检索结果-内蒙古大学图书馆

Atf-Bss: Adaptive Time-Frequency Blind Source Separation for High Reverberation and Echo Environments

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Xie, Yuan Zou, Tao Chen, Ci Sun, Weijun Xie, Shengli School of Mechanical and Electrical Engineering Guangzhou University Guangdong-Hong Kong-Macao Key Laboratory of Multi-scale Information Fusion and Collaborative Optimization Control of Complex Manufacturing Process Guangzhou510006 China School of Automation Guangdong University of Technology Joint International Research Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education of the P.R.C. Guangzhou510006 China School of Automation Guangdong University of Technology Guangdong Key Laboratory of IoT Information Processing Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China School of Automation Guangdong University of Technology Key Laboratory of Intelligent Detection and the IoT in Manufacturing Ministry of Education 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou510006 China

Blind source separation with high reverberation and echoes is an open and extremely challenging issue. Because the room reverberation and echoes have an important influence on acoustics quality, bringing great difficulty to the independent source separation. In the paper, an adaptive time-frequency blind source separation (ATF-BSS) algorithm is designed to deal with the high reverberation and echoes, which can adaptively attenuate the audible echoes and enhance the harmonic structure of the real-world audio signals, achieving excellent separation performance. Firstly, an equalizer network is designed for the room impulse response to weakening audible echoes under the high reverberation and echo environments without changing the perceived timbre. Furthermore, an adaptive time-frequency Wiener-like masking is presented to enhance the dominant signal and attenuate the other components having less energy than the dominant signal. To the best of our knowledge, this is the first attempt to incorporate the advantages of an equalizer network for removing or weakening audible echoes and adaptive time-frequency masking to solve blind separation with high reverberation and echoes. Experimental results on the public audio datasets demonstrate that the proposed ATF-BSS algorithm improves signal intelligibility and achieves much better separation performance than the state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Reverberation

Room Impulse Response Reshaping-Based Blind Source Separation in an Underdetermined Reverberant Environment

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Xie, Yuan Zou, Tao Yang, Junjie Sun, Weijun Xie, Shengli School of Mechanical and Electrical Engineering Guangzhou University Guangdong-Hong Kong-Macao Key Laboratory of Multi-scale Information Fusion and Collaborative Optimization Control of Complex Manufacturing Process Guangzhou510006 China School of Automation Guangdong University of Technology Joint International Research Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education of the P.R.C. Guangzhou510006 China School of Automation Guangdong University of Technology Guangdong Key Laboratory of IoT Information Processing Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China School of Automation Guangdong University of Technology Key Laboratory of Intelligent Detection and the IoT in Manufacturing Ministry of Education 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou510006 China

Blind source separation in an underdetermined reverberation environment is a very challenging issue. The classical method is based on the expectation-maximization algorithm. However, it is limited in a high reverberation environment, resulting in bad or even invalid separation performance. To get rid of this restriction, a room impulse response reshaping-based blind source separation algorithm is designed to solve the signal separation problem in an underdetermined reverberant environment. Firstly, a room impulse response reshaping technology is designed to eliminate the influence of audible echo for the reverberant environment, improving the quality of the received signals. Then, a new mathematical model of time-frequency mixing signals is established to reduce the approximation error of model transformation caused by high reverberation. Furthermore, an improved expectation-maximization algorithm is proposed for real-time update learning rules of model parameters, and then the sources are separated using the estimators provided by the improved expectation maximization method. Experimental results based on source separation of speech and music mixtures demonstrate that the proposed algorithm achieves better separation performance while maintaining much better robustness than the popular expectation-maximization methods. © 2023, The Authors. All rights reserved.

关键词： Blind source separation

Atf-Bss: Adaptive Time-Frequency Blind Source Separation for High Reverberation and Echo Environments

学校读者我要写书评

暂无评论

SSRN 2023年

Blind source separation with high reverberation and echoes is an open and extremely challenging issue. Room reverberation and echoes have an important influence on acoustics quality, causing great difficulty in independent source separation. In the paper, an adaptive time-frequency blind source separation algorithm (ATF-BSS) is designed to deal with high reverberation and echoes, which can adaptively attenuate audible echoes and enhance the harmonic structure of real-world audio signals, achieving excellent separation performance. Firstly, an equalizer network is designed for the room impulse response to weakening audible echoes under high reverberation and echo environments without changing the perceived timbre. Furthermore, an adaptive time-frequency Wiener-like masking is presented to enhance the dominant signal and attenuate the other components that have less energy than the dominant signal. To the best of our knowledge, this is the first attempt to incorporate the advantages of an equalizer network for removing or weakening audible echoes and adaptive time-frequency masking to solve blind separation with high reverberation and echoes. Experimental results on public audio datasets demonstrate that the proposed ATF-BSS algorithm improves signal intelligibility and achieves much better separation performance than state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Reverberation

Atf-Bss: Adaptive Time-Frequency Blind Source Separation for High Reverberation and Echo Environments

学校读者我要写书评

暂无评论

SSRN 2023年

Blind source separation with high reverberation and echoes is an open and extremely challenging issue. Room reverberation and echoes have an important influence on acoustics quality, causing great difficulty in independent source separation. In the paper, an adaptive time-frequency blind source separation algorithm (ATF-BSS) is designed to deal with high reverberation and echoes, which can adaptively attenuate audible echoes and enhance the harmonic structure of real-world audio signals, achieving excellent separation performance. Firstly, an equalizer network is designed for the room impulse response to weakening audible echoes under high reverberation and echo environments without changing the perceived timbre. Furthermore, an adaptive time-frequency Wiener-like masking is presented to enhance the dominant signal and attenuate the other components that have less energy than the dominant signal. ATF-BSS algorithm incorporates the advantages of an equalizer network for removing or weakening audible echoes and adaptive time-frequency masking for high reverberation and echoes scene, improving the performance of blind separation. Experimental results on public audio datasets demonstrate that the proposed ATF-BSS algorithm improves signal intelligibility and achieves much better separation performance than state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Reverberation

control Strategies for Target-Attacker-Defender Games of USVs

学校读者我要写书评

暂无评论

Control Strategies for Target-Attacker-Defender Games of USV...

作者： Bin Lin Lei Qiao Zehua Jia Zhijian Sun Min Sun Weidong Zhang Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information ProcessingMinistry of Education State Key Laboratory of Ocean Engineering Shanghai Jiao Tong University School of Naval ArchitectureOcean and Civil EngineeringShanghai Jiao Tong University Department of Automation Shanghai Jiao Tong University CROSSOCEAN OF SUZHOU TECHNOLOGY CO.ITD

This paper presents two strategies for the targetattacker-defender(TAD) game of unmanned surface vessels(USVs) with bounded velocity and angular *** use nonlinear model predictive control(NMPC) to design strategies which minimize the effort for each agent to win the game.A novel R-C-S trajectory framework is proposed to evaluate the time for USVs to reach the prearranged coordinates,and is applied to both sides' strategies of the TAD *** is assumed that strategies of both sides are unknown to each *** attacker's strategy is based on the dynamic artificial potential field method,which guides the attacker to evasive actions according to the threat level of the *** strategy for the defender and the target guides the two agents to cooperate for the overall interest of the *** performance of the proposed algorithms is tested in numerical simulations,and it turns out that the the strategies perform better than traditional methods.

关键词： USV target-attacker-defender game active defense dynamic artificial potential field

Early Forest Fire Segmentation Based on Deep Learning

学校读者我要写书评

暂无评论

Early Forest Fire Segmentation Based on Deep Learning

Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS), CAA Symposium on

作者： Mengna Li Youmin Zhang Jing Xin Lingxia Mu Ziquan Yu Han Liu Guo Xie Shangbin Jiao Yingmin Yi Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an University of Technology Xi’an Shaanxi China Concordia University Montreal Quebec Canada College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing 211106 China

ISBN: (纸本)9781665401166

Fire segmentation is very important for fire rescue. It can make firefighters get the information on fire area, spread direction and so on, and then help them make quick and effective fire-fighting plan. Therefore, this paper proposes an early forest fire segmentation algorithm based on a deep learning model, named F-Unet, which mainly uses the architecture idea of Unet for reference. F-Unet consists of contraction path, feature fusion layer and expansion path. The contraction path is composed of the first 13 layers of VGG16, which is used to obtain feature maps with different scales. In order to improve the segmentation accuracy of the model, the feature fusion network proposed in this paper is added to the Unet architecture to fuse these feature maps with different scales. The expansion path is used for upsampling these feature maps to restore the size of the original input image and obtain the fire segmentation results. The experimental testing results on the FLAME dataset show that F-Unet can significantly improve the fire segmentation precision, and also prove that the proposed feature fusion network is effective to improve the performance of fire segmentation.

关键词： Deep learning Image segmentation Fuses Fault detection Fires Forestry Safety

Evolution of opinion dynamics with eccentric agents ⁎

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2020年第2期53卷 11012-11017页

作者： Qi Zhang Lin Wang Xiaofan Wang Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China Shanghai Key Laboratory of Power Station Automation Technology School of Mechatronic Engineering and Automation Shanghai University Shanghai China

More recently, there has been a surge of studies that seek mechanisms of the opinion evolution. While many studies have been dedicated to this field, much less attention has been paid to the joint influence of diverse agents on the opinion evolution. In this paper, we proposed an opinion dynamic model based on the Deffuant Weisbuch(DW) model with the existence of eccentric agents. The eccentric agent will change its opinion if the eccentric agent is selected and the opinion difference between two selected agents is beyond the bounded confidence. Previous studies have demonstrated that consensus usually cannot be achieved in the DW model. However, our study suggests that the existence of a single eccentric agent is able to promote consensus in numerical simulations, regardless of any bounded confidence and initial opinion distribution. We further proved that the DW model with the single eccentric agent achieves quasi-consensus. The equilibrium of the system was also proposed. Lastly, we analyzed the final opinion distribution and convergence time with varying bounded confidence and convergence parameters.

关键词： Social network Opinion dynamics Bounded confidence the Deffuant Weisbuch model Quasi-Consensus

On Nash-Stackelberg-Nash Games under Decision-Dependent Uncertainties: Model and Equilibrium

学校读者我要写书评

暂无评论

arXiv

arXiv 2022年

作者： Zhang, Yunfan Liu, Feng Wang, Zhaojian Chen, Yue Feng, Shuanglei Wu, Qiuwei Hou, Yunhe State Key Laboratory of Power Systems Department of Electrical Engineering Tsinghua University Beijing China MOE Key Laboratory of System Control and Information Processing Department of Automation Shanghai Jiao Tong University Shanghai China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong Hong Kong Renewable Energy Research Center China Electric Power Research Institute Beijing China Center for Electric Power and Energy Department of Electrical Engineering Technical University of Denmark Kgs. Lyngby Denmark Shenzhen Institute of Research and Innovation The University of Hong Kong Hong Kong

In this paper, we discuss a class of two-stage hierarchical games with multiple leaders and followers, which is called Nash-Stackelberg-Nash (N-S-N) games. Particularly, we consider N-S-N games under decision-dependent uncertainties (DDUs). DDUs refer to the uncertainties that are affected by the strategies of decision-makers and have been rarely addressed in game equilibrium analysis. In this paper, we first formulate the N-S-N games with DDUs of complete ignorance, where the interactions between the players and DDUs are characterized by uncertainty sets that depend parametrically on the players’ strategies. Then, a rigorous definition for the equilibrium of the game is established by consolidating generalized Nash equilibrium and Pareto-Nash equilibrium. Afterward, we prove the existence of the equilibrium of N-S-N games under DDUs by applying Kakutani’s fixed-point theorem. Finally, an illustrative example is provided to show the impact of DDUs on the equilibrium of N-S-N games. Copyright © 2022, The Authors. All rights reserved.

关键词： Game theory

A Dual Splitting Method for Distributed Economic Dispatch in Multi-energy systems

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2020年第2期53卷 12566-12571页

作者： Zhibin Wang Jinming Xu Shanying Zhu Cailian Chen Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China College of Control Science and Engineering Zhejiang University Hangzhou 310027 China

Multi-energy systems which bring together different forms of energy, such as electricity, gas and heat, to coordinate in the process of supply, transmission and consumption provide much higher flexibility over traditional energy systems in energy utilization. This paper deals with the economic dispatch problem in multi-energy systems in a distributed manner. Each agent optimizes its local objective function with regard to local coupled limits and a global constraint via local communications only. A distributed algorithm is proposed based on duality analysis and splitting *** algorithm adopts a non-linear mapping method to linearize the nonlinearity arisen from coupling relationship among energy carriers. We show that the proposed algorithm converges at a nonergodic rate of O(1/k). Simulations are demonstrated to show the effectiveness of the algorithm.

关键词： Multi-energy systems economic dispatch distributed algorithm duality splitting method