检索结果-内蒙古大学图书馆

Artificial Intelligence for Security and Defence Applications II 2024

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

ISBN: (纸本)9781510681200

Vector Symbolic Architecture (VSA), a.k.a. Hyperdimensional Computing (HDC) has transformative potential for advancing cognitive processing capabilities at the network edge. This paper examines how this paradigm offers r obust s olutions f or A I a nd A utonomy w ithin a f uture c ommand, c ontrol, c ommunications, computers, cyber, intelligence, surveillance and reconnaissance (C5ISR) enterprise by effectively m odelling t he cognitive processes required to perform Observe, Orient, Decide and Act (OODA) loop processing. The paper summarises the theoretical underpinnings, operational efficiencies, and synergy between VSA and current AI methodologies, such as neural-symbolic integration and learning. It also addresses major research challenges and opportunities for future exploration, underscoring the potential for VSA to facilitate intelligent decision-making processes and maintain information superiority in complex environments. The paper intends to serve as a cornerstone for researchers and practitioners to harness the power of VSA in creating next-generation AI applications, especially in scenarios that demand rapid, adaptive, and autonomous responses. © 2024 SPIE.

关键词： Computer architecture

来源：评论

学校读者我要写书评

暂无评论

VTWSAR: A Fast Calculation Method for Visible Time Window of SAR Satellite to Regional Target

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 14063-14075页

作者： Shi, Xin Xing, Wenjie Liu, Huitao Wang, Yanxue Xing, Mengdao Xidian University National Key Laboratory of Radar Signal Processing Xi'an710071 China Fudan University Key Laboratory for Information Science of Electromagnetic Waves Shanghai200438 China Xidian University Academy of Advanced Interdisciplinary Research Xi'an710071 China Shandong Vocational College of Industry Zibo256414 China

The calculation of the visible time window (VTW) of Synthetic Aperture radar (SAR) satellite to regional target plays an important role in SAR satellite mission planning. At present, the VTW calculation for regional target mainly uses the grid point approach (GPA), which faces the problem of high spatial and temporal computational complexity. In addition, the current VTW calculation method is mainly designed for optical satellite, without considering the imaging characteristics of SAR satellite. To address the above problems, this study proposes a fast VTW calculation method for SAR satellite to regional target (VTWSAR). First, a fast orbit filtering method for regional target is proposed based on a joint simplified visible field (JSVF), which reduces a large amount of irrelevant orbit calculations. Then, a fine VTW calculation method is proposed based on the boundary intersection judgment of the projection plane and time dichotomy (PPTD), which reduces both the space complexity and the time complexity. Finally, a SAR satellite VTW calculation model including two-dimensional steering is constructed, and the VTW calculation method is expanded to different SAR satellite imaging modes. The simulation experiment is conducted using 6 SAR satellites and 9 regional targets. Compared with the professional software STK, the proposed method can improve the calculation efficiency by two times, and the average calculation error is 0.015s, which proves the effectiveness of the proposed algorithm. And experimental verification is carried out on the SmartSat-X1 satellite, the measured data results confirm the effectiveness of the proposed method. © 2008-2012 IEEE.

关键词： NP-hard

来源：评论

学校读者我要写书评

暂无评论

A Time-domain strip-map processing scheme for FMCW imaging

A Time-domain strip-map processing scheme for FMCW imaging

引用

2021 CIE International Conference on radar, radar 2021

作者： Zhang, Tao Liao, Guisheng Li, Yachao Gu, Tong Zhang, Tinghao Chen, Chilian Xidian University National Laboratory of Radar Signal Processing Xi'an China The 20th Research Institute of Cetc Key Laboratory of Technology on Datalink Xi'an China

ISBN: (纸本)9781665498142

For strip-map frequency-modulated continuous wave synthetic aperture radar (FMCW-SAR) imaging, a time-domain processing scheme is proposed in this paper. For no loss of resolution, the angle-overlapped unified polar coordinate is established. Time-domain FMCW back-projection integration is carried out in sub-aperture(SA) process. And the SA wavenumber fusion and full-strip-map wavenumber fusion are successively performed to obtain whole strip-map image. Simulation and real SAR data mapping are used to demonstrate the effectiveness of proposed scheme. © 2021 IEEE.

关键词： frequency-modulated continuous wave(FMCW) strip-map sub-aperture(SA) synthetic aperture radar(SAR) time-domain imaging

来源：评论

学校读者我要写书评

暂无评论

Moving Target Tracking Based on Shadow with Unsupervised Deep Track in Video-SAR

Moving Target Tracking Based on Shadow with Unsupervised Dee...

引用

2021 CIE International Conference on radar, radar 2021

作者： Fang, Hui Liu, Yongjun Liao, Guisheng Li, Haichuan Chen, Chilian Liu, Xuchen Xidian University National Laboratory of Radar Signal Processing Xi'an China The 20th Research Institute of Cetc Key Laboratory of Technology on Datalink Xi'an China

ISBN: (纸本)9781665498142

The moving target is always defocused and shifted out of the scene in image sequences in video Synthetic Aperture radar (video-SAR), which makes moving target tracking be a formidable challenge. In this paper, a new moving target tracking method based on shadow with unsupervised deep track (UDT) is proposed. Our track network is built on the Siamese network framework and is trained on a series of unlabeled SAR image sequences with unsupervised learning way. Meanwhile, we use the trajectory detection technology to get more accurate tracking results. Finally., the processing results of the real data are provided to verify the effectiveness of the proposed method. © 2021 IEEE.

关键词： moving target shadow tracking unsupervised deep track (UDT) video Synthetic Aperture radar (video-SAR)

来源：评论

学校读者我要写书评

暂无评论

Integrated radar and Jammer Waveform Design Based on PNFM-NLFM

Integrated Radar and Jammer Waveform Design Based on PNFM-NL...

引用

2021 CIE International Conference on radar, radar 2021

作者： Chen, Zhuochen Zhu, Shengqi Liu, Yongjun Li, Haichuan Chen, Chilian Xidian University National Laboratory of Radar Signal Processing Xi'an China The 20th Research Institute of Cetc Key Laboratory of Technology on Datalink Xi'an China

ISBN: (纸本)9781665498142

To achieve the integration of radar and jammer in the waveform, we proposed a pseudo-code noise and nonlinear frequency modulation (PNFM-NLFM) waveform. The PNFM-NLFM waveform is a combination of pseudo-random-codes noise frequency modulation (PNFM) and nonlinear frequency modulation (NLFM). The detection performance is evaluated by ambiguity function, and we study the interference performance through pulse compression(PC) processing. Finally, the simulation results show that compared with the existing noise-linear frequency modulation (Noise-LFM) signal, the PNFM-NLFM has low autocorrelation side lobe while keeping interference performance. © 2021 IEEE.

关键词： autocorrelation side lobe integration of radar and jammer nonlinear frequency modulation pseudo-random-codes noise frequency modulation

来源：评论

学校读者我要写书评

暂无评论

Pipeline Chain-of-Thought: A Prompt Method for Large Language Model Relation Extraction

Pipeline Chain-of-Thought: A Prompt Method for Large Languag...

引用

International Conference on Asian Language processing (IALP)

作者： Hangtian Zhao Hakiz Yilahun Askar Hamdulla Xinjiang Key Laboratory of Signal Detection and Processing School of Computer Science and Technology XinJiang University Urumqi China

The development of language models has been influencing approaches to relation extraction (RE) problems. Although large language models (LLMs) have demonstrated breakthrough potential in certain aspects, they are still in the exploratory stage for RE tasks. Currently, the mainstream approach to improving the RE performance of LLMs is through prompt fine-tuning, but most methods require providing entity information in the prompt, which effectively only allows the LLMs to perform relationship classification tasks. We propose the Pipeline Chain-of-Thought (Pipeline-COT), which breaks down the RE task into steps and transforms it into reasoning tasks that have flat scaling curves, thereby enabling the use of Chain-of-Thought (COT) to enhance model inference. In addition, our method utilizes n-shot samples to provide signals for the Bayesian inference of the model by prompting the LLMs to focus on specific concepts to generate answers. We evaluated pipeline-COT on the Chinese dataset DuIE2.0, and compared with baseline methods that require including entity information in the prompt, our method still shows competitive performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Position Determination Using Low-Rank Matrix Completion

Efficient Position Determination Using Low-Rank Matrix Compl...

引用

signal, Information and Data processing (ICSIDP), IEEE International Conference on

作者： Zehui Zhang Wenqiang Pu Rui Zhou Mingyi You Wei Wang Junkun Yan Shenzhen Research Institute of Big Data Shenzhen China National Key Laboratory of Electromagnetic Space Security Jiaxing China National Key Laboratory of Radar Signal Processing Hangzhou Institute of Technology Xidian University Xi’an China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

In increasingly complex electromagnetic environments, distributed systems are crucial for passive target localization. These systems, consisting of spatially dispersed sensing nodes, collaboratively enhance the localization of target signals. Particularly in blind localization tasks within low signal-to-noise ratio (SNR) settings, distributed passive localization offers improved positioning performance. Traditional passive localization methods typically follow a two-step process: initially extracting parameters, such as the direction of arrivals (DOA), from raw data, followed by localizing the target. This approach often requires a high SNR. In contrast, Direct Position Determination (DPD) methods directly leverage all the received raw data, thus overcoming the constraints of the two-step process. However, DPD methods involve a time-consuming grid search within the area of interest. To address this challenge, we propose a radiation source localization method that utilizes random sampling. This method capitalizes on the low-rank properties of the grid search matrix used in DPD methods. By integrating random sampling with low-rank matrix completion algorithms, our approach efficiently localizes the radiation source. Simulation results demonstrate that this random sampling-based method significantly reduces computational demands while preserving high localization accuracy.

关键词： Location awareness Accuracy Direction-of-arrival estimation Simulation Data processing Sensors Computational efficiency Data mining Electromagnetics signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Power Allocation for Multiple Sensing and Communication Tasks Using Massive MIMO Base Station

Power Allocation for Multiple Sensing and Communication Task...

引用

International Conference on Control, Automation and Information sciences (ICCAIS)

作者： Ziyi Cao Xuanqi Wang Ye Yuan Wei Yi Junkun Yan School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China Glasgow College University of Electronic Science and Technology of China Chengdu China National Key Laboratory of Radar Signal Processing Xidian University Xi’an China

In this paper, we consider a joint sensing and communication scenario with the simultaneous implementation of multiple sensing and communication tasks employing a massive multiple-input multiple-output (MIMO) base station system. This system operates on orthogonal frequency-division multiplexing (OFDM) modulations for both communication and sensing signals. To evaluate the performance of dual functions, we derive the lower bound on the achievable downlink rate for communication and signal-to-interference-plus-noise ratio (SINR) for radar detection. By focusing on the power allocation strategy, we propose two optimization cases with different emphasis on sensing and communication to explore the trade-off between radar performance and communication quality. The formulated optimization problem can be effectively solved via the binary search technique, and simulation results demonstrate its efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Postprocessing Method for Ship Detection in SAR Images Using Greedy Strategies

A Novel Postprocessing Method for Ship Detection in SAR Imag...

引用

IEEE Joint International Information technology and Artificial Intelligence Conference (ITAIC)

作者： Yunfeng Liu Tianyi Car Xiaonan Wu Tong Gu Linglong Zhang Yachao Li HangZhou Institute of Technology Xian University HangZhou China Institute of the second Academy of Aerospace Science and industry Beijing China National Key Laboratory of Radar Signal Processing Xian University Xian China

This article proposes a novel post-processing method for ship detection in synthetic aperture radar (SAR) images, which addresses the issue of head to tail separation that cannot be avoided when using morphological compensation to process candidate regions generated by the constant false alarm detection (CFAR). This algorithm first constructs a connected domain for the candidate regions generated by CFAR, uses a greedy strategy to update the centroid and size of the connected domain, and finally unreasonable candidate connected domains are removed to eliminate high noise sea clutter and large volume non ship targets. Compared to the morphological compensation post-processing method, the greedy strategy the greedy strategy fully utilizes the prior knowledge of ship data in the post-processing of constant false alarm ship detection results, overcomes the disadvantage of complex morphological compensation methods that require fine-tuning parameters in post-processing, and completely solves the problem of head tail separation that cannot be completely solved, improving the accuracy of synthetic aperture radar ship detection. The effectiveness and robustness of our method have been demonstrated by the data from the domestically produced Gaofen 3 satellite and the data from the European Space Agency's TerraSAR-X satellite.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Standardized-Based Knowledge Distillation Model for Multimodal Emotion Recognition in Conversation

SSRN

引用

SSRN 2024年

作者： Li, Yihao Tohti, Turdi Han, Dongfang Liang, Yi Zuo, Zicheng Liao, Yuanyuan Yang, Qingwen School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China

In recent years, with the rapid development of artificial intelligence and deep learning technology, Multimodal Emotion Recognition in Conversation (MERC) has gradually attracted widespread attention. However, existing methods rely on designed models to learn modal representations, there is a lack of research on enhancing modal representations. Therefore, we propose a method for standardized knowledge distillation. This method uses the intra-modal Transformer module for learning intra-modal representations, as well as employing the Cross-Modal Transformer module to effectively integrate different modalities. In addition, we further design a novel standardized knowledge distillation strategy, which uses the soft labels of the text modality as training supervision, thereby achieving the migration of semantic and contextual information from the text modality to the audio and visual modalities. This strategy fully borrows the idea of information sharing, allowing the audio and visual modalities to learn the fine-grained features and complex decision boundaries of the text modality. To demonstrate the effectiveness of our proposed model, we conduct extensive experiments on two public emotion recognition datasets: IEMOCAP and MELD. Experimental results further demonstrate the superiority of our method compared with the state-of-the-art methods. © 2024, The Authors. All rights reserved.

关键词： Distillation

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：