检索结果-内蒙古大学图书馆

A Multi-Step Multivariate Fuzzy-based Time Series Forecasting on Internet of Things Data

IEEE Internet of Things Journal 2025年第12期12卷 21679-21690页

作者： Bitencourt, Hugo Vinicius Lucas, Patri-Cia de Oliveira Orang, Omid Silva, Petronio C. L. Guimaraes, Frederico Gadelha Universidade Federal de Minas Gerais -UFMG Graduate Program in Electrical Engineering MG Belo Horizonte31270-901 Brazil Federal Institute of Northern Minas Gerais IFNMG MG Salinas Brazil Universidade Federal de Minas Gerais -UFMG Computer Science MG Belo Horizonte31270-901 Brazil Federal Institute of Northern Minas Gerais IFNMG MG Januaria Brazil Universidade Federal de Minas Gerais -UFMG Department of Computer Science MG Belo Horizonte Brazil

Multi-step ahead time series forecasting is essential in Internet of Things (IoT) applications in smart cities and smart homes to make accurate future predictions and precise decision-making. Thus, this study introduces a novel multiple-input single-output (MISO) forecasting method called Multi-Step Embedding-based Fuzzy Time Series (MS-EFTS), designed to predict high-dimensional non-stationary time series data. As a first-order approach, it employs a direct strategy that integrates an embedding transformation with a weighted multivariate FTS (WMVFTS) model. This combination allows for effective predictions over long-term horizons within low-dimensional, learned continuous representations. The effectiveness of the proposed MS-EFTS is assessed using three high-dimensional IoT time series in this investigation. The obtained results showcase the superior performance of the proposed method compared to some deep learning forecasting methods, including LSTM, BiLSTM, TCN, and CNN-LSTM, in terms of accuracy, parsimony, and efficiency. © 2014 IEEE.

关键词： Smart homes

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

Development of Detection Lung Disease Stand Alone System Based on Convolutional Neural Network (CNN)

Development of Detection Lung Disease Stand Alone System Bas...

引用

International Conference of computer and Informatics engineering (IC2IE)

作者： Edgar Caesar Liewarnata Yosica Mariana Sofyan Tan Suryadiputra Liawatimena Winda Astuti Automotive and Robotics Program Computer Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia Product Design Program Industrial Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia Automotive & Robotics Program Computer Engineering Department BINUS ASO School of Engineering Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331505530

ISBN: (纸本)9798331505547

Lung disease, especially Tuberculosis (TBC), placed the highest death rate in Indonesia. Tuberculosis (TB) in Indonesia is ranked second after India. Therefore, it is important to reduce or early detection of the lung disease, to prevent this disease and speed up handling. The system can recognize the disease lung identification, and the system applied as standalone system. In this work, the Convolutional Neural Network (CNN) approach for identifying diseases lung identification is proposed. The Mel Frequency Cepstral Coefficient (MFCC) applied to process the stethoscope sounds which will used as input to the CNN. The performance of the proposed system has been investigated and resulted. The accuracy of 99% and 98%, for training and testing accuracy respectively. Furthermore, the system accurately detects lung diseases identification.

关键词： Training Accuracy Tuberculosis Pulmonary diseases Lungs Stethoscope Recording Convolutional neural networks Mel frequency cepstral coefficient Testing

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 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

Multi-robot Map Exploration Based on Multiple Rapidly-Exploring Randomized Trees

引用

SN computer science 2024年第1期5卷 31页

作者： Mukhopadhyay, Shayok Umari, Hassan Koirala, Koshish Electrical & Computer Engineering and Computer Science Department University of New Haven 300 Boston Post Rd West Haven 06516 CT United States Department of Electrical Engineering American University of Sharjah Sharjah P.O. Box 26666 United Arab Emirates Mechatronics Engineering graduate program American University of Sharjah Sharjah P.O. Box 26666 United Arab Emirates

A map is necessary for tasks such as path planning or localization, which are common to mobile robot navigation. However, a map may be unavailable if the environment in which a robot navigates is unknown. Creating a map requires an exploration algorithm. Such algorithms guide robots to boundaries that separate known portions of a map from the unknown portions. Such boundaries are known as frontiers. There are image processing-based algorithms that detect frontiers. The authors’ previous work uses two, i.e., local and global, rapidly exploring random trees (RRTs) for two-dimensional exploration using a single robot. The present work applies the above to a multiagent system with three robots. A market-based strategy is used to allocate exploration tasks to the robots. Results show that the developed exploration strategy successfully explores a map in a reasonable amount of time compared to image processing-based approaches, and also reduces the map exploration cost. This strategy is readily usable for three-dimensional exploration with drones. It is also shown that the usage of a local frontier detector along with a global frontier detector helps reduce exploration time compared to simply using a global frontier detector alone. As an outline to future work, the paper also shows an extension of the proposed approach towards three-dimensional mapping using a single robot. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Exploration Mapping Multi-agent Navigation ROS RRT

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

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 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 Hybrid Inference Engine to Predict Uncertain Sugar Content for Sugar Industry

引用

Procedia computer science 2024年 245卷 480-489页

作者： Muhammad Asrol Napthaleni Ditdit Nugeraha Utama Suharjito Christian Harito Muhammad Syafrudin Industrial Engineering Department BINUS Graduate Program – Master of Industrial Engineering Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Department of Artificial Intelligence and Data Science Sejong University Seoul 05006 South Korea

The sugar industry is facing challenges in increasing productivity to meet consumer demand. One opportunity for productivity improvement lies in ensuring sugar content. This study proposes a hybrid model to predict sugar content by considering uncertainty factors. A hybrid model combining fuzzy subtractive clustering, and a fuzzy inference system is proposed to predict sugar content. The clustering results using silhouette and fuzzy subtractive clustering successfully identified 6 cluster centres from 2225 datasets collected in a sugar industry in East Java Province. The hybrid inference engine model is designed with fuzzy rules derived from the clustered data. Two inference models are developed: triangular and Gaussian fuzzy numbers. The testing results indicate that the hybrid model with triangular fuzzy numbers shows the smallest error with an R2 value of 0.95. This model is possible to applied in the sugar industry for decision makers in improving productivity with taking attention into uncertain factors influencing sugar content.

关键词： Clustering Fuzzy Hybrid model Inference System Prediction Sugarcane

来源：评论

学校读者我要写书评

暂无评论

A ShuffleNet Architecture-Based Multi-Layer Feature Scaling and Fusion Approach for Underwater Net Cage Damage Detection in Aquaculture

A ShuffleNet Architecture-Based Multi-Layer Feature Scaling ...

引用

IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia)

作者： Xiang-Rui Huang Yi-Cheng Chen Liang-Bi Chen Wu-Chih Hu Department of Electrical Engineering Master Program in Electrical Engineering and Computer Science National Penghu University of Science and Technology Penghu Taiwan Department of Computer Science and Information Engineering National Penghu University of Science and Technology Penghu Taiwan

ISBN: (数字)9798331530839

ISBN: (纸本)9798331530846

In offshore aquaculture operations, personnel equipped with diving gear are often necessary to inspect the underwater net cages for damage, particularly on the sea floor. This manual inspection process is time-consuming and complex. To overcome this problem, this paper proposes a computer vision solution for identifying damage in underwater net cages to address the inefficiencies and challenges of traditional manual inspections. The proposed scheme utilizes a high-performance multi-branch computational architecture designed based on ShuffleNet architecture to detect net cage damage more efficiently. Experimental results demonstrate that this work performs well on the ImageNet ILSVRC-2010 dataset and achieves an accuracy of 88.54% in underwater net damage detection.

关键词： Accuracy Gears Computational modeling Sea floor computer architecture Manuals Inspection Feature extraction Personnel Aquaculture

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：