检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Integrated Circuits, Technologies and Applications, ICTA 2023

作者： Yang, Fan Zhang, Bowen Song, Leijun Xu, Yuehang School of Electronic Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China Beijing Institute of Radio Measurement Microwave Technology Research and Development Center Beijing100854 China

ISBN: (纸本)9798350344288

In order to adapt to the development, a 60W power amplifier microwave monolithic integrated circuit (MMIC) with an operating frequency of 5.2-6.2 GHz is designed for C-band radar systems. The harmonics suppression characteristics of the proposed power amplifier are improved by adopting inductor-capacitor resonance in the output matching network. The size of the power amplifier MMIC is 3.6× 4.1 mm2. The measured results show that the output power is greater than 60 W, the power gain is 20 dB, the harmonics suppression are greater than 45 dB, and the power additional efficiency (PAE) is higher than 53%, under the verification condition of 50 μ s pulse width and 5% duty cycle. The characteristics of the power amplifier proposed in this paper are beneficial for miniaturization of radar transceiver systems. © 2023 IEEE.

关键词： Power amplifiers

来源：评论

学校读者我要写书评

暂无评论

research on Speaker Recognition Based on the ECAPA-TDNN Method 9

Research on Speaker Recognition Based on the ECAPA-TDNN Meth...

引用

9th International Symposium on Computer and information Processing technology, ISCIPT 2024

作者： Gan, Zhenye Zhang, Xu Northwest Normal University College of Physics and Electronic Engineering Lanzhou China Engineering Research Center of Gansu Province for Intelligent Information Technology and Application Lanzhou China

ISBN: (纸本)9798350388404

Speaker recognition, also known as speaker identification, encompasses two major functions: speaker identification and speaker verification. It is a critical branch of speech processing. The aim of this technology is to recognize or verify the identity of a speaker. Speaker recognition technologies are widely applied in various domains, including security authentication, law enforcement, and personalized interaction systems. Despite their extensive application, speaker recognition technologies face numerous challenges in practical applications such as noise interference and recording quality. Given the limited research on speaker recognition for ethnic minorities within the country, this study employs an improved ECAPATDNN model and conducts experimental validation on a selfconstructed Tibetan speaker recognition dataset. The experimental results indicate an Equal Error Rate (EER) of 0.013, a True Positive Rate (TPR) of 0.992, and a False Positive Rate (FPR) of 0.006, with the threshold set at 0.30. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Platooning of Connected Automated Vehicles at Intersections 6

Platooning of Connected Automated Vehicles at Intersections

引用

6th IEEE International Conference on Knowledge Innovation and Invention, ICKII 2023

作者： Hsu, Tsung-Ming Tian, Jheng-Hong Automotive Research and Testing Center Electronic Control and Information Communication Technology Group of R&d Division Changhua Taiwan

ISBN: (纸本)9798350323535

Traffic efficiency and safety were improved by platooning connected autonomous vehicles. In this study, an optimized speed model was proposed for platooning CAVs traveling through V2I-regulated intersections without stop-and-go driving behavior in corridors to support human-driven vehicles. The platooning decision at the V2I-regulated traffic intersection was developed to enable platooning to pass the intersection in the least amount of time based on V2V communication and traffic light depending on the remaining seconds. The results of the simulation and on-road experiments showed that the proposed methodology allowed the platoon to safely pass through V2I traffic light intersections and improved the efficiency of passing through intersections by 10% without a vehicle in front. © 2023 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

A Novel Unsupervised Learning Network for Direction-of-Arrival Estimation in Internet of Things Scenarios 15

A Novel Unsupervised Learning Network for Direction-of-Arriv...

引用

15th IEEE International Conference on Wireless Communications and Signal Processing, WCSP 2023

作者： Yao, Zhiwei Zhao, Ming Beijing National Research Center for Information Science and Technology Beijing China Tsinghua University Department of Electronic Engineering Beijing China

ISBN: (纸本)9798350324662

Unsupervised learning is an emerging technique in the field of signal processing that allows for autonomous feature learning without reliance on annotated data. In this paper, we propose a novel unsupervised learning network to address the challenges of Direction-of-Arrival (DoA) estimation in indoor localization for the Internet of Things (IoT). Our focus is on resolving the issue of inadequate DoA estimation performance in complex scenarios. The proposed network is based on a multilayer and multi-path feature extraction approach. We employ a multi-layer feature extraction approach to separately extract general and specialized features, and then implement multi-path feature extraction to extract different parameters. Through the design of multi-layer and multi-path, we can improve the estimation performance of the network. In addition, considering the impact of noise on the estimation performance of the network, we devise a novel decoding scheme in the decoder module, further enhancing the performance of the network. Simulation results demonstrate the superiority of the proposed method over existing approaches in terms of DoA estimation performance. © 2023 IEEE.

关键词： deep neural network Direction-of-Arrival estimation Internet of Things unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Construction of a Digital Integrated Circuit Backend Design System Based on Machine Learning

Construction of a Digital Integrated Circuit Backend Design ...

引用

International Conference on Smart Applications and Sustainability in the Artificial Intelligence of Things, SAS-AIoT 2024

作者： Lin, Kongcheng Sun, Xiyan Ji, Yuanfa School of Information and Communication Guilin University of Electronic Technology Guangxi541004 China Guangxi Key Laboratory of Precision Navigation Technology and Application Guilin University of Electronic Technology Guangxi541004 China Nation & Local Joint Engineering Research Center of Satellite Navigation Positioning and Technology Guilin University of Electronic Technology Guangxi541004 China

ISBN: (纸本)9783031782756

With the increasing complexity of integrated circuit (IC) design, traditional backend design methods have become increasingly difficult to meet the requirements, and there is an urgent need for new technological means to improve system design efficiency and reduce system errors. This article can be based on machine learning to reconstruct the backend IC design process, and intelligently analyze and identify it, in order to optimize the layout and wiring. By predicting and optimizing the layout, signal transmission delay and power consumption can be effectively reduced, thereby improving the overall performance of the IC. In cross technology node testing, from the perspective of failure rate, as the number of technology nodes decreases, the failure rate gradually decreases, ranging from 1.5% to 55%. The research results of this article can greatly improve the design accuracy and processing speed of chips, while also greatly reducing the power consumption and cost of chips, providing a new approach for IC design. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Failure rate

来源：评论

学校读者我要写书评

暂无评论

Real-Time Lightweight Convolutional Neural Network for Polyp Detection in Endoscope Images

引用

Journal of Shanghai Jiaotong University (Science) 2025年第3期30卷 521-534页

作者： Si, Bingqi Pang, Chenxi Wang, Zhiwu Jiang, Pingping Yan, Guozheng School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai200240 China Shanghai Engineering Research Center of Intelligent Drug Detoxification and Rehabilitation Shanghai200240 China College of Computer Science and Technology Jilin University Changchun130012 China

Colorectal cancer is the most common cancer with a second mortality rate. Polyp lesion is a precursor symptom of colorectal cancer. Detection and removal of polyps can effectively reduce the mortality of patients in the early period. However, mass images will be generated during an endoscopy, which will greatly increase the workload of doctors, and long-term mechanical screening of endoscopy images will also lead to a high misdiagnosis rate. Aiming at the problem that computer-aided diagnosis models deeply depend on the computational power in the polyp detection task, we propose a lightweight model, coordinate attention-YOLOv5-Lite-Prune, based on the YOLOv5 algorithm, which is different from state-of-the-art methods proposed by the existing research that applied object detection models or their variants directly to prediction task without any lightweight processing, such as faster region-based convolutional neural networks, YOLOv3, YOLOv4, and single shot multibox detector. The innovations of our model are as follows: First, the lightweight EfficientNetLite network is introduced as the new feature extraction network. Second, the depthwise separable convolution and its improved modules with different attention mechanisms are used to replace the standard convolution in the detection head structure. Then, the α-intersection over union loss function is applied to improve the precision and convergence speed of the model. Finally, the model size is compressed with a pruning algorithm. Our model effectively reduces parameter amount and computational complexity without significant accuracy loss. Therefore, the model can be successfully deployed on the embedded deep learning platform, and detect polyps with a speed above 30 frames per second, which means the model gets rid of the limitation that deep learning models must rely on high-performance servers. © Shanghai Jiao Tong University 2023.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Parallel Implementation of the CCSDS Turbo Decoder on GPU

引用

China Communications 2024年第10期21卷 70-77页

作者： Liu Zhanxian Liu Rongke Zhang Haijun Wang Ning Sun Lei Wang Jianquan School of Computer&Communication Engineering University of Science and Technology BeijingBeijing 100083China School of Electronic and Information Engineering Beihang UniversityBeijing 100191China Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services Institute of Artificial IntelligenceUniversity of Science and Technology BeijingBeijing 100083China School of Information Engineering Zhengzhou UniversityZhengzhou 450001China School of Automation and Electrical Engineering University of Science and Technology BeijingBeijing 100083China

This paper presents a software turbo decoder on graphics processing units(GPU).Unlike previous works,the proposed decoding architecture for turbo codes mainly focuses on the Consultative Committee for Space Data Systems(CCSDS)***,the information frame lengths of the CCSDS turbo codes are not suitable for flexible sub-frame parallelism *** mitigate this issue,we propose a padding method that inserts several bits before the information frame *** obtain low-latency performance and high resource utilization,two-level intra-frame parallelisms and an efficient data structure are *** presented Max-Log-Map decoder can be adopted to decode the Long Term Evolution(LTE)turbo codes with only small *** proposed CCSDS turbo decoder at 10 iterations on NVIDIA RTX3070 achieves about 150 Mbps and 50Mbps throughputs for the code rates 1/6 and 1/2,respectively.

关键词： CCSDS CUDA GPU parallel decoding turbo codes

来源：评论

学校读者我要写书评

暂无评论

RISMCNet: A Two-Timescale CSI Feedback Solution for RIS-aided Multi-Carrier systems 6

RISMCNet: A Two-Timescale CSI Feedback Solution for RIS-aide...

引用

6th International Conference on electronics technology, ICET 2023

作者： Tang, Xinyi Xiao, Limin Zhao, Ming Li, Yunzhou Beijing National Research Center for Information Science and Technology Beijing China Tsinghua University Department of Electronic Engineering Beijing China

ISBN: (纸本)9798350337693

In this letter, a novel deep learning-based solution named RISMCNet is introduced to tackle the challenge of high overhead and low accuracy in RIS-aided multi-carrier communication channel state information (CSI) feedback. The proposed method utilizes the two-timescale feature of the RIS-aided systems by designing separate feedback periods for the base station (BS)-RIS and RIS-user equipment (UE) channels. RISM-CNet leverages the sparsity of the angular-delay domain channel and apply an attention-based encoder at the UE end to compress the channel for limited feedback overhead. A multi-resolution decoder is designed at the BS end to recover high-precision CSI. Simulations results reveal that RISMCNet outperforms conventional compressive sensing (CS)-based and deep learning-based methods in CSI recovery accuracy. Moreover, RISMCNet achieves 270 to 810 times faster running times compared to CS-based methods. © 2023 IEEE.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Accelerated SF-PPP Convergence of BDS-3 B1 Band by Wideband Signal Observations 36

Accelerated SF-PPP Convergence of BDS-3 B1 Band by Wideband ...

引用

36th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS+ 2023

作者： Qi, Yunhan Yao, Zheng Lu, Mingquan Department of Electronic Engineering Tsinghua University Beijing China Beijing National Research Center for Information Science and Technology Beijing China

ISBN: (纸本)9780936406350

The third-generation BeiDou Navigation Satellite System (BDS-3) officially provided Positioning, Navigation, and Timing (PNT) services to global users in 2020. BDS-3 B1 band not only retains the B1I signal broadcast at 1561.098 MHz, but also broadcast a new B1C signal with advanced modulation at 1575.42 MHz, which provides more various options for the PNT service of BDS-3 B1 band. In terms of high-precision positioning, although the Single Frequency Precise Point Positioning (SF-PPP) of the B1 band can provide centimeter-level positioning results, it requires serval hours of convergence time, which cannot meet the requirements of real-time applications. Therefore, in order to accelerate the convergence speed of B1 SF-PPP, unlike existing methods that focus on reducing the impact of atmospheric delays, this paper fully explores the excellent potential of the B1 wideband signal composed of B1I and B1C signals in anti-thermal noise and anti-multipath, and innovatively introduces the B1 wideband signal observations with higher precisions than B1I and B1C observations to B1 SF-PPP for the first time. The real-data experiment results show that, compared with the B1 SF-PPP using B1I and B1C observations, the B1 SF-PPP using B1 wideband signal observations has a significantly reduced convergence time, which is shortened by 43.2% and 33.7% respectively when convergence threshold is 2.5 dm, demonstrating the effectiveness of B1 wideband signal observations in accelerating B1 SF-PPP convergence. © 2023 Proceedings of the 36th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS+ 2023. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Imperfect-Spectrum-Sensing-Aware DRL-Based Dynamic Spectrum Access for Underlay Satellite Systems with Multiple Primary Transmit Power Levels Sensing 2

Imperfect-Spectrum-Sensing-Aware DRL-Based Dynamic Spectrum ...

引用

2nd International Conference on Frontiers of Communications, information System and Data Science, CISDS 2023

作者： Yu, Boren Yang, Kunze Ni, ZuYao Su, Ming Information Science and Technology Xiamen University Department of Electronic Science Xiamen China Tsinghua University Department of Electronic Engineering Beijing China Tsinghua University Beijing National Research Center for Information Science and Technology Beijing China

ISBN: (纸本)9798350381474

This paper investigates a dynamic spectrum access (DSA) scheme for the underlay scenario of coexistence between geostationary orbit (GSO) and nongeostationary orbit (NGSO) satellite systems, in which NGSO satellites can estimate the status of GSO satellites via spectrum sensing to avoid interfering with GSO systems when selecting a spectrum sharing strategy. However, in practice, an NGSO system cannot obtain completely correct information because of sensing errors. Therefore, the DSA problem considering imperfect spectrum sensing is regarded as a partially observable Markov decision process (POMDP) in this work. A deep reinforcement learning (DRL)- based algorithm is proposed to update the access strategy of the NGSO system every slot, including channel selection and power control. In addition, a more practical scenario in which the GSO satellites transmit with multiple power levels is considered in the proposed DSA scheme. We simulate the proposed algorithm in several sensing cases in which different capabilities and accuracies of NGSO spectrum sensing are considered, and the simulation results prove the effectiveness and superiority of the proposed DRL-based DSA algorithm. © 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：