检索结果-内蒙古大学图书馆

Anomalous Sound Detection Using Time-Frequency Feature and Mixbatch

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

Refined Modeling and Simulation Method of Raw signal Returns for Space-based radar 3

Refined Modeling and Simulation Method of Raw Signal Returns...

引用

3rd IEEE International Conference on Power, Electronics and Computer Applications, ICPECA 2023

作者： Wang, Zhikang Xi, Xingjuan Liao, Guisheng Lan, Lan Chen, Hui Xidian University National Laboratory of Radar Signal Processing Xi'an China Jiangsu Cyber Space Science and Technology Co. Ltd Nanjing China Southeast University School of Information Science and Engineering Nanjing China

ISBN: (纸本)9781665472784

radar echo refinement simulation is an important means to provide data for space-based radar design demonstration. Most of the current simulation methods ignore the real surface topography and complex geomorphic distribution, and the target characteristics are not sufficiently described, resulting in a shortage of refined radar echo data, which is difficult to meet the demonstration requirements of space-based radar early warning detection system. This paper proposes a more refined simulation method for space-based radar echo, mainly from the background clutter and target echo two aspects of fine modeling: Firstly, based on the real ground battlefield environment fluctuation model and complex geomorphic distribution attributes constructed by GIS (Geographic Information System) data, a refined space-time two-dimensional clutter simulation model of space-based radar is constructed which simultaneously includes the characteristics of terrain fluctuation scattering distribution, terrain occlusion and diffraction, earth-sea clutter distribution and earth rotation. Secondly, based on the efficient modeling technology of ray-tracing high-frequency electromagnetic scattering, the target characteristics in the detection scene are finely modeled, which can fully consider the changes of target characteristics under different conditions. Finally, the rationality of space-time two-dimensional echo signal is verified and analyzed by simulation cases. The echo generated by this method is closer to the real situation, and provide support for the research of space-based radar system design and clutter suppression algorithm. © 2023 IEEE.

关键词： Space-based radar

来源：评论

学校读者我要写书评

暂无评论

A Novel Environment Reconstruction Method based on Distributed NLOS signals 16

A Novel Environment Reconstruction Method based on Distribut...

引用

16th International Conference on signal processing Systems, ICSPS 2024

作者： Yu, Fangrui Li, Junlin Xie, Wei Zhang, Kehao Wan, Qun School of Information and Communication Engineering Nation Key Laboratory on Blind Signal Processing University of Electronic Science and Technology of China Sichuan Chengdu611731 China

ISBN: (纸本)9781510689251

Integrated Sensing and Communication (ISAC) is a rapidly evolving field with extensive application prospects. Environmental reconstruction (ER) is an important content of ISAC. Existing ER techniques often require large sample sizes or specific signals, which significantly limit their application. User Equipments (UEs) widely distributed in the environment and their communication signals provide an adequate measurement basis. However, there are challenges in utilizing communication signals due to limited research, and difficulties in identifying and extracting Non-Line-of-Sight (NLOS) signals. This paper proposes a distributed ER algorithm based on Angle of Arrival (AOA) and Time of Flight (TOF) information of NLOS signals, enabling identification and utilization of various order NLOS signals under complex NLOS conditions. A series of simulation delays validate the effectiveness of the proposed method. © 2025 SPIE.

关键词： Non line of sight propagation Reflection Reconstruction algorithms Mirror pointing signal processing Environmental sensing Wireless communications

来源：评论

学校读者我要写书评

暂无评论

Pseudo-linear Approach to Joint LOS and NLOS Localization 16

Pseudo-linear Approach to Joint LOS and NLOS Localization

引用

16th International Conference on signal processing Systems, ICSPS 2024

作者： Lv, Meng Rou Li, Bei Ning Chang, Xuan Yu Qin, Hao Wan, Qun School of Information and Communication Engineering Nation Key Laboratory on Blind Signal Processing University of Electronic Science and Technology of China Sichuan Chengdu611731 China

ISBN: (纸本)9781510689251

Wireless indoor positioning currently has a wider range of application, and high-precision positioning is considered a key capability after 5G. Angle-of-Arrival (AOA) and Time-of-arrival (TOA) positioning techniques has received widespread attention because it requires only two base stations and does not need synchronization time to complete the positioning. However, the disadvantage is that a small angle measurement error will have a large impact on the positioning accuracy. In this paper, an approach to joint line-of-sight (LOS) and non-line-of-sight (NLOS) localization based on TOA and AOA measurements of both direct and reflected paths was proposed. In addition, a pseudo-linear algorithm was used to provide a closed form solution for localization. The effect of measurement errors on pseudo-linear estimation was analyzed to enhance estimation accuracy and compare it with maximum likelihood estimation and CRLB (Cramér-Rao Lower Bound). Simulation results indicate that the positioning model and error analysis employed in this study are feasible and meet the requirements for high-precision positioning. © 2025 SPIE.

关键词： Time of arrival

来源：评论

学校读者我要写书评

暂无评论

Linear Subspace Surrogate Modeling for Large-Scale Expensive Single/Multi-Objective Optimization

引用

IEEE Transactions on Evolutionary Computation 2023年第3期29卷 1-1页

作者： Si, Langchun Zhang, Xingyi Tian, Ye Yang, Shangshang Zhang, Limiao Jin, Yaochu School of Computer Science and Technology Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei China School of Artificial Intelligence Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei China Faculty of Technology Bielefeld University Bielefeld Germany

Despite that the surrogate-assisted evolutionary algorithms have achieved great success in addressing expensive optimization problems, they still suffer from stiff challenges when the number of dimensions of problems becomes large. The primary reason lies in that it is very hard to build an acceptable surrogate model in the high-dimensional search space with small amounts of evaluated historical data in evolution. To tackle this issue, we suggest an effective surrogate modeling method for large-scale expensive optimization in this paper, where the models are built on a number of linear subspaces instead of the original search space. Specifically, a linear subspace is constructed by a pair of points/solutions which are generated based on the set of elite solutions. For each linear subspace, several historical solutions are first associated according to their distance to the linear subspace, and then a surrogate model is trained by the associated solutions and used to evaluate the offspring. To ensure the exploration and exploitation capacity of the proposed method, these linear subspaces and the surrogate models are updated after a few iterations. Experimental results on CEC’2010 and CEC’2013 single-objective optimization problems with up to 1500 decision variables show that the proposed algorithm is superior over six comparison algorithms. Moreover, we also extend the proposed algorithm to multi-objective optimization problems and verified its competitiveness on problems with up to 1500 decision variables. IEEE

关键词： Evolutionary algorithms

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：