检索结果-内蒙古大学图书馆

Double-mode Integrated System for Observing Sea-surface Wind Field 2

2nd China International SAR Symposium, CISS 2021

作者： Li, Hang Liu, WenKang Sun, GuangCai Xing, MengDao Zhang, ZhenHua Zhang, Jie Xidian University The National Laboratory of Radar Signal Processing Xi' an China Xidian University Academy of Advanced Interdisciplinary Research Xi' an China Xidian University Academy of Advanced Interdisciplinary Research Xidian University The National Laboratory of Radar Signal Processing Xi' an China Ministry of Natural Resources Beijing Research Institute of Telemetry Ocean Telemetry Technology Innovation Center Beijing China Ministry of Natural Resources First Institute of Oceanography Ministry of Natural Resources Ocean Telemetry Technology Innovation Center Qingdao China

ISBN: (纸本)9787000000001

Spaceborne SAR and scatterometer have their own advantages and weaknesses for measuring sea-surface wind field. The former can measure wind speed with high spatial resolution, but the accuracy is depended on the accuracy of external wind direction. The latter can obtain high-accuracy wind direction and speed simultaneously, but the spatial resolution is relatively low. This paper proposes a new system adopting a single digital antenna to integrate SAR and scatterometer to observe sea-surface wind field simultaneously based on multiple beamforming, and designs the joint time sequence of the transceiver. The proposed double-mode integrated system can not only improve observation accuracy of sea-surface wind field, but also expand observable areas. © 2021 SISE.

关键词： Image resolution

来源：评论

学校读者我要写书评

暂无评论

Bidirectional LSTM with Multiple Input Multiple Fusion Strategy for Speech Emotion Recognition

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer science 2021年第3期48卷 1-6页

作者： Fang, Yuanbo Fu, Hongliang Tao, Huawei Wang, Xia Zhao, Li Ministry of Education Zhengzhou450001 China Ministry of Education Zhengzhou450001 China Lecture of the Key Laboratory of Grain Information Processing and Control Henan University of Technology Ministry of Education Zhengzhou450001 China School of information science and engineering Southeast University Nanjing210096 China Lecture of the School of Information Science and Technology Nantong University Nantong226000 China Professor of the Laboratory of Underwater Acoustic Signal Processing Southeast University Nanjing210096 China

Speech emotion recognition is one of the important challenges in the field of artificial intelligence. In order to further improve the accuracy of speech emotion recognition, a double bidirectional long short-term memory network with multiple input multiple fusion strategy (DBL-MM) for speech emotion recognition is proposed. Firstly, log Mel spectrum feature and frame-level statistical feature are extracted from speech signals, and then the two types of frame-level features are input into two bidirectional LSTM networks for learning simultaneously. Secondly, attention pooling and average pooling are used to fuse the outputs of the two BiLSTM networks to obtain two high-level fusion features which are concatenated and batch normalized later. Finally, a softmax classifier is used to classify emotions. The proposed DBL-MM model simultaneously processes two different types of features and a multiple fusion strategy is used to better learn the subtle changes in emotion. The experimental results on two public datasets show the superiority of this method. © 2021. All Rights Reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

HIGF-Net: Hierarchical information-guided fusion network for polyp segmentation based on transformer and convolution feature learning

引用

Computers in Biology and Medicine 2023年第1期161卷 107038-107038页

作者： Wang, Junwen Tian, Shengwei Yu, Long Zhou, Zhicheng Wang, Fan Wang, Yongtao College of Software Xinjiang University Urumqi830000 China Key Laboratory of Software Engineering Technology Xinjiang University Urumqi830000 China College of Network Center Xinjiang University Urumqi830000 China Signal and Signal Processing Laboratory College of Information Science and Engineering Xinjiang University Urumqi830000 China

Polyp segmentation plays a role in image analysis during colonoscopy screening, thus improving the diagnostic efficiency of early colorectal cancer. However, due to the variable shape and size characteristics of polyps, small difference between lesion area and background, and interference of image acquisition conditions, existing segmentation methods have the phenomenon of missing polyp and rough boundary division. To overcome the above challenges, we propose a multi-level fusion network called HIGF-Net, which uses hierarchical guidance strategy to aggregate rich information to produce reliable segmentation results. Specifically, our HIGF-Net excavates deep global semantic information and shallow local spatial features of images together with Transformer encoder and CNN encoder. Then, Double-stream structure is used to transmit polyp shape properties between feature layers at different depths. The module calibrates the position and shape of polyps in different sizes to improve the model's efficient use of the rich polyp features. In addition, Separate Refinement module refines the polyp profile in the uncertain region to highlight the difference between the polyp and the background. Finally, in order to adapt to diverse collection environments, Hierarchical Pyramid Fusion module merges the features of multiple layers with different representational capabilities. We evaluate the learning and generalization abilities of HIGF-Net on five datasets using six evaluation metrics, including Kvasir-SEG, CVC-ClinicDB, ETIS, CVC-300, and CVC-ColonDB. Experimental results show that the proposed model is effective in polyp feature mining and lesion identification, and its segmentation performance is better than ten excellent models. © 2023

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Stable Extended U-Net for Noise-Robust Speaker Verification

Stable Extended U-Net for Noise-Robust Speaker Verification

引用

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

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

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

With advancements in deep learning, speaker verification systems have significantly improved their performance in noisy environments. Researchers typically demonstrate the effectiveness of their improved models by comparing performance on specific datasets, such as the VoxCeleb benchmark. However, in diverse real-world noise conditions, the out-of-domain generalization ability is also a crucial factor in evaluating a model’s performance improvement. Research on stable learning indicates that eliminating the spurious correlation between training and testing data can enhance the generalization of the model. Building on this idea, we propose an improved speaker verification system with high generalization based on the extended U-Net (ExU-Net). It uses the sample reweighting method from stable learning to eliminate sample correlations and retains more effective speaker information through subpixel convolutions and coordinate attention mechanisms. We validate the effectiveness of this approach through extensive evaluations on VoxCeleb1, VOiCES, and other out-of-domain noise test sets, highlighting its generalization capability and model robustness.

关键词： Training Correlation Attention mechanisms Convolution Data models Stability analysis Robustness Noise measurement Speech processing signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A Machine-Learning Architecture for Sensor Fault Detection, Isolation, and Accommodation in Digital Twins

A Machine-Learning Architecture for Sensor Fault Detection, ...

引用

作者： Darvishi, Hossein Ciuonzo, Domenico Rossi, Pierluigi Salvo Norwegian University of Science and Technology Department of Electronic Systems Trondheim 7491 Norway École Polytechnique Fédérale de Lausanne (EPFL) Signal Processing Laboratory (LTS4) Lausanne 1015 Switzerland University of Naples Federico Ii Department of Electrical Engineering and Information Technologies (DIETI) Naples 80125 Italy Sintef Energy Research Department of Gas Technology Trondheim 7491 Norway

Sensor technologies empower Industry 4.0 by enabling integration of in-field and real-time raw data into digital twins (DTs). However, sensors might be unreliable due to inherent issues and/or environmental conditions. This article aims at detecting anomalies instantaneously in measurements from sensors, identifying the faulty ones and accommodating them with appropriate estimated data, thus paving the way to reliable DTs. More specifically, a real-time general machine-learning-based architecture for sensor validation is proposed, built upon a series of neural-network estimators and a classifier. Estimators correspond to virtual sensors of all unreliable sensors (to reconstruct normal behavior and replace the isolated faulty sensor within the system), whereas the classifier is used for detection and isolation tasks. A comprehensive statistical analysis on three different real-world datasets is conducted and the performance of the proposed architecture is validated under hard and soft synthetically generated faults. © 2001-2012 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

A Long Synthetic Aperture Passive Localization Method Using Two Planes

A Long Synthetic Aperture Passive Localization Method Using ...

引用

IEEE International Conference on radar

作者： Bowei Chen Yuqi Wang Guang-Cai Sun Mengdao Xing Zijing Zhang Xiaoniu Yang National Laboratory of Radar Signal Processing Xidian University Xi'an China Science and Technology on Communication Information Security Control Laboratory Jiaxing China

ISBN: (纸本)9781665468893

A long synthetic aperture passive localization algorithm is proposed in this paper. First of all, the Doppler change rate of signal can be measured by the image contrast and then, grid points are divided within the maximum possible latitude and longitude of the emitter location, the Doppler change rate at each grid point can be calculated by using known position and velocity of the receiver. The grid points at which the calculated Doppler change rate is equal to the value measured by the received signal form an isoline. Two receivers can draw two isolines on the ground and the intersection of the isolines gives estimate of the emitter location.

关键词： Location awareness Passive radar Chirp Estimation Receivers Apertures Position measurement

来源：评论

学校读者我要写书评

暂无评论

Double-Local Conditional Probability Based Fast Calculation Method for Approximation Regions of Probabilistic Rough Sets

SSRN

引用

SSRN 2023年

作者： Xu, Yi Zhou, Meng Sun, Weikang School of Computer Science and Technology Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230601 China

As an extended rough set model, the probabilistic rough sets can effectively process data with noise. How to effectively calculate three approximation regions, is a crucial issue of probability rough sets. Existing calculation methods for approximation regions are based on conditional probability, the time complexity is O(|U||U||C|). In order to improve the computing efficiency of three approximation regions of probabilistic rough sets, we propose a double-local conditional probability based fast calculation method. First, to improve the computational efficiency of equivalence class, we define the double-local equivalence class. Second, based on the double-local equivalence class, we define the double-local conditional probability. Finally, given the probability thresholds and a local equivalence class, the monotonicity of double-local conditional probability is proved, on this basis, a double-local conditional probability based fast calculation method for approximation regions of probabilistic rough sets is presented, and the time complexity is O(MAX(X||U||C|, |XC||U||C|)). Experimental results based on 12 datasets from UCI demonstrate the effectiveness of the proposed method. © 2023, The Authors. All rights reserved.

关键词： Equivalence classes

来源：评论

学校读者我要写书评

暂无评论

Design of a New Sensor Integrating Scatterometer and SAR to Observe Sea Surface Wind Field

Design of a New Sensor Integrating Scatterometer and SAR to ...

引用

2021 CIE International Conference on radar, radar 2021

作者： Li, Hang Liu, Wenkang Sun, Guangcai Xing, Mengdao Zhang, Zhenhua Zhang, Jie Xidian University The National Laboratory of Radar Signal Processing Xi'an China Academy of Advanced Interdisciplinary Research Xidian University Xi'an China Xidian University The National Laboratory of Radar Signal Processing Academy of Advanced Interdisciplinary Research Xidian University Xi'an China Beijing Research Institute of Telemetry Ocean Telemetry Technology Innovation Center Ministry of Natural Resources Beijing China First Institute of Oceanography Ministry of Natural Resources Ocean Telemetry Technology Innovation Center Ministry of Natural Resources Qingdao China

ISBN: (纸本)9781665498142

The sea surface wind vectors in different sea areas such as the general waters and offshore waters, change in different spatial scales and requires different resolutions. Due to different retrieving mechanisms, the scatterometer is suitable for observing wind fields with low resolution in general waters, while the SAR can be applied to obtain wind fields with higher resolution in offshore waters. In order to retrieve wind fields in all kinds of sea areas, this paper proposes a new sensor integrating scatterometer and SAR, which adopts a single digital array antenna, but functions as a SAR and a scatterometer simultaneously through multiple beamforming Besides, this paper designs the operating mode, together with the joint time sequence of the transceiver for two modes to work simultaneously. This proposed concept can benefit the system development in simpler architecture, lighter weight, and lower cost. Moreover, the multiple observation modes working synchronously can improve the retrieving accuracy, and may give birth to some new applications. © 2021 IEEE.

关键词： integrate scatterometer and SAR sea surface wind time sequence design

来源：评论

学校读者我要写书评

暂无评论

An Improved Differential Evolution Algorithm Integrating the Plant Evolutionary Strategy

SSRN

引用

SSRN 2024年

作者： Zhang, Xiaoming Cheng, Hongwei Li, Jun Li, Tingjuan Zhang, Panpan Tian, Ye Institutes of Physical Science and Information Technology Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230601 China Qinghai Institute of Science and Technology Information Xining810008 China School of Computer Science and Technology Anhui University Hefei230601 China

Differential evolution algorithm (DE) and their variants often encounter a decrease in population diversity and convergence rate along with the evolution, resulting in local optima and premature convergence. To address this issue, this paper proposes an improved differential evolution integrating the plant evolutionary strategy, named DEPES, leveraging the exploitation capability of DE and the exploration capability of the plant population distribution evolutionary strategy. First, a tri-subpopulation optimization framework with a mutation strategy is introduced to cope with diversity maintenance, convergence enhancement, and local optima a Cauchy mutation operator based on plant population distribution evolutionary model is employed to enhance the exploration capability of the mutation strategy. Second, a parameter control strategy is performed on the superior and inferior solutions to balance the exploitation and exploration of the population. Third, a covariance matrix-based crossover strategy is designed to minimize interference from local population information, consequently generating high-quality solutions. The superior efficiency of DEPES is fully verified by comparing it with advanced DE-based variants and other algorithms on the IEEE CEC2020 test suite and engineering design problems. © 2024, The Authors. All rights reserved.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

CosDiff: Code-Switching TTS Model Based on A Multi-Task DDIM

CosDiff: Code-Switching TTS Model Based on A Multi-Task DDIM

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Ke Chen Zhihua Huang Kexin Lu Yonghong Yan School of Computer Science and Technology Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi China Chinese Academy of Sciences Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics Beijing China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Although existing Text-To-Speech (TTS) synthesizers are able to generate high-quality speech in most cases, their overall performance is still affected by the distribution of the training data. When processing tasks that involve complex data distributions, such as code-switching TTS, these models might generate speech that sounds unnatural or has low speaker similarity. In this paper, we propose CosDiff, a Code-Switching TTS model based on a multi-task Denoising Diffusion Implicit Model (DDIM), which integrates Voice Conversion (VC) and TTS functionalities. Utilizing the VC function, we construct a single-speaker bilingual dataset for training, achieving a superior code-switching synthesis performance compared to the outcomes of the speaker encoder method, which trains with multiple single-speaker monolingual datasets. In addition, we employ strategies of directly predicting the clean data x 0 and progressive diffusion distillation, further accelerating the model’s sampling process. The experimental results demonstrate the efficacy of this method in improving the quality of generation, increasing sampling speed, and distilling the model.

关键词： Training Speech coding Synthesizers Training data Multitasking Probabilistic logic Data models Text to speech Speech processing Spectrogram

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：