检索结果-内蒙古大学图书馆

5th International Conference on Artificial Intelligence Technologies and Applications, ICAITA 2023

作者： Gao, Xiaoxin Liu, Yongqing Sun, Ming Guan, Wangning Beijing China-Power Information Technology Co. Ltd. Beijing China State Grid Information & Telecommunication Group Co. Ltd. Beijing China North China Electric Power University School of Control and Computer Engineering Beijing China

ISBN: (纸本)9781643684840

This paper presents an intelligent method for analyzing differences in the electricity industry standards by utilizing natural language processing. The main goal of this approach is to detect variations between standards and identify their distinguishing factors, aiming to enhance standardization, regulation, and consistency. Consequently, it will improve the safety and reliability of electricity equipment and systems while reducing production, operation, and management costs. To begin with, the paper constructs a dataset of electricity standard differences based on the open-world assumption theory. Then, it employs a noisy technique to fine-tune the SBERT model, enabling the identification of discrepancies in electricity standard clauses. Lastly, by optimizing the SimCSE model using a relaxed optimal transport distance, the interpretability of the model is enhanced, and a matrix representing text similarity is generated. This matrix facilitates the visualization of discrepancies in clause text. The proposed method achieves precision and recall rates of 81.26% and 82.90%, respectively, for identifying standard discrepancies. By employing this method, not only can the sustainability of the electricity industry be improved, but it also provides valuable data and decision-making references for electricity enterprises to effectively address issues related to standard management and implementation. © 2024 The Authors.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

An improved ant colony optimization for communication network routing problem

An improved ant colony optimization for communication networ...

引用

International Conference on Bio-Inspired Computing: Theories and Applications, BICTA

作者： Dongming Zhao Liang Luo Kai Zhang School of Electronic Engineering and Computer Science Peking University Beijing China Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan China

Ant colony optimization (ACO) is a population-based meta-heuristic for combinatorial optimization problems such as communication network routing problem (CNRP). This paper proposes an improved ant colony optimization (IACO), which adapts a new strategy to update the increased pheromone, called ant-weight strategy, and a mutation operation, to solve CNRP. The simulation result for a benchmark problem is reported and compared to the simple ant colony optimization (ACO).

关键词： Ant colony optimization Communication networks Routing DNA computing Encoding Sequences Algorithm design and analysis Concurrent computing Constraint optimization Design optimization

来源：评论

学校读者我要写书评

暂无评论

Solving the 0–1 multi-objective knapsack problem using self-assembly of DNA tiles

Solving the 0–1 multi-objective knapsack problem using self...

引用

International Conference on Bio-Inspired Computing: Theories and Applications, BICTA

作者： Uzhen Cheng Yufang Huang Zhihua Chen Xuncai Zhang Jin Xu Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan China School of Electronics Engineering and Computer Science Peking University Beijing China

Recently, many researchers have demonstrated that computation by DNA tile self-assembly may be scalable and it is considered as a promising technique in nanotechnology. In this paper, we show how the tile self-assembly process can be used for solving the 0-1 multi-objective knapsack problem by mainly constructing four small systems which are nondeterministic guess system, multiplication system, addition system and comparing system, by which we can probabilistically get the feasible solution of the problem. Our model can successfully perform the 0-1 multi-objective knapsack problem in polynomial time with optimal Theta(1) distinct tile types, parallely and at very low cost.

关键词： Self-assembly Tiles DNA computing Concurrent computing Crystals Assembly Nanotechnology NP-complete problem Nanostructures Cryptography

来源：评论

学校读者我要写书评

暂无评论

Exponential Synchronization for Mobile Robotic Formation: A Hybrid Dynamic Event-Triggered Intermittent control Method

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-10页

作者： Chang, Zhenyu Guo, Ying Zong, Guangdeng Qi, Wenhai Zhao, Xudong School of Control Science and Engineering Tiangong University Tianjin China School of Computer Science Beijing University of Posts and Telecommunications Beijing China School of Engineering Qufu Normal University Rizhao China Faculty of Electronic Information and Electrical Engineering Dalian University of Technology Dalian China

To address the formation tracking issue of mobile robotic systems, this paper constructs a novel hybrid dynamic event-triggered intermittent control strategy, which can achieve the exponential synchronization of the systems. Considering the limited control resources, the intermittent control method is introduced into the distributed control strategy to save resources, and the existing intermittent control model is reconstructed to describe the system model better. A hybrid dynamic event-triggered mechanism is developed by combining the dynamic event-triggered method with the time sampling strategy, eliminating the Zeno phenomenon. The control time sequences in the developed intermittent control strategy are automatically selected by the hybrid dynamic event-triggered sequences, rather than artificially designed in advance, which reduces a certain degree of design complexity. The developed control strategy effectively saves control resources while alleviating the burden of network communication. Sufficient conditions for achieving exponential synchronization formation tracking are provided, and the exponential convergence of the formation error is demonstrated through the proposed lemma. Finally, a control task of multi-mobile robots formation is presented to verify the effectiveness of the theoretical analysis. IEEE

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

Convergence Analysis of Gaussian Belief Propagation for Distributed State Estimation

Convergence Analysis of Gaussian Belief Propagation for Dist...

引用

IEEE Annual Conference on Decision and control

作者： Tianju Sui Damian E. Marelli Minyue Fu Department of Control Science and Engineering Zhejiang University Hangzhou 310013 China School of Electrical Engineering and Computer Science University of Newcastle NSW 2308 Australia

ISBN: (纸本)9781479978878

Belief propagation (BP) is a well-celebrated iterative optimization algorithm in statistical learning over network graphs with vast applications in many scientific and engineering fields. This paper studies a fundamental property of this algorithm, namely, its convergence behaviour. Our study is conducted through the problem of distributed state estimation for a networked linear system with additive Gaussian noises, using the weighted least-squares criterion. The corresponding BP algorithm is known as Gaussian BP. Our main contribution is to show that Gaussian BP is guaranteed to converge, under a mild regularity condition. Our result significantly generalizes previous known results on BP's convergence properties, as our study allows general network graphs with cycles and network nodes with random vectors. This result is expected to inspire further investigation of BP and wider applications of BP in distributed estimation and control.

关键词： State estimation Belief propagation Converge Gauss Gaussian noise Statistical learning Distribute Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Visual tracking based on compressive sensing and particle filter

Visual tracking based on compressive sensing and particle fi...

引用

Canadian Conference on Electrical and computer engineering (CCECE)

作者： Wenhui Huang Jason Gu Xin Ma School of Control Science and Engineering Shandong University Jinan Shandong China Department of Electrical and Computer Engineering Dalhousie University Halifax Nova Scotia Canada

ISBN: (纸本)9781479958306

A robust appearance model is usually required in visual tracking, which can handle pose variation, illumination variation, occlusion and many other interferences occurring in video. So far, a number of tracking algorithms make use of image samples in previous frames to update appearance models. There are many limitations of that approach: 1) At the beginning of tracking, there exists no sufficient amount of data for online update because these adaptive models are data-dependent and 2) in many challenging situations, robustly updating the appearance models is difficult, which often results in drift problems. In this paper, we proposed a tracking algorithm based on compressive sensing theory and particle filter framework. Features are extracted by random projection with data-independent basis. Particle filter is employed to make a more accurate estimation of the target location and make much of the updated classifier. The robustness and the effectiveness of our tracker have been demonstrated in several experiments.

关键词： Target tracking Particle filters Classification algorithms Feature extraction Sparse matrices Filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

A Loopless Distributed Algorithm for Personalized Bilevel Optimization

A Loopless Distributed Algorithm for Personalized Bilevel Op...

引用

IEEE Conference on Decision and control

作者： Youcheng Niu Ying Sun Yan Huang Jinming Xu College of Control Science and Engineering Zhejiang University Hangzhou China School of Electrical Engineering and Computer Science The Pennsylvania State University State College PA

This paper studies a class of personalized distributed bilevel optimization problems over networks, where nodes aim at jointly optimizing the sum of outer-level objectives that depend on the solution of inner-level optimization problems. The existing algorithms for distributed bilevel optimization problems usually require extra computation loops for estimating hypergradients. To facilitate computational efficiency, we develop a loopless distributed algorithm that employs certain steps to approximate the optimal solution of innerlevel optimization problems, and track Hessian-inverse-vector products in a recursive manner. We prove that for stochastic nonconvex-strongly-convex problems, the proposed algorithm achieves the state of the art O(∊ −2 ) communication cost, while improving the computational cost by O(1og(1/∊)). Numerical experiments validate our theoretical findings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Disentangled Feature Distillation for Light Field Super-Resolution with Degradations

Disentangled Feature Distillation for Light Field Super-Reso...

引用

IEEE International Conference on Multimedia and Expo Workshops (ICMEW)

作者： Linjie Zhou Wei Gao Ge Li Hui Yuan Tiesong Zhao Guanghui Yue School of Electronic and Computer Engineering Peking University Shenzhen China School of Control Science and Engineering Shandong University Jinan China Department of Communication Engineering Fuzhou University Fuzhou China School of Biomedical Engineering Shenzhen University Shenzhen China

Light field (LF) super-resolution has achieved remarkable results with the assumption of only downsampling. However, real-world LF scenes contain multiple degradation effects, which makes it difficult for existing methods to deal with hybrid distortions. In this paper, we propose a disentangled feature distillation framework for LF super-resolution with degradations. To reduce the learning difficulty, we propose a feature disentanglement mechanism to split the mixed reconstruction for both super-resolution and denoising into two single task learning processes. We also propose a feature enhancement strategy via knowledge distillation to transfer prior feature of each single reconstruction to our task of mixed reconstruction. Finally, the separate restored representations are fused to reconstruct a clean high-resolution LF. Experiments demonstrate the superior performance of our framework for different scale factors and noise levels. Additionally, our approach can also obtain excellent performance for joint super-resolution and deblurring, showing its gencralization for practical LF super-resolution applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the real-time interactive motion transitions for an articulated body by the Uniform Posture Map

On the real-time interactive motion transitions for an artic...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Jin Ok Kim Bum Ro Lee Chin Hyun Chung School of Electrical and Computer Engineering Sungkyunkwan University Suwon Gyeonggi South Korea Department of Information and Control Engineering Kwangwoon University Seoul South Korea

ISBN: (纸本)0780374371

It is important to reuse existing motion capture data for reduction of the animation producing costs as well as the efficiency of the producing process. Because its motion curve has no control point, however, captured data is difficult to modify interactively. Motion transition is a useful method for reusing existing motion data. It generates a seamless intermediate motion with two short motion sequences. In this paper, the Uniform Posture Map (UPM) is proposed to perform motion transitions. The UPM is organized through the quantization of various postures with an unsupervised learning algorithm; it places the output neurons with similar postures in adjacent positions. Using this property, an intermediate posture of applied two postures is generated; the generating posture is used as a key-frame to make an interpolating motion. The UPM needs fewer computational costs, in comparison with other motion transition algorithms. It provides a control parameter; an animator can not only control the motion simply by adjusting this parameter but also produce animation interactively. The UPM prevents the generating of the invalid output neurons to present unreal postures in the learning phase; thus, it makes more realistic motion curves; finally it contributes to the making of more natural motions. The motion transition algorithm proposed in this paper can be applied to various fields such as real time 3D games virtual reality applications, and web 3D applications.

关键词： Animation Bones Motion control control systems Costs Automatic control Automation Sensor systems Reflection Databases

来源：评论

学校读者我要写书评

暂无评论

Correlation filter-based self-paced object tracking

Correlation filter-based self-paced object tracking

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Wenhui Huang Jason Gu Xin Ma Yibin Li School of Control Science and Engineering Shandong University Jinan Shandong China Department of Electrical and Computer Engineering Dalhousie University Halifax Nova Scotia Canada

Object tracking is an important capability for robots tasked with interacting with humans and the environment, and it enables robots to manipulate objects. In object tracking, selecting samples to learn a robust and efficient appearance model is a challenging task. Model learning determines both the strategy and frequency of model updating, which concerns many details that can affect the tracking results. In this paper, we propose an object tracking approach by formulating a new objective function that integrates the learning paradigm of self-paced learning into object tracking such that reliable samples can be automatically selected for model learning. Sample weights and model parameters can be learned by minimizing this single objective function under the framework of kernelized correlation filters. Moreover, a real-valued error-tolerant self-paced function with a constraint vector is proposed to combine prior knowledge, i.e., the characteristics of object tracking, with information learned during tracking. We demonstrate the robustness and efficiency of our object tracking approach on a recent object tracking benchmark data set: OTB 2013.

关键词： Object tracking Linear programming Reliability Robots Correlation Computational modeling Minimization

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：