检索结果-内蒙古大学图书馆

17th IEEE International Conference on Solid-State and Integrated Circuit Technology, ICSICT 2024

作者： Pan, Yu Zhang, Yuejun Guo, Shuaicheng Tian, Yuanxin Hong, Bo Fang, Rui Wen, Liang Ding, Yong Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China China Coast Guard Academy Department of Electronic Technology Ningbo315211 China College of Integrated Circuits Zhejiang University Hangzhou310058 China

ISBN: (纸本)9798350361834

As fundamental components of programmable logic circuits, Lookup Table (LUT) circuits enable the implementation of arbitrary combinational logic. The volatility, standby power dissipation, and propagation delay of LUT circuits critically affect the performance of programmable logic circuits. In order to address the problems of circuit volatility, propagation delay and standby power dissipation, a high-performance Magnetic Tunnel Junction LUT (MTJ-LUT) circuit design scheme is proposed based on the 4T1M structure. According to the characteristics of MTJ principle, and comparing with the classical MTJ-LUT memory cell, MTJ-LUT memory module based on 4T1M structure is proposed;Based on the LUT circuit principle of 4T1M structure, a circuit architecture with current mirror bias circuitry is proposed to adopt the compliant reference resistor, and the steady-current-powered reading mode is used to achieve the optimal reading operation and reduce the delay;The circuit function is implemented in SMIC 40nm process using SPICE simulation tool. The experimental results show that the propagation delay and power dissipation of the MTJ-LUT circuit proposed are reduced by 72% and 15%, respectively, compared with the conventional MTJ-LUT circuit. © 2024 IEEE.

关键词： Delay circuits

来源：评论

学校读者我要写书评

暂无评论

Identification of Haploid Maize Seeds Using Efficient Channel Attention with Selective Kernel Networks and Multi-layer Stacked Ensemble

Identification of Haploid Maize Seeds Using Efficient Channe...

引用

Cognitive Computing and Complex Data (ICCD), International Conference on the

作者： Lieto Wamunyima Haiyi Bian Bobwillie Kessellie Sulonteh Faculty of Electronic Information Engineering Huaiyin Institute of Technology Huai’an City China Faculty of Computer Application and Engineering RIMT University Mandi Gobindgarh Punjab India

ISBN: (数字)9798350352894

ISBN: (纸本)9798350352900

This study focuses on the recognition of maize haploid seeds using convolutional neural networks (CNNs). A dataset comprising 3,000 maize seed images, consisting of 1,230 haploid maize seed images and 1,770 diploid maize seed images, was utilized for experimentation. Classical CNN models, including VGG, AlexNet, ResNet, and SKNet, were employed to compare their effectiveness in haploid maize seed recognition. Additionally, this study proposes the ECA-SKEnsemble model, which enhances the SKNet architecture by replacing its fully connected layer with a one-dimensional convolution, thus reducing model complexity. The ECA-SKEnsemble integrates multiple instances of the ECA-SKNet model, each trained with different initializations and training techniques. By combining these models using ensemble techniques such as weighted voting or averaging, ECA-SKEnsemble achieves superior performance in maize seed recognition. The model attained an accuracy of 93.04%, outperforming standard CNN architectures, including VGG and ResNet. This work demonstrates the effectiveness of ensemble learning combined with efficient channel attention for improving maize seed recognition accuracy.

关键词： Training Accuracy Convolution Computational modeling computer architecture Convolutional neural networks Ensemble learning Kernel Tuning Standards

来源：评论

学校读者我要写书评

暂无评论

Photonics Applications and Web engineering - WILGA 2022

Photonics Applications and Web Engineering - WILGA 2022

引用

Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments 2022

作者： Romaniuk, Ryszard S. Smolarz, Andrzej Wójcik, Waldemar Warsaw University of Technology Institute of Electronic Systems Poland Lublin University of Technology Faculty of Electrical Engineering and Computer Science Poland

ISBN: (纸本)9781510660595

Wilga 2022 Summer Symposium on Photonics Applications and Web engineering was the 50th edition of the research and technical meetings series. Traditionally, the whole week lasting annual series of technical conferences and topical sessions was split to one winter meeting in January and two summer events in May/June, and in September 2022. The hybrid meetings were held in Wilga resort near Warsaw, owned by the Warsaw University of Technology and in Lublin. Nearly 100 participants took part in all of the Wilga 2022 events, most of them being young researchers active in all aspects of photonics, electronics and ICT science and technology. Wilga Symposium embraces hardware and software technologies associated with photonics like optics, optical engineering, optoelectronics, electronics and electrical engineering, mechatronics, chemical and material engineering, applied physics, industrial solutions and applications. Around 100 papers were presented during Wilga 2022, oral and poster. Out of this number, some papers chosen by authors are published in this volume of Proc. SPIE mostly related to photonics. The major change was that during Wilga 2020, 2021 and 2022 Symposia, during summer editions, no traditional large young researcher sessions at large were possible to be organized. © 2022 SPIE. All rights reserved.

关键词： Photonics

来源：评论

学校读者我要写书评

暂无评论

Robust Active and Reactive Power Control by using Single-Phase Grid connected H-Bridge Inverter

Robust Active and Reactive Power Control by using Single-Pha...

引用

International Smart Grid Workshop and Certificate Program (ISGWCP)

作者： Resul Coteli Korhan Kayisli Ruhi Zafer Caglayan Dept. of Energy Systems Engineering Technology Faculty Firat University Elazig Turkiye Dept. of Electrical- Electronic Engineering Engineering Faculty Gazi University Ankara Turkiye Dept. of Computer Engineering Engineering Faculty TED University Ankara Turkiye

ISBN: (数字)9798350361612

ISBN: (纸本)9798350361629

In a single-phase power network, inverters can be used to control the active and reactive power between sources. This task can be achieved by proper control of the current of the single-phase inverter. The current controllers using dq-frame components have a wide application area because of their superior features such as zero steady-state error and using the DC quantities. In this study, the active and reactive power between sources in a single-phase power system consisting of an AC voltage source and a DC voltage source are controlled via dq-frame based super twisting sliding mode (ST-SMC) current controller. For this aim, a Matlab/Simulink model is constructed. The model includes single phase H-bridge inverter, DC voltage source, AC voltage source, AC load, LCL filter and control unit. Two super twisting sliding mode controllers are used to control d and q-axis currents. Decoupling terms are added to output of each controller for independent control of active and reactive power. The simulation studies are performed to demonstrate the controller's ability to provide/absorb active and reactive power. To demonstrate the ability to provide/absorb active power, the d-axis current command is set to 10 A up to 2 s from the start of the simulation, and then, it is set to – 10 A between 2 s to 4 s. To demonstrate the ability to provide/absorb reactive power, the q-axis current command is set to 10 A up to 2 s from the start of the simulation, and then, it is set to – 10 A between 2 s to 4 s. The simulation results show that the controller provides/absorbs the desired active and reactive power quickly and without steady-state error.

关键词： Reactive power Reactive power control Simulation Inverters Mathematical models Steady-state Smart grids

来源：评论

学校读者我要写书评

暂无评论

Dielectric Material Characterization for Reflectarray Antennas Designed at Sub-6GHz and Millimeter Wave Bands of 5G

Dielectric Material Characterization for Reflectarray Antenn...

引用

IEEE International Conference on Telecommunications and Malaysia Communications (ICT-MICC)

作者： Sher Dali Khan Muhammad Inam Abbasi Imran Mohd Ibrahim Izhar Ahmed Sohu Sanaullah Khan Faculty of Electrical and Electronic Engineering Technology Universiti Teknikal Malaysia Melaka (UTeM) Faculty of Electronic and Computer Engineering Universiti Teknikal Malaysia Melaka (UTeM)

The future compliance of reflectarray antenna necessitates a methodical examination of its primary traditional configurations to anticipate improvements. The current design, which utilizes microwave and millimeter wave frequencies, serves as a fundamental foundation for further investigation. This study offers a comparison and characterization of various dielectric substrates employed in Sub-6 GHz and millimeter wave reflectarray antenna, based on unit cells designed at 3.5 GHz and 28 GHz. The analysis utilizes a range of commercially accessible dielectric materials characterized by dielectric permittivity $({{\varepsilon _r}})$ values spanning 2 to 3.6 and loss tangent (tan) values ranging from 0.0009 to 0.001. The performance of different dielectric materials in the design of infinite reflectarray is assessed in terms of bandwidth and reflection loss, providing a comprehensive comparison. It is observed that the bandwidth of patch element unit cells at different levels exhibits significant variations depending on the material properties, with a 10% bandwidth range. Furthermore, it is illustrated that the reflectarray antenna's reflection loss can be deconstructed into dielectric and conductor losses, both contingent upon the material properties utilized in the design. This article presents a comparison of eleven distinct substrate materials that have the potential to result in disruptive designs for both the architecture and components, thereby impacting the performance of the reflectarray antenna.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep CNN Model for Multimodal Medical Image Denoising

引用

computers, Materials & Continua 2022年第11期73卷 3795-3814页

作者： Walid El-Shafai Amira A.Mahmoud Anas M.Ali El-Sayed M.El-Rabaie Taha E.Taha Osama F.Zahran Adel S.El-Fishawy Naglaa F.Soliman Amel A.Alhussan Fathi E.Abd El-Samie Department Electronics and Electrical Communications Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Security Engineering Laboratory Department of Computer SciencePrince Sultan UniversityRiyadh11586Saudi Arabia Alexandria Higher Institute of Engineering&Technology(AIET) AlexandriaEgypt Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadhSaudi Arabia

In the literature,numerous techniques have been employed to decrease noise in medical image modalities,including X-Ray(XR),Ultrasonic(Us),Computed Tomography(CT),Magnetic Resonance Imaging(MRI),and Positron Emission Tomography(PET).These techniques are organized into two main classes:the Multiple Image(MI)and the Single Image(SI)*** the MI techniques,images usually obtained for the same area scanned from different points of view are used.A single image is used in the entire procedure in the SI *** denoising techniques can be carried out both in a transform or spatial *** paper is concerned with single-image noise reduction techniques because we deal with single medical *** most well-known spatial domain noise reduction techniques,including Gaussian filter,Kuan filter,Frost filter,Lee filter,Gabor filter,Median filter,Homomorphic filter,Speckle reducing anisotropic diffusion(SRAD),Nonlocal-Means(NL-Means),and Total Variation(TV),are ***,the transform domain noise reduction techniques,including wavelet-based and Curvelet-based techniques,and some hybridization techniques are ***,a deep(Convolutional Neural Network)CNN-based denoising model is proposed to eliminate Gaussian and Speckle noises in different medical image *** model utilizes the Batch Normalization(BN)and the ReLU as a basic *** a result,it attained a considerable improvement over the traditional *** previously mentioned techniques are evaluated and compared by calculating qualitative visual inspection and quantitative parameters like Peak Signal-to-Noise Ratio(PSNR),Correlation Coefficient(Cr),and system complexity to determine the optimum denoising algorithm to be applied *** on the quality metrics,it is demonstrated that the proposed deep CNN-based denoising model is efficient and has superior denoising performance over the traditionaldenoising techniques.

关键词： Image enhancement medical imaging speckle noise Gaussian noise denoising filters CNN denoising

来源：评论

学校读者我要写书评

暂无评论

Visual Motion Segmentation in Crowd Videos Based on Spatial-Angular Stacked Sparse Autoencoders

引用

computer Systems Science & engineering 2023年第10期47卷 593-611页

作者： Adel Hafeezallah Ahlam Al-Dhamari Syed Abd Rahman Abu-Bakar Department of Electrical Engineering Taibah UniversityMadinahSaudi Arabia Department of Electronic and Computer Engineering Faculty of Electrical EngineeringUniversiti Teknologi MalaysiaJohor Bahru81310Malaysia Department of Computer Engineering Hodeidah UniversityHodeidahYemen

Visual motion segmentation(VMS)is an important and key part of many intelligent crowd *** can be used to figure out the flow behavior through a crowd and to spot unusual life-threatening incidents like crowd stampedes and crashes,which pose a serious risk to public safety and have resulted in numerous fatalities over the past few *** clustering has become one of the most popular methods in ***,complex data,such as a large number of samples and parameters,makes it difficult for trajectory clustering to work well with accurate motion segmentation *** study introduces a spatial-angular stacked sparse autoencoder model(SA-SSAE)with l2-regularization and softmax,a powerful deep learning method for visual motion segmentation to cluster similar motion patterns that belong to the same *** proposed model can extract meaningful high-level features using only spatial-angular features obtained from refined tracklets(a.k.a‘trajectories’).We adopt l2-regularization and sparsity regularization,which can learn sparse representations of features,to guarantee the sparsity of the *** employ the softmax layer to map the data points into accurate cluster *** of the best advantages of the SA-SSAE framework is it can manage VMS even when individuals move around *** framework helps cluster the motion patterns effectively with higher *** put forward a new dataset with itsmanual ground truth,including 21 crowd *** conducted on two crowd benchmarks demonstrate that the proposed model can more accurately group trajectories than the traditional clustering approaches used in previous *** proposed SA-SSAE framework achieved a 0.11 improvement in accuracy and a 0.13 improvement in the F-measure compared with the best current method using the CUHK dataset.

关键词： Visual motion segmentation crowd behavior analysis trajectory analysis crowd dynamics autoencoders motion patterns

来源：评论

学校读者我要写书评

暂无评论

Aerial ISAC: A HAPS-Assisted Integrated Sensing, Communications and Computing Framework for Enhanced Coverage and Security

IEEE Transactions on Green Communications and Networking

引用

IEEE Transactions on Green Communications and Networking 2025年

作者： Benaya, Ahmed M. Hassan, Mohamed S. Ismail, Mahmoud H. American University of Sharjah Department of Electrical Engineering Sharjah United Arab Emirates Menoufia University Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Egypt Cairo University Faculty of Engineering Department of Electronics and Electrical Communications Engineering Giza12613 Egypt American University of Sharjah Department of Computer Science and Engineering United Arab Emirates

In this paper, we propose a framework for a non-terrestrial ISAC system, where a high-altitude platform station (HAPS)-mounted full duplex (FD) ISAC base station (BS) is deployed to deliver communication services to multiple user equipment (UEs) and, at the same time, sense multiple targets. Moreover, the ISAC-BS offloads part of the sensed data to a dedicated edge server for computation purposes. Additionally, an unmanned aerial vehicle (UAV) is deployed to transmit jamming signals aimed at degrading the reception quality of malicious targets or potential eavesdroppers identified through the sensing process. A multi-objective optimization problem is formulated to jointly optimize the transmit/receive beamforming and UAV trajectory to maximize the communication sum spectral efficiency under radar performance, security, offloading, and power constraints. Since the formulated problem is non-convex, we use alternating optimization (AO), semi-definite relaxation (SDR), and successive convex approximation (SCA) approaches to solve it. Simulation results show that the communication and radar achieved rates from the proposed algorithm outperforms the cases of using non-optimized UAV’s trajectory and using the Rayleigh-quotient method to design the receive beamforming vectors. © 2017 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Fundamental Limits of Doppler Shift-Based, ToA-Based,and TDoA-Based Underwater Localization

引用

IEEE/CAA Journal of Automatica Sinica 2023年第7期10卷 1637-1639页

作者： Zijun Gong Cheng Li Ruoyu Su Hong Kong University of Science and Technology(Guangzhou) IOT ThrustGuangzhou 511400 Department of Electronic and Computer Engineering The Hong Kong University of Science and TechnologyHong Kong 999077China Faculty of Engineering and Applied Science Memorial University of NewfoundlandNewfoundland A1B 3X5Canada School of Internet of Things Nanjing University of Posts and TelecommunicationsNanjing 210003China

Dear Editor,This paper is concerned with the underwater localization based on acoustic signals. Specifically, we will focus on the search of an underwater target that can constantly broadcast a beacon signal, such as a black box. Common measurements for localization are Doppler shift [1], time of arrival(ToA) [2]–[4], time difference of arrival(TDoA) [5], [6], angle of arrival(AoA) [7], etc.

关键词： TDoA ToA underwater

来源：评论

学校读者我要写书评

暂无评论

Brain-computer Interface System Based on Common Spatial Patterns for Inner Speech Recognition from Electroencephalography Signal by Using a Convolutional Neural Networks

Brain-Computer Interface System Based on Common Spatial Patt...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Abdalla, Hussna Elnoor M. Al-Haddad, Syed Abdul Rahman Basri, Hamidon Bin Aris, Ishak Bin Yusofv, Abdul Hanif Khan Bin Neyaz, Hisham University Putra Malaysia Malaysia & Sudan International University Sudan University Putra Malaysia Department of Computer and Communication System Engineering Malaysia University Putra Malaysia Faculty of Medicine and Health Sciences Department of Medicine Malaysia University Putra Malaysia Department of Electrical and Electronic Engineering Malaysia University Putra Faculty of Medicine and Health Sciences Department of Medicine Malaysia

ISBN: (纸本)9781665410205

Inner speech recognition is a modern advancement in Brain computer interfaces (BCI) that facilitates a communication between the computer and the brain in a direct way. It is particularly beneficial for individuals who face communication issues due to speech disability. In this research, an end-to-end brain-computer interface system was developed that uses Electroencephalography (EEG) signals to recognize inner speech straight from the brain. The study utilized an open-access dataset presented on four Spanish words from ten participants. The proposed system involved preprocessing to clean and enhance the signal. Common Spatial Pattern (CSP) was utilized to extract features to improve the discrimination between the selected four words. A Convolutional Neural Networks (CNNs) deep learning model was used to enhance the inner speech recognition performance from spatial features. The result shows that the model can decode the inner speech with an average accuracy of 81.40% for the un-seeing dataset and 89.80% for the entire dataset, indicating that the proposed method outperforms previous works that used the same dataset. © 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

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：