检索结果-内蒙古大学图书馆

Research Square 2021年

作者： Nie, Rong Du, Wenli Li, Zhongmei Zhou, Zhao He, Shuping Key Laboratory of Smart Manufacturing in Energy Chemical Process East China University of Science and Technology Ministry of Education Shanghai200237 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Electrical Engineering and Automation Anhui University Hefei230601 China School of Electronic Information and Electrical Engineering Chengdu University Chengdu610106 China

This paper is concerned with the asynchronous problem for a class of Markovian jumping Lur’s system (MJLSs) via sliding mode control (SMC) in continuous-time domain. Specifically, the discrete hidden Markovian model (DHMM) is employed to describe the nonsynchronization between the controller modes and the MJLSs modes. In particular, considering the nonlinearity of MJLSs, a novel Lur’e-integral-type sliding surface is constructed. In order to ensure the finite-time stability of sliding mode dynamics and the accessibility of the specified sliding surface, the asynchronous Lur’e-type SMC law of the detector mode is presented. Finally, an example of DC motor is provided to demonstrate the effectiveness of the proposed technique. © 2021, CC BY.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

An Interpretable MRI Reconstruction Network with Two-grid-cycle Correction and Geometric Prior Distillation

arXiv

引用

arXiv 2022年

作者： Fan, Xiaohong Yang, Yin Chen, Ke Zhang, Jianping Dong, Ke The School of Mathematics and Computational Science Xiangtan University Key Laboratory of Intelligent Computing & Information Processing of Ministry of Education Xiangtan411105 China The School of Mathematics and Computational Science Xiangtan University Hunan National Applied Mathematics Center Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan411105 China Centre for Mathematical Imaging Techniques Department of Mathematical Sciences The University of Liverpool Merseyside LiverpoolL6972L United Kingdom The School of Mathematics and Computational Science Xiangtan University Hunan National Applied Mathematics Center Key Laboratory of Intelligent Computing & Information Processing of Ministry of Education Xiangtan411105 China Department of Radiation Oncology Xiangtan Central Hospital Xiangtan411101 China

Although existing deep learning compressed-sensing-based Magnetic Resonance Imaging (CS-MRI) methods have achieved considerably impressive performance, explainability and generalizability continue to be challenging for such methods since the transition from mathematical analysis to network design not always natural enough, often most of them are not flexible enough to handle multi-sampling-ratio reconstruction assignments. In this work, to tackle explainability and generalizability, we propose a unifying deep unfolding multi-sampling-ratio interpretable CS-MRI framework. The combined approach offers more generalizability than previous works whereas deep learning gains explainability through a geometric prior module. Inspired by the multigrid algorithm, we first embed the CSMRI-based optimization algorithm into correction-distillation scheme that consists of three ingredients: pre-relaxation module, correction module and geometric prior distillation module. Furthermore, we employ a condition module to learn adaptively step-length and noise level, which enables the proposed framework to jointly train multi-ratio tasks through a single model. The proposed model not only compensates for the lost contextual information of reconstructed image which is refined from low frequency error in geometric characteristic k-space, but also integrates the theoretical guarantee of model-based methods and the superior reconstruction performances of deep learning-based methods. Therefore, it can give us a novel perspective to design biomedical imaging networks. Numerical experiments show that our framework outperforms state-of-the-art methods in terms of qualitative and quantitative evaluations. Our method achieves 3.18 dB improvement at low CS ratio 10% and average 1.42 dB improvement over other comparison methods on brain dataset using Cartesian sampling mask. Copyright © 2022, 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

Using Deep Active Learning to Save Sensing Cost When Estimating Overall Air Quality 15th

Using Deep Active Learning to Save Sensing Cost When Estimat...

引用

15th International Conference on Green, Pervasive, and Cloud computing, GPC 2020

作者： Lei, Dehao Yu, Zhiyong Li, Peiguan Han, Lei Huang, Fangwan College of Mathematics and Computer Science Fuzhou University Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou China

ISBN: (纸本)9783030642426

Air quality is widely concerned by the governments and people. To save cost, air quality monitoring stations are deployed at only a few locations, and the stations are actuated at partial time. Therefore, it is necessary to study how to actively collect a subset of air quality data to maximize the estimation accuracy of air quality at other locations and time. In order to solve this challenge, we propose the active variational adversarial model (AVAM) that selects the most valuable unlabeled samples through two iterative phases of active learning. In the first phase of our model, a candidate set with unlabeled samples is selected through traditional active learning. In the second phase, variational auto-encoder (VAE) is used to obtain the compressed representation of the candidate set and the training set with labeled samples, then a discriminator based on three-layer neural network is trained from the compressed representation. Finally the discriminator can output the most valuable unlabeled samples from the candidate set. The experimental results show that the AVAM proposed in this paper is superior to active learning models with the first or second phase only. © 2020, Springer Nature Switzerland AG.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Echo State Network Based on L0 Norm Regularization for Chaotic Time Series Prediction 15th

Echo State Network Based on L0 Norm Regularization for Chaot...

引用

15th International Conference on Green, Pervasive, and Cloud computing, GPC 2020

作者： Li, Li Huang, Fangwan Yu, Zhiyong College of Mathematics and Computer Science Fuzhou University Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Key Laboratory of Spatial Data Mining & Information Sharing Ministry of Education Fuzhou China

ISBN: (纸本)9783030642426

The echo state network introduces a large and sparse reservoir to replace the hidden layer of the traditional recurrent neural network, which can solve the gradient-based problem of most recurrent neural networks in the training process. However, there may be an ill-posed problem when the least square method is used to calculate the output weight. In this paper, we proposed an echo state network based on L0 norm regularization. The main idea is to limit the number of output connections to compute the output effectively by removing unimportant ones. The simulation results of the chaotic time series prediction show the effectiveness of the proposed model. © 2020, Springer Nature Switzerland AG.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

An Improved Sparse Representation Classifier Based on Data Augmentation for Time Series Classification 15th

An Improved Sparse Representation Classifier Based on Data A...

引用

15th International Conference on Green, Pervasive, and Cloud computing, GPC 2020

作者： Lu, Juhong Huang, Fangwan Yu, Zhiyong College of Mathematics and Computer Science Fuzhou University Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Key Laboratory of Spatial Data Mining & Information Sharing Ministry of Education Fuzhou China

ISBN: (纸本)9783030642426

Sparse Representation-based Classification (SRC), which has achieved good performance in face recognition and other image classification, has been successfully extended to time series classification in recent years. As a generalization of the nearest subspace classifier, the performance of SRC depends on a rich set of training samples for each class, which can span as many variations of each class as possible under testing conditions. However, due to the difficulty of sample collection, many important applications can only provide a few or even a single sample for each class, which inevitably affects the performance of SRC. To address the problem of insufficient training samples, ESRC (Extended SRC) was proposed to put some samples that reflect the variations within the class into the dictionary, to obtain better generalization ability than SRC for under-sampled face recognition. In this paper, a new approach IESRC (Improved extend sparse representation based classification) is developed by splitting the dictionary into an original dictionary and auxiliary dictionary. The proposed model was first evaluated in 30 baseline data sets in the University of California, Riverside time series classification archive and then applied to classify the effects of aerobic exercise intervention in 24 young hypertensive patients based on the time series of the cardiopulmonary exercise test. Experimental results show that the proposed model can achieve better performance than SRC and ESRC in time series classification. © 2020, Springer Nature Switzerland AG.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A New Energy-Efficient Flooding Broadcast Time Synchronization for Wireless Sensor Networks 6th

A New Energy-Efficient Flooding Broadcast Time Synchronizati...

引用

6th International Conference on Positive Systems, POSTA 2018

作者： Xia, Tengfei He, Shuping Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education School of Electrical Engineering and Automation Anhui University Hefei230601 China

ISBN: (纸本)9783030043261

With the increasing scale of wireless sensor networks (WSN), it inevitably exists some problems in time synchronization, such as the sensitivity to the data of the normal error range, the large energy consumption and the long synchronous convergence time. To solve these problems, a high precision energy efficient broadcast time synchronization algorithm is proposed in this paper. This algorithm firstly sets the membership degree of each class and each sample. Then, by constantly iterating and adjusting the membership degree until convergence, it gets the only cluster by calculating each data to improve the accuracy. Finally, the MATLAB simulation results show that the proposed algorithm can not only improve the time synchronization accuracy, but also reduce the overall energy consumption level of the whole WSN effectively. © 2019, Springer Nature Switzerland AG.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

An Improved Leaky-ESN for Electricity Load Forecasting 15th

An Improved Leaky-ESN for Electricity Load Forecasting

引用

15th International Conference on Green, Pervasive, and Cloud computing, GPC 2020

作者： Lin, Qiaoying Huang, Fangwan Yu, Zhiyong Li, Li College of Mathematics and Computer Science Fuzhou University Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou China

ISBN: (纸本)9783030642426

In the recent decade, recurrent neural networks become a hot research field, with the powerful capability to capture temporal information from time series. To avoid the vanishing/exploding gradient problem caused by the gradient descent algorithm involved in most recurrent networks, echo state network (ESN) was proposed to contain a large but sparse reservoir instead of traditional hidden layers. However, the performance of ESN is very sensitive to the parameters of the reservoir. In this paper, we focus on the improvements of ESN in the background of electricity load forecasting. With the goal of effectively and efficiently computation in the context of pervasive and cloud computing, two versions of adaptive echo state network (AESN) are designed to adopt a modular control strategy to automatically adjust some parameters of the reservoir. Applying AESN on two synthetic datasets and two real world electricity datasets, experimental results demonstrate that AESN is viable. © 2020, Springer Nature Switzerland AG.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

LLR processing of Polar Codes in Concatenation Systems

引用

China Communications 2019年第9期16卷 201-208页

作者： Ya Meng Yi Fang Chuan Zhang Liping Li Key Laboratory of Intelligent Computing and Signal Processing of the Ministry of Education of China Anhui UniversityHefei 230031China School of Information Engineering Guangdong University of TechnologyGuangzhou 510006China National Mobile Communications Research Laboratory Southeast UniversityNanjingChina

This paper studies the decoding performance of low-density parity-check(LDPC)codes in a serial concatenation system with polar codes employing the successive cancellation(SC)*** is known that the absolute incorrect log-likelihood ratio(LLR)values from the SC decoding can be very *** phenomenon dramatically deteriorates the error correcting performance of the outer LDPC *** this paper,the LLR values of polar codes are regulated by a log processing before being sent to the LDPC *** results show that the log processing is an efficient approach with a low optimization complexity compared with the existing procedures to improve the performance of the serial concatenation systems.

关键词： polar codes SC decoding LDPCcodes concatenation

来源：评论

学校读者我要写书评

暂无评论

A CPW-Fed Miniaturized Dual-Band Antenna for 5G Applications

A CPW-Fed Miniaturized Dual-Band Antenna for 5G Applications

引用

International Conference on Numerical Electromagnetic Modeling and Optimization for RF, Microwave, and Terahertz Applications (NEMO)

作者： Xuemei Li Haoran Zhu Zhixiang Huang Key Lab of Intelligent Computing & Signal Processing Ministry of Education AnHui University AnHui University Heifei China

ISBN: (数字)9781728169668

ISBN: (纸本)9781728169675

This paper designs a CPW-fed single-fed single- layer dual-frequency antenna for 5G applications. The overall size of the antenna is only 23×30.5×0.254mm 3 . The antenna consists of an improved folded rectangular slot, a Y-shaped monopole radiator fed by a coplanar waveguide (CPW) with cross-notched slots, and a curved sub-ring slot for isolating frequency bands. The dual frequency characteristics are realized by deformed folded rectangular grooves and Y-shaped monopoles with split ring grooves and cross grooves. By adjusting the position and size of these structures separately, two working frequency bands can be realized. Reduce the size of the antenna by folding the rectangular ground slot to increase the surface current (6.92 λ 0 × 9.17 λ 0 × 0.08 λ 0 ). The simulation results show that the working bandwidth of the antenna is 2.82- 3.84Ghz (31.58%) and 4.48-5.53Ghz (25.68%) respectively. It not only covers 5G bands 3.4-3.8Ghz and 4.8-5.0Ghz, but also covers up to part of the working frequency band of WLAN and WiMAX. The antenna has a good omnidirectional radiation pattern. The antenna is small in size, easy to integrate, and is well-suited to 5G wireless communication equipment.

关键词： Slot antennas 5G mobile communication Dual band Bandwidth Numerical models Coplanar waveguides Antenna radiation patterns

来源：评论

学校读者我要写书评

暂无评论

THE DATABASE AND BENCHMARK FOR THE SOURCE SPEAKER TRACING CHALLENGE 2024

arXiv

引用

arXiv 2024年

作者： Li, Ze Lin, Yuke Yao, Tian Suo, Hongbin Zhang, Pengyuan Ren, Yanzhen Cai, Zexin Nishizaki, Hiromitsu Li, Ming School of Computer Science Wuhan University Wuhan China Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems Duke Kunshan University Kunshan China AI Center OPPO Beijing China Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics CAS China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University China Center for Language and Speech Processing Johns Hopkins University United States Integrated Graduate School of Medicine Engineering and Agricultural Sciences University of Yamanashi 4-4-37 Takeda Yamanashi Kofu400-8510 Japan

Voice conversion (VC) systems can transform audio to mimic another speaker’s voice, thereby attacking speaker verification (SV) systems. However, ongoing studies on source speaker verification (SSV) are hindered by limited data availability and methodological constraints. This paper presents the Source Speaker Tracking Challenge (SSTC) on STL 2024, which aims to fill the gap in the database and benchmark for the SSV task. In this study, we generate a large-scale converted speech database with 16 common VC methods and train a batch of baseline systems based on the MFA-Conformer architecture. In addition, we introduced a related task called conversion method recognition, with the aim of assisting the SSV task. We expect SSTC to be a platform for advancing the development of the SSV task and provide further insights into the performance and limitations of current SV systems against VC attacks. Further details about SSTC can be found here 1 Copyright © 2024, The Authors. All rights reserved.

关键词： Database systems

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：