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： Zhang, Guang Wang, Zhaocheng Wang, Ruonan Song, Hualiang Kang, Hailong Hebei University of Technology School of Electronics and Information Engineering Tianjin China Xidian University Hangzhou Institute of Technology Hangzhou China Xidian University National Key Laboratory of Radar Signal Processing Xi'an China

ISBN: (纸本)9798331515669

As a critical branch of synthetic aperture radar (SAR) interpretation, SAR target detection has many applications in the military and civil fields. Although traditional deep learning methods achieve some satisfactory performance in target detection tasks, they inherently require significant computational resources and interpretation time. Hence, traditional deep learning methods frequently struggle to maintain a balance between high efficiency and precision. It is undoubtedly a huge challenge for target detection tasks. To address this problem, an efficient SAR target detector based on multi-teacher knowledge distillation (MTKD-Det) is proposed in this paper, which can effectively enhance target detection accuracy while reducing inference time. Specifically, a multiple-teacher knowledge distillation strategy is used in the proposed method, which integrates the experiences and methodologies of multiple teachers to collaboratively guide the training and learning of the student network, ultimately enhancing the robustness of the student network. In this work, a novel teacher network is developed to enhance the detection performance of the proposed method specifically for small targets. Furthermore, an attention mechanism is incorporated into the student network to enable it to focus on more critical information, thereby improving overall detection efficacy. Experimental results obtained from a measured SAR target detection dataset convincingly validate the benefits of the proposed approach. © 2024 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

A Refined Tracking Filtering Algorithm Based on IMM 12

A Refined Tracking Filtering Algorithm Based on IMM

引用

12th IEEE International Conference on Control, Automation and Information sciences, ICCAIS 2023

作者： Jiao, Hao Liu, Yudong Yan, Junkun Liu, Hongwei Xidian University National Key Laboratory of Radar Signal Processing Xi'an China China Academy of Launch Vehicle Technology Department of Research and Development China

ISBN: (纸本)9798350328783

Maneuvering targets, distinguished by their pronounced dynamic characteristics, present significant challenges to radar tracking. To address these problems, a refined tracking method based on IMM (IMM-RTF) is proposed in this paper. The key idea of the method is to adaptively correct the recursive residual covariance by using the observation residual based on the consistency of residual and residual covariance to reduce the influence of model mismatch. In addition, to realize refined filtering, this paper analyzes the influence of model mismatch on the filter, and models the consistency problem of residual and residual covariance as a convex optimization problem. By analyzing the unique structure of the problem, the analytical solution of the problem under two assumptions is derived. Meanwhile, the adaptive IMM framework is adopted, thus effectively improving the tracking performance of maneuvering targets and non-maneuvering targets under steady-state conditions. Simulation results demonstrate that compared with the IMM, the IMM-RTF not only accentuates the tracking precision for maneuvering targets in steady states but also significantly fortifies target tracking robustness amidst model mismatch. © 2023 IEEE.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Improving Speaker Verification Back-End with Graph Neural Networks

引用

Journal of Shanghai Jiaotong University (science) 2025年 1-9页

作者： Chen, Jinfeng Fang, Zhihua He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China School of Intelligence Science and Technology Xinjiang University Urumqi830017 China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

Currently, research on speaker verification tasks is primarily concentrated on enhancing deep speaker models to extract high-quality speaker embeddings. Nevertheless, this speaker embeddings can be regarded as potential graph structures. Therefore, this paper introduces a graph neural network-based speaker verification back-end approach, treating the speaker embeddings derived from the front-end as graph structures and leveraging graph neural networks to uncover the relationships among embeddings, thereby achieving superior-quality speaker embeddings. In addition, we propose a group updating method to solve the problem of memory overflow when the number of nodes is excessive. Extensive experiments and ablation studies were carried out on the VoxCeleb dataset, and the experimental outcomes validate the effectiveness of our proposed graph neural network speaker back-end in significantly boosting the performance of speaker verification systems. (Figure presented.) © Shanghai Jiao Tong University 2025.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

A knowledge-assisted space-time spectrum compensation method for bistatic array radar clutter

A knowledge-assisted space-time spectrum compensation method...

引用

IET International radar Conference 2023, IRC 2023

作者： Yu, Chunyu Tian, Min Liao, Guisheng Li, Yu Hangzhou Institute of Technology Xidian University Hangzhou China National Key Laboratory of Radar Signal Processing Xidian University Xi'an China Xi'an Institute of Space Radio Technology National Key Laboratory of Science and Technology on Space Microwave Xi'an China

ISBN: (纸本)9781839539954

When the spaceborne bistatic radar looks down, radar returns from ground, referred to as clutter, may be powerful and cause severe interferences. Space-time adaptive processing is an effective way to suppress the clutter for moving target detection. However, as the space-time spectrum of clutter in the bistatic radar system is rapidly changing in space, the space-time spectrum in a range gate may be severely spread, resulting in deterioration of processing performance. In order to solve this problem, a knowledge-assisted space-time spectrum compensation method for the bistatic radar system is proposed. Specifically, the detection area is divided into small-scale resolution units, and the space-time clutter model of the bistatic system is established according to the system geometry, platform relative motion and radar detection mechanism, which forms prior knowledge of the space-time vectors. Then, the knowledge-assisted space-time matrixes of the clutter units in the range gate to be compensated is constructed. Meanwhile, the space-time matrixes of the reference clutter units is searched by the Capon spectrum in the circular domain to fit the original clutter data. Based on the two matrixes, a transformation matrix is constructed to realize the space-time spectrum compensation. Finally, the validation of the proposed compensation algorithm is present by simulations. © The Institution of Engineering & technology 2023.

关键词： radar clutter

来源：评论

学校读者我要写书评

暂无评论

Anomalous Sound Detection Using Time-Frequency Feature and Mixbatch

引用

Journal of Shanghai Jiaotong University (science) 2025年 1-8页

作者： Huang, Shun Zhang, Yunxiang Fang, Zhihua Tang, Minrui Xu, Ruifeng He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China School of Intelligence Science and Technology Xinjiang University Urumqi830017 China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

The sound emitted by machines under abnormal working conditions exhibits various frequency patterns. Currently, the most advanced anomalous sound detection (ASD) approach is to apply a multi-head self-attention mechanism to the Log-Mel spectrogram for automatic frequency pattern analysis. However, the Log-Mel spectrogram may filter out high-frequency components of abnormal sounds;thus the use of self-attention mechanisms on Log-Mel spectrogram seems to have certain limitations. In this paper, we construct a simple convolutional neural network to extract comprehensive frequency features from raw audio to complement spectral-temporal information fusion. The parameters of this neural network are continuously updated during the training process to extract better frequency features for downstream classification neural networks in ASD. Additionally, a method for data augmentation in the batch dimension was developed to help the classification model learn both types of comprehensive features simultaneously. The proposed method achieved an AUC of 94.13% and a pAUC of 89.09% on the DCASE 2020 Challenge Task 2 dataset. Even when using only the features proposed in this paper, an AUC of 84.62% was achieved. (Figure presented.). © Shanghai Jiao Tong University 2025.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

Dual-Path Spectrogram Refinement Network for Robust Speaker Verification

引用

Journal of Shanghai Jiaotong University (science) 2025年 1-9页

作者： Wang, Zonghui Fang, Zhihua He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China School of Intelligence Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

The accuracy and reliability of automatic speaker verification (ASV) face significant challenges in noisy environments. In recent years, joint training of speech enhancement front-end and ASV back-end has been widely applied to improve the robustness of ASV systems. Traditional joint training directly uses the enhanced speech features as the input of the back-end. However, the diversity of noise types and noise intensities will excessively suppress the enhanced features, resulting in speech distortion or residual noise. To alleviate this problem, we propose a dual-path spectrogram refinement network that enables the enhanced features to learn supplementary information from the separated noise features. In addition, we incorporate coordinate attention into the overall joint architecture to capture more comprehensive frequency and temporal information of the speaker from different spatial positions. We conduct extensive experiments on the VoxCeleb1 test set, the out-of-domain noise test set, and the VOiCES corpus. The experimental results demonstrate that our proposed method significantly improves the accuracy and robustness of speaker verification systems in both clean and noisy environments. (Figure presented.) © Shanghai Jiao Tong University 2025.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

Electrochemical protein biosensors for disease marker detection:progress and opportunities

引用

Microsystems & Nanoengineering 2024年第3期10卷 1-20页

作者： Lanpeng Guo Yunong Zhao Qing Huang Jing Huang Yanbing Tao Jianjun Chen Hua-Yao Li Huan Liu School of Integrated Circuits Wuhan National Laboratory for OptoelectronicsOptics Valley LaboratoryHuazhong University of Science and TechnologyWuhan 430074China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Integrated CircuitsAnhui UniversityHefei 230601China School of Optoelectronic Materials and Technology Jianghan UniversityWuhan 430056China Department of Otorhinolaryngology Union HospitalTongji Medical CollegeHuazhong University of Science and Technology1277 Jiefang AvenueWuhan 430022China Wenzhou Institute of Advanced Manufacturing Technology Huazhong University of Science and TechnologyWenzhou 325000China

The development of artificial intelligence-enabled medical health care has created both opportunities and challenges for next-generation biosensor *** are extensively used as biological macromolecular markers in disease diagnosis and the analysis of therapeutic *** protein biosensors have achieved desirable specificity by using the specific antibody–antigen binding principle in ***,the active centers of protein biomarkers are surrounded by a peptide matrix,which hinders charge transfer and results in insufficient sensor ***,electrode-modified materials and transducer devices have been designed to increase the sensitivity and improve the practical application prospects of electrochemical protein *** this review,we summarize recent reports of electrochemical biosensors for protein biomarker *** highlight the latest research on electrochemical protein biosensors for the detection of cancer,viral infectious diseases,inflammation,and other *** corresponding sensitive materials,transducer structures,and detection principles associated with such biosensors are also addressed ***,we present an outlook on the use of electrochemical protein biosensors for disease marker detection for the next few years.

关键词： diagnosis specificity Electrochemical

来源：评论

学校读者我要写书评

暂无评论

Position Determination from CSI Measurements of Multiple UEs under Unaware Environment 16

Position Determination from CSI Measurements of Multiple UEs...

引用

16th International Conference on signal processing Systems, ICSPS 2024

作者： Wang, Chenchen Ma, Yubin Yu, Fangrui Wen, Hao Liu, Weiyu Wan, Qun Nation Key Laboratory on Blind Signal Processing School of Information and Communication Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China

ISBN: (纸本)9781510689251

In urban environment, communication signals encompass non-line-of-sight (NLOS) paths that contain environmental information. This paper investigates utilizing NLOS component signal to estimate the environment parameters, and uses these environmental parameters to achieve blind UEs (User Equipment) positioning. Specifically, this paper first analyzes the relationship between environmental parameters and the time of arrival (TOA) of NLOS signals. Second, an algorithm is proposed that utilizes the TOA of one-order NLOS signals in uplink signals between distributed UEs and base stations (BS) to estimate environmental parameters via maximum likelihood estimation. Subsequently, leveraging the obtained environmental parameters, achieving the positioning of blind UEs. Finally, numerical simulations validate the effectiveness of the proposed method. © 2025 SPIE.

关键词： Reflection Non line of sight propagation Mirrors Reconstruction algorithms Environmental sensing Mirror surfaces Point clouds LIDAR Monte Carlo methods Numerical simulations

来源：评论

学校读者我要写书评

暂无评论

A Fast Non-Searching Method for Maneuvering Weak Target Detection Using Ubiquitous radar 6

A Fast Non-Searching Method for Maneuvering Weak Target Dete...

引用

6th International Conference on Information Communication and signal processing, ICICSP 2023

作者： Wang, Le Tao, Haihong Yang, Aodi Yang, Fusen Wang, Xiangmeng Xidian University National Key Laboratory of Radar Signal Processing Xi'an China Xi'an Haizhong Electronic Technology Co. Ltd. Xi'an China

ISBN: (纸本)9798350339994

Severe range migration and Doppler frequency migration occur in the long-time coherent integration for maneuvering target using ubiquitous radar, which degrades the radar detection performance and motion parameter estimation. In this paper, a fast non-searching method is applied to counteract range-Doppler coupling and accumulate target energy. First, the range migration is corrected by adopting the fast-time frequency reversal operation, and the non-searching parameter estimation is realized through Lv's distribution. Then, the compensation function with the estimated parameters is employed to match the original echo after pulse compression. Finally, the target energy is focused in the range-Doppler domain along the slow-time dimension. Additionally, compared with other algorithms, the presented algorithm achieves excellent integration and detection performance. Experiment results are provided to verify the effectiveness of this method. © 2023 IEEE.

关键词： Doppler frequency migration Lv's distribution parameter estimation range migration weak target detection

来源：评论

学校读者我要写书评

暂无评论

Compressed Sampling Time Difference of Arrival Estimation Method based on Amplitude and Phase Clustering 16

Compressed Sampling Time Difference of Arrival Estimation Me...

引用

16th International Conference on signal processing Systems, ICSPS 2024

作者： Jiao, Yang Wang, Chenchen Zhai, Jingyu Liu, Yipeng Wan, Qun Nation Key Laboratory on Blind Signal Processing School of Information and Communication Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China

ISBN: (纸本)9781510689251

In the realm of signal processing, modulation signals like PSK (Phase Shift Keying) and QAM (Quadrature Amplitude Modulation) can achieve a substantial signal-to-noise ratio enhancement through aliasing transmission subsequent to clustering and sorting. This paper introduces a novel approach to compressed Time Difference of Arrival (TDOA) estimation, leveraging amplitude-phase clustering signals. The compression matrix is meticulously crafted based on the distinctive amplitude and phase characteristics. Subsequently, the study delves into an analysis of the Cramer-Rao Lower Bound (CRLB) under full sampling conditions. Ultimately, TDOA estimation is carried out employing the Approximate Maximum Likelihood (AML) method. Simulation outcomes underscore the commendable performance of compressed sampling TDOA estimation predicated on amplitude and phase clustering, falling within an order of magnitude of that achieved through full sampling. © 2025 SPIE.

关键词： Quadrature amplitude modulation

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：