检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Metaverse Computing, networking and Applications, MetaCom 2023

作者： Wang, Xiucheng Cheng, Nan Ma, Longfei Yin, Zhisheng Luan, Tom. Lu, Ning Xidian University School of Telecommunications Engineering Xi'an China Xidian University School of Cyber Engineering Xi'an China Xi'an Jiaotong University School of Cyber Science and Engineering China Queen's University Department of Electrical and Computer Engineering ON Canada

ISBN: (纸本)9798350333336

Deep Reinforcement Learning (DRL) is widely used to optimize the performance of multi-UAV networks. However, the training of DRL relies on the frequent interactions between the UAVs and the environment, which consumes lots of energy due to the flying and communication of UAVs in practical experiments. Inspired by the growing digital twin (DT) technology, which can simulate the performance of algorithms in the digital space constructed by coping features of the physical space, the DT is introduced to reduce the costs of practical training, e.g., energy and hardware purchases. Different from previous DT-assisted works with an assumption of perfect reflecting real physics by virtual digital, we consider an imperfect DT model with deviations for assisting the training of multi-UAV networks. Remarkably, to trade off the training cost, DT construction cost, and the impact of deviations of DT on training, the natural and virtually generated UAV mixing deployment method is proposed. Two cascade neural networks (NN) are used to optimize the joint number of virtually generated UAVs, the DT construction cost, and the performance of multi-UAV networks. These two NNs are trained by unsupervised and reinforcement learning, both low-cost label-free training methods. Simulation results show the training cost can significantly decrease while guaranteeing the training performance. This implies that an efficient decision can be made with imperfect DTs in multi-UAV networks. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Chinese Medical Video Retrieval Framework with LLM 12th

A Two-Stage Chinese Medical Video Retrieval Framework with ...

引用

12th National CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2023

作者： Lei, Ningjie Cai, Jinxiang Qian, Yixin Zheng, Zhilong Han, Chao Liu, Zhiyue Huang, Qingbao School of Electrical Engineering Guangxi University Guangxi Nanning China School of Computer Electronics and Information Guangxi University Guangxi Nanning China Guangxi Key Laboratory of Multimedia Communications and Network Technology Nanning China

ISBN: (纸本)9783031446986

With the increasing popularity of online videos, research on video corpus retrieval (VCR) has made significant progress. However, existing VCR models have not performed well in the medical field due to the unique characteristics of medical VCR task. Specifically, the open-ended queries used in medical VCR are more challenging compared to image-caption style queries, and the long duration of medical videos poses a great burden on model retrieval efficiency. To address these challenges, we propose a two-stage framework based on GPT-3.5 and cross-modal contrastive global-span (CCGS) for medical video VCR (termed GPT-CMR). In the first stage, we leverage the powerful natural language processing capabilities of the large language model (LLM) GPT-3.5 to improve retrieval efficiency. In the second stage, we use CCGS model to further enhance retrieval accuracy. Additionally, we developed a CCGS-VCR Analyzer to leverage the characteristics of the CCGS model’s output without additional training costs. According to the official result, our method achieve first place in Track 2 of the NLPCC 2023 Task 5 competition. Experiments show that our method has retrieval efficiency and accuracy far exceeding the official baseline. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Characterization of Embedded and Thinned RF Chips 24

Characterization of Embedded and Thinned RF Chips

引用

24th European Microelectronics and Packaging Conference, EMPC 2023

作者： Yin, Ran Morath, Helmuth P. E. Hoyer, Christian Nieweglowski, Krzysztof Meier, Karsten Wagner, Jens Ellinger, Frank Bock, Karlheinz Institute of Electronic Packaging Technology Technische Universität Dresden Germany Chair of Circuit Design and Network Theory Dresden Germany Technische Universität Chair of Circuit Design and Network Theory Department of Electrical and Computer Engineering Dresden Germany Institute of Electronic Packaging Technology Department of Electrical and Computer Engineering Technische Universität Dresden Germany

ISBN: (纸本)9780956808691

This work studies the effect of thinning down chips with transmission line structures for flexible embedding technology. Test chips with 90 Ω grounded coplanar waveguide (G-CPW) transmission lines have been designed and manufactured to characterize the high-frequency performance before and after embedding in sheet molding compound (SMC), and thinning down from 300 μm to 20 μm, Molding first technology enables single-die or multiple-die thinning with the embedding material while being held in the exact position, where the subsequent fan-out copper (Cu) redistribution layer (RDL) structuring realizes the direct contacts to the embedded chip, followed by semi-Additive manufacturing of traces. The embedded and thinned chips are characterized by S-parameter measurements in the frequency range from 20 MHz to 65 GHz using a vector network analyzer (VNA). The results show the feasibility of the examined embedding and thinning processes which are suitable for millimeter wave (mmWave) components as shown by the example of a G-CPW transmission line without degrading its RF performance in terms of characteristic impedance and attenuation. © 2023 IMAPS-Europe.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Enhancing near-infrared luminescence of Cs2NaBiCl6:Yb3+/RE3+ (Er, Pr, Tm) double perovskite through codoping Cr3+ ions and bioimaging applications

引用

Ceramics International 2025年

作者： Zhang, Yuhong Sun, Chunhui Tian, Haozhou Wang, Qiang Zhu, Hongqun Yang, Xuezhong Wang, Haoran Liu, Hang School of electrical and computer engineering Jilin jianzhu university Changchun130118 China

Here, Cr3+ doped Cs2NaBiCl6:Yb3+/RE3+(RE = Er,Pr,Tm) lead-free double perovskite(DPs) materials are successfully prepared by solvothermal method. The optical properties, temperature characteristics and imaging application of these phosphors are systematically investigated. Upon exposure to 980 nm laser irradiation, a broad near-infrared one-region (NIR-I) emission peak of Cr3+ ion 4T2→4A2 transition at 851 nm is obtained for the Cs2NaBiCl6:Yb3+/Cr3+/RE3+ phosphor. In comparison with Cs2NaBiCl6:Yb3+/RE3+ phosphor, the near-infrared two-region(NIR-II) emission intensity of Er3+ at 1540 nm(4I13/2 → 4I15/2) is increased by 10.7 times through codoping Cr3+ ion. Similarly, the NIR-II luminescence intensity at 1380 nm(1G4→3H5) of Pr3+ is increased by 1.5 times. The near-infrared three-region (NIR-III) emission intensity of Tm3+ at 1849 nm(3F4→3H6) is increased by 3.3 times due to dop Cr3+ ions. The possible sensitization strategy is discussed in detail. The thermal stability of the above sample is tested. The excellent near-infrared luminescence properties and thermal stability of Cs2NaBiCl6:Yb3+/Cr3+/RE3+ phosphors show great application prospects in the fields of biological imaging. © 2025 Elsevier Ltd and Techna Group S.r.l.

关键词： Luminescence of organic solids

来源：评论

学校读者我要写书评

暂无评论

On accuracy rate of community detection and pairing in mobile social network 19

On accuracy rate of community detection and pairing in mobil...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Tu, Jinbin Li, Qing Wang, Yun Southeast University Key Lab of Computer Network and Information Integration School of Computer Science and Engineering Moe Nanjing China

ISBN: (纸本)9798350346558

Mobile Social network(MSN) is an opportunity network that considers the social attributes of nodes, and also uses the 'store-carry-forward' model to carry out data transfer between nodes. The community nature of nodes is an important reference in MSN to select messaging path. In this paper, a new community cluster problem based on our observed pickup strategies for car-hailing is proposed, which is involving community detection and community pairing. Then we formulate it by using T-Sorokin mobility model. The Cluster-First algorithm and Pair-First algorithm are proposed based on the defined community dependency metric to maximize the accuracy rate. Simulation experimental results show that both CFA and PFA can effectively solve this problem with an accuracy rate of over 70%. And it is concluded that cluster-first is superior to pair-first for this considered problem. © 2022 IEEE.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Image Fire Quantification Method Though Flame Imaging Target Detection 7

Image Fire Quantification Method Though Flame Imaging Target...

引用

7th International Conference on Data Science and Information Technology, DSIT 2024

作者： Haoran, Jiang Zhezhe, Han Zewen, Qian Jiaqi, Tang Hao, Ma Shiyu, He Mengchao, Fan Nanjing Institute of Technology School of Communication and Artificial Intelligence School of Integrated Circuits Nanjing China Nanjing Institute of Technology School of Electrical Power Engineering School of Communication and Artificial Intelligence School of Integrated Circuits Nanjing China Nanjing Institute of Technology School of Computer Engineering Nanjing China Nanjing Institute of Technology School of Electrical Power Engineering Nanjing China Nanjing Institute of Technology School of Mechanical Engineering Nanjing China

ISBN: (纸本)9798350384093

With the continuous development of urbanization and the increase of population, fire as a catastrophic event poses a great threat to the safety of life and property. However, traditional fire monitoring methods mainly rely on devices such as sensors and detectors, which are difficult to reflect the fire condition and development trend at the scene and are not conducive to rescue preparation. To improve the accuracy of fire condition analysis, this study proposes an image fire quantification method based on flame imaging target detection. The method firstly uses the YOLOv8 network model with integrated Receptive-Field Attention convolutional operation to pre-locate to the area where the fire occurs and performs feature extraction for each flame frame;then, the correlation coefficients between each flame feature and the pre-set fire potential values are calculated and the flame features with higher correlation are screened out;finally, a quantitative assessment model is developed based on five flame characteristics, including flame area and flame profile perimeter, to quantitatively map the fire potential to the [0, 1] value range. A pilot study was carried out on an outdoor platform and the effectiveness of the proposed method was evaluated using the obtained flame images. The results show that the model mean-square error is maintained within 0.001 throughout the training process;under different testing conditions, there is a high degree of consistency between the predicted values and the true values of the test set, which proves the effectiveness of the proposed fire quantification method. Compared to the original YOLOv8 model, the improved model achieves significant performance enhancement in terms of prediction rate. © 2024 IEEE.

关键词： Premixed flames

来源：评论

学校读者我要写书评

暂无评论

Robust Design of Permanent Magnet Motors for Electric Traction Applications

Robust Design of Permanent Magnet Motors for Electric Tracti...

引用

2023 IEEE International Magnetic Conference - Short Papers, INTERMAG Short Papers 2023

作者： Sakkas, Georgios K. Kladas, Antonios G. National Technical University of Athens School of Electrical and Computer Engineering 9 Iroon Polytechneiou street Athens15780 Greece

ISBN: (纸本)9798350338362

This paper presents a methodology enabling robust design of permanent magnet motors constituting a favored choice in electric traction applications, particularly promising in high speed ranges. Appropriate permanent magnet grade and configuration selection ensuring satisfaction of standard design criteria such as high efficiency and high power density over a wide range of operating conditions are considered in conjunction with fault risk avoidance offering enhanced robustness and drive viability. Higher harmonic phenomena introduce increased stray losses in high speeds such as eddy current losses in surface mounted permanent magnets and are taken into consideration through an appropriate coupled field and circuit approach. The proposed modeling techniques are validated by measurements in prototype linear machine experimental set-up. © 2023 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Development and Evaluation of ANN, ACOR-ANN, ALO-ANN Based Small-Signal Behavioral Models for GaN-on-Si HEMT 30

Development and Evaluation of ANN, ACOR-ANN, ALO-ANN Based S...

引用

30th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2023

作者： Khan, Kashif Husain, Saddam Nauryzbayev, Galymzhan Hashmi, Mohammad Nazarbayev University School of Engineering and Digital Sciences Dept. of Electrical and Computer Engg. Astana010000 Kazakhstan

ISBN: (纸本)9798350326499

Many analyses show that Artificial Neural network (ANN) based final solutions are more likely to trapped in local minimums, provide poor generalization and extrapolation behaviors, and are not unique due to the inappropriate values of initial weights. To address these issues, this paper develops and presents accurate small-signal behavioral modelling schemes for gallium nitride high electron mobility transistor by exploiting the global minimums oriented initial weights generated by Ant Lion Optimization (ALO) and the variant of Ant Colony Optimization for continuous domains (ACOR) with ANN. The models are trained and tested on many operating conditions, and simultaneously examined for temperature interpolation and extrapolation tests. Moreover, ANN, ALO-ANN, and ACOR-ANN based models are also examined for numerous conventional regression metrics. We found that ALO-ANN and ACOR-ANN based models provide more accurate behavioral models and better convergence behaviors than ANN based models. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

MPC-Based Faster Joint Control of Hybrid Energy Storage System 49

MPC-Based Faster Joint Control of Hybrid Energy Storage Syst...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Jing, Pengxiang Zhang, Xibeng Ukil, Abhisek Swain, Akshya The University of Auckland Department of Electrical Computer and Software Engineering New Zealand School of Artificial Intelligence Henan University China

ISBN: (纸本)9798350331820

In this paper, an MPC-based faster joint control method is proposed for hybrid energy storage system (HESS), which consists of battery and supercapacitor in photovoltaic dc-microgrid. The proposed method utilizes the uncompensated power from the battery to improve the dc-link restoration and decrease overshoot. Simulations are conducted to validate the robustness and rapidity of the proposed method, and the results are compared with traditional double-loop PI controllers. The comparison results demonstrate that the new controller has higher dynamic performance and better robustness. © 2023 IEEE.

关键词： Supercapacitor

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning for Sequential Decoding of Generalized LDPC Codes 12

Reinforcement Learning for Sequential Decoding of Generalize...

引用

12th International Symposium on Topics in Coding, ISTC 2023

作者： Habib, Salman Mitchell, David G. M. New Mexico State University Klipsch School of Electrical and Computer Engineering Las CrucesNM88003 United States

ISBN: (纸本)9798350326116

In this work, we propose reinforcement learning (RL) for sequential decoding of moderate length generalized low-density parity-check (GLDPC) codes. Here, sequential decoding refers to scheduling all the generalized constraint nodes (GCNs) and single parity-check nodes (SPCNs) of a GLDPC code serially in each iteration. A GLDPC decoding environment is modeled as a finite Markov decision process (MDP) in which the state-space comprises of all possible sequences of hard-decision values of the variables nodes (VNs) connected to the scheduled GCN or SPCN, and the action-space of the MDP consists of all possible actions (GCN and SPCN scheduling). The goal of RL is to determine an optimized scheduling policy, i.e., one that results in a decoded codeword by minimizing the complexity of the belief propagation (BP) decoder. For training, we consider the proportion of correct bits at the output of the GCN or SPCN as a reward once it is scheduled. The expected rewards for scheduling all the GCNs/SPCNs in the code's Tanner graph are earned via BP decoding during the RL phase. The proposed RL-based decoding scheme is shown to significantly outperform the standard BP flooding decoder, as well as a sequential decoder in which the GCNs/SPCNs are scheduled randomly. © 2023 IEEE.

关键词： Reinforcement learning

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：