检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Tao, Ruijie Qian, Xinyuan Jiang, Yidi Li, Junjie Wang, Jiadong Li, Haizhou Department of Electrical and Computer Engineering National University of Singapore Singapore Department of Computer Science and Technology University of Science and Technology Beijing Beijing100083 China Chinese University of Hong Kong Shenzhen518172 China Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong Shenzhen518172 China Shenzhen Research Institute of Big data Shenzhen518172 China Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore University of Bremen 28359 Germany

Audio-visual target speaker extraction (AV-TSE) aims to extract the specific person’s speech from the audio mixture given auxiliary visual cues. Previous methods usually search for the target voice through speech-lip synchronization. However, this strategy mainly focuses on the existence of target speech, while ignoring the variations of the noise characteristics, i.e., interference speaker and the background noise. That may result in extracting noisy signals from the incorrect sound source in challenging acoustic situations. To this end, we propose a novel selective auditory attention mechanism, which can suppress interference speakers and non-speech signals to avoid incorrect speaker extraction. By estimating and utilizing the undesired noisy signal through this mechanism, we design an AV-TSE framework named Subtraction-and-ExtrAction network (SEANet) to suppress the noisy signals. We conduct abundant experiments by re-implementing three popular AV-TSE methods as the baselines and involving nine metrics for evaluation. The experimental results show that our proposed SEANet achieves state-of-the-art results and performs well for all five datasets. The code can be found in: https://***/TaoRuijie/*** © 2024, CC BY.

关键词： Background noise

来源：评论

学校读者我要写书评

暂无评论

Minimizing the THz Communication Outage Probability with ISAC for Delay-Sensitive Services

Minimizing the THz Communication Outage Probability with ISA...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Sha Xie Marie Siew Lingxiang Li Zhi Chen Tianlong Yang National Key Laboratory of Wireless Communications Electrical and Computer Engineering Carnegie Mellon University Pittsburgh PA USA University of Electronic Science and Technology of China Chengdu China

Integrated sensing and communication (ISAC) in terahertz (THz) networks for delay-sensitive services is regarded as a key enabler for future 6G networks, with ISAC helping to aid beam alignment and improve communication reliability in THz networks. Nevertheless, in ISAC systems, there exists resource and performance tradeoffs amongst sensing, communication and computation. For instance, while better sensing accuracy adds information to aid communication beam alignment, it reduces the temporal resources available for communication. Therefore, in this paper we present a joint sensing, communication and computation model, with a non-uniform frame structure allowing the sensing and communication time to be flexibly adjusted. Based on our model, we formulate an average communication outage probability minimization problem, which optimizes the time and carrier frequency allocation schemes, given constrained resources. We then derive in closed-form the available communication outage probability subject to a given delay threshold, decoupling the computation sub-problem from the original problem. Based on this result, we reformulate the original problem into a joint resource allocation problem between sensing and communication, and solve it by applying the Hungarian algorithm. Numerical results show that our strategy outperforms existing baselines in the average communication outage probability performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Collaborative and Autonomous Black Start: Theory and Implementation

Collaborative and Autonomous Black Start: Theory and Impleme...

引用

Innovative Smart Grid Technologies (ISGT)

作者： Cecilia Klauber Hannah Burroughs Alec Zhou Cyber and Infrastructure Resilience Lawrence Livermore National Laboratory Livermore CA USA Department of Electrical Engineering and Computer Sciences University of California Berkeley Berkeley CA USA

As the number of and capabilities of distributed and inverter-based energy resources increase, there is also an increasing opportunity to utilize such devices to provide resilience to large-scale power outages. During traditional power system restoration, natural hazard disruption or cyber attack of a central controller could cause the necessary processes to halt, but self-determining, decentralized schemes provide new opportunities for robustness. Therefore, a collaborative, autonomous restoration method is proposed and demonstrated in the field on a test microgrid with distributed energy resources. The methodology and test set-up is described and field demonstration results provided. The novel method is shown to effectively black start the microgrid using grid-forming inverter-based resources in a decentralized fashion, enabling future grid reliability even in the face of natural hazards and cyber disruptions.

关键词： Collaboration Process control Microgrids Reliability theory Hazards Robustness Power system reliability

来源：评论

学校读者我要写书评

暂无评论

A Cybertwin-Based Trading Mechanism for Personalized Transmission Services in Cloud Native Networks

引用

IEEE Wireless Communications Letters 2025年

作者： Zeng, Zhiyong Liang, Dandan Qin, Meng Sun, Ruijin Liang, Hui Zhang, Wei Peking University Shenzhen Graduate School School of Electronic and Computer Engineering Shenzhen518055 China Pengcheng Laboratory Shenzhen518055 China Pengcheng Laboratory Department of Strategic and Advanced Interdisciplinary Research Shenzhen518055 China Xidian University Guangzhou institute of technology Guangzhou510555 China Dongguan University of Technology School of Electrical Engineering and Intelligentization Dongguan523808 China University of New South Wales School of Electrical Engineering and Telecommunications SydneyNSW2052 Australia

The Cybertwin-based cloud native network (CCNN) with a cloud-edge-end architecture is to provide personalized user services, which includes both wireless access networks and cloud networks. However, the limited availability of resources and intense user competition present significant challenges. While prior studies have contributed to this issue, they overlook the feasibility of using resources as the trading object in a user-centric approach, particularly in wireless networks. To address this gap, this letter proposes a Cybertwin-based Personalized Transmission Service Trading Mechanism (CPTSTM), employing a one-to-many concurrent bilateral negotiation model for dynamic multi-provider trading. An optimization problem is formulated to minimize user costs by modeling the negotiation as a sequential decision-making process, accounting for individual rationality and system uncertainties. Given restricted and hybrid action spaces, we introduce a Constrained Parameterized Deep Q-learning Network (CPDQN)-based negotiation strategy integrating offer evaluation, acceptance, and bidding strategies. Simulation results confirm the feasibility of the proposed mechanism and demonstrate that the CPDQN-based algorithm outperforms existing methods in terms of trade success rate (nearly 100%) and the number of negotiation rounds (reduced by 75%) while maintaining comparable user utility across various scenarios. © 2012 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

A Resilient Controller for Frequency Regulation of Power Grids against Cyber Attacks

A Resilient Controller for Frequency Regulation of Power Gri...

引用

Renewable Energy and Hydrogen Technologies (GlobConHT), IEEE IAS Global Conference on

作者： Shaohua Yang Keng-Weng Lao Hongxun Hui Yulin Chen Department of Electrical and Computer Engineering State Key Laboratory of Internet of Things for Smart City University of Macau Macao China Hainan Institute of Zhejiang University Sanya China

Maintaining system frequency at a rated value is a fundamental requirement to ensure the stability and security of power grids. However, the advanced frequency regulation process is more cyber-dependent, and raises a cyber-security issue for the power system. Traditional methods cannot avoid the adverse impacts of cyber attacks, which may lead to frequency deviations and, in severe cases, even blackouts. To address this issue, we propose an attack-resilient control algorithm for the smart grid's frequency regulation to defend the system frequency against cyber attacks. The stability of the system with the proposed controller can be guaranteed, which is strictly proved by Lyapunov theorem. Furthermore, the effectiveness of the proposed resilient controller is validated by case studies. The results show that in comparison with the existing methods, the proposed controller can make the system frequency achieve faster recovery with a minor frequency deviation. Specifically, using the proposed method, the maximum frequency deviation can be reduced from 0.17 Hz to approximately 0 Hz even under a cyber attack, which means that the adverse effects of a cyber attack can be almost eliminated. Therefore, the proposed controller can well counter potential cyber attacks, which helps improve the stability of the system frequency.

关键词： Renewable energy sources Hydrogen Power system stability Smart grids Security Frequency control Cyberattack

来源：评论

学校读者我要写书评

暂无评论

Improved Multistep Model Predictive Control for Six-Step Operation of Traction PMSM Drives

Improved Multistep Model Predictive Control for Six-Step Ope...

引用

Workshop on Predictive Control of electrical Drives and Power Electronics (PRECEDE)

作者： Zhenyao Sun Shuai Xu Guangtong Ma Juri Jatskevich State Key Laboratory of Rail Transit Vehicle System Southwest Jiaotong University Chengdu China Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada

Model predictive control (MPC) has recently been considered for many permanent magnet synchronous machine (PMSM) drive applications. However, the conventional MPC lacks accurate current tracking and fast dynamic responses in the overmodulation region and the six-step operation, which limits its application areas. This paper proposes a six-step operation scheme based on MPC for PMSM drives in traction applications. The current trajectory long-horizon prediction and the average current-based objective function are introduced to determine the optimal switching instants. To enhance the method’s precision, a trapezoidal integration rule has been used in the prediction step. The voltage angle control principle is introduced to clamp the voltage vectors. The effectiveness of the proposed method has been validated by detailed studies. The proposed method is demonstrated to have excellent current tracking accuracy and fast dynamic response in six-step operation, which is an advantage over existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data Association for Maneuvering Targets Through a Combined Siamese Network and Xgboost Model

SSRN

引用

SSRN 2023年

作者： Gao, Chang Yan, Junkun Chen, Bo Varshney, Pramod K. Jia, Tianyi Liu, Hongwei National Laboratory of Radar Signal Processing Xidian University Xian710071 China Department of Electrical Engineering and Computer Science Syracuse University NY13244 United States

Data association plays an important role in forming target tracks when false alarms exist. Its accuracy is key to reducing the computational burden of the combinatorial explosion problem inherent to target tracking in environments where false alarms are densely distributed. Traditional methods are usually developed according to some assumed motion models and suffer performance degradation when there is mismatch between assumed models and the actual motion, which may often be the case for maneuvering targets. To cope with this problem, we propose a data-driven method that learns the association criteria directly from data. By use of the domain knowledge and a convolutional Siamese network, features of different attributes present in the observations are extracted. Then the features are fused through the use of XGBoost. Simulation results show that the proposed method performs better than the traditional model-based methods in correlating observations of maneuvering targets and avoiding correlations of false alarms. By visualizing the decision process of the feature fusion model, it is found that the proposed method learns from the data to make comprehensive use of multiple features and does not simply set hard thresholds for the features. The computational complexity is also analyzed both theoretically and experimentally. © 2023, The Authors. All rights reserved.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Multimodal Joint Prediction of Traffic Spatial-Temporal Data with Graph Sparse Attention Mechanism and Bidirectional Temporal Convolutional Network

arXiv

引用

arXiv 2024年

作者： Zhang, Dongran Yan, Jiangnan Polat, Kemal Alhudhaif, Adi Li, Jun Guangdong Provincial Key Laboratory of Intelligent Transportation System School of Intelligent Systems Engineering Sun Yat-sen University Shenzhen518107 China Department of Electrical and Electronics Engineering Faculty of Engineering Bolu Abant Izzet Baysal University Bolu Turkey Department of Computer Science College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al-Kharj11942 Saudi Arabia

Traffic flow prediction plays a crucial role in the management and operation of urban transportation systems. While extensive research has been conducted on predictions for individual transportation modes, there is relatively limited research on joint prediction across different transportation modes. Furthermore, existing multimodal traffic joint modeling methods often lack flexibility in spatial-temporal feature extraction. To address these issues, we propose a method called Graph Sparse Attention Mechanism with Bidirectional Temporal Convolutional Network (GSABT) for multimodal traffic spatial-temporal joint prediction. First, we use a multimodal graph multiplied by self-attention weights to capture spatial local features, and then employ the Top-U sparse attention mechanism to obtain spatial global features. Second, we utilize a bidirectional temporal convolutional network to enhance the temporal feature correlation between the output and input data, and extract inter-modal and intra-modal temporal features through the share-unique module. Finally, we have designed a multimodal joint prediction framework that can be flexibly extended to both spatial and temporal dimensions. Extensive experiments conducted on three real datasets indicate that the proposed model consistently achieves state-of-the-art predictive performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

MSMB-GCN: Multi-scale Multi-branch Fusion Graph Convolutional Networks for 3D Human Pose Estimation

MSMB-GCN: Multi-scale Multi-branch Fusion Graph Convolutiona...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Shanshan Ji Qiwei Meng Wen Wang Zheyuan Lin Te Li Minhong Wan Chunlong Zhang Jason Gu Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Hangzhou China Department of Electrical and Computer Engineering Dalhousie University Halifax NS Canada

In human-robot interaction (HRI), human pose estimation is a necessary technology for the robot to perceive the dynamic environment and make interactive actions. Recently, graph convolutional networks (GCNs) have been increasingly used for 2D to 3D pose estimation tasks since the skeleton topologies can be viewed as graph structures. In this paper, we propose a novel graph convolutional network architecture, Multi-scale Multi-branch Fusion Graph Convolutional Networks (MSMB-GCN), for 3D Human Pose Estimation(3D HPE) task. The proposed model consists of multiple GCN blocks with a multi-branch architecture. This multi-branch architecture enables the model to get multi-scale features for human skeletal representations. The group of GCN blocks, which has strong multi-level feature extraction capabilities, allows the model to learn global and local features, lower-level and higher-level features. Experiment results on the HumanPose benchmark demonstrate that our model outperforms the state-of-the-art and ablation studies validate the effectiveness of our approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Real-World Active Speaker Detection with Multi-Modal Extraction Pre-Training

arXiv

引用

arXiv 2024年

作者： Tao, Ruijie Qian, Xinyuan Das, Rohan Kumar Gao, Xiaoxue Wang, Jiadong Li, Haizhou The Department of Electrical and Computer Engineering National University of Singapore Singapore The Department of Computer Science and Technology University of Science and Technology Beijing Beijing100083 China Fortemedia Singapore138637 Singapore Institute for Infocomm Research A*STAR Singapore The Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong Shenzhen518172 China Shenzhen Research Institute of Big data Shenzhen518172 China The Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore The University of Bremen 28359 Germany

Audio-visual active speaker detection (AV-ASD) aims to identify which visible face is speaking in a scene with one or more persons. Most existing AV-ASD methods prioritize capturing speech-lip correspondence. However, there is a noticeable gap in addressing the challenges from real-world AV-ASD scenarios. Due to the presence of low-quality noisy videos in such cases, AV-ASD systems without a selective listening ability are short of effectively filtering out disruptive voice components from mixed audio inputs. In this paper, we propose a Multi-modal Speaker Extraction-to-Detection framework named ‘MuSED’, which is pre-trained with audio-visual target speaker extraction to learn the denoising ability, then it is fine-tuned with the AV-ASD task. Meanwhile, to better capture the multi-modal information and deal with real-world problems such as missing modality, MuSED is modelled on the time domain directly and integrates the multi-modal plus-and-minus augmentation strategy. Our experiments demonstrate that MuSED substantially outperforms the state-of-the-art AV-ASD methods and achieves 95.6% mAP on the AVA-ActiveSpeaker dataset, 98.3% AP on the ASW dataset, and 97.9% F1 on the Columbia AV-ASD dataset, respectively. We will publicly release the code in due course. © 2024, CC BY.

关键词： Extraction

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：