检索结果-内蒙古大学图书馆

6th International Conference on Communications, Information System and computer Engineering, CISCE 2024

作者： Tian, Daoqiang Wang, Bo Xie, Liping College of Computer Science and Technology Taiyuan University of Science and Technology Taiyuan China Chinese Academy of Sciences Institute of Automation Beijing China

ISBN: (纸本)9798350353174

To address the issue of insufficient extraction of global features in CNN monocular depth estimation networks, leading to scale ambiguity and object edge ambiguity in predicted depth maps, this paper presents a pixel-level monocular depth estimation method based on global-local feature fusion. Multiple pre-trained Transformer blocks are employed as encoders to extract global features at multiple scales. Additionally, a global area enhancement module based on pyramid pool is designed to increase the receptive field of the network, providing effective global context prior for in-depth scene analysis and enhancing the network's ability to obtain feature information. Furthermore, a feature fusion module based on large kernel convolution attention is proposed to better utilize global and local features such as shape and texture, refining semantic scenes and improving the global contours of depth maps. Finally, an adaptive distribution depth interval and estimation module are designed according to the requirements of depth features in different regions of the scene. The depth information is estimated by the probability distribution of pixels and linear combination of discrete pixels, resulting in clearer predicted depth maps with detailed and smooth object outlines. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Fixed-time-synchronized control: a system-dimension-categorized approach

引用

science China(Information sciences) 2023年第7期66卷 177-194页

作者： Wanyue JIANG Shuzhi Sam GE Dongyu LI Institute for Future & Shandong Key Laboratory of Industrial Control Technology School of Automation Qingdao University Department of Electrical and Computer Engineering National University of Singapore School of Cyber Science and Technology Beihang University Shanghai Institute of Satellite Engineering

This study addresses the fixed-time-synchronized control problem of perturbed multi-input multioutput(MIMO) systems. In the task of fixed-time-synchronized control, different dimensions of the output signal in MIMO systems are required to reach the desired value simultaneously within a fixed time *** MIMO system is categorized into two cases: the input-dimension-dominant and the state-dimensiondominant cases. The classification is defined according to the dimension of system signals and, more importantly, the capability of converging at the same time. For each kind of MIMO system, sufficient Lyapunov conditions for fixed-time-synchronized convergence are explored, and the corresponding robust sliding mode controllers are designed. Moreover, perturbations are compensated using the super-twisting technique. The brake control of the vertical takeoff and landing aircraft is considered to verify the proposed method for the input-dimension-dominant case, which shows the essential advantages of decreasing the energy consumption and the output trajectory length. Furthermore, comparative numerical simulations are performed to show the semi-time-synchronized property for the state-dimension-dominant case.

关键词： fixed-time-synchronized convergence sliding mode control perturbed MIMO systems

来源：评论

学校读者我要写书评

暂无评论

Parallel Vision ■ Image Synthesis/Augmentation

引用

IEEE/CAA Journal of Automatica Sinica 2024年第3期11卷 782-784页

作者： Wenwen Zhang Wenbo Zheng Qiang Li Fei-Yue Wang the School of Computer Science Shaanxi Normal UniversityXi’an 710119China the School of Computer Science and Technology Wuhan 430070China the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Dear Editor,Scene understanding is an essential task in computer *** ultimate objective of scene understanding is to instruct computers to understand and reason about the scenes as humans *** vision is a research fram... 详细信息

关键词： instru explanation computer

来源：评论

学校读者我要写书评

暂无评论

Node-Decomposition Privacy-Preserving for Finite-Time Secondary Control of DC Microgrids

引用

IEEE Transactions on Smart Grid 2025年第4期16卷 3295-3304页

作者： Wu, Han Zhu, Si-Min Chai, Li Zhu, Zhen-Hua Tian, Yu-Chu Wuhan University of Science and Technology Engineering Research Center of Metallurgical Automation and Measurement Technology School of Artificial Intelligence and Automation Wuhan430081 China Zhejiang University State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Hangzhou310027 China Huzhou Institute of Industrial Control Technology Huzhou China Queensland University of Technology School of Computer Science BrisbaneQLD4001 Australia

In the distributed secondary control of DC microgrids, achieving both rapid convergence and robust information security is critical for enhancing control performance and maintaining power quality. However, current privacy-preserving approaches often compromise either control performance or privacy preservation performance. To address this challenge, this paper presents a node-decomposition privacy-preserving (NDPP) method for fully distributed, finite-time secondary control in DC microgrids. By splitting each node in the communication graph into multiple sub-nodes, the method enhances both convergence speed and privacy preservation without sacrificing control accuracy. Sub-nodes communicate within groups, and the topology of the generated graph is concealed from malicious nodes and eavesdroppers. Theoretical analysis is provided to prove finite-time voltage regulation and current sharing with privacy preservation against malicious nodes and external eavesdroppers. Simulations are conducted to verify the effectiveness of the method in maintaining control performance and power quality. © 2010-2012 IEEE.

关键词： Privacy by design

来源：评论

学校读者我要写书评

暂无评论

An Investigation of Structural Bias in Particle Swarm Optimization 28th

An Investigation of Structural Bias in Particle Swarm Opti...

引用

28th European Conference on Applications of Evolutionary Computation, EvoApplications 2025, held as part of EvoStar 2025

作者： Ibehej, David Kůdela, Jakub Institute of Automation and Computer Science Brno University of Technology Technicka 2 Brno621 00 Czech Republic

ISBN: (纸本)9783031900648

Many complex optimization problems, for which standard methods do not provide good-enough solutions, require the utilization of efficient metaheuristics. However, it has been found that several metaheuristics suffer from different types of structural biases, that may undermine their performance. In this paper, we investigate one of the most used evolutionary computation methods, the Particle Swarm Optimization algorithm. We utilize a recently developed modular framework for the construction of 123,900 parameterizations of PSO and investigate the effect of the different parameter choices on the identified types of structural bias. We also analyze and discuss the impact of the different types of structural bias found in these parameterizations on their performance on functions from a standard test set. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Ontology-Based Semantic Reasoning for Multi-Source Heterogeneous Industrial Devices Using OPC UA

引用

IEEE Internet of Things Journal 2025年第13期12卷 25020-25032页

作者： Bi, Jing Wu, Rina Yuan, Haitao Wang, Ziqi Zhang, Jia Zhou, MengChu Beijing University of Technology College of Computer Science Beijing100124 China Beihang University School of Automation Science and Electrical Engineering Beijing China Southern Methodist University Department of Computer Science Lyle School of Engineering DallasTX75205 United States New Jersey Institute of Technology Department of Electrical and Computer Engineering NewarkNJ07102 United States

The advent of smart manufacturing in Industry 4.0 signifies the era of connections. As a communication protocol, Object linking and embedding for Process Control Unified Architecture (OPC UA) can address most semantic heterogeneity issues. However, its semantics are not formally defined at the application layer. To address the information silo problem caused by semantic heterogeneity, an integration framework named Querying of Ontology Mapping-based OPC UA (QOMOU) is proposed. QOMOU extracts information models of OPC UA servers into resource description framework triples and utilizes web ontology language for semantic enrichment and inference. Then, an Event Class Semantic Similarity Calculation (ECSSC) method is proposed for device type identification, enabling the classification of semantically heterogeneous OPC UA devices. The effectiveness of ECSSC is validated through queries with the RDF query language (SPARQL) protocol in Apache Jena. Experimental results demonstrate that ECSSC improves the accuracy of device identification by approximately 7% compared to benchmark device identification models. Specifically, compared with graph embedding-based methods, QOMOU’s query performance is approximately 13% higher, and its query efficiency is 5% higher on average compared to both structured query and extensible markup languages. Moreover, by employing a keyword-matching algorithm, the query accuracy of the existing heterogeneous data integration scheme is improved by 4% on average. This enhancement can boost the operational efficiency of Internet of Things systems based on the OPC UA architecture. © 2014 IEEE.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Multivariate time series imputation for energy data using neural networks

引用

Energy and AI 2023年第3期13卷 25-35页

作者： Christopher Bulte Max Kleinebrahm Hasan Umitcan Yilmaz Juan Gomez-Romero Institute for Industrial Production(IIP) Chair of Energy EconomicsKarlsruhe Institute of Technology(KIT)Germany Department of Computer Science and Artificial Intelligence University of GranadaSpain

Multivariate time series with missing values are common in a wide range of applications,including energy *** imputation methods often fail to focus on the temporal dynamics and the cross-dimensional correlation *** this paper we propose a two-step method based on an attention model to impute missing values in multivariate energy time ***,the underlying distribution of the missing values in the data is *** information is then further used to train an attention based imputation *** learning the distribution prior to the imputation process,the model can respond flexibly to the specific characteristics of the underlying *** developed model is applied to European energy data,obtained from the European Network of Transmission System Operators for *** different evaluation metrics and benchmarks,the conducted experiments show that the proposed model is preferable to the benchmarks and is able to accurately impute missing values.

关键词： Missing value estimation Multivariate time series Neural networks Attention model Energy data

来源：评论

学校读者我要写书评

暂无评论

Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent

Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Yu, Xiaoyan Luo, Tongxu Wei, Yifan Lei, Fangyu Huang, Yiming Peng, Hao Zhu, Liehuang School of Computer Science and Technology Beijing Institute of Technology China University of Science and Technology Beijing China Beihang University China Institute of Automation Chinese Academy of Sciences China

ISBN: (纸本)9798891761643

Large Language Models (LLMs) have revolutionized open-domain dialogue agents but encounter challenges in multi-character role-playing (MCRP) scenarios. To address this issue, this work presents Neeko, an innovative framework designed for efficient multiple-character role-playing. The proposed framework breaks down the role-playing agent's training process into agent pre-tuning, multiple character playing, and character incremental learning, effectively handling both seen and unseen roles. Neeko employs a dynamic low-rank adapter (LoRA) strategy by training separate LoRA blocks independently for each character, alongside incorporating a gating network for role selection. This design allows Neeko to seamlessly adjust to a wide range of characters, thereby bolstering its adaptability to distinctive attributes, personalities, and speech patterns. As a result, Neeko demonstrates superior performance in MCRP over most existing methods, offering more engaging and versatile user interaction experiences. Code and data are available at https://***/weiyifan1023/Neeko. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Learning Intensity and Optical Flow From High-Speed Spike Stream

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5126-5139页

作者： Zhu, Lin Yan, Weiquan Chang, Yi Tian, Yonghong Huang, Hua Beijing Institute of Technology School of Computer Science and Technology Beijing100081 China Peng Cheng Laboratory Shenzhen518055 China Huazhong University of Science and Technology School of Artificial Intelligence and Automation Wuhan430074 China Peking University School of Computer Science Beijing100081 China Beijing Normal University School of Artificial Intelligence Beijing100875 China

Bio-inspired vision sensors, which emulate the human retina by recording light intensity as binary spikes, have gained increasing interest in recent years. Among them, the spike camera is capable of perceiving fine textures by simulating a small retinal region called the fovea and producing high temporal resolution (20,000 Hz) spatiotemporal spike streams. To bridge the gap between binary spike streams and human vision in high-speed scenes, reconstructing intensity and optical flow from high temporal resolution spikes is particularly important. In this paper, we present a hybrid SNN-ANN network designed for simultaneous intensity and optical flow learning from spike streams. To adaptively extract spatial and temporal features from continuous spike streams, we propose a spiking neuron module with dense connections that efficiently processes both short-term and long-term spike data, while maintaining low power consumption characteristics. Subsequently, we introduce two decoders for optical flow and intensity estimation that complement each other. A temporal-aware warping module, based on flow features, is specifically designed to align the temporal features of the intensity decoder, thereby reducing motion artifacts. Concurrently, improved intensity features contribute to more accurate flow feature predictions, resulting in a mutually beneficial relationship within our network. To evaluate the effectiveness of our proposed network, we conduct experiments on both simulated and real spike datasets. Our network outperforms existing state-of-the-art spike-based reconstruction and optical flow estimation methods, demonstrating its potential for advancing the field of bio-inspired vision sensors. © 1991-2012 IEEE.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Learning Scale-Aware Spatio-temporal Implicit Representation for Event-based Motion Deblurring 41

Learning Scale-Aware Spatio-temporal Implicit Representation...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yu, Wei Li, Jianing Zhang, Shengping Ji, Xiangyang School of Computer Science and Technology Harbin Institute of Technology Weihai China School of Computer Science Peking University Beijing China Department of Automation Tsinghua University Beijing China

Existing event-based motion deblurring methods mostly focus on restoring images with the same spatial and temporal scales as events. However, the unknown scales of images and events in the real world pose great challenges and have rarely been explored. To address this gap, we propose a novel Scale-Aware Spatio-temporal Network (SASNet) to flexibly restore blurred images with event streams at arbitrary scales. The core idea is to implicitly aggregate both spatial and temporal correspondence features of images and events to generalize at continuous scales. To restore highly blurred local areas, we develop a Spatial Implicit Representation Module (SIRM) to aggregate spatial correlation at any resolution through event encoding sampling. To tackle global motion blur, a Temporal Implicit Representation Module (TIRM) is presented to learn temporal correlation via temporal shift operations with long-term aggregation. Additionally, we build a High-resolution Hybrid Deblur (H2D) dataset using a new-generation hybrid event-based sensor, which comprises images with naturally spatially aligned and temporally synchronized events at various scales. Experiments demonstrate that our SASNet outperforms state-of-the-art methods on both synthetic GoPro and real H2D datasets, especially in high-speed motion scenarios. Code and dataset are available at https://***/aipixel/SASNet. Copyright 2024 by the author(s)

关键词： Spatio-temporal data

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：