检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Signal, information and Data Processing, ICSIDP 2024

作者： Fang, Delin Lin, Ruiqi Chang, Ningyuan Chen, Youwang Tian, Weiming Deng, Yunkai Beijing Institute of Technology Radar Technology Research Institute Beijing China Beijing Key Laboratory of Embedded Realtime Information Processing Technology Radar Technology Beijing China Beijing Institute of Technology School of Information and Electronic Beijing China Chongqing Innovation Center Beijing Institute of Technology Chongqing China Beijing Institute of Technology Advanced Technology Research Institute Jinan China

ISBN: (纸本)9798331515669

The embedded Graphics Processing Unit (GPU) module, which includes both Central Processing Unit (CPU) and GPU processors, can be easily integrated into radar systems, offering high performance and flexibility. Phased array radar tracking algorithm involves numerous modules with poor parallelism between them, leading to significant data blocking issues during sequential execution. Traditional implementations using CPUs or DSPs are time-consuming and inefficient. To address this problem, this paper proposes a real-time implementation solution based on embedded GPU. The solution decouples logic-intensive and computation-intensive tasks in the algorithm and maps them separately to the CPU and GPU within the embedded GPU module. Then three-level hybrid parallel processing method is adopted, which is based on grid-stride-based intra-kernel thread parallelism, CUDA stream asynchronous parallelism and CPU thread parallelism in order to realize real-time processing of radar echo data. Verification experiment using real measured data indicates that the proposed real-time implementation solution achieves significant acceleration with no loss of accuracy on the Jetson AGX Xavier embedded GPU platform, markedly improving tracking efficiency. © 2024 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Fall Direction Detection Using Parallel CNN Based on Millimeter-Wave Radar Multi-Dimensional Feature Fusion

Fall Direction Detection Using Parallel CNN Based on Millime...

引用

2024 Conference on Spectral technology and Applications, CSTA 2024

作者： Ren, Shukun Chen, Hanbo Liao, Kefei Deng, Honggao Liao, Guisheng Fu, Tao Li, Jingjing School of Information and Communication Guilin University of Electronic Technology Guangxi Guilin541004 China State and Local Joint Engineering Research Center for Satellite Navigation and Location Service Guilin University of Electronic Technology Guangxi Guilin541004 China Engineering Research Center of Trustworthy AI Ministry of Education Jinan University Guangzhou China

ISBN: (纸本)9781510683082

Falls pose a serious threat to the safety of the elderly. Accurately detecting falls and their direction is crucial for medical personnel to assess injury locations and promptly formulate treatment plans. Traditional methods primarily integrate distance and Doppler features of fall behavior, neglecting a significant amount of spatial features. Additionally, the determination of fall direction is easily affected by environmental noise and limb-induced Doppler interference. To this end, this paper proposes a parallel convolutional neural network fall direction detection method based on millimeter-wave radar multidimensional feature fusion, which introduces the fall angle as spatial information while effectively attenuating the interference of environmental noise and limb micro-Doppler frequency to improve the accuracy of fall direction detection. Specifically, this method utilizes techniques such as pulse compression, MTI, Range Fast Fourier Transform (RFFT), STFT, and Capon beamforming to obtain the range-time, Doppler-time, and angle-time features from the human motion state to the falling state. Then, the Doppler-time-map (DTM) and angle-time-map (ATM) after the accumulation of multiple frames are subjected to column threshold feature extraction and column normalization feature processing, respectively, to achieve the effect of scrambling frequency removal and feature enhancement. Finally, the processed feature spectrograms are input into the parallel convolutional neural network for independent extraction of each dimension's features and multi-dimensional fusion, enabling the detection of the fall direction. The experimental results show that the proposed method achieves an average recognition accuracy of 97.52% for different fall directions, compared to an improvement of 2.31% over the traditional feature fusion method. © 2024 SPIE.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of a High-Speed PPM-SPAD System Based on Multi-Aperture Reception 4

Performance Analysis of a High-Speed PPM-SPAD System Based o...

引用

4th International Conference on Communication technology and information technology, ICCTIT 2024

作者： Xie, Wentong Liu, Zhi Changchun University of Science and Technology CUST School of Electronic Information Engineering Changchun China Changchun University of Science and Technology CUST National and Local Joint Engineering Research Center of Space Optoelectronics Technology Changchun China

ISBN: (纸本)9798331528973

To address the challenges of severe signal attenuation and weak signal detection in satellite-to-ground optical communication, this paper proposes a pulse position modulation-single photon avalanche diode (PPM-SPAD) scheme based on a single-input multiple-output (SIMO) structure. In this scheme, multiple SPAD receivers are deployed at the receiver end to mitigate the impact of the inherent dead-time characteristics of SPADs on system performance through reception diversity. A theoretical analysis framework is established in this study, and expressions for the bit error rate (BER) of the SIMO PPM-SPAD system, considering the effects of dead time, are derived. The accuracy of the theoretical analysis is validated through simulations. The simulation results demonstrate that the SIMO structure can effectively exploit reception diversity to gain significant improvement in BER performance. This research provides a solid theoretical foundation and practical guidance for the design and optimization of satellite-to-ground optical communication systems, showcasing the great potential of the SIMO PPM-SPAD scheme in enhancing system transmission performance. © 2024 IEEE.

关键词： Pulse position modulation

来源：评论

学校读者我要写书评

暂无评论

Wide Stopband Substrate Integrated Waveguide Filter Using Bisection and Trisection Coupling in Multilayer

引用

Chinese Journal of electronics 2024年第2期33卷 436-442页

作者： Peng CHU Jianguo FENG Peng ZHU Lei GUO Long ZHANG Leilei LIU Guoqing LUO Ke WU College of Electronic and Optical Engineering Nanjing University of Posts and Telecommunications National and Local Joint Engineering Laboratory of RF Integration and Micro-Assembly Technology School of Information and Communication Engineering Dalian University of Technology Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Sun Yat-sen University College of Electronics and Information Engineering Shenzhen University School of Electronics and Information Hangzhou Dianzi University Poly-Grames Research Center Polytechnique Montreal

This article presents a highly efficient method for substrate-integrated-waveguide（SIW） filters to achieve very wide stopbands. By employing the proposed trisection slots in addition to the bisection slots as the inter-coupling structures, all spurious modes below TE505 of a SIW filter working in the fundamental mode TE101（f0）can be eliminated without requiring additional structure or complex theoretical analysis, without affecting the design of the fundamental passbands, and without degrading the performance of the filters. For verification, two prototype filters are designed, fabricated, and measured with wide stopbands up to 4.15f0 and 4.83f0, respectively. The proposed technique could facilitate the development of high-performance wide-stopband SIW filters for microwave/wireless circuits and systems.

关键词： Bandpass filter Wide stopband Substrate integrated waveguide Spurious mode suppression Multilayer

来源：评论

学校读者我要写书评

暂无评论

LEGF-DST:LLMs-Enhanced Graph-Fusion Dual-Stream Transformer for Fine-Grained Chinese Malicious SMS Detection

引用

Computers, Materials & Continua 2025年第2期82卷 1901-1924页

作者： Xin Tong Jingya Wang Ying Yang Tian Peng Hanming Zhai Guangming Ling School of Information and Cybersecurity People’s Public Security University of ChinaBeijing100038China Cyber Investigation Technology Research and Development Center The Third Research Institute of the Ministry of Public SecurityShanghai201204China Department of Cybersecurity Defense Beijing Police CollegeBeijing102202China School of Computer Science Henan Institute of EngineeringZhengzhou451191China

With the widespread use of SMS(Short Message Service),the proliferation of malicious SMS has emerged as a pressing societal *** deep learning-based text classifiers offer promise,they often exhibit suboptimal performance in fine-grained detection tasks,primarily due to imbalanced datasets and insufficient model representation *** address this challenge,this paper proposes an LLMs-enhanced graph fusion dual-stream Transformer model for fine-grained Chinese malicious SMS *** the data processing stage,Large Language Models(LLMs)are employed for data augmentation,mitigating dataset *** the data input stage,both word-level and character-level features are utilized as model inputs,enhancing the richness of features and preventing information loss.A dual-stream Transformer serves as the backbone network in the learning representation stage,complemented by a graph-based feature fusion *** the output stage,both supervised classification cross-entropy loss and supervised contrastive learning loss are used as multi-task optimization objectives,further enhancing the model’s feature *** results demonstrate that the proposed method significantly outperforms baselines on a publicly available Chinese malicious SMS dataset.

关键词： Transformers malicious SMS multi-task learning large language models

来源：评论

学校读者我要写书评

暂无评论

Training Photonic Neural Networks with Dual Backpropagation

Training Photonic Neural Networks with Dual Backpropagation

引用

CLEO: Science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics

作者： Zheng, Ziyang Duan, Zhengyang Chen, Hang Yang, Rui Gao, Sheng Zhang, Haiou Xiong, Hongkai Lin, Xing Department of Electronic Engineering Tsinghua University Beijing China Department of Electronic Engineering Shanghai Jiao Tong University Shanghai China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China

We report dual backpropagation training for end-to-end optimizing photonic neural networks (PNNs). We demonstrate the effectiveness of the proposed method by using diffractive and interference-based PNNs on image classification tasks under significant systematic errors. © Optica Publishing Group 2024, © 2023 The Author(s)

关键词： Systematic errors

来源：评论

学校读者我要写书评

暂无评论

Brain-like training of a pre-sensor optical neural network with a backpropagation-free algorithm

引用

光子学研究（英文） 2025年第4期13卷 915-923页

作者： ZHENG HUANG CONGHE WANG CAIHUA ZHANG WANXIN SHI SHUKAI WU SIGANG YANG HONGWEI CHEN Department of Electronic Engineering Tsinghua UniversityBeijing 100084China Beijing National Research Center for Information Science and Technology Beijing 100084China China Mobile Research Institute Beijing 100053China

Deep learning has rapidly advanced amidst the proliferation of large models,leading to challenges in computa-tional resources and power *** neural networks(ONNs)offer a solution by shifting com-putation to optics,thereby leveraging the benefits of low power consumption,low latency,and high *** current training paradigm for ONNs primarily relies on backpropagation(BP).However,the reliance is incompatible with potential unknown processes within the system,which necessitates detailed knowledge and precise mathematical modeling of the optical *** this paper,we present a pre-sensor multilayer ONN with nonlinear activation,utilizing a forward-forward algorithm to directly train both optical and digital parameters,which replaces the traditional backward pass with an additional forward *** proposed nonlinear optical system demonstrates significant improvements in image classification accuracy,achieving a maximum enhancement of 9.0%.It also validates the efficacy of training parameters in the pres-ence of unknown nonlinear components in the optical *** proposed training method addresses the limitations of BP,paving the way for applications with a broader range of physical transformations in ONNs.©2025 Chinese Laser Press

关键词： algorithm network with backpropagation brain-like free neural optical pre-sensor training

来源：评论

学校读者我要写书评

暂无评论

Semantic and secure search over encrypted outsourcing cloud based on BERT

引用

Frontiers of Computer Science 2022年第2期16卷 152-159页

作者： Zhangjie FU Yan WANG Xingming SUN Xiaosong ZHANG Engineering Research Center of Digital Forensice Ministry of EducationNanjing University of Information Science and TechnologyNanjing 210044China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing 210044China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China

Searchable encryption provides an effective way for data security and privacy in cloud *** can retrieve encrypted data in the cloud under the premise of protecting their own data security and ***,most of the current content-based retrieval schemes do not contain enough semantic information of the article and cannot fully reflect the semantic information of the *** this paper,we propose two secure and semantic retrieval schemes based on BERT(bidirectional encoder representations from transformers)named SSRB-1,*** training the documents with BERT,the keyword vector is generated to contain more semantic information of the documents,which improves the accuracy of retrieval and makes the retrieval result more consistent with the user’s ***,through testing on real data sets,it is shown that both of our solutions are feasible and effective.

关键词： cloud computing semantic search BERT model searchable encryption

来源：评论

学校读者我要写书评

暂无评论

Training Photonic Neural Networks with Dual Backpropagation

Training Photonic Neural Networks with Dual Backpropagation

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

ISBN: (纸本)9781957171395

We report dual backpropagation training for end-to-end optimizing photonic neural networks (PNNs). We demonstrate the effectiveness of the proposed method by using diffractive and interference-based PNNs on image classification tasks under significant systematic errors. CLEO 2024 © Optica Publishing Group 2024 © 2024 The Author(s)

关键词： Photonics

来源：评论

学校读者我要写书评

暂无评论

Modulational instability induced by mode perturbation in normal-dispersion microresonators

引用

Physical Review A 2025年第3期111卷 033519-033519页

作者： Bofan Yang Shangyuan Li Xiaoping Zheng Xiaoxiao Xue Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing 100084 China

Mode coupling has been proven to be an effective method for initiating modulational instability (MI) in a normal-dispersion microresonator. In various mode-coupling systems, mode loss perturbation occurs alongside mode frequency perturbation. In this study, we present a detailed analysis of MI induced by either loss or frequency perturbations added to the pump mode of a normal-dispersion cavity. By distinguishing the individual contributions of frequency and loss perturbations to MI gain, we demonstrate that, in addition to the widely studied frequency perturbation, the introduction of an additional loss to the pump mode can also induce MI even without frequency perturbation, enabling the spontaneous excitation of frequency combs. The effects of pump mode perturbations in various mode-coupling schemes are compared, revealing that loss perturbation has a more significant impact when the pump power is relatively low or when the auxiliary mode experiences a sufficiently higher loss than the main mode. Our findings provide an alternative perspective on illustrating the underlying mechanisms of normal-dispersion Kerr frequency combs generation aided by mode perturbation.

关键词： Microresonators

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：