检索结果-内蒙古大学图书馆

Feature Selection and Feature Learning for High-dimensional Batch Reinforcement Learning: A Survey

International Journal of Automation and computing 2015年第3期12卷 229-242页

作者： De-Rong Liu Hong-Liang Li Ding Wang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences

Tremendous amount of data are being generated and saved in many complex engineering and social systems every *** is significant and feasible to utilize the big data to make better decisions by machine learning techniques. In this paper, we focus on batch reinforcement learning(RL) algorithms for discounted Markov decision processes(MDPs) with large discrete or continuous state spaces, aiming to learn the best possible policy given a fixed amount of training data. The batch RL algorithms with handcrafted feature representations work well for low-dimensional MDPs. However, for many real-world RL tasks which often involve high-dimensional state spaces, it is difficult and even infeasible to use feature engineering methods to design features for value function approximation. To cope with high-dimensional RL problems, the desire to obtain data-driven features has led to a lot of works in incorporating feature selection and feature learning into traditional batch RL algorithms. In this paper, we provide a comprehensive survey on automatic feature selection and unsupervised feature learning for high-dimensional batch RL. Moreover, we present recent theoretical developments on applying statistical learning to establish finite-sample error bounds for batch RL algorithms based on weighted Lpnorms. Finally, we derive some future directions in the research of RL algorithms, theories and applications.

关键词： intelligent control reinforcement learning adaptive dynamic programming feature selection feature learning big data.

来源：评论

学校读者我要写书评

暂无评论

Analysis and Forecasting of Urban Traffic Condition Based on Categorical Data

Analysis and Forecasting of Urban Traffic Condition Based on...

引用

2016年IEEE/INFORMS服务运筹、物流与信息化国际会议

作者： Yuan-yuan Chen Yisheng Lv State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences

Urban traffic prediction is a critical component in intelligent transportation systems for both citizens and traffic management agencies. It is beneficial to know current and future traffic conditions prior a trip or a route for travelers. And it is also very helpful for proactive traffic management for transportation administrative sectors. In this paper, we apply classification techniques to forecast traffic conditions based on categorical data collected from open web maps. To this end, we first collect traffic condition data from AMAP which is a web map, navigation and location based services provider in China. Then we primarily analyze AMAP data with trend analysis and power spectrum analysis. Finally, we employ random walk, na?ve Bayes, decision tree and support vector machine methods to forecast traffic conditions in the future based on historical and current conditions. Experimental results demonstrate that it is feasible to make forecast on traffic conditions with reasonable accuracy.

关键词： urban traffic prediction traffic condition intelligent transportation systems route planning

来源：评论

学校读者我要写书评

暂无评论

Positional Accuracy Analysis of Welding Robot under Mechanism Clearance and Elastic Deformation

Positional Accuracy Analysis of Welding Robot under Mechanis...

引用

World Congress on intelligent control and Automation

作者： Yijian Mao Fengshui Jing Zize Liang Zaojun Fang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences

ISBN: (纸本)9781467384155

Aiming at the special environment of aluminum plant, a dual-arm robot composed of carrying arm, welding arm and sliding rail is developed. It is able to accomplish automatic welding a certain amount of steel sheets between the two ends of the cathode bus in aluminum electrolytic cells. Designed welding robot can be abstracted as a planar mechanism with three revolute joints. Position accuracy, one of the most significant performance evaluations of an industrial robot, is analyzed under joint clearance, drive backlash and elastic deformation. Normally joint clearances and drive backlash are identified as two contributors for positional errors in serial chain manipulator. In our model, elastic deformation is taken into consideration for higher precision. Deformation differs with different position, causing highly coupling degree and computation complexity. Experiments about the effects of the three influence factors are well conducted. Maximum errors influenced by clearance, backlash and deformation are estimated at all possible manipulator positions.

关键词： Manipulators Welding Mathematical model Kinematics Gravity Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Fast Rejecting Mismatches Using Pair-wise Similarity

Fast Rejecting Mismatches Using Pair-wise Similarity

引用

World Congress on intelligent control and Automation

作者： Deheng Qian Xu Yang Yuren Zhang Hong Qiao State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences

ISBN: (纸本)9781467384155

Point matching problem seeks the optimal correspondences between two sets of points. However, the matching result often includes some mismatches that decrease the matching precision. In this paper, we propose a fast algorithm to reject mismatches using pair-wise similarity. The intuition of our algorithm is that the matches should be similar with their neighboring matches due to local consistency. Our algorithm consists of two steps. In the first step, the algorithm eliminates mismatches at the cost of rejecting some correct matches to obtain a refined matching result with a high precision. In the second step, the algorithm regains the correct matches rejected in the first step to improve the recall of the final matching result. The time complexity of the algorithm is O(n~2), which is asymptotically faster than conventional algorithms that reject mismatches. We demonstrate the effectiveness of the proposed algorithm by multiple experiments over widely used datasets.

关键词： MISMATCH complexity classes algorithms recall Mental Recall

来源：评论

学校读者我要写书评

暂无评论

Parallel control and management system for biomimetic robotic fish based on ACP approach

Parallel control and management system for biomimetic roboti...

引用

World Congress on intelligent control and Automation (WCICA)

作者： Jincun Liu Zhengxing Wu Xiang Yang Junzhi Yu State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781467384155

This paper deals with the management and control of a biomimetic robotic fish within a control framework of artificial systems, computational experiments, and parallel execution (ACP). Without the need of precise hydrodynamic modeling and control implementation, we firstly built a functionally equivalent artificial robotic fish by using the Agent technology. When performing a specific task, network-stored control strategies and environment models can be downloaded for computing, testing, and optimizing purposes. By parallel execution, the optimal algorithm can be transferred to the physical robotic fish, where error feedback signals serve to seek the optimal solution in the network. Furthermore, the optimized control strategies, environment models, as well as the newly learned knowledge will be uploaded to the network after accomplishing the mission. At last, we demonstrate this ACP-centered control method through pushball experiment on robotic fish.

关键词： Fish Robot sensing systems Computational modeling Robot kinematics control systems Biological system modeling

来源：评论

学校读者我要写书评

暂无评论

sEMG-based Prediction of Human Lower Extremity Movements by Using a Dynamic Recurrent Neural Network

sEMG-based Prediction of Human Lower Extremity Movements by ...

引用

第28届中国控制与决策会议

作者： Chengkun Cui Gui-Bin Bian Zeng-Guang Hou Xiao-Liang Xie Liang Peng Dongxu Zhang The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

ISBN: (纸本)9781467397155

In this paper,a novel robust nonlinear model is proposed to predict human lower extremity motion based on the multi-channel surface electromyography(sE MG) *** prediction model is established by a data-driven dynamic recurrent neural *** sE MG signals acquired from human lower extremity muscles are used as the inputs of the prediction *** outputs of the model are joint angles of hip,knee and *** from the traditional feedforward network structure,this model has several feedback loops,thus it can take advantage of the output feedback *** validate the effectiveness of the proposed method,five able-bodied people participated in the cycling exercises and relevant data were recorded in real *** performance of the proposed prediction model is compared to those of the feedforward neural network with augmented inputs(FFNNAI) for the motion prediction accuracy and *** results show that the proposed method provides acceptable performance which is clearly better than the FFNNAI-based approach under different experimental schemes.

关键词： sEMG motion prediction dynamic recurrent neural networks human-robot interaction

来源：评论

学校读者我要写书评

暂无评论

Overview of deep learning

Overview of deep learning

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Xuedan Du Yinghao Cai Shuo Wang Leijie Zhang The State Key Laboratory of Management and Control for Complex Systems Institute of Automation CAS Beijing China

ISBN: (纸本)9781509044245

In recent years, deep learning has achieved great success in many fields, such as computer vision and natural language processing. Compared to traditional machine learning methods, deep learning has a strong learning ability and can make better use of datasets for feature extraction. Because of its practicability, deep learning becomes more and more popular for many researchers to do research works. In this paper, we mainly introduce some advanced neural networks of deep learning and their applications. Besides, we also discuss the limitations and prospects of deep learning.

关键词： Decision support systems Erbium Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Travel Time Prediction with LSTM Neural Network

Travel Time Prediction with LSTM Neural Network

引用

IEEE International Conference on intelligent Transportation systems

作者： Yanjie Duan Yisheng Lv Fei-Yue Wang The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences

ISBN: (纸本)9781509018901

Travel time is one of the key concerns among travelers before starting a trip and also an important indicator of traffic conditions. However, travel time acquisition is time delayed and the pattern of travel time is usually irregular. In this paper, we explore a deep learning model, the LSTM neural network model, for travel time prediction. By employing the travel time data provided by Highways England, we construct 66 series prediction LSTM neural networks for the 66 links in the data set. Through model training and validation, we obtain the optimal structure within the setting range for each link. Then we predict multi-step ahead travel times for each link on the test set. Evaluation results show that the 1-step ahead travel time prediction error is relatively small, the median of mean relative error for the 66 links in the experiments is 7.0% on the test set. Deep learning models considering sequence relation are promising in traffic series data prediction.

关键词： Travel time Travelers relative errors Traffic Model trains Neural network TEST SETS

来源：评论

学校读者我要写书评

暂无评论

An overall solution of Virtual Reality Classroom

An overall solution of Virtual Reality Classroom

引用

2016年IEEE/INFORMS服务运筹、物流与信息化国际会议

作者： Xisong Dong The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences Institute of Smart Education Systems Qingdao Academy of Intelligent Industries

Virtual Reality(VR) is a three-dimensional computergenerated virtual world. It is essential to introduced VR technology to education area to develop new teaching mode to improve the efficiency and quality of teaching and learning. Among them, VR classroom has quickly become most dazzling star with its subversive advantage. This paper proposes an overall integration solution of VR classroom, including its composition, its scene design of various disciplines and its main advantage. Finally, a case study of a geography lesson is provided to show its advantages and strong potentiality.

关键词： Virtual Reality Education virtual classroom

来源：评论

学校读者我要写书评

暂无评论

How to “STEAM” Children at Home? Let Children “STEAM” Themselves

How to “STEAM” Children at Home? Let Children “STEAM” Th...

引用

2016年IEEE/INFORMS服务运筹、物流与信息化国际会议

作者： Xiaoyan Gong The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences Institute of Smart Education Systems Qingdao Academy of Intelligent Industries

In this article, I would like to share my daughter's experience on self-STEAM education. In our daily life, she can always find problems and then dream them with her imagination, finally narrows down her solutions to solve problems in her own way. During these problem-solving processes, I noticed that she went through sciences, technology, engineering, arts and mathematics in a very natural way. So I would like to say, STEAM is the way we learn and grow ever since we were born. But later at school, we are trained in a way that subjects are completely disconnected. It might take time to change this situation at school, but at home, as parents, we need to realize that children can discover new things by themselves even from young ages, and provide rich learning environment for them and let them "STEAM " themselves in their own way.

关键词： STEM STEAM education maker education

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：