检索结果-内蒙古大学图书馆

14th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2023

作者： Huynh, Trinh Walter, James Aveta, Federica University of Michigan Robotics Department Ann ArborMI48109 United States Wentworth Insitute of Technology Electrical and Computer Engineering Program BostonMA02115 United States

ISBN: (纸本)9798350304138

An intelligent and self-sufficient robot is essential across a wide range of fields, including transportation, industry, space exploration, and defense. Mobile robots possess the capability to undertake diverse tasks such as handling materials, aiding in disaster scenarios, conducting patrols, and executing rescue operations. As a result, the development of an autonomous robot that can navigate through both unchanging and ever-changing surroundings has become important. The primary objective of mobile robot navigation revolves around ensuring the seamless and secure traversal of the robot through complex environments, starting from an initial position, and reaching a designated goal position. This paper presents the design and implementation of a Jetson Nano powered robot car which uses local sensors to interact with an unknown environment. Object following, obstacle avoidance, and wall following features are built for the car to navigate to reach its desired destinations. © 2023 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

LSCS-Net: A lightweight skin cancer segmentation network with densely connected multi-rate atrous convolution

引用

computers in Biology and Medicine 2024年 173卷 108303-108303页

作者： Din, Sadia Mourad, Omar Serpedin, Erchin Electrical and Computer Engineering Program Texas A&M University Doha Qatar Weill Cornell Medicine Doha Qatar Department of Electrical and Computer Engineering Texas A&M University College StationTX United States

The rising occurrence and notable public health consequences of skin cancer, especially of the most challenging form known as melanoma, have created an urgent demand for more advanced approaches to disease management. The integration of modern computer vision methods into clinical procedures offers the potential for enhancing the detection of skin cancer. The UNet model has gained prominence as a valuable tool for this objective, continuously evolving to tackle the difficulties associated with the inherent diversity of dermatological images. These challenges stem from diverse medical origins and are further complicated by variations in lighting, patient characteristics, and hair density. In this work, we present an innovative end-to-end trainable network crafted for the segmentation of skin cancer. This network comprises an encoder–decoder architecture, a novel feature extraction block, and a densely connected multi-rate Atrous convolution block. We evaluated the performance of the proposed lightweight skin cancer segmentation network (LSCS-Net) on three widely used benchmark datasets for skin lesion segmentation: ISIC 2016, ISIC 2017, and ISIC 2018. The generalization capabilities of LSCS-Net are testified by the excellent performance on breast cancer and thyroid nodule segmentation datasets. The empirical findings confirm that LSCS-net attains state-of-the-art results, as demonstrated by a significantly elevated Jaccard index. © 2024 The Author(s)

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Image Classification Using Custom Spectral Convolutional Neural Networks (CSCNNs) 14

Hyperspectral Image Classification Using Custom Spectral Con...

引用

14th International Conference on Information Science and Technology, ICIST 2024

作者： Rouamba, Stephanie Zhang, Nian Mahmoud, Wagdy Thompson, Lara Denis, Max Deksissa, Tolessa University of the District of Columbia Department of Electrical and Computer Engineering WashingtonDC United States University of the District of Columbia Department of Mechanical Engineering Biomedical Engineering Program WashingtonDC United States University of the District of Columbia Department of Mechanical Engineering WashingtonDC United States Water Resources Research Institute University of the District of Columbia WashingtonDC United States

ISBN: (纸本)9798350353334

Custom spectral convolutional neural networks (CSCNNs) combine the strengths of convolutional neural networks with specialized spectral processing, resulting in improved classification accuracy by effectively capturing subtle variations in hyperspectral data. This paper proposes a CSCNNs based approach to classify hyperspectral images. The proposed method leverages the high-dimensional spectral data inherent in hyperspectral images, employing convolutional layers specifically designed to capture spectral-spatial features. By reducing dimensionality through principal component analysis and creating image patches, the model is trained to recognize complex patterns across different spectral bands. In addition, a comprehensive analysis of CSCNN performance is carried out, focusing on its architecture, key features, and benefits in computational efficiency and spectral representation. Experimental results on datasets such as Salinas-A, Pavia university (Pavia-U), and Indian Pines demonstrate that the CSCNN model surpasses traditional methods, achieving higher classification accuracy and more robust performance metrics like overall accuracy (OA), average accuracy (AA), and Kappa coefficient. The proposed model achieved an overall accuracy (OA) of 98.2%, 96.7%, and 92.5% for the Salinas-A, Pavia-U, and Indian Pines datasets, respectively. The model's average accuracy (AA) was 97.5%, 95.4%, and 89.8% for the same datasets. Furthermore, the model attained Kappa coefficients of 97.7%, 95.2%, and 89.1% for Salinas-A, Pavia-U, and Indian Pines, respectively. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Reconstruction of Layered Rough Surfaces Using a Two-Step RTM Scheme

Reconstruction of Layered Rough Surfaces Using a Two-Step RT...

引用

Antennas and Propagation & USNC/URSI National Radio Science Meeting

作者： Ahmet Sefer Hakan Bagci Electrical and Computer Engineering (ECE) Program Computer Electrical and Mathematical Science and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia

ISBN: (数字)9798350369908

ISBN: (纸本)9798350369915

An imaging scheme, which uses the frequency- domain reverse time migration (RTM) method to reconstruct two rough surfaces between three dielectric media from the scattered field measurements, is developed. The proposed method requires two steps for the reconstructions. At the first step, the RTM function that is computed using the scattered field measurements reveals only the upper rough surface. At the second step, it is first assumed that there is only one surface, the upper one. The forward scattering problem is solved for this scenario. Then, to reconstruct the lower surface, the difference between the scattered fields obtained from this forward scattering problem and the scattered field measurements is used to compute the RTM function of the second step. This second RTM function reveals the lower surface. Numerical experiments demonstrate that the proposed two-step scheme is effective and promising.

关键词： Surface reconstruction Time-frequency analysis Integral equations Imaging Media Surface roughness Dielectric measurement

来源：评论

学校读者我要写书评

暂无评论

Reconstruction of Rough Surface Profiles using a CNN-enhanced RTM-based Inversion Scheme

Reconstruction of Rough Surface Profiles using a CNN-enhance...

引用

International Review of Progress in Applied Computational Electromagnetics (ACES)

作者： Ahmet Sefer Guang Ooi Shehab Ahmed Hakan Bagci Electrical and Computer Engineering (ECE) Program Computer Electrical and Mathematical Science and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia

ISBN: (数字)9781733509671

ISBN: (纸本)9798350362978

Numerical methods that can accurately reconstruct rough surface profiles are used in various fields of engineering such as remote sensing, microwave imaging, optics, nondestructive testing, etc. These methods express the electromagnetic scattered fields measured away from the surface itself as an integral function of the surface profile. This mapping is highly nonlinear and ill-posed (D. Colton and R. Kress, 1998, SpringerVerlag, Berlin), and therefore its inversion for reconstruction of the surface profile from measured scattered fields is challenging. This inversion can done using semi-analytic asymptotic approaches such as the small perturbation and the Rytov approximation methods (A.G. Voronovich, 2013, Springer-Verlag, Berlin), however the range of applicability of these approaches is rather limited. Fully numerical methods that rely on Newton-type iterative linearization techniques and regularization schemes such as those in (S. Arhab, et al., PIERS, pp. 3495–3500, 2017) and (A. Sefer, A. Yapar, IEEE Trans. Geosci Remote Sens., vol. 59, pp. 1041–1051, 2021) have a wider range of applicability but they suffer from convergence and accuracy issues.

关键词： Microwave measurement Surface reconstruction Perturbation methods Nondestructive testing Optical variables measurement Optics Surface roughness

来源：评论

学校读者我要写书评

暂无评论

Electromagnetic Inversion Regularized by a Plug-and-Play Deep Neural Network Denoiser

Electromagnetic Inversion Regularized by a Plug-and-Play Dee...

引用

Antennas and Propagation & USNC/URSI National Radio Science Meeting

作者： Lingqi Gao Hakan Bagci Electrical and Computer Engineering (ECE) Program Computer Electrical and Mathematical Science and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia

ISBN: (数字)9798350369908

ISBN: (纸本)9798350369915

A plug-and-play scheme that relies on a deep neural network for image denoising is used to regularize the nonlinear electromagnetic (EM) inversion. It is shown that any state-of-the-art denoiser can be plugged into the conventional inversion framework as an implicit regularization step. Thus, a pretrained Swin-Conv-UNet (SCUNet) is employed in the EM inversion. SCUNet combines the advantages of residual convolutional layers and swin transformer blocks in accounting for different image priors and it is remarkably effective in image denoising. Nu-merical results obtained using this framework clearly shows its benefits over existing inversion algorithms.

关键词： Conferences Artificial neural networks Transformers Antennas and propagation Electromagnetics Image denoising

来源：评论

学校读者我要写书评

暂无评论

A Ratio-Norm Regularization for Sparsity-Promoting Electromagnetic Inversion

A Ratio-Norm Regularization for Sparsity-Promoting Electroma...

引用

International Review of Progress in Applied Computational Electromagnetics (ACES)

ISBN: (数字)9781733509671

ISBN: (纸本)9798350362978

A nonlinear electromagnetic inversion method that promotes the sparsity in the model gradient is proposed for reconstruction of dielectric profiles. For regularization, the method uses the ratio of $l_{1}$ -norm to $l_{2}$ -norm ( $l_{1}/l_{2}$ -norm) which is a better approximation to $l_{0}$ -norm than $l_{1}$ -norm due to its scale-invariant property. To deal with the non-convexity of the resulting optimization problem, the alternating direction method of mul-tipliers is used to split the quotient structure of the $l_{1}/l_{2}$ -norm. Consequently, the optimization problem is separated into several sub-steps that are executed iteratively in an alternating fashion. Numerical results show that the proposed method produces more accurate reconstructions of spatially sparse dielectric profiles (by preserving edges and reducing artifacts) compared to the methods relying on Tikhonov and total variation regularization.

关键词： Accuracy Computational electromagnetics Dielectrics Electromagnetics Optimization

来源：评论

学校读者我要写书评

暂无评论

A Wide-angle and Polarization-independent Plasmonic Absorber for UV to Near-IR Range

A Wide-angle and Polarization-independent Plasmonic Absorber...

引用

Antennas and Propagation & USNC/URSI National Radio Science Meeting

作者： Partha Mondal Omar Alkhazragi Boon S. Ooi Hakan Bagci Electrical and Computer Engineering (ECE) Program Computer Electrical and Mathematical Science and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia

ISBN: (数字)9798350369908

ISBN: (纸本)9798350369915

A metamaterial-based plasmonic absorber is designed, fabricated, and characterized. The absorber consists of a periodic array of Ti unit-cells at the top, a layer of Al at the bottom, and a thin SiO 2 layer that is sandwiched between the top and the bottom layers. Simulations and experiments show that the proposed design supports an average absorption of 96% over the wavelength range changing from 280 nm to 1000 nm (frequency range between ultraviolet [UV] and near-infrared [IR]). Furthermore, the absorption spectrum is polarization insensitive and has a large incidence angle tolerance. The proposed absorber has the potential to be used in photovoltaic applications such as solar cells and photo-detectors.

关键词： Silicon compounds Photovoltaic systems Absorption Photovoltaic cells Conferences Plasmons Antennas and propagation

来源：评论

学校读者我要写书评

暂无评论

An Inversion Algorithm to Reconstruct Star-Like Penetrable Objects from Scattered Far-Field Pattern

An Inversion Algorithm to Reconstruct Star-Like Penetrable O...

引用

Antennas and Propagation & USNC/URSI National Radio Science Meeting

ISBN: (数字)9798350369908

ISBN: (纸本)9798350369915

An iterative inversion algorithm to reconstruct the shape of two-dimensional dielectric objects from far-field measurements is formulated and implemented. The proposed method uses an integral operator to map the unknown boundary of the object onto the far-field pattern of the scattered field. This mapping is inherently ill-posed and nonlinear. Therefore, Newton iterations are used for linearization, and the resulting linear equation at each iteration is regularized using a Tikhonov scheme. Numerical results validate the accuracy and the applicability of the proposed method.

关键词： Shape Shape measurement Conferences Integral equations Electromagnetic scattering Antennas and propagation Iterative algorithms

来源：评论

学校读者我要写书评

暂无评论

A Local Time-Stepping Discontinuous Galerkin Time-Domain Scheme for Simulation of Electromagnetic Problems Involving Resistive Boundary Condition

A Local Time-Stepping Discontinuous Galerkin Time-Domain Sch...

引用

USNC-URSI Radio Science Meeting (Joint with AP-S Symposium)

作者： Ruitao Sun Ming Dong Liang Chen Hakan Bagci Electrical and Computer Engineering (ECE) Program Computer Electrical and Mathematical Science and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia

ISBN: (数字)9789463968119

ISBN: (纸本)9798350359497

Thin layers with high conductivity values, such as metal sheets, conductive paint, graphene, and other two-dimensional (2D) materials, are commonly used in various electromagnetic applications. One of the fundamental challenges in numerical modeling of these thin conductive layers is the requirement for an extremely fine mesh that can accurately capture field variations and account for the intricate geometrical features of the structure (H. Chen, A. J. Taylor and N. Yu, Rep. Prog. Phy., 79,10-35,2016). A dense mesh translates into high computational cost since the number of unknowns is increased and the time step size must be reduced for an explicit time marching scheme (to ensure that the Courant-Friedrichs-Lewy (CFL) condition is satisfied). One can replace the thin conductive layer with an infinitesimally thin sheet on which the resistive boundary condition (RBC) is enforced (T. B. A. Senior and J. L. Volakis, London, UK: IET, 1995). This approach completely avoids the dense mesh and the high computational cost that comes with it. However, RBC has to be incorporated into the electromagnetic solver.

关键词： Two-dimensional displays Graphene Metals Boundary conditions Computational efficiency Numerical models Electromagnetics

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：