检索结果-内蒙古大学图书馆

Combining Character-Based Bigrams with Word-Based Bigrams in Contextual Postprocessing for Chinese Script Recognition

引用

ACM Transactions on Asian Language Information Processing 2002年第4期1卷 297-309页

作者： Li, Yuanxiang Tan, Chew Lim Ding, Xiaoqing School of Computing National University of Singapore Kent Ridge 117543 Singapore State Key Lab. of Intelligent Technology and Systems Department of Electronic Engineering Tsinghua University Beijing 100084 P. R China

It is crucial to use contextual information to improve the recognition accuracy of Chinese script in an offline, handwritten Chinese character-recognition system. However, with the increase in the number of candidates given by a character recognizer, contextual postprocessing using a word-based bigram is time-consuming. This article presents a novel contextual postprocessing method that integrates character-based bigram postprocessing with word-based bigram postprocessing in light of the complementary action between Chinese characters and Chinese words. On the basis of isolated character recognition, character-based bigram postprocessing using a forward-backward search is first executed on a big candidate set, which improves both the accuracy and efficiency of the candidate set (the cumulative accuracy of the top ten candidates is greatly boosted). Then, to further improve accuracy, word-based bigram postprocessing (WBP) is executed on a small candidate set. This method obtains high accuracy while paying attention to postprocessing speed at the same time. Experimental results for three Chinese scripts (about 66,000 characters in total) demonstrate the effectiveness of our method: character-based bigram postprocessing improves accuracy from 81.58% to 94.50%, and the cumulative accuracy of the top ten candidates rises from 94.33% to 98.25%. After WBP, 95.75% accuracy is achieved, which is equivalent to the accuracy of WBP executed on a big candidate set. However, our method is more than 100 times faster than that of WBP. © 2002, ACM. All rights reserved.

关键词： Algorithms Chinese character recognition contextual postprocessing efficiency of candidate set forward-backward search Languages Performance statistical language model

来源：评论

学校读者我要写书评

暂无评论

A social choice force model for estimating collective action manipulation 19

A social choice force model for estimating collective action...

引用

19th IFAC World Congress on International Federation of Automatic control, IFAC 2014

作者： Zhang, Jie Zeng, Shuai Liu, Wenli Wang, Tao Wang, Fei-Yue Chen, C.L. Philip State Key Lab. of Management and Control for Complex Systems CASIA Beijing100190 China National University of Defense Technology Hunan410073 China University of Macau China

ISBN: (纸本)9783902823625

For e-commerce websites collective actions have significant influence on the behaviors and decisions of individual customers. In this work, we propose a dynamic utility model for customers in e-commerce by considering a "social choice force" (SCF) effect on utility functions of agents. We apply the Artificial societies, Computational experiments, and Parallel execution (ACP) approach to investigate the short-term efforts of collective action manipulation. Experimental results show that the proposed agent model and algorithm outperform the baseline prediction algorithm and illustrate the effect of collective action manipulation in a group buying directory website. © IFAC.

关键词： Software agents

来源：评论

学校读者我要写书评

暂无评论

Evolution of Cooperation in Snowdrift Game with Multi-Memory Mechanism 42

Evolution of Cooperation in Snowdrift Game with Multi-Memory...

引用

42nd Chinese control Conference, CCC 2023

作者： Liu, Yaojun Liu, Xingwen Tashi, Nyima College of Electrical Engineering Southwest Minzu University Lab. of Complex Systems & Intelligent Control Key Lab. of Electronic Information of State Ethnic Affairs Commission Sichuan Chengdu610225 China Engineering Research Center for Tibetan Information Processing School of Information Science and Technology Tibet University Lhasa850000 China

ISBN: (纸本)9789887581543

Cooperative behavior has been of great concern in evolutionary game researches because of its important role in social life and natural evolution. Since memory can greatly influence the emergence of cooperative behavior, memory-based research on evolutionary games has proliferated in recent years. In the present paper, inspired by the well-known 'Stanford marshmallow experiment' (SME), we proposed a multi-memory mechanism in Snowdrift game (SDG) on spatial lattice networks whose core lies in what follows: Players are divided into two groups according to individual self-control;different memory lengths are set by group and by time in a single realization. The simulation results show that our proposed mechanism promotes cooperation level of the considered evolutionary game. More specifically, as memory length increases to an intermediate length, the cooperation level increases as well. For mechanism with short memory length, the effect of population structure is obvious and small values of adjusting factor can intensively facilitate high-frequency cooperative behavior. These findings may be helpful to understand the connection between population heterogeneity and the emergence of high cooperation. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

Data-driven control of Event-triggered Linear systems 11

Data-driven Control of Event-triggered Linear Systems

引用

11th IEEE Data Driven control and Learning systems Conference, DDCLS 2022

作者： Wang, Xin Sun, Jian Wang, Gang State Key Lab of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing100081 China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

The present paper considers the data-driven control of unknown linear time-invariant discrete-time systems under an event-triggering transmission scheme. To this end, we begin by presenting a dynamic event-triggering scheme (ETS) based on periodic sampling, and a discrete-time looped-functional (DLF) approach, through which a model-based stability condition is derived. Combining the model-based condition with a recent data-based system representation, a data-driven stability criterion in the form of linear matrix inequalities (LMIs) is established, which offers a way of co-designing the ETS matrix and the controller using pre-collected noisy input-state data. Finally, numerical simulations showcase the efficacy of ETS in reducing data transmissions as well as of the proposed co-design methods. © 2022 IEEE.

关键词： Stability criteria

来源：评论

学校读者我要写书评

暂无评论

An Optimal control Based Trajectory Planning Method for Cooperative Merging Maneuvers 3

An Optimal Control Based Trajectory Planning Method for Coop...

引用

3rd International Symposium on intelligent Robotics and systems, ISoIRS 2023

作者： Wang, Qi Ge, Hao Duan, Xuting Zhou, Jianshan School of Transportation Science and Engineering Beihang University State Key Lab of Intelligent Transportation System Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control State Key Laboratory of Air Traffic Management System and Technology Beijing China Nanjing Research Institute of Electronic Engineering State Key Laboratory of Air Traffic Management System and Technology Nanjing China School of Transportation Science and Engineering Beihang University State Key Lab of Intelligent Transportation System Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control Beijing China

ISBN: (纸本)9798350339963

Due to the prediction errors and diverse driving styles of surrounding vehicles, traffic congestion and even accidents can occur in the traffic bottleneck area where vehicles merge into the main road. To ensure that connected and automated vehicles (CAVs) can quickly and efficiently merge into the main road, this paper proposes a cooperative trajectory planning method based on optimal control for vehicle cut-in scenarios. A optimal control model is constructed, and a quintic polynomial is used to generate the initial solution of the optimal control problem to accelerate the solution process and improve the success rate. Finally, The obtained merging trajectory is then synchronized with the movement of vehicles on the main road to optimize their actions and ensure a safe merging process. Joint simulation with Robot Operating System (ROS) and RVIZ is utilized, and the results show that the proposed algorithm can quickly obtain cooperative results, the locally successful merging trajectory meets the requirements of smoothness and safety, and if the solution does not allow merging, the merging vehicle is instructed to terminate the execution. © 2023 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Domain transfer via multiple sources regularization

Domain transfer via multiple sources regularization

引用

18th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, PAKDD 2014

作者： Hu, Shaofeng Ren, Jiangtao Zhang, Changshui Zhang, Chaogui School of Software Sun Yat-sen University Guangzhou China Department of Automation Tsinghua University Beijing China State Key Lab. of Intelligent Technologies and Systems Beijing China China

ISBN: (纸本)9783319066042

The common assumption that training and testing samples share the same distribution is often violated in practice. When this happens, traditional learning models may not generalize well. To solve this problem, domain adaptation and transfer learning try to employ training data from other related source domains. We propose a multiple sources regularization framework for this problem. The framework extends classification model with regularization by adding a special regularization term, which penalizes the target classifier far from the convex combination of source classifiers. Then this framework guarantees the target classifier minimizes the empirical risk in target domain and the distance from the convex combination of source classifier simultaneously. By the way, the weights of the convex combination of source classifiers are embedded into the learning model as parameters, and will be learned through optimization algorithm automatically, which means our framework can identify similar or related domains adaptively. We apply our framework to SVM classification model and develop an optimization algorithm to solve this problem in iterative manner. Empirical study demonstrates the proposed algorithm outperforms some state-of-art related algorithms on real-world datasets, such as text categorization and optical recognition. © 2014 Springer International Publishing.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Measurement techniques on transient process of lightning striking overhead transmission lines

Measurement techniques on transient process of lightning str...

引用

CIGRE Session 46

作者： Xie, S.J. Li, J.M. Zhang, Y. Zeng, R. Zhuang, C.J. Wang, H. State Grid Sichuan Electric Power Research Institute State Grid Sichuan Electric Power Company China State Key Lab. of Control and Simulation of Power Systems and Generation Equipment Tsinghua University China

Obtaining the lightning strike density along an overhead transmission line and identifying the lightning strike types are the key to evaluating the lightning protection performance and proposing reasonable protection schemes of transmission lines. In addition, the waveform characteristics of lightning invasion overvoltage are the basis to establish the standard on the insulation tests of power equipment. Measuring the transient process of lightning striking overhead transmission lines is the basis to carry out the work mentioned above. In this paper, a distributed measurement method of transient current on conductors caused by lightning strikes is proposed. The measuring units are installed on the field conductors of transmission lines every 30 km to obtain less-distorted transient current waveforms. In order to enable measuring units to work in field isolated environment, a power supply coil using Faraday electric-magnetic effect and a wireless communication module is designed and developed. By far, 4776 measuring units have been installed on 597 transmission lines of China's power grid. According to measured transient current waveforms, the lightning strike point can be located using the double-end or single-end travelling wave location method, and the lightning strike type can also be identified. Moreover, a novel measurement method of lightning transient voltage based on the integrated optical electric field sensor (IOEFS) is proposed. In this method, the transient voltage waveforms are inversed from space electric field waveforms measured by IOEFSs. A series of performance tests of IOEFS have been carried out. The test results indicate that the response speed can reach several nanoseconds, and the frequency response can cover 5Hz∼100MHz which is wide enough for the measurement of the lightning transient voltage. In order to test the field measurement effect, the measurement equipment is used to measure a transient voltage when a group of capacitor voltage trans

关键词： Frequency response

来源：评论

学校读者我要写书评

暂无评论

Nonlinear control of robot spatial motion in dynamic environments

Nonlinear control of robot spatial motion in dynamic environ...

引用

Proceedings of 2002 International Conference on Machine Learning and Cybernetics

作者： Miroshnik, I.V. Huang, Xian-Lin Lab. of Cybernetics and Ctrl. Syst. State Inst. Fine Mech. and Optics Sablinskaya 14 Saint-Petersburg 197101 Russia Lab. of Intelligent Control Systems Harbin Institute of Technology Dazhi Street 92 Harbin 150001 China

ISBN: (纸本)0780375084

The paper concerns trajectory problems for stationary, platform-mounted or mobile robots interacting with moving external objects. The main contribution consists of a new task oriented model of special motion in mobile environment and appropriate nonlinear control laws based on geometric methodologies of the nonlinear theory and MEMO system coordination, being an extension of the results on robot spatial motion techniques' and active robotic strategies.

关键词： Motion control

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptation Based Automatic COVID-19 CT Segmentation 7

Unsupervised Domain Adaptation Based Automatic COVID-19 CT S...

引用

7th International Conference on Image, Vision and Computing, ICIVC 2022

作者： Zhang, Zhen Guo, Dalei University of Chinese Academy of Sciences School of Artificial Intelligence China Chinese Academy of Sciences State Key Lab. of Management and Control for Complex Systems Institute of Automation Beijing China

ISBN: (数字)9781665467346

ISBN: (纸本)9781665467346

The outbreak of COVID-19 has brought huge challenges to health systems around the world. Computed Tomography (CT), as an effective method to screen COVID-19, can provide explainable visual information which can be used for the diagnosis and quantification of COVID-19. It will make diagnosis easier and more effective by providing segmentation results of infections from given CT scans. Deep learning based methods can perform well in tasks that have abundant annotated data, while they may suffer from great performance drops when there is little annotated data availab.e. To collect and annotate CT scans of COVID-19 cases is time-consuming and lab.r-intensive, which will demand highly-proficient radiology expertise. To tackle this bottleneck, this paper provides a novel unsupervised domain adaptation method that bridges the gap of distributions between the availab.e annotated CT scans and private CT scans, thus reducing dependence on private annotated CT scans. Quantitative analysis demonstrates the effectiveness of our proposed method, which achieves 20 increments in Dice score compared to models without adaptation. © 2022 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Stochastic stabilization of networked control systems with time-varying sampling periods

Stochastic stabilization of networked control systems with t...

引用

2008 11th IEEE International Conference on Communication Technology, ICCT 2008

作者： Wang, Yan Sun, Zeng Qi School of Automation Science and Electrical Engineering Beihang University Beijing 100084 China State Key Lab. of Intelligent Technology and Systems Department of Computer Science Tsinghua University Beijing 100084 China

ISBN: (纸本)9781424422517

This paper presents a stochastic control method for networked control systems(NCSs) with time-varying sampling periods and random delay. The random delay of the NCS is modelled as intervals governed by a Markov chain. With the switching of the sampling periods, a discrete-time Markovian jump system with parameter uncertainties is presented to model the NCS. By introducing a delay-compensating control term, we construct an augmented state feedback controller. The controller gains can be constructed via LMIs using the stochastic Lyapunov function approach. An example is given to show the proposed results. © 2008 IEEE.

关键词： Networked control systems

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：