检索结果-内蒙古大学图书馆

2021 CIE International Conference on radar, radar 2021

作者： Zhang, Tinghao Li, Yachao Song, Xuan Zhang, Tao Wu, Chunfeng Sun, Ziyue Xidian University National Laboratory of Radar Signal Processing Xi'an China Chengdu Aerospace Science and Technology Microelectronics System Research Institute Chengdu China University of Exeter BEng Electronic Enginnering Cornwall United Kingdom

ISBN: (纸本)9781665498142

Accurate two dimension frequency spectrum (2D FS) with acceleration, two-way range coupling terms, and spatial variant Doppler parameters are main problems to be solved in translational variant bistatic forward-looking SAR (TV BFSAR) with curved trajectory. For these issues, a modified Omega-K imaging algorithm is derived in this paper. The maximum usage of 2D FS based on method of series reversion (MSR) is achieved by linear range cell migration correction and 2D FS is linearized in bistatic range by using high-order polynomial fitting. Then, a method of azimuth resampling is introduced to implement compensation of spatial variant Doppler parameters. And the small-aperture data is focused in the azimuth frequency domain to avoid azimuth aliasing without padding zeros. Finally, the raw bistatic SAR data verifies the effectiveness of the proposed method © 2021 IEEE.

关键词： bistatic Omega-K algorithm space variance Translational variant bistatic forward-looking synthetic aperture radar (TV BFSAR)

来源：评论

学校读者我要写书评

暂无评论

Small Target Insect Detection Based on Improved YOLOv8n

Small Target Insect Detection Based on Improved YOLOv8n

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Jianyu Shi Yuan Jia Gang Zhou Jiajia Wang Zhenhong Jia School of Computer Science and Technology Xinjiang University Urumqi China Xinjiang Uygur Autonomous Region Signal Detection and Processing Key Laboratory School of Statistics Renmin University of China Beijing

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Insect pests greatly affect the growth and harvest of crops, and accurate identification of insect species is very important to the agricultural industry. The insect dataset has the problem that the target is too small to locate, detect, and identify. To solve this problem, We designed a modified YOLOv8n for detecting small target insects. First, we add a small object detection head to the network structure of the YOLOv8n (You Only Look Once) model. Then, we improve C2f and Conv in YOLOv8n, construct C2f-RFAConv by adding Receptive-Field Attention Convolutional Operation (RFAConv) into C2f for the first time, and replace the original convolution with RFAConv for feature extraction. Finally, we improve Wise-IoU (WIoU) loss function to solve the problem of small object detection difficulty. When the number of parameters is reduced, the performance of our model YOLOv8n-Improved on the Yellow Sticky Traps dataset and self-built dataset is greatly improved compared with YOLOv8n, and it also has great advantages compared with other models in the YOLO series. This work plays an important role in our efforts to achieve intelligent pest management in agriculture.

关键词： YOLO Smart agriculture Accuracy Head Convolution Insects signal processing algorithms Pesticides Feature extraction Speech processing

来源：评论

学校读者我要写书评

暂无评论

Prompt Fusion and Aspect-Oriented Filtration for Aspect-Based Multimodal Sentiment Analysis

Prompt Fusion and Aspect-Oriented Filtration for Aspect-Base...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Jiachang Sun Xiuhong Li Fuxian Zhu School of Computer Science and Technology XinJiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China School of Economics and Management XinJiang University Urumqi China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Currently, aspect-based multimodal sentiment analysis (ABMSA) remains a highly hot research field, aiming to leverage various modalities such as images and text to determine the sentiment orientation of viewpoint entities. Although deep learning methods have made significant progress in this field, some challenges still exist: Image information unrelated to the viewpoint entity can introduce noise, insufficient interaction during modal fusion. To solve these problems, we propose a novel ABMSA model with prompt fusion and noise filtration. Specifically, we introduced an Image Noise Filtering (INF) module that can filter the extracted image features to reduce the noise introduced by the irrelevant between viewpoint entity and the image. Additionally, we implemented Multimodal Prompt Fusion (MPF) module to enhance the interaction between modalities, addressing the issue of minimal effective features related to viewpoint entity during the fusion stage of text and image features. Experimental results show that the model outperforms the baseline model on two public datasets, Twitter-2015 and Twitter-2017, demonstrating that our proposed approach effectively enhances the accuracy of aspect-based multimodal sentiment analysis tasks.

关键词： Deep learning Sentiment analysis Analytical models Accuracy Filtration Noise Feature extraction Information filters Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Using Monotonic Neural Networks for Accurate and Efficient Passive Localization Performance Modeling

Using Monotonic Neural Networks for Accurate and Efficient P...

引用

IEEE Conference on Wireless Communications and Networking

作者： Hanyue Guo Rui Zhou Wenqiang Put Ming-Yi You JunKun Yan Hangzhou Institute of Technology Xidian University Hangzhou China Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen Shenzhen China National Key Laboratory of Electromagnetic Space Security Jiaxing China National Key Laboratory of Radar Signal Processing Xi'an China

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

Integrated Sensing and Communication (ISAC) systems are at the forefront of next-generation wireless technologies, enhancing high-precision target localization. Accurate prediction of localization performance is crucial for the design and optimization of these systems. Traditionally, the Cramer- Rao Lower Bound (CRLB) has been used as a theoretical benchmark for estimating localization errors, but it often does not reflect actual errors encountered in practice. The Monte Carlo simulation method, while accurate, is computationally intensive and less adaptable to varying parameters. To bridge this gap, we introduce LocNet-Mono, a novel approach based on monotonic neural networks, designed specifically for predicting localization errors. This approach maintains a consistent, monotonic relationship between input and output features, addressing the shortcomings of traditional methods. Our numerical experiments validate the high accuracy and efficiency of LocNet-Mono, confirming its potential as a superior tool for performance prediction in ISAC systems.

关键词： Location awareness Wireless communication Wireless sensor networks Monte Carlo methods Accuracy Neural networks Predictive models Integrated sensing and communication Numerical models Optimization

来源：评论

学校读者我要写书评

暂无评论

A demonstration of vector symbolic architecture as an effective integrated technology for AI at the network edge 2

A demonstration of vector symbolic architecture as an effect...

引用

Artificial Intelligence for Security and Defence Applications II 2024

作者： Bent, Graham Davies, Cai Vilamala, Marc Roig Li, Yuhua Preece, Alun Di Caterina, Gaetano Sola, Alex Vicente Kirkland, Paul Pearson, Gavin Tutcher, Benomy Neurosynapse Ltd. United Kingdom Security Crime and Intelligence Institute Cardiff University United Kingdom Neuromorphic Sensor Signal Processing Lab. EEE Dept. University of Strathclyde United Kingdom Defence Science and Technology Laboratory Porton Down United Kingdom Frazer-Nash Consultancy Ltd. Bristol United Kingdom

ISBN: (纸本)9781510681200

Vector Symbolic Architecture (VSA), a.k.a. Hyperdimensional Computing has transformative potential for advancing cognitive processing capabilities at the network edge. This paper presents a technology integration experiment, demonstrating how the VSA paradigm offers robust solutions for generation-after-next AI deployment at the network edge. Specifically, we show how VSA effectively models and integrates the cognitive processes required to perform intelligence, surveillance, and reconnaissance (ISR). The experiment integrates functions across the observe, orientate, decide and act (OODA) loop, including the processing of sensed data via both a neuromorphic event-based camera and a standard CMOS frame-rate camera;declarative knowledge-based reasoning in a semantic vector space;action planning using VSA cognitive maps;access to procedural knowledge via large language models (LLMs);and efficient communication between agents via highly-compact binary vector representations. In contrast to previous ‘point solutions’ showing the effectiveness of VSA for individual OODA tasks, this work takes a ‘whole system’ approach, demonstrating the power of VSA as a uniform integration technology. © 2024 SPIE.

关键词： Photons

来源：评论

学校读者我要写书评

暂无评论

Recurrence Plot and Quantification of Glottal signal for Pathological Voice Analysis

Recurrence Plot and Quantification of Glottal Signal for Pat...

引用

International Conference on Systems and Control (ICSC)

作者： M. Dahmani N. Bettayeb Laboratory of Speech Communication and Signal Processing of University of Science and Technology Houari Boumediene Electrical Engineering Faculty Faculté des News Technologies of information and Communications University Kasdi Merbah

ISBN: (数字)9798331531812

ISBN: (纸本)9798331531829

In this work, the information obtained from plotting the Recurrence Plot (RP) diagram and Recurrence Quantification Analysis (RQA), referring to the glottal signal waveform, is explored for the diagnosis and assessment of human voice disorders. For that, the glottal signal was initially obtained from the vocal signal through the use of an inverse filtering algorithm : Iterative Adaptive Inverse Filtering (IAIF). RP tracing and RQA were applied to the glottal signal to evaluate the dynamic process and vibration of Vocal Folds (VFs). the normal or healthy voice is considered as a reference. Visual inspection of the RPs and parametric analysis reveals a valuable information about the state of vocal folds under pathologies.

关键词： Vibrations Pathology Visualization Hospitals Speech enhancement Inspection Iterative algorithms Human voice Medical diagnostic imaging Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

High-Speed Targets Detection with Large Pulse Width Wideband LFM signal Based on IAA-CICPF Algorithm

High-Speed Targets Detection with Large Pulse Width Wideband...

引用

IEEE International Conference on Information Communication and signal processing (ICICSP)

作者： Hang Dong Fengzhou Dai Gaojun Feng National Laboratory of Radar Signal Processing Xidian University Xi'an China North Automatic Control Technology Institute Tai'yuan China

High-speed targets (radial velocity) cause the target echo spectrum spreading and center frequency shift, which causes great difficulties to the traditional target detection and target parameter estimation. The baseband signal of the received echo of a single broadband pulse of a high-speed target is still a linear frequency modulation (LFM) signal, thus the problem of high-speed target detection and parameter estimation can be transformed into the problem of estimating the centroid frequency (CF) and chirp rate (CR) of the LMF signal. In this paper, a method of broadband radar high-speed target detection based on coherent integrated cubic phase function (CICPF) is proposed to detect multiple high-speed moving targets. In addition, the CICPF algorithm is combined with an ultra-fast two-dimensional iterative adaptive approach (2D-IAA) spectral estimation algorithm to reduce the computational cost as well as to reduce the main lobe width and suppress the sideband of the target spectrum for improving the resolution. Simulation experiments show that the method in this paper is effective.

关键词： Frequency modulation Chirp modulation signal processing algorithms radar detection Object detection radar Frequency estimation

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Assisted Revocable Cross-Domain Authentication for Vehicular Ad-Hoc Networks

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Li, Ru Cui, Jie Zhang, Jing Wei, Lu Zhong, Hong He, Debiao Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Hefei230039 China Anhui University Anhui Engineering Laboratory of IoT Security Technologies Hefei230039 China Wuhan University School of Cyber Science and Engineering 430072 China

With the rapid development of vehicular ad-hoc networks (VANETs) and the increasing diversification of user demands, interactions between different management domains have become more frequent. Identity authentication is an effective way to establish cross-domain trust and secure communication. However, the existing cross-domain authentication schemes of VANETs are limited to the same management or authentication technology for each domain and rely on centralized cross-domain identity management. Even distributed management solutions encounter latency sensitivity, security and privacy challenges. To address these challenges, we propose a blockchain-assisted revocable cross-domain authentication scheme for VANETs. The proposed scheme can establish trust between domain entities by deploying different authentication methods and using distributed management to avoid single-point failures. In addition, the scheme can revoke the identity of malicious vehicles by updating the group public key, thereby ensuring the security and privacy of cross-domain Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communication. This design avoids the additional impacts of blockchain technology constraints on the high mobility and real-time requirements of VANETs. Security analysis and performance evaluation show that our scheme can resist more attacks and has better security than other related schemes while also achieving a better balance between communication and computational cost. © 2025 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Polarimetric Adaptive radar Target Detection in Sea Clutter with Lognormal Texture

SSRN

引用

SSRN 2024年

作者： Xue, Jian Yan, Jiali Xu, Shuwen Liu, Jun School of Communications and Information Engineering Xi’an University of Posts and Telecommunications Xi’an710121 China National Laboratory of Radar Signal Processing and Collaborative Innovation Center of Information Sensing and Understanding Xidian University Xi’an710071 China Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China

This paper addresses the problem of polarimetric adaptive coherent detection for maritime radar targets in the non-Gaussian sea clutter background. First, the radar sea clutter data at multiple polarimetric channels are modelled using the compound Gaussian model with an unknown speckle covariance matrix and a lognormal-distributed texture. Then, three adaptive polarimetric coherent detectors are derived based on estimation of unknown parameters and the two-step versions of generalized likelihood ratio test (GLRT), complex parameter Rao and Wald tests. All the proposed detectors exploit the clutter texture distribution information and the polarimetric information of radar data to enhance the detection performance. Finally, simulation experiments on simulated and measured radar data are utilized to evaluate the performance of the proposed detectors. The experimental results indicate that three proposed detectors outperform their competitors, and that their performance is affected by polarimetric channel parameters, i.e., the number of secondary data, the correlation of target signal or clutter speckle, the difference of signal-to-clutter ratio. Moreover, the proposed detectors approximately exhibit the constant false alarm rate property in relation to the average clutter power and the speckle covariance matrix. © 2024, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Design of a Wideband SIW Slot Antenna with Enhanced Gain

Design of a Wideband SIW Slot Antenna with Enhanced Gain

引用

2023 IEEE International Workshop on Electromagnetics: Applications and Student Innovation Competition, iWEM 2023

作者： Wang, Min Li, Xuan Mo, Dongsheng Chen, Zhengchuan Chongqing University of Posts and Telecommunications Postdoctoral Research Center of Chongqing Key Laboratory of Optoelectronic Information Sensing and Transmission Technology Chongqing400065 China Guilin University of Electronic Technology Guangxi Wireless Broadband Communication and Signal Processing Key Laboratory Guilin541004 China University of Electronic Science and Technology of China Chengdu611731 China Chongqing University School of Microelectronics and Communication Engineering Chongqing400044 China

ISBN: (纸本)9798350336740

This article demonstrates a wideband SIW slot antenna with gain-enhancing capability. The upper layer of SIW is composed of a 50 Ω microstrip line and radiation slots. The radiation slots are composed of a multiple branch slot and a couple of oblique slots. The multiple branch slot can excite triple resonant modes for extending impedance matching bandwidth and gain, while the oblique slots are utilized to match the microwave line so that further enhancing the impedance matching bandwidth. Simulated results of the SIW slot antenna indicate that the relative bandwidth is up to 16.7%. The gain at 9.0 GHz reaches 9.3 dBi, while the 1-dB gain bandwidth reaches 25.5%. © 2023 IEEE.

关键词： Slot antennas

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：