检索结果-内蒙古大学图书馆

International electrical engineering Congress (iEECON)

作者： Pipat Sakarin Suchada Sitjongsataporn The Electrical Engineering Graduate Program Faculty of Engineering and Technology Mahanakorn University of Technology Bangkok Thailand Department of Electronic Engineering Mahanakorn Institute of Innovation (MII) Mahanakorn University of Technology Bangkok Thailand

ISBN: (数字)9798350383591

ISBN: (纸本)9798350383607

This paper presents the human fall detection by convolutional neural network (CNN) classification and MobileNet algorithm. In order to reduce the number of parameter, we propose a vision-based fall detection model, that is called “Applied Depthwise separable-based CNN-MobileNet (ACM) algorithm”. This model is based on CNN, deptwise convolution and pointwise convolution of MobileNet algorithm. Experimental results show the accuracy of proposed ACM model about 97.68% and number of parameters of proposed ACM model is less than conventional CNN model.

关键词： electrical engineering Convolution Classification algorithms Convolutional neural networks Fall detection Standards

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

Modeling Small Signal Analysis Using Kharitonov’s Theorem Case: Inverter Based Microgrid

Modeling Small Signal Analysis Using Kharitonov’s Theorem C...

引用

International Conference on High Voltage engineering and Power Systems (ICHVEPS)

作者： Jason Kevin M. Banjar-Nahor Nanang Hariyanto Electrical Power Engineering Study Program Bandung Institute of Technology Bandung Indonesia

Microgrid systems are becoming more popular and the main component in a microgrid system is generation, which in a microgrid system usually consists of distributed generations (DGs). Because the renewable energy (RE) generators are an inverter-based generator, a microgrid dominated by RE generators is called inverter-based microgrid. Due to intermittency of RE generator, such as solar PV, the RE power generation variation may cause instability. The conventional method to analyze system stability due to the variation of loads and generation is modal analysis. In this experiment the proposed method for analyzing small signal stability is by using Kharitonov’s Theorem. The objective of this experiment is to analyze inverter-based stability using Kharitonov’s Theorem and compare it to the result using conventional analysis method which is modal analysis. Using Kharitonov’s Theorem, the system stability can be determined for several operation scenarios within certain time range. In this experiment, the inverter-based microgrid will be modeled using DIgSILENT PowerFactory and the system matrices will be exported into MATLAB software to be analyzed and converted to four transfer functions using Kharitonov’s Theorem. The four output transfer function will determined the system small signal stability of modeled microgrid in one day operation.

关键词：

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 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

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

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

The design and evaluation of an AR-based serious game to teach programming

引用

Computers and Graphics (Pergamon) 2022年 103卷 1-18页

作者： Sharma, Vandit Bhagat, Kaushal Kumar Huang, Huai-Hsuan Chen, Nian-Shing Department of Electronics and Electrical Communication Engineering Indian Institute of Technology Kharagpur Kharagpur721302 India Advanced Technology Development Centre Indian Institute of Technology Kharagpur Kharagpur721302 India Institute for Research Excellence in Learning Sciences Program of Learning Sciences National Taiwan Normal University Taiwan

The ubiquity of smartphone and tablet devices, combined with the increasing availability of serious games, has enabled students to learn various abstract concepts in an appealing and convenient manner. While several researchers have explored the use of Augmented Reality (AR) in serious games, many of these games have not been critically explained or evaluated. To that end, we employed game-based learning methodologies and Game Learning Analytics (GLA) to systematize the design and evaluation of an AR-based serious game to teach programming. We evaluated our game for usability and effectiveness by conducting a user study on twenty-seven undergraduate students. The evaluation primarily consisted of a learning test conducted twice – before and after playing the game – along with a usability questionnaire that players completed after playing the game. Our results showed that players made significant progress after playing the game. The game helped players improve their basic programming skills, especially for the group having lower prior programming skills. The results highlighted various ways in which GLA can be used to benefit different stakeholders in the game. Based on players’ qualitative responses, we also identified several areas of improvement, most prominently the trade-off between ease of use and game complexity. We provide suggestions and discuss implications for future work. © 2022 Elsevier Ltd

关键词： Serious games

来源：评论

学校读者我要写书评

暂无评论

Leveraging Heart Rate Variability and Machine Learning for Daily Activity Classification in Healthy Adult Males

Leveraging Heart Rate Variability and Machine Learning for D...

引用

International Conference on Telecommunication Systems, Services, and Applications (TSSA)

作者： Vidya Ikawati Rahadian Yusuf Ary Setijadi Prihatmanto Tatang Sudrajat Didin Saepudin Welly Surjono Doctoral Program of School of Electrical and Information Engineering Institute of Technology Bandung Bandung Indonesia Departement of Electrical and Information Engineering Institute of Technology Bandung Bandung Indonesia Universitas Sangga Buana Bandung Indonesia

ISBN: (数字)9798331527686

ISBN: (纸本)9798331527693

Advancements in machine learning techniques for analyzing heart rate variability (HRV) show great potential in accurately measuring various activities in the field of health monitoring. This work examines the feasibility of using non-invasive HRV data gathered during everyday activities to train machine learning models for accurate activity classification. In the field of personalization, the study focuses on the difficulty of adapting to individual differences in baseline HRV. It also acknowledges that HRV is influenced by stress, physical activity, and external influences, and that it is a dynamic measure. The experimental methodology consists of a pilot study using a retrospective observational cohort approach. It utilizes a waistband device to continuously record heart rate variability (HRV) during different daily activities. The study utilizes a thorough methodology that includes statistical data description, correlation analysis, variance analysis, outlier detection, and identification of cycle periods using power spectral density. The performance of various machine learning models, such as Random Forest, Naïve Bayes, Decision Tree, and Logistic Regression, was evaluated for activity classification. The Decision Tree model exhibited superior performance. The work provides useful insights into the potential of machine learning for HRV-based activity monitoring, highlighting the importance of collecting reliable data and developing tailored models to improve accuracy and practicality.

关键词： Accuracy Databases Data models Telecommunications Decision trees Reliability Heart rate variability Monitoring Stress Stress measurement

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：