检索结果-内蒙古大学图书馆

IEEE Conference on Vehicular technology (VTC)

作者： Shahrukh Khan Kasi Umair Sajid Hashmi Sabit Ekin Ali Imran AI4Networks Research Center Electrical & Computer Engineering University of Oklahoma USA Electrical Engineering & Computer Science National University of Sciences & Technology Pakistan Electrical & Computer Engineering Texas A&M University USA James Watt School of Engineering University of Glasgow UK

With highly heterogeneous application requirements, 6G and beyond cellular networks are expected to be demand-driven, elastic, user-centric, and capable of supporting multiple services. A redesign of the one-size-fits-all cellular architecture is needed to support heterogeneous application needs. This paper addresses this need by proposing an intelligent, demand-driven, elastic user-centric cloud radio access network (UCRAN) architecture capable of providing services to a diverse set of use cases ranging from augmented/virtual reality to high-speed rails to industrial robots to E-health applications, and more. The proposed framework leverages deep reinforcement learning to adjust the size of a user-centered virtual cell based on each application’s heterogeneous throughput and latency requirements. Finally, numerical results are presented to validate the convergence and network adaptability of the proposed approach against the brute-force method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ka-Band 3D-Printed Dielectric GRIN Planar Lens Antenna with Beam Forming Capabilities

Ka-Band 3D-Printed Dielectric GRIN Planar Lens Antenna with ...

引用

Antennas and Propagation & USNC/URSI national Radio Science Meeting

作者： Adnan Nadeem Nosherwan Shoaib Photos Vryonides Antonis Papadakis Symeon Nikolaou Frederick Research Center Nicosia Cyprus Electrical Engineering Department Frederick University Nicosia Cyprus School of Electrical Engineering and Computer Science (SEECS) National University of Sciences and Technology (NUST) Islamabad Pakistan KYAMOS LTD Nicosia Cyprus

ISBN: (数字)9798350369908

ISBN: (纸本)9798350369915

The manuscript describes the design of a planar dielectric graded index (GRIN) lens antenna for 5G applications operating in the 28 GHz Ka-band. The seven parallel slabs comprising the designed lens each have a distinct relative permittivity value. The required refractive indexes for each section are obtained through the arrangement of their relative permittivity values. The lens antenna demonstrates a maximum gain of 16.2 dBi in the broadside direction. The proposed lens antenna exhibits a beam-scanning capability of ± 30° and a gain exceeding 14 dBi in 60-degree scan range. The lens can be manufactured through the utilization of 3D-printing technology, employing low-loss high $\varepsilon_{r}$ dielectric filaments. In order to produce the distinct permittivity values for each slab, the infill percentage of the sections utilized during the 3D printing procedure will be varied accordingly.

关键词： Three-dimensional displays 5G mobile communication Refractive index Three-dimensional printing Dielectrics Slabs Permittivity

来源：评论

学校读者我要写书评

暂无评论

Paired regions for shadow removal approach based on multi-features

引用

High technology Letters 2023年第2期29卷 174-180页

作者：张之政 GUO Mingqiang WU Liang HUANG Ying CHEN Xueye Key Laboratory of Urban Land Resources Monitoring and Simulation Ministry of Natural ResourcesShenzhen 518034P.R.China National Engineering Research Center of Geographic Information System China University of GeosciencesWuhan 430074P.R.China School of Computer Science China University of GeosciencesWuhan 430074P.R.China Wuhan Zondy Cyber Technology Co. Ltd.Wuhan 430074P.R.China

The existence of shadow leads to the degradation of the image qualities and the defect of ground object *** removal is therefore an essential research topic in image processing *** biggest challenge of shadow removal is how to restore the content of shadow areas correctly while removing the shadow in the *** regions for shadow removal approach based on multi-features is proposed, in which shadow removal is only performed on related sunlit *** distance between regions is calculated to find the optimal paired regions with considering of multi-features(texture, gradient feature, etc.) *** in different scenes with peak signal-to-noise ratio(PSNR) and structural similarity(SSIM) evaluation indexes are chosen for *** results are shown with six existing comparison methods by visual and quantitative assessments, which verified that the proposed method shows excellent shadow removal effect, the brightness, color of the removed shadow area, and the surrounding non-shadow area can be naturally fused.

关键词： paired region feature distance texture peak signal-to-noise ratio(PSNR) structural similarity(SSIM)

来源：评论

学校读者我要写书评

暂无评论

Outage Analysis of UAV-Assisted Cooperative Cognitive NOMA in IoT-Enabled Air-Ground Networks with Imperfect SIC and CSI

引用

IEEE Internet of Things Journal 2025年

作者： Hao, Yawen Li, Meiling Xue, Peng Bouanani, Faissal El Chen, Wei Han, Zhu Taiyuan University of Science and Technology School of Electronics Information Engineering Taiyuan030024 China Mohammed V University in Rabat ENSIAS Rabat10000 Morocco Tsinghua University Beijing National Research Center for Information Science and Technology Department of Electronic Engineering Beijing100084 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

This paper addresses the challenges faced by air-ground vehicle networks (AGVN), with a focus on the rapid mobility of both unmanned ground vehicle (UGV) and unmanned aerial vehicles (UAVs) clusters. UAVs employ the non-orthogonal multiple access (NOMA) transmission technique to efficiently transfer data to UGV, aiming to enhance network performance by increasing spectral efficiency and supporting simultaneous transmissions. The system integrates UAV into the network perception environment, enabling cognitive activities and convenient transmission for UGV beyond base station coverage. We provide closed-form outage probability (OP) expressions for UAVs and UGV in two assist modes, i.e., amplify-and-forward UAV (A-UAV) and decode-and-forward UAV (D-UAV), using real-world situations with double Rayleigh fading (DRF) and outdated and imperfect channel state information (ipCSI). Additionally, in both relaying modes, the asymptotic expression for the OP is provided in the high SNR regime for UAV and UGV links. In addition, the system’s diversity order is derived, and the asymptotic analysis shows an intricate interplay of relative speed, channel outdatedness, and OP. Our research results show that when the relative speed decreases or the power increases, the OP decreases. Under the same conditions, the performance of A-UAV is more stable than that of D-UAV. Additionally, the study underscores the importance of assist mode and the number of UAVs in achieving optimal outage performance. Simulation results confirm our analytical results, emphasizing the trade-offs and performance indicators for AGVN system design. The study demonstrates potential avenues for maximizing system performance even within stringent constraints through strategic parameter adjustments. © 2014 IEEE.

关键词： Trucks

来源：评论

学校读者我要写书评

暂无评论

A GSO-based multi-objective technique for performance optimization of blockchain-based industrial Internet of things

引用

International Journal of Communication Systems 2024年第15期37卷

作者： Zanbouri, Kouros Darbandi, Mehdi Nassr, Mohammad Heidari, Arash Navimipour, Nima Jafari Yalcın, Senay Department of Computer Engineering Tabriz Branch Islamic Azad University Tabriz Iran Pôle Universitaire Léonard de Vinci Paris France Communication Technology Engineering Department Tartous University Tartus Syria Department of Mathematics and Natural Sciences Gulf University for Science and Technology Mishref Campus Kuwait Department of Computer Engineering Faculty of Engineering and Natural Science İstanbul Atlas University Turkey Department of Software Engineering Haliç University Istanbul Turkey Department of Computer Engineering Kadir Has University Istanbul Turkey Research Center of High Technologies and Innovative Engineering Western Caspian University Baku Azerbaijan Future Technology Research Center National Yunlin University of Science and Technology Douliou Taiwan Department of Energy System Engineering School of Engineering and Natural Sciences Bahçeşehir University Istanbul Turkey

The latest developments in the industrial Internet of things (IIoT) have opened up a collection of possibilities for many industries. To solve the massive IIoT data security and efficiency problems, a potential approach is considered to satisfy the main needs of IIoT, such as high throughput, high security, and high efficiency, which is named blockchain. The blockchain mechanism is considered a significant approach to boosting data protection and performance. In the quest to amplify the capabilities of blockchain-based IIoT, a pivotal role is accorded to the Glowworm Swarm Optimization (GSO) algorithm. Inspired by the collaborative brilliance of glowworms in nature, the GSO algorithm offers a unique approach to harmonizing these conflicting aims. This paper proposes a new approach to improve the performance optimization of blockchain-based IIoT using the GSO algorithm due to the blockchain's contradictory objectives. The proposed blockchain-based IIoT system using the GSO algorithm addresses scalability challenges typically associated with blockchain technology by efficiently managing interactions among nodes and dynamically adapting to network demands. The GSO algorithm optimizes the allocation of resources and decision-making, reducing inefficiencies and bottlenecks. The method demonstrates considerable performance improvements through extensive simulations compared to traditional algorithms, offering a more scalable and efficient solution for industrial applications in the context of the IIoT. The extensive simulation and computational study have shown that the proposed method using GSO considerably improves the objective function and blockchain-based IIoT systems' performance compared to traditional algorithms. It provides more efficient and secure systems for industries and corporations. © 2024 John Wiley & Sons Ltd.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for 6G Edge Intelligence: Concepts, Challenges and Solutions 10th

Federated Learning for 6G Edge Intelligence: Concepts, Chal...

引用

10th International Conference on Artificial Intelligence and Mobile Services, AIMS 2021 held as Part of the Services Conference Federation, SCF 2021

作者： Wang, Han Hu, Jianhe Xing, Chunxiao Zhang, Liang-Jie Research Institute of Information Technology Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Department of Computer Science and Technology Institute of Internet Industry Tsinghua University Beijing100084 China Department of Economics College of Letters and Science University of California Davis DavisCA95616 United States National Engineering Research Center for Supporting Software of Enterprise Internet Services Shenzhen518057 China Kingdee Research Kingdee International Software Group Company Limited Shenzhen518057 China

ISBN: (纸本)9783030960322

Along with continuous evolution, the future 6G network will become a converged "Cloud-Edge-Terminal" ecosystem which can carry various crucial AI applications on edge computing units, formulating an ubiquitous "Edge Intelligence" paradigm to enable differentiated service innovations and empower intelligent transformation of vertical industries. However, due to issues of data security, user privacy, wireless network transmission capability and etc., it is not feasible for conventional machine learning methods to build AI models by directly collecting massive distributed edge data together, and hence resulting a large number of "isolated data islands" in the edge units. In order to break the data sharing barrier and drive cross-edge data cooperation, this paper studies a federated learning based AI model training method by which sensitive raw data can be maintained and protected in its original edge units. Based on the general scheme, some challenging problems are discussed to implement this new paradigm in practical scenarios, and the corresponding promising solutions and key techniques are proposed to inspire further researches. © 2022, Springer Nature Switzerland AG.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Novel nonlinear fractional order Parkinson's disease model for brain electrical activity rhythms: Intelligent adaptive Bayesian networks

引用

Chaos, Solitons and Fractals 2024年 180卷

作者： Mukhtar, Roshana Chang, Chuan-Yu Raja, Muhammad Asif Zahoor Chaudhary, Naveed Ishtiaq Shu, Chi-Min Graduate School of Engineering Science and Technology National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan Department of Computer Science and Information Engineering National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan Future Technology Research Center National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan Department of Safety Health and Environmental Engineering National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan

In this study, a novel investigation in developing intelligent adaptive Bayesian networks (IABN) is carried out to solve the fractional order Parkinson's disease model (FOPDM) represented with a system of three fractional differential equations reflecting the brain's electrical activity rhythms at different cerebral cortex positions. The IABN are developed by using the competency of the multi-layer architecture of neural networks with backpropagation through Bayesian regularization optimization scheme. The reference dataset for IABN is created through Grunwald-Letnikov fractional derivative-based numerical solver for FOPDM in case of varying sensor locations on the cerebral cortex, as well as, considering different fractional orders in FOPDM. The proposed IABN is applied to the created datasets arbitrarily partitioned into training and testing sets by optimizing the fitness criterion based on mean square error (MSE) metric. The detailed analyses of the proposed IABN through extensive simulations and comparison with the reference numerical solutions of FOPDM in terms of MSE training/testing plots, absolute error, training/testing regression plots, and error histogram results, endorse the worth of the proposed intelligent scheme for different fractional orders. © 2024 Elsevier Ltd

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Semantic Structural and Occlusive Feature Fusion for Pedestrian Detection 18th

Semantic Structural and Occlusive Feature Fusion for Pedestr...

引用

18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021

作者： Wang, Hui Zhang, Yu Ke, Hongchang Wei, Ning Xu, Zhongyu The College of Computer Science and Engineering Changchun University of Technology Changchun130012 China The School of Computer Technology and Engineering Changchun Institute of Technology Changchun130012 China National and Local Joint Engineering Research Center for Intelligent Distribution Network Measurement Organization Control and Safe Operation Technology of National Development and Reform Commission Changchun Institute of Technology Changchun130012 China

ISBN: (纸本)9783030891879

Pedestrian detection under occlusion scenes remains a formidable challenge in computer vision. Recently, anchor-free approach has been raised on the object detection and pedestrian detection field, anchor-free detector center and Scale Prediction (CSP) has been proposed in pedestrian detection without special measures for occlusion. In this paper, we propose an anchor-free detector named OCSP with power ful occlusion handling ability to existing anchor-free detection network. OCSP integrates prior information into the network to handle occlusion. This high-fusion prior information gives the detector a hint about identifying the structural features of pedestrians. OCSP becomes more robust with the prior information which fusion the semantic head, the visible part, and the size and center body for each pedestrian. The detector enhances the perception of occlusion by predicting the semantic head and visible part. Besides, we design a head branch and add predicting the visible box to achieve a similar result. Experiments show that this fusion of prior information represents a suitable combination. We compare our OCSP with state-of-arts models on the Citypersons dataset, the proposed OCSP detector achieves the state-of-arts result on the CityPersons benchmark. © 2021, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Learning Approach Featuring Graph-Based Algorithm for Cell Segmentation and Tracking

A Novel Deep Learning Approach Featuring Graph-Based Algorit...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Zhao, Keliang Niyogisubizo, Jovial Xiao, Linxia Pan, Yi Wei, Dongqing Rosiyadi, Didi Wei, Yanjie Chinese Academy of Sciences Shenzhen Key Laboratory of Intelligent Bioinformatics and Center for High Performance Computing Shenzhen Institute of Advanced Technology Shenzhen518055 China Chinese Academy of Sciences College of Computer Science and Control Engineering Shenzhen Institutes of Advanced Technology Shenzhen518055 China Shanghai Jiao Tong University State Key Laboratory of Microbial Metabolism School of Life Sciences and Biotechnology Shanghai200240 China National Research and Innovation Agency Research Center for Artificial Intelligence and Cybersecurity Bandung Indonesia

ISBN: (纸本)9798350337488

The precise segmentation and tracking of cells in microscopy image sequences play a pivotal role in biomedical research, facilitating the study of tissue, organ, and organism development. However, manual segmentation and tracking of cells is time-consuming and often require professional experiences. Besides, segmenting cells in the images with a low signal-to-noise ratio remains difficult. While deep learning (DL) has become a common method for cell segmentation, few DL- based methods address concurrent cell segmentation and tracking. In this paper, we propose a novel DL approach featuring graph-based tracking for cell segmentation and tracking in microscopy images. We combine Deeplabv3+ for semantic segmentation and ResNet50 for enhanced feature extraction, enabling comprehensive cell detection and instance segmentation. Post-processing, involving non-maxima suppression and outlier detection, refines predictions and produces final segmentation. The tracking method is based on the relative position of graph nodes to track segmented cells, encompassing cell division and apoptosis. We conduct our experiments on the induced pluripotent stem (iPS) cell datasets, and the results show that the segmentation and tracking performance of our method yields superior performance compared to the benchmark models. More specifically, our approach achieved DET values of 0.955 and 0.913, TRA values of 0.951 and 0.906, and SEG values of 0.690 and 0.665 on two iPS dataset videos, respectively. Additionally, the performance assessment encompasses four real microscopy datasets from the Cell Tracking Challenge (CTC). Our method greatly reduces the cost of manual labeling and labor-intensive costs. © 2023 IEEE.

关键词： cell segmentation cell tracking deep learning Deeplabv3+ instance segmentation iPS cell reprogramming

来源：评论

学校读者我要写书评

暂无评论

Age-of-Computing Constrained Energy-minimal Resource Allocation in MEC-Assisted High-Speed Railway Networks

Age-of-Computing Constrained Energy-minimal Resource Allocat...

引用

International Conference on computers, Communications, and Systems (ICCCS)

作者： Yingying Wu Zhifei Zhang Yiyang Ge Jin Mao Zhipeng Chu Ke Xiong Pingyi Fan Engineering Research Center of Network Management Technology for High Speed Railway of Ministry of Education School of Computer and Information Technology Beijing Jiaotong University Beijing China Collaborative Innovation Center of Railway Traffic Safety Beijing Jiaotong University Beijing China National Engineering Research Center of Advanced Network Technologies Beijing Jiaotong University Beijing China Department of Electronic Engineering Tsinghua University Beijing China

ISBN: (数字)9798350350210

ISBN: (纸本)9798350350227

This paper investigates mobile edge computing (MEC) assisted high-speed railway networks (HSRNs), where a MEC server positioned at the ground base station (GBS) assists train users in task computing. When the computing capacity of users' equipment is insufficient, the users are allowed to offload their tasks to the MEC server. To well measure the timeliness of users' task computation, we extend the traditional age of information (AoI) to the concept of age of computing (AoC), which is defined as the time elapsed since the last completed task was generated. To pursue the green HSRN design, this paper formulates an energy minimization problem by jointly optimizing task offloading vectors and power allocation vectors. To ensure the timeliness of task execution, AoC is taken as constraints into account. Besides, the maximum available power constraints are also considered. To tackle this non-convex mixed integer nonlinear programming (MINLP) problem, we firstly reformulate it as a Markov Decision Process (MDP) and then propose a Multi-Agent Twin Delayed Deep Deterministic Policy Gradient based resource allocation (MATD3-RA) framework. To characterize the energy consumption of user equipment under the constraints of AoC, we define a utility function as the negative linear combination of the violation of AoC constraints and the energy consumption. Simulation results show that the utility function value of the proposed MATD3-RA is increased by about 14% and about 39% respectively compared to the resource allocation with only MEC and local computing, about 23% compared to the Multi-agent Deep Deterministic Policy Gradient based resource allocation (MADDPG-RA) method, and about 28% compared to the random power allocation method. We also observe that there is a trade-off between energy consumption and AoC.

关键词： Energy consumption Multi-access edge computing Simulation Rail transportation Vectors Time measurement Resource management

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：