carlos Sanmiguel Discetti, Stefano Aerospace Engineering Research Group Universidad Carlos III de Madrid Leganés Spain San Martín de la Vega Spain

reconstruction of field quantities from sparse measurements is a problem arising in a broad spectrum of applications. This task is particularly challenging when the mapping between sparse measurements and field quantities is performed in an unsupervised manner. Further complexity is added for moving sensors and/or random on-off status. Under such conditions, the most straightforward solution is to interpolate the scattered data onto a regular grid. However, the spatial resolution achieved with this approach is ultimately limited by the mean spacing between the sparse measurements. In this work, we propose a super-resolution generative adversarial network (GAN) framework to estimate field quantities from random sparse sensors without needing any full-field high-resolution training. The algorithm exploits random sampling to provide incomplete views of the high-resolution underlying distributions. It is hereby referred to as RAndomly-SEEDed super-resolution GAN (RaSeedGAN). The proposed technique is tested on synthetic databases of fluid flow simulations, ocean surface temperature distributions measurements, and particle image velocimetry data of a zero-pressure-gradient turbulent boundary layer. The results show excellent performance even in cases with high sparsity or with levels of noise. To our knowledge, this is the first GAN algorithm for full-field high-resolution estimation from randomly-seeded fields with no need of full-field high-resolution representations. © 2022, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Imaging from Temporal data via Spiking Convolutional Neural Networks 3

Imaging from Temporal Data via Spiking Convolutional Neural ...

引用

conference on Emerging Imaging and Sensing Technologies for Security and Defence V / conference on Advanced Manufacturing Technologies for Micro- and Nanosystems in Security and Defence iii

作者： Kirkland, Paul Kapitany, Valentin Lyons, Ashley Soraghan, John Turpin, Alex Faccio, Daniele Di Caterina, Gaetano Univ Strathclyde Glasgow Lanark Scotland Univ Glasgow Glasgow Lanark Scotland

ISBN: (纸本)9781510638945

A new approach for imaging that is solely based on the time of flight of photons coming from the entire imaged scene, combined with a novel machine learning algorithm for image reconstruction: a spiking convolutional neural network (SCNN) named Spike-SPI (Spiking - Single Pixel imager). The approach uses a single point detector and the corresponding time-counting electronics, which provide the arrival time of photons in the form of spikes distributed over time. This data is transformed into a temporal histogram containing the number of photons per arrival time. A SCNN that converts the 1D temporal histograms into a 3D image (2D image with depth map) by exploiting the feature extraction capabilities of convolutional neural networks (CNNs), the high dimensional compressed latent space representations of a variational encoder-decoder network structure, and the asynchronous processing capabilities of a spiking neural network (SNN). The performance of the proposed SCNN is analysed to demonstrate the state-of-the-art feature extraction capabilities of CNNs and the low latency asynchronous processing of SNNs that offer both higher throughput and higher accuracy in image reconstruction from the ToF data, when compared to standard ANNs. The results of Spike-SPI show an increase in spatial accuracy of 15% over then ANN, using the Intersection of Union (IoU) for the objects in the scene. While also delivering a 100% increase over then ANN in object reconstruction signal to noise ratio (RSNR) from similar to 3dB to similar to 6dB. These results are also consistent across a range of IRF (Instrument Response Functions) values and photo counts, highlighting the robust nature of the new network structure. Moreover, the asynchronous processing nature of the spiking neurons allow for a faster throughput and less computational overhead, benefiting from the operational sparsity in the single point sensor.

关键词： LiDAR SPAD SCNN CNN Neural Network Imaging Depth

来源：评论

学校读者我要写书评

暂无评论

Processing of incomplete images by (Graph) Convolutional Neural Networks 27th

Processing of Incomplete Images by (Graph) Convolutional Neu...

引用

27th International conference on Neural Information Processing

作者： Danel, Tomasz Smieja, Marek Struski, Lukasz Spurek, Przemyslaw Maziarka, Lukasz Jagiellonian Univ Fac Math & Comp Sci Lojasiewicza 6 PL-30428 Krakow Poland

ISBN: (纸本)9783030638320;9783030638337

We investigate the problem of training neural networks from incomplete images without replacing missing values. For this purpose, we first represent an image as a graph, in which missing pixels are entirely ignored. The graph image representation is processed using a spatial graph convolutional network (SGCN) - a type of graph convolutional networks, which is a proper generalization of classical CNNs operating on images. On one hand, our approach avoids the problem of missing data imputation while, on the other hand, there is a natural correspondence between CNNs and SGCN. Experiments confirm that our approach performs better than analogical CNNs with the imputation of missing values on typical classification and reconstruction tasks.

关键词： Graph convolutional networks Convolutional neural networks Missing data

来源：评论

学校读者我要写书评

暂无评论

Learning Functions Using data-Dependent Regularization: Representer Theorem Revisited 20th

Learning Functions Using Data-Dependent Regularization: Repr...

引用

20th Annual International conference on Computational Science (ICCS)

作者： Zou, Qing Univ Iowa Appl Math & Computat Sci Iowa City IA 52242 USA

ISBN: (纸本)9783030504205;9783030504199

We introduce a data-dependent regularization problem which uses the geometry structure of the data to learn functions from incomplete data. We show another proof of the standard representer theorem when introducing the problem. At the end of the paper, two applications in image processing are used to illustrate the function learning framework.

关键词： Function learning Manifold structure Representer theorem

来源：评论

学校读者我要写书评

暂无评论

Air Fraction Correction in PET Imaging of Lung Disease – Kernel Determination

Air Fraction Correction in PET Imaging of Lung Disease – Ke...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： Francesca Leek Andrew P. Robinson Robert M. Moss Frederick J. Wilson Brian F. Hutton Kris Thielemans Institute of Nuclear Medicine UCL London UK NPL Teddington Middlesex UK NPL Christie Medical Physics and Engineering The Christie NHS Foundation Trust UK Schuster Laboratory School of Physics and Astronomy The University of Manchester UK Department of Medical Physics and Biomedical Engineering UCL London UK GlaxoSmithKline Research & Development Limited Stevenage Herts UK Institute of Nuclear Medicine UCL. K.T. Centre for Medical Image Computing UCL

Accurate quantification of radiotracer uptake from lung PET/CT is challenging due to large variations in fractions of tissue, air, blood, and water. The air fraction correction (AFC) determines voxel-wise air fractions (AF) from the CT acquired for attenuation correction (AC) to correct for the variable air content. However, the resolution mismatch between PET and CT can cause artefacts in the AF-corrected image. In this work, we compare different methodologies for determining the optimal kernel to smooth the CT for AFC, when PET images were reconstructed with iterative reconstruction methods, and in the case where AF-corrected lungs exhibit uniform uptake. Noiseless simulations and non-TOF MLEM reconstructions were performed with STIR via SIRF using a digital test-object constructed from a CT scan of a patient with idiopathic pulmonary fibrosis. The optimal smoothing for AFC was determined via i) the point-source insertion-and-subtraction-method, h pts ; ii) artefact reduction in the AF-corrected volume-of-interest (VOI), h AFC ; iii) smoothing a ground-truth image to match the reconstructed image within the VOI, h PVC . Each of the three kernels were used to smooth the mu-map for AFC of the reconstructed emission data and the RMSE of each of the AF-corrected VOIs, with respect to the ground-truth, was assessed. Applicability of the preferred method was assessed with phantom acquisitions on a clinical scanner. Results demonstrated that, for iterative reconstruction methods, image resolution is dependent on iteration number and VOI density/uptake. Smoothing by h pts resulted in the least quantitatively accurate AF-corrected images at fewer than 40 iterations. For both h AFC and h PVC , RMSE in the AF-corrected IPF regions is fairly stable across iterations. h PVC has the potential to be utilised for determining the appropriate kernel for AFC on clinical scanners for application to patient PET/CT lung scans.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self-supervised and supervised deep learning for PET image reconstruction

引用

AIP conference Proceedings 2024年第1期3061卷

作者： Andrew J. Reader School of Biomedical Engineering and Imaging Sciences King’s College London London United Kingdom

A unified self-supervised and supervised deep learning framework for PET image reconstruction is presented, including deep-learned filtered backprojection (DL-FBP) for sinograms, deep-learned backproject then filter (DL-BPF) for backprojected images, and a more general mapping using a deep network in both the sinogram and image domains (DL-FBP-F). The framework accommodates varying amounts and types of training data, from the case of having only one single dataset to reconstruct through to the case of having numerous measured datasets, which may or may not be paired with high-quality references. For purely self-supervised mappings, no reference or ground truth data are required at all, but at minimum just the measured dataset to reconstruct from. Instead of a supplied reference, the output reconstruction from the trainable mapping is forward modelled, and the input data serve as a reference target for this forward-modelled data. The self-supervised deep learned reconstruction operators presented here all use a conventional image reconstruction objective within the loss function (e.g. maximum Poisson likelihood, maximum a posteriori). If it is desired for the reconstruction networks to generalise (i.e. to need either no or minimal retraining for a new measured dataset, but to be fast, ready to reuse), then these self-supervised networks show potential even when previously trained from just one single dataset. For any given new measured dataset, finetuning is however usually necessary for improved agreement with the reconstruction objective, and of course the initial training set should ideally go beyond just one dataset if a generalisable network is sought. This work presents preliminary results for the purely self-supervised single-dataset case, but the proposed networks can be i) trained uniquely for any measured dataset in hand to reconstruct, ii) pretrained on multiple datasets and then used with no retraining for new measured data, iii) pretrained and then finet

关键词：

来源：评论

学校读者我要写书评

暂无评论

Depth image reconstruction Using Low Rank and Total Variation Representations 6th

Depth Image Reconstruction Using Low Rank and Total Variatio...

引用

6th EAI International conference on Industrial Networks and Intelligent Systems, INISCOM 2020

作者： Tang, Van Ha Nguyen, Mau Uyen Faculty of Information Technology Le Quy Don Technical University Hanoi Viet Nam

ISBN: (纸本)9783030630829

Rapid advancement and active research in computer vision applications and 3D imaging have made a high demand for efficient depth image estimation techniques. The depth image acquisition, however, is typically challenged due to poor hardware performance and high computation cost. To tackle such limitations, this paper proposes an efficient approach for depth image reconstruction using low rank (LR) and total variation (TV) regularizations. The key idea is LR incorporates non-local depth information and TV takes into account the local spatial consistency. The proposed model reformulates the task of depth image estimate as a joint LR-TV regularized minimization problem, in which LR is used to approximate the low-dimensional structure of the depth image, and TV is employed to promote the depth sparsity in the gradient domain. Furthermore, this paper introduces an algorithm based on alternating direction method of multipliers (ADMM) for solving the minimization problem, whose solution provides an estimate of the depth map from incomplete pixels. Experimental results are conducted and the results show that the proposed approach is very effective at estimating high-quality depth images and is robust to different types of data missing models. © 2020, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

UD-ETR based restoration CNN approach for underwater object detection from multimedia data 2

UD-ETR based restoration CNN approach for underwater object ...

引用

2nd International conference on data, Engineering and Applications, IDEA 2020

作者： Martin, Martina Sharma, Sanjeev Mishra, Nishchol Pandey, Gunjan School of Information Technology RGPV Bhopal India Shri Govindram Seksaria Institute of Technology and Science Indore India

ISBN: (纸本)9781728157184

In this paper, the work has been done in the field of underwater world, which includes restoration of the obtained images and then the detection of objects. The identification of the objects is performed in order to check the presence of items in the video and to unequivocally find a particular object. This is the area of interest for researchers because of the presence of various species under water. The images which are taken in the water lacks some factors such as: non-uniform lighting, low contrast, turbid water etc. which leads to the generation of improper outputs. These issues give rise to the involvement of restoration technique, which is a fundamental technique used for removing some severe abnormalities from the obtained images such as: low contrast, blurring etc. The proposed algorithm UD-ETR (UDCP based Energy Transmission Restoration) is used to restore the green channel images. It contains multiple stages of restoration which ultimately gives final restored image. Further, CNN (Convolutional Neural Network) is used for detecting the fish from the restored image. This algorithm is implemented using the MATLAB tool and the efficiency obtained shows its capability. © 2020 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Adversarial Feature Disentanglement for Place Recognition Across Changing Appearance

Adversarial Feature Disentanglement for Place Recognition Ac...

引用

IEEE International conference on Robotics and Automation (ICRA)

作者： Tang, Li Wang, Yue Luo, Qianhui Ding, Xiaqing Xiong, Rong Zhejiang Univ State Key Lab Ind Control Technol Hangzhou 310012 Peoples R China

ISBN: (纸本)9781728173955

When robots move autonomously for long-term, varied appearance such as the transition from day to night and seasonal variation brings challenges to visual place recognition. Defining an appearance condition (e.g. a season, a kind of weather) as a domain, we consider that the desired representation for place recognition (i) should be domain-unrelated so that images from different time can be matched regardless of varied appearance, (ii) should be learned in a self-supervised manner without the need of massive manually labeled data, and (iii) should be able to train among multiple domains in one model to keep limited model complexity. This paper sets to find domain-unrelated features across extremely changing appearance, which can be used as image descriptors to match between images collected at different conditions. We propose to use the adversarial network to disentangle domain-unrelated and domain-related features, which are named place and appearance features respectively. During training, only domain information is needed without requiring manually aligned image sequences. Experiments demonstrated that our method can disentangle place and appearance features in both toy case and images from the real world, and the place feature is qualified in place recognition tasks under different appearance conditions. The proposed network is also adaptable to multiple domains without increasing model capacity and shows favorable generalization.

关键词： Feature extraction Training image reconstruction image recognition Robustness Machine learning Neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：