检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Hao Ma Zhiyuan Peng Xu Li Yukai Li Mingjie Shao Qiuqiang Kong Ju Liu School of Information Science and Engineering Shandong University Qingdao China Department of Computer Science North Carolina State University North Carolina USA ARC Lab Tencent PCG Key Laboratory of System and Control AMSS Chinese Academy of Sciences Beijing China The Chinese University of Hong Kong China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extensively annotated parallel audio-text data, which are labor-intensive. We introduce a parallel-data-free training scheme, requiring only unlabelled audio clips for TSE model training by utilizing the contrastive language-audio pre-trained model (CLAP). In a vanilla parallel-data-free training stage, target audio is encoded using the pre-trained CLAP audio encoder to form a condition embedding, while during testing, user language queries are encoded by CLAP text encoder as the condition embedding. This vanilla approach assumes perfect alignment between text and audio embeddings, which is unrealistic. Two major challenges arise from training-testing mismatch: the persistent modality gap between text and audio and the risk of overfitting due to the exposure of rich acoustic details in target audio embedding during training. To address this, we propose a retrieval-augmented strategy. Specifically, we create an embedding cache using audio captions generated by a large language model (LLM). During training, target audio embeddings retrieve text embeddings from this cache to use as condition embeddings, ensuring consistent modalities between training and testing and eliminating information leakage. Extensive experiment results show that our retrieval-augmented approach achieves consistent and notable performance improvements over existing state-of-the-art with better generalizability.

关键词： Training Large language models Training data Signal processing Information leakage Acoustics Data models Data mining Speech processing Overfitting

来源：评论

学校读者我要写书评

暂无评论

On the Approximation of the Quotient of Two Gaussian Densities for Multiple-Model Smoothing

On the Approximation of the Quotient of Two Gaussian Densiti...

引用

International Conference on Information Fusion

作者： Yi Liu Xi Li Le Yang Lyudmila Mihaylova Yanbo Xue Department of Electrical and Computer Engineering University of Canterbury Christchurch NZ State Key Lab of Complex Electromagnetic Environment Effects on Electronics and Information Systems National University of Defense Technology Changsha China Department of Automatic Control and System Engineering University of Sheffield Sheffield UK Career Science Lab Beijing China

The quotient of two multivariate Gaussian densities can be written as an unnormalized Gaussian density, which has been applied in some recently developed multiple-model fixed-interval smoothing algorithms. However, this expression is invalid if instead of being positive definite, the covariance of the unnormalized Gaussian density is indefinite (i.e., it has both positive and negative eigenvalues) or undefined (i.e., computing it requires inverting a singular matrix). This paper considers approximating the quotient of two Gaussian densities in this case using two different approaches to mitigate the caused numerical problems. The first approach directly replaces the indefinite covariance of the unnormalized Gaussian density with a positive definite matrix nearest to it. The second approach computes the approximation through solving, using the natural gradient, an optimization problem with a Kullback-Leibler divergence-based cost function. This paper illustrates the application of the theoretical results by incorporating them into an existing smoothing method for jump Markov systems and utilizing the obtained smoothers to track a maneuvering target.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Calculation and Simulation Analysis of Current Carrying Capacity and Thermal Effect of 500kV Tunnel Cable

Calculation and Simulation Analysis of Current Carrying Capa...

引用

IEEE Conference on Energy Internet and Energy system Integration (EI2)

作者： Ruipeng Liang Qi Huang Olusola Bamisile Jian Li Zhenyuan Zhang Dongsheng Cai School of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China Sichuan Provincial Key Lab of Power System Wide-Area Measurement and Control University of Electronic Science and Technology of China Chengdu China Sichuan Provincial Key Lab of Power System Wide-Area Measurement and Control University of Electronic Science and Technology of China

The Qinghai-Tibet Plateau contains the most abundant clean energy such as hydropower, wind and solar in the world. However, it is very difficult to add overhead transmission lines on the ground due to the complex geographical environment. The large-capacity tunnel cables which is less affected by the earth surface environment, may play an important role on the energy transmission in such area. Based on the cable thermal circuit model, the electrical-magnetic-thermal multiphysics coupling of the cable is modeled in COMSOL Multiphysics. The parameter changes of the material during the temperature rising process, the influence of different ventilation conditions and different current-carrying capacities on the changes of the cable temperature field are quantitatively analyzed. The results show that the proposed model is valid in certain conditions. The research on the current carrying capacity and thermal effect of tunnel cables is of great significance for the transportation and consumption of large-scale clean energy resources.

关键词： Couplings Surface cleaning Analytical models Power cables Transportation Hydroelectric power generation system integration

来源：评论

学校读者我要写书评

暂无评论

On the Gaussian Filtering for Nonlinear Dynamic systems Using Variational Inference

On the Gaussian Filtering for Nonlinear Dynamic Systems Usin...

引用

International Conference on Information Fusion

作者： Yi Liu Xi Li Le Yang Lyudmila Mihaylova Ji Li Department of Electrical and Computer Engineering University of Canterbury Christchurch NZ State Key Lab of Complex Electromagnetic Environment Effects on Electronics and Information Systems National University of Defense Technology Changsha China Department of Automatic Control and System Engineering University of Sheffield Sheffield UK Locaris Electronic Technology Co. Ltd Zhengzhou China

ISBN: (数字)9781737749769

ISBN: (纸本)9798350371420

This paper introduces a new variational Gaussian filtering approach for estimating the state of a nonlinear dynamic system. We first assume that the predictive distribution of the state is Gaussian and derive an iterative method for updating the state posterior in the natural parameter space through KullbackLeibler divergence minimization. The obtained update rule is the same as that of the conjugate-computation variational inference technique in Bayesian learning. The derivation here is simpler and more insightful. We then impose a Wishart prior on the inverse of the state prediction covariance to take into account the impact of approximating the state predictive distribution using a Gaussian density on the state posterior estimation. The prediction covariance is identified jointly with the state using variational inference and the established state posterior update rule to achieve the desired Gaussian filtering. Simulation study examines the performance of the proposed filtering framework in target tracking based on bearing and range measurements.

关键词： Target tracking Smoothing methods Filtering Estimation Filtering algorithms Prediction algorithms Minimization Nonlinear dynamical systems Bayes methods Iterative methods

来源：评论

学校读者我要写书评

暂无评论

The 2022 report of synergetic roadmap on carbon neutrality and clean air for China:Accelerating transition in key sectors

引用

Environmental Science and Ecotechnology 2024年第3期19卷 4-18页

作者： Yu Lei Zhicong Yin Xi Lu Qiang Zhang Jicheng Gong Bofeng Cai Cilan Cai Qimin Chai Huopo Chen Renjie Chen Shi Chen Wenhui Chen Jing Cheng Xiyuan Chi Hancheng Dai Xiangzhao Feng Guannan Geng Jianlin Hu Shan Hu Cunrui Huang Tiantian Li Wei Li Xiaomei Li Jun Liu Xin Liu Zhu Liu Jinghui Ma Yue Qin Dan Tong Xuhui Wang Xuying Wang Rui Wu Qingyang Xiao Yang Xie Xiaolong Xu Tao Xue Haipeng Yu Da Zhang Ning Zhang Shaohui Zhang Shaojun Zhang Xian Zhang Xin Zhang Zengkai Zhang Bo Zheng Yixuan Zheng Jian Zhou Tong Zhu Jinnan Wang Kebin He Center of Air Quality Simulation and System Analysis Chinese Academy of Environmental PlanningBeijing100041China Center for Carbon Neutrality Chinese Academy of Environmental PlanningBeijing100041China Key Laboratory of Meteorological Disaster Ministry of Education/Joint International Research Laboratory of Climate and Environment Change(ILCEC)/Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters(CIC-FEMD)Nanjing University of Information Science&TechnologyNanjing210044China State Key Joint Laboratory of Environment Simulation and Pollution Control School of EnvironmentTsinghua UniversityBeijing100084China Institute for Carbon Neutrality Tsinghua UniversityBeijing100084China Ministry of Education Key Laboratory for Earth System Modelling Department of Earth System ScienceTsinghua UniversityBeijing100084China State Key Joint Laboratory for Environment Simulation and Pollution Control College of Environmental Sciences and Engineering and Center for Environment and HealthPeking UniversityBeijing100871China National Center for Climate Change Strategy and International CooperationBeijing100035China Nansen-Zhu International Research Centre Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing100029China School of Public Health Key Lab of Public Health Safety of the Ministry of Education and Key Lab of Health Technology Assessment of the Ministry of HealthFudan UniversityShanghai200032China School of Economics and Management Beijing University of Chemical TechnologyBeijing100029China Department of Earth System Science University of CaliforniaIrvineCA92697USA National Meteorological Center China Meteorological AdministrationBeijing100081China College of Environmental Sciences and Engineering Peking UniversityBeijing100871China Policy Research Center for Environment and Economy Ministry of Ecology and Environment of the People's Republic of ChinaBeijing100029China Jiangsu Key Laboratory of Atmospheric Environment Monitoring

China is now confronting the intertwined challenges of air pollution and climate *** the high synergies between air pollution abatement and climate change mitigation,the Chinese government is actively promoting synergetic control of these two *** Synergetic Roadmap project was launched in 2021 to track and analyze the progress of synergetic control in China by developing and monitoring key *** Synergetic Roadmap 2022 report is the first annual update,featuring 20 indicators across five aspects:synergetic governance system and practices,progress in structural transition,air pollution and associated weather-climate interactions,sources,sinks,and mitigation pathway of atmospheric composition,and health impacts and benefits of coordinated *** to the comprehensive review presented in the 2021 report,the Synergetic Roadmap 2022 report places particular emphasis on progress in 2021 with highlights on actions in key sectors and the relevant *** milestones include the proportion of non-fossil power generation capacity surpassing coal-fired capacity for the first time,a decline in the production of crude steel and cement after years of growth,and the surging penetration of electric ***,in 2022,China issued the first national policy that synergizes abatements of pollution and carbon emissions,marking a new era for China's pollution-carbon *** changes highlight China's efforts to reshape its energy,economic,and transportation structures to meet the demand for synergetic control and sustainable ***,the country has witnessed a slowdown in carbon emission growth,improved air quality,and increased health benefits in recent years.

关键词： Synergetic roadmap Carbon neutrality Clean air

来源：评论

学校读者我要写书评

暂无评论

Prototype Guided Personalized Federated Intrusion Detection system

Prototype Guided Personalized Federated Intrusion Detection ...

引用

Smart World Congress (SWC), IEEE

作者： Long Cheng Huiru Yan Hanlin Zhou Ying Wang Haichuan Tang Fang Fang State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer Engineering North China Electric Power University Beijing China Chinese Academy of Sciences Institute of Computing Technology Beijing China AI Lab of CRRC Academy Beijing China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

Preventing network attacks and protecting user privacy are consistently hot research topics in the Internet of Things (IoT) and edge computing fields. Recent advancements in Federated Learning (FL) have shown promise in addressing these challenges. FL allows various clients to collaboratively build an intrusion detection system (IDS) without sharing their private data. However, most existing methods train a single intrusion detection model for all clients and assume that the training and test data distribution are identical, leading to unsatisfactory detection accuracy and generalization abilities in practice. To overcome these challenges, this paper introduces a prototype-guided personalized FL approach named PG-FedIDS. We propose two novel mechanisms within this method. Firstly, we utilize class prototypes as auxiliary information carriers to generate personalized models for each client, rather than generating a single global model as in previous works. Secondly, we propose a prototype-guided ensemble learning strategy, which can leverage the global knowledge in prototypes to enhance detection accuracy and generalization abilities for each client. We conduct extensive experiments on two benchmark datasets with different evaluation test settings. The results demonstrate that our PG-FedIDS achieves promising detection accuracy and consistently outperforms other FL baselines.

关键词： Training Privacy Accuracy Federated learning Image edge detection Prototypes Intrusion detection Data models Ensemble learning Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Cloud-edge-device Collaboration Mechanisms of Cloud Manufacturing for Customized and Personalized Products 25

Cloud-edge-device Collaboration Mechanisms of Cloud Manufact...

引用

25th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2022

作者： Yang, Chen Wang, Yingchao Tang, Runze Lan, Shulin Wang, Lihui Shen, Weiming Huang, George Q. Beijing Institute of Technology School of Cyberspace Science and Technology Beijing China Beijing Institute of Electronic System Engineering Beijing China University of Chinese Academy of Science School of Economics and Management Beijing China Kth Royal Institute of Technology Department of Production Engineering Sweden Huazhong University of Science and Technology State Key Lab of Digital Manufacturing Equipment and Technology Wuhan China University of Hong Kong Department of Industrial and Manufacturing Systems Engineering Hong Kong

ISBN: (纸本)9781665405270

With the increasingly developed industry and more comprehensive product offerings, customized and personalized products (CPPs) gradually become a main business model of many enterprises. However, the characteristics of CPPs, such as large differences in product modules and short product delivery cycles, put forward very high demands for the intelligence, flexibility and real-time performance of cloud manufacturing (CMfg). To satisfy the above typical demands, a cloud-edge-device collaborative framework of CMfg is proposed to support distributed data processing and fast decision-making. In the context of Cloud-edge-device collaboration, the vertically and horizontally distributed deployment and update mechanisms of deep learning models (DLMs) are brought forward and analyzed in detail to provide rapid response and high-performance decision-making services for CPPs. In addition, related key technologies are presented to provide references for the technical research direction. © 2022 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Multi-Dimensional Spectrum Data Denoising Based on Tensor Theory 4

Multi-Dimensional Spectrum Data Denoising Based on Tensor Th...

引用

4th IEEE International Conference on Electronics and Communication engineering, ICECE 2021

作者： Zhai, Chengkai Zhang, Wensheng Sun, Jian Zhu, Weihong Ma, Piming Bai, Zhiquan Zhang, Lei Shandong Provincial Key Lab of Wireless Communication Technologies School of Information Science and Engineering Shandong University Qingdao China Shandong Provincial Key Lab of Wireless Communication Technologies Shandong University Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Nanjing University of Aeronautics and Astronautics Qingdao China Department of Traffic Information and Control Engineering Tongji University Shanghai China

ISBN: (纸本)9781728194226

In this paper, we propose a novel multi-dimensional spectrum data denoising scheme from the perspective of tensor theory. The spectrum data is organized into spectrum tensor comprehensively from multiple dimensions. The optimal low rank approximation of the noisy spectrum tensor can be calculated by TUCKALS3 algorithm to reduce noise. Estimating the n-rank of tensor more accurately is necessary to improve the denoising performance of the TUCKALS3 algorithm. Therefore, we further improve the existing minimum description length (MDL) algorithm. Experimental results show that the signal-to-noise ratio (SNR) of the spectrum tensor can be increased by 15dB averagely by applying the enhanced algorithm, even at a higher noise level. The enhanced TUCKALS3 algorithm can effectively denoise multi-dimensional spectrum data and improve the corresponding system performance. ©2021 IEEE

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

LDGCN: An Edge-End Lightweight Dual GCN Based on Single-Channel EEG for Driver Drowsiness Monitoring

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Huang, Jingwei Wang, Chuansheng Huang, Jiayan Fan, Haoyi Xue, Xingsi Zhang, Fuquan Fuzhou University College of Computer and Big Data Fuzhou China Polytechnic University of Catalonia Department of Automatic Control Barcelona Spain Putian University New Engineering Industry College Putian China Fujian University of Technology Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian Fuzhou350118 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China Minjiang University College of Computer and Control Engineering Fuzhou China Sichuan Conservatory of Music Digital Media Art Key Laboratory of Sichuan Province Chengdu China Minjiang University Fuzhou Technology Innovation Center of Intelligent Manufacturing information System Fuzhou China Fuzhou China

Driver drowsiness electroencephalogram (EEG) signal monitoring can promptly alert drivers of their drowsiness in edge-end Consumer Electronics (CE), thereby reducing the probability of traffic accidents. Graph convolutional networks (GCNs) have shown significant advancements in processing the non-stationary, time-varying, and non-Euclidean nature of EEG signals. However, the existing single-channel EEG adjacency graph construction process lacks interpretability, which hinders the ability of GCNs to effectively extract adjacency graph features, thus affecting the performance of drowsiness monitoring. To address this issue, we propose an edge-end Lightweight Dual Graph Convolutional Network (LDGCN). Specifically, we are the first to incorporate neurophysiological knowledge to design a Baseline Drowsiness Status Adjacency Graph (BDSAG), which characterizes driver drowsiness status. Additionally, to express more features within limited EEG data, we introduce the Augmented Graph-level Module (AGM). This module captures global and local information at the graph level, ensuring that BDSAG features remain intact while enhancing effective feature expression capability. To further enhance the application of CE, we apply Adaptive Pruning Optimization (APO) to the channels and neurons of LDGCN, which nearly halves the inference latency. Experiments on benchmark datasets demonstrate that LDGCN offers the best trade-off between monitoring performance and hardware resource utilization, outperforming existing state-of-the-art algorithms. © 1975-2011 IEEE.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Coordinated Guiding Vector Field Design for Ordering-Flexible Multi-Robot Surface Navigation

arXiv

引用

arXiv 2024年

作者： Hu, Bin-Bin Zhang, Hai-Tao Yao, Weijia Sun, Zhiyong Cao, Ming The School of Artificial Intelligence and Automation The Engineering Research Center of Autonomous Intelligent Unmanned Systems The Key Laboratory of Image Processing and Intelligent Control The State Key Lab of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China The School of Robotics Hunan University Hunan410082 China The Institute of Engineering and Technology University of Groningen Groningen9747 AG Netherlands Department of Electrical Engineering Eindhoven University of Technology Netherlands

We design a distributed coordinated guiding vector field (CGVF) for a group of robots to achieve ordering-flexible motion coordination while maneuvering on a desired two-dimensional (2D) surface. The CGVF is characterized by three terms, i.e., a convergence term to drive the robots to converge to the desired surface, a propagation term to provide a traversing direction for maneuvering on the desired surface, and a coordinated term to achieve the surface motion coordination with an arbitrary ordering of the robotic group. By setting the surface parameters as additional virtual coordinates, the proposed approach eliminates potential singularity of the CGVF and enables both the global convergence to the desired surface and the maneuvering on the surface from all possible initial conditions. The ordering-flexible surface motion coordination is realized by each robot to share with its neighbors only two virtual coordinates, i.e. that of a given target and that of its own, which reduces the communication and computation cost in multi-robot surface navigation. Finally, the effectiveness of the CGVF is substantiated by extensive numerical simulations. Copyright © 2024, The Authors. All rights reserved.

关键词： Navigation

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：