检索结果-内蒙古大学图书馆

World Congress on Intelligent control and Automation

作者： Yancai Xu Derong Liu Qinglai Wei Biao Luo The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing 100083 China

ISBN: (纸本)9781467384155

Residential energy scheduling on demand side is a hot research area for saving energy and balancing loads. In this paper, an adaptive dynamic programming method is proposed for residential energy scheduling to reduce cost between two adjacent housing units. Two sets of storage batteries and solar stations make energy scheduling problems quite complicated while using traditional methods. The scheduling algorithm is designed based on action dependent heuristic dynamic programming. In the utility function, the weighting function is given to adjust the remaining capacities of batteries. Furthermore, the temperature becomes an input of neural networks to stay close to reality. Simulation results show the effectiveness of saving cost and balancing loads.

关键词： Batteries Dynamic programming Solar energy Discharges (electric) Training Dynamic scheduling

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of the deep learning approach for traffic flow prediction at different times

Performance evaluation of the deep learning approach for tra...

引用

IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI

作者： Yanjie Duan Yisheng Lv Fei-Yue Wang The State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China Qingdao Academy of Intelligent Industries Qingdao Shandong China Beijing Engineering Research Center of Intelligent Systems and Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781509029280

Traffic flow prediction is very important in the deployment of intelligent transportation system. Based on our previous research on deep learning approach for traffic data prediction, we further evaluates the performance of the SAE model for traffic flow prediction at daytime and nighttime. Through 250 experimental tasks training a SAE model and evaluating its performance at daytime and nighttime with 3 different criteria, we obtain the best combination of hyper parameters for each criterion at different times on weekday and non-weekday, respectively. Experimental results show that the MAE and RMSE at daytime are larger than that at nighttime, while the MRE at daytime are smaller than that at nighttime. For different criteria, the hyper parameters of the SAE model should vary accordingly. The results in this paper indicate that in real applications, traffic flow prediction using the deep learning approach can be a combination of multiple SAE models with different parameters suitable for different periods, which is of significance in future research.

关键词： Predictive models Machine learning Training Data models Roads Mathematical model Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-player pursuit–evasion games with one superior evader

引用

Automatica 2016年 71卷 24-32页

作者： Jie Chen Wenzhong Zha Zhihong Peng Dongbing Gu School of Automation Beijing Institute of Technology Beijing 100081 China State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing 100081 China School of Computer Science and Electronic Engineering University of Essex Colchester CO4 3SQ UK

Inspired by the hunting and foraging behaviors of group predators, this paper addresses a class of multi-player pursuit–evasion games with one superior evader, who moves faster than the pursuers. We are concerned with the conditions under which the pursuers can capture the evader, involving the minimum number and initial spatial distribution required as well as the cooperative strategies of the pursuers. We present some necessary or sufficient conditions to regularize the encirclement formed by the pursuers to the evader. Then we provide a cooperative scheme for the pursuers to maintain and shrink the encirclement until the evader is captured. Finally, we give some examples to illustrate the theoretical results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ACP-based social computing and parallel intelligence： Societies 5.0 and beyond

引用

CAAI Transactions on Intelligence Technology 2016年第4期1卷 377-393页

作者： XiaoWang Lingxi Li Yong Yuan Peijun Ye Fei-Yue Wang The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China Qingduo Academy of Intelligent Industries Qingduo 266100 China Department of Electrical and Computer Engineering Purdue School of Engineering and Technology Indiana University-Purdue University Indianapolis Indianapolis IN 46202 USA

Social computing, as the technical foundation of future computational smart societies, has the potential to improve the effectiveness of opensource big data usage, systematically integrate a variety of elements including time, human, resources, scenarios, and organizations in the current cyber-physical-social world, and establish a novel social structure with fair information, equal rights, and a flat configuration. Meanwhile, considering the big modeling gap between the model world and the physical world, the concept of parallel intelligence is introduced. With the help of software-defined everything, parallel intelligence bridges the big modeling gap by means of constructing artificial systems where computational experiments can be implemented to verify social policies, economic strategies, and even military operations. Artificial systems play the role of ＂social laboratories＂ in which decisions are computed before they are executed in our physical society. Afterwards, decisions with the expected outputs are executed in parallel in both the artificial and physical systems to interactively sense, compute, evaluate and adjust system behaviors in real-time, leading system behaviors in the physical system converging to those proven to be optimal in the artificial ones. Thus, the smart guidance and management for our society can be achieved.

关键词： Social computing Societies 5.0 Parallel intelligence Knowledge automation Cyber-physical-social system Artificial societies Computational ex-periments Parallel execution

来源：评论

学校读者我要写书评

暂无评论

Contributions of Social Manufacturing to Sustainable Apparel Industry

Contributions of Social Manufacturing to Sustainable Apparel...

引用

2016年IEEE/INFORMS服务运筹、物流与信息化国际会议

作者： Babak Mohajeri Timo Nyberg Jesse Karjalainen Mark Nelson Gang Xiong Aalto University Department of Industrial Engineering and Management Human Sciences and Technologies Advanced Research Institute (H-STAR)Stanford University The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Science

The global apparel and textile market has been changed considerably during the recent years. At the one hand, new trends and consumer preferences for different styles and fashion products emerge continuously, thus the apparel industry becomes more mass customized. On the other hand, attention to social and environmental sustainability has been dramatically increased in the entire industry. However, the current fast-changing fashion trends result to significant environmental and resource depletion problems in the textile lifecycle. As a result, the apparel industry should consider sustainable manufacturing strategies. The current options such as organic fibers and environmentally safe dyes seem promising. Nonetheless, there are significant challenges for apparel manufacturers and retailers to capitalize sustainability. To address these problems, in this paper, we develop a conceptual model of Social Manufacturing for the apparel industry. We study the current value chain of the apparel industry and identify its challenges from the sustainability's view. Then, we propose a new model to improve the sustainability throughout the value chain of the apparel industry

关键词： Social Manufacturing Apparel Industry Value chain sustainability

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor fusion robust localization for indoor mobile robots based on a set-membership estimator

Multi-sensor fusion robust localization for indoor mobile ro...

引用

IEEE International Conference on Cyber Technology in Automation, control, and Intelligent systems

作者： Bo Zhou Kun Qian Fang Fang Xudong Ma Xianzhong Dai Key Laboratory of Measurement and Control of Complex Systems of Engineering Southeast University Nanjing P. R. China Key Laboratory of Measurement and Control of Complex Systems of Engineering Southeast University China

Autonomous localization is a primary and crucial issue in mobile robot navigation tasks. In this article, the long-distance robust localization problem of indoor mobile robots is studied and solved by a combination style of using a laser scanner and an odometer. Firstly, a point-to-line iterative closest point(PLICP) approach is adopted to match the successive environmental information collected by a laser scanner to estimate the relative pose transformation of the robot. And then the multi-sensor fusion technology based on bounded-error set-membership estimator is proposed to to use scan matching results to correct the cumulative error of the odometer periodically to achieve precious location of the robot in indoor environments. Experimental results show that the accuracy and robustness of the proposed localization system has been improved greatly with respect to the single odometer localization approach.

关键词： Ellipsoids Iterative closest point algorithm Mobile robots Noise measurement Robot kinematics

来源：评论

学校读者我要写书评

暂无评论

Distributed average tracking for multiple nonlinear time-varying signals with output measurements 34

Distributed average tracking for multiple nonlinear time-var...

引用

第三十四届中国控制会议

作者： ZHAO Yu DUAN Zhisheng Liu Yongfang Department of Traffic and Control Engineering School of Automation Northwestern Polytechnical University State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering Science College of Engineering Peking University

ISBN: (纸本)9781467374439

This paper studies the distributed average tracking problem for multiple time-varying signals with nonlinear *** only on relative output measurements, a pair of continuous algorithms with, respectively, static and adaptive coupling strengths are designed and utilized. From the concept of boundary layer approach, the proposed continuous algorithm with static coupling strengths can asymptotically obtain the average value of the multiple reference signals without chattering ***, a simulation example is presented to show the validity of the theoretical results.

关键词： Distributed average tracking,nonlinear dynamics,output feedback,continuous algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimizing Market Segmentation Granularity in RTB Advertising: A Computational Experimental Study

Optimizing Market Segmentation Granularity in RTB Advertisin...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Rui Qin Yong Yuan Fei-Yue Wang Beijing Engineering Research Center of Intelligent Systems and Technology Beijing China The State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China Research Center of Military Computational Experiments and Parallel System National University of Defense Technology Changsha China

ISBN: (纸本)9781509039371

Real Time Bidding (RTB) is a novel business model of online computational advertising with the integration of Internet economy and big data analysis. It can help advertisers achieve the precision marketing through the market segmentation strategies of Demand Side Platforms (DSPs). Based on a mathematical programming approach, this paper studied DSPs' strategies for market segmentation, and established a selection model of the granularity for segmenting RTB advertising markets. We proposed to validate our model using the computational experiment approach, and the experimental results show that: 1) with the increasing refinement of the market segmentation granularity, the total revenue has a tendency of a rise first followed by a decline, 2) the optimal granularity of market segmentation will be significantly influenced by the number of advertisers on the DSP, but less influenced by the number of ad requests. Our findings show the crucial role of market segmentation on the RTB advertising effect, and indicate that the DSPs should adjust their market segmentation strategies according to their total number of advertisers. Our findings also highlight the importance of advertisers as well as the characteristics of the target audiences in DSPs' market segmentation decisions.

关键词： Digital signal processing Computational modeling Advertising Numerical models Big data complex systems Automation

来源：评论

学校读者我要写书评

暂无评论

Exploring Optimal Frequency Caps in Real Time Bidding Advertising

Exploring Optimal Frequency Caps in Real Time Bidding Advert...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

ISBN: (纸本)9781509039371

Benefited from the high-speed development of Internet and the popularization of big data technology, Real Time Bidding (RTB) emerged and developed quickly, and has become one of the most important and popular model for online computational advertising. In the pay-per-impression based RTB advertising, frequency capping is undoubtedly one of the most crucial issues faced by advertisers and Demand Side Platforms (DSPs), since there are generally vast amount of ad requests in RTB markets, among which many may be triggered by the same target audience. As such, choosing the optimal frequency cap considering all the advertisers becomes a critical issue faced by DSPs. Considering that displaying one advertisement multiple number of times to the same user will diminish the advertising effect, we introduce the concept of discount factor and establish an optimization model of frequency capping to seek for the optimal frequency cap for each advertiser. We also design some experiments to validate our proposed model by utilizing the computational experiment approach, and the experimental results show that the optimal frequency cap can be influenced by the values of the discount factors, and higher value of the discount factor can deduce the advertising effect of larger frequency cap. Moreover, when the discount factors of the advertisers take different values, there also exists an optimal frequency cap, at which the advertisers can get the expected maximum revenue in the long run.

关键词： Advertising Digital signal processing Computational modeling Big data Time-frequency analysis Radio spectrum management Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Optimal Self-Learning Cooperative control for Continuous-Time Heterogeneous Multi-Agent systems 34

Optimal Self-Learning Cooperative Control for Continuous-Tim...

引用

第三十四届中国控制会议

作者： WEI Qinglai LIU Derong SONG Ruizhuo The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences School of Automation and Electrical Engineering University of Science and Technology Beijing

ISBN: (纸本)9781467374439

In this paper, an optimal self-learning cooperative control for heterogeneous multi-agent systems by iterative adaptive dynamic programming(ADP) is developed. The main idea is to design an optimal control law by policy iteration based ADP technique which makes all the agents track a given dynamics and simultaneously makes the iterative performance index function reach the Nash equilibrium. The cooperative policy iteration algorithm for graphical differential games is developed to achieve the optimal control law for the agent of each node. Convergence properties are analyzed which make the performance index functions of heterogeneous multi-agent differential graphical games converge to the Nash equilibrium. Simulation example is given to show the effectiveness of the developed optimal self-learning control scheme.

关键词： Adaptive Critic Designs,Adaptive Dynamic Programming,Approximate Dynamic Programming,Heterogeneous Multi-Agents,Graphical Games,Policy Iteration,Synchronization

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：