检索结果-内蒙古大学图书馆

6th IEEE International Conference on Electronic Information and Communication technology, ICEICT 2023

作者： Zhen, Yang Qi, Junwei Li, Yingsong College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Ministry of Education Anhui University Key Laboratory of Intelligent Computing and Signal Processing Hefei China College of Computer Science and Technology Harbin Engineering University Harbin150001 China

ISBN: (纸本)9798350399059

Multi-exposure image fusion (MEF) is one of the effective ways to obtain high dynamic range (HDR) images. Multi-scale structural patch decomposition based MEF(MSPD) and edge-preserving structural patch decomposition (MESPD) have achieved state-of-the-art fusion quality. MESPD incorporates edge-preserving factors into MSPD to preserve details in a single-scale setting. However, we find that the edge-preserving factors put too much emphasis on the edge, resulting in artifacts on some edges and loss of details. To tackle this issue, guided filter is introduced into MSPD, which is directly used as an edge-preserving filter instead of mean filter to implicitly decompose images. In addition, we have designed a flexible adaptive weight, which can further maintain details of the light and dark areas. Likewise, we inherit MESPD and MSPD to extend our method to multi-scale framework. Extensive experimental results demonstrate our method can produce satisfactory results in both static and dynamic scenes with fewer artifacts and low computational cost. © 2023 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Prosody Prediction with Discriminative Representation Method 3

Prosody Prediction with Discriminative Representation Method

引用

3rd International Conference on Pattern Recognition and Machine Learning, PRML 2022

作者： Zhang, Jipeng Yilahun, Hankiz Feng, Xiaoqin Chen, Yunlin Yang, Xipeng Hamdulla, Askar School of Information Science and Engineering Xinjiang University of China China Xinjiang Key Laboratory of Signal Detection and Processing China Xinjiang Key Laboratory of Multilingual Information Technology China Mobvoi Ai Lab Suzhou China

ISBN: (数字)9781665499507

ISBN: (纸本)9781665499507

Rhythm affects the naturalness and intelligibility of Text-To-Speech (TTS). However, rhythm prediction remains a great challenge, usually in two aspects: 1) the united annotation is a relatively difficult task, which depends on expert's experience. 2) traditional methods based on conditional random field (CRF), which heavily rely on feature engineering, such as word segmentation, part of speech(pos) etc. For above problems, we propose a method to reduce the dependency for united annotation data and conduct the joint experiment which use one unified model on independent data. Meanwhile, we also propose an algorithm of Layer Look Up Table (LLUT): use an embedding layer to learn a discriminative representation for different level of prosody data without any feature engineering. By using this method, the classifier can share the parameters and predict for different prosody level separately, which reduces the number of trainable model parameters. In order to better represent the input text, we use the pre-training model, like BERT, to provide the semantic information. Our experiment shows that the method of LLUT, is better able to acquire the discriminative meaning of different prosody levels. And also, our algorithm is proved to be general for sequence annotation tasks thus we can do extra task, like polyphone-prosody prediction. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Covert Communications in D2D Underlaying Cellular Networks With Dual Uncertainties at the Warden

引用

IEEE Internet of Things Journal 2025年第12期12卷 21195-21209页

作者： Du, Zhiyi Chen, Weiyu Luo, Junshan Ding, Haiyang Wang, Shilian Sun, Zhengbo National University of Defense Technology College of Electronic Science and Technology Changsha410073 China National University of Defense Technology College of Information and Communication Wuhan430019 China National Key Laboratory on Blind Signal Processing Chengdu610041 China

Covert device-to-device (D2D) communication aims to hide the existence of D2D transmission behavior from the warden, which plays a pivotal role in bolstering D2D communication security. The existing research on covert D2D communication either considered the interference's assistance with perfect channel state information (CSI) available at the warden, or considered channel distribution information (CDI) at the warden without the assistance of interference. These setups facilitate the performance analyses and the parameters design, which, however, did not fully exploit the potential of covert D2D communication, since both channel uncertainty and interference uncertainty exist in practice. In this paper, two covert schemes are proposed for covert D2D communication with dual uncertainties at the warden, where the warden has imperfect CSI. The base station transmits artificial noise to assist covert communication in the first scheme. In the second scheme, the cellular user adopts variable power to confuse the warden. For both schemes, the closed-form expressions of the warden's approximate minimum detection error probability and the achievable D2D communication rate are derived. The achievable D2D communication rate is maximized by jointly optimizing the transmit power of different links with given covertness requirement. The results suggest that the proposed schemes achieve higher communication performance by considering dual uncertainties. Moreover, the scheme with variable cellular user's transmit power performs better when the covert receiver can not well handle the interference from artificial noise. © 2025 IEEE.

关键词： Mobile telecommunication systems

来源：评论

学校读者我要写书评

暂无评论

Maximum Likelihood Distillation for Robust Modulation Classification

Maximum Likelihood Distillation for Robust Modulation Classi...

引用

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

作者： Javier Maroto Gérôme Bovet Pascal Frossard Signal Processing Laboratory (LTS4) EPFL Switzerland Armasuisse Science & Technology Cyber-Defence Campus Switzerland

Deep Neural Networks are being extensively used in communication systems and Automatic Modulation Classification (AMC) in particular. However, they are very susceptible to small adversarial perturbations that are carefully crafted to change the network decision. In this work, we build on knowledge distillation ideas and adversarial training in order to build more robust AMC systems. We first outline the importance of the quality of the training data in terms of accuracy and robustness of the model. We then propose to use the Maximum Likelihood function, which could solve the AMC problem in offline settings, to generate better training labels. Those labels teach the model to be uncertain in challenging conditions, which permits to increase the accuracy, as well as the robustness of the model when combined with adversarial training. Interestingly, we observe that this increase in performance transfers to online settings, where the Maximum Likelihood function cannot be used in practice. Overall, this work highlights the potential of learning to be uncertain in difficult scenarios, compared to directly removing label noise.

关键词： Training Knowledge engineering Perturbation methods Neural networks Modulation Training data Rician channels

来源：评论

学校读者我要写书评

暂无评论

Data Association with Amplitude Information Based on the Copula Theory 10

Data Association with Amplitude Information Based on the Cop...

引用

10th International Conference on Control, Automation and Information sciences, ICCAIS 2021

作者： Liu, Tian Tong, Hao Zhou, Shenghua Zhao, Yihuan Dai, Zongwu Xidian University National Laboratory of Radar Signal Processing xi'An. China Xi'an710071 China China Academy of Space Technology Beijing100094 China

ISBN: (纸本)9781665440295

In radar data association, amplitudes of radar target returns are widely used in tracking algorithms, but the correlation between signal amplitudes, depending on the correlation of returns from the same target, is not well addressed, especially when jamming signals with higher powers are present. After the target detection operation, the amplitudes are typically positive real numbers, which makes the correlation even more complicated. In this paper, we analyze the correlation of squared amplitudes of signals based on a statistical correlation model of target returns. The Copula theory is used to approximate the joint distribution of squared amplitudes and the probability density function (PDF) of the signal amplitude conditioned on former amplitudes are formulated in theory and through numerical results. This method can be used for data association in the target-detection-during-tracking problem with intensive jamming or clutter returns. © 2021 IEEE.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Robust Adaptive Beamforming Based on MR-FDA-MIMO radar Jamming Suppression

Robust Adaptive Beamforming Based on MR-FDA-MIMO radar Jammi...

引用

IEEE International Conference on radar

作者： Zhixia Wu Shengqi Zhu Jingwei Xu Lan Lan Yanhong Xu Ximin Li Jie Gao National Key Lab. of Radar Signal Processing Xidian University Xi’an China School of Communication and Information Engineering Xi’an University of Science and Technology Xi’an China

In this work, an adaptive beamforming algorithm based on a minimum redundancy frequency diverse array multiple-input multiple-output (MR-FDA-MIMO) radar is proposed. The algorithm utilizes the transmit virtual domain signal of a MR-FDA-MIMO radar to perform transmit adaptive beamforming, overcoming the limitations of transmit array elements and suppressing multiple mainlobe deceptive jamming. To mitigate the beamforming performance degradation resulting from including the true target in the samples, the jamming plus noise covariance matrix is restructured to obtain the optimal performance of jamming suppression. To fully utilize the virtual degree of freedom (DOF) in the transmit dimension of MR-FDA-MIMO radar, sidelobe barrage jamming and mainlobe deceptive jamming are suppressed separately. Sidelobe barrage jamming is suppressed in the receive dimension. Multiple false targets are suppressed in the equivalent transmit dimension. The simulation results demonstrate the effectiveness of the algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Smart radar signal processing Solution for Ground-Based UAVs Surveillance 6

A Smart Radar Signal Processing Solution for Ground-Based UA...

引用

6th International Forum on Research and technology for Society and Industry, RTSI 2021

作者： Yang, Tianyuan De Maio, Antonio Zheng, Jibin Su, Tao Carotenuto, Vincenzo Aubry, Augusto National Laboratory of Radar Signal Processing Xidian University Xi'an China University of Naples Federico II Department of Electrical and Information Technology Engineering Naples Italy

ISBN: (纸本)9781665441353

Unmanned Aerial Vehicles (UAVs) have become widely used in civilian and military applications. There is a recognised need for UAVs surveillance against their malicious use. In this context, radar has emerged as a powerful tool in detecting and tracking UAVs. However, the task is quite complicate due to the low-Altitude, low velocity and low radar cross section of small UAVs. In this paper, a smart radar signal processing solution in the presence of multiple unresolved UAVs is devised and applied to UAVs surveillance, which fully capitalizes on the coherent integration, constant false alarm rate detection, target multiplicity test and sparse methods to achieve low computational complexity and high angular resolution. At the analysis stage, numerical simulations are carried out to highlight the capability of proposed solution to detect UAVs and resolve them when they are closely spaced. © 2021 IEEE.

关键词： radar cross section

来源：评论

学校读者我要写书评

暂无评论

Fast Node Selection of Networked radar Based on Transfer Reinforcement Learning 5th

Fast Node Selection of Networked Radar Based on Transfer R...

引用

5th IFIP TC 12 International Conference on Intelligence science, ICIS 2022

作者： Cao, Yanjun Wang, Yuan Guo, Jingjing Han, Li Zhang, Chao Zhu, Jin Zhang, Tianyang Zhang, Xiangrong The 54th Research Institute of China Electronics Technology Group Corporation Beijing China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Shaanxi Xian710071 China National Laboratory of Radar Signal Processing Xidian University Xian710071 China

ISBN: (纸本)9783031149023

The networked radar system can synthesize different echo signals received by various radars and realize the cooperative detection of multiple radars, becoming more and more critical for data fusion sharing and network collaboration. However, due to the large number and wide range of nodes in the networked radar system, there exists a redundancy problem in radar node assignment, which causes additional resource consumption and slows down the task execution speed of radar node selection. To solve the above problem, this paper proposes a fast radar node selection method based on transfer reinforcement learning to quickly select the optimal and minimum node resources. The proposed method devises a novel reward function for the Monte Carlo Tree and a different termination state of iteration to select the minimize the number of radar nodes. In order to further accelerate the selection of radar nodes, transfer reinforcement learning is presented to fully leverage the previous knowledge. Experimental results show that our proposed method can quickly select the optimal and minimum radar nodes in a brief period, significantly improving the speed of radar node selection in the networked radar. © 2022, IFIP International Federation for Information processing.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Adaptive DoA Estimation Strategy for UAVs Detection

An Adaptive DoA Estimation Strategy for UAVs Detection

引用

2021 CIE International Conference on radar, radar 2021

作者： Yang, Tianyuan De Maio, Antonio Zheng, Jibin Su, Tao Carotenuto, Vincenzo Aubry, Augusto Xidian University National Laboratory of Radar Signal Processing Xi'an China University of Naples Federico Ii Department of Electrical and Information Technology Engineering Naples Italy

ISBN: (纸本)9781665498142

This paper presents a new strategy to estimate Direction of Arrival (DoA) of UAVs which relies, as first step on a binary test to establish the number of targets present in a given cell under test. Specifically, based on the result of the mention binary test, different DoA estimation algorithms are employed to minimize the computational burden required for the entire processing. The performance of the signal processor is assessed on measured data collected by a C-band radar equipped with a 12-channel phased-array. The results confirm that the proposed strategy is able to discriminate the single from the multiple targets scenario and resolve the UAVs when they are located in one range-Doppler-angle cell. © 2021 IEEE.

关键词： Adaptive DoA estimation unmanned aerial vehicles detection

来源：评论

学校读者我要写书评

暂无评论

keqing: knowledge-based question answering is a nature chain-of-thought mentor of LLM

arXiv

引用

arXiv 2023年

作者： Wang, Chaojie Xu, Yishi Peng, Zhong Zhang, Chenxi Chen, Bo Wang, Xinrun Feng, Lei An, Bo Liu, Xinyang National Key Laboratory of Radar Signal Processing Xidian University Shaanxi Xi’an710071 China School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore

Large language models (LLMs) have exhibited remarkable performance on various natural language processing (NLP) tasks, especially for question answering. However, in the face of problems beyond the scope of knowledge, these LLMs tend to talk nonsense with a straight face, where the potential solution could be incorporating an Information Retrieval (IR) module and generating response based on these retrieved knowledge. In this paper, we present a novel framework to assist LLMs, such as ChatGPT, to retrieve question-related structured information on the knowledge graph, and demonstrate that Knowledge-based question answering (Keqing) could be a nature Chain-of-Thought (CoT) mentor to guide the LLM to sequentially find the answer entities of a complex question through interpretable logical chains. Specifically, the workflow of Keqing will execute decomposing a complex question according to predefined templates, retrieving candidate entities on knowledge graph, reasoning answers of sub-questions, and finally generating response with reasoning paths, which greatly improves the reliability of LLM’s response. The experimental results on KBQA datasets show that Keqing can achieve competitive performance and illustrate the logic of answering each question. © 2023, CC BY.

关键词： Knowledge graph

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：