检索结果-内蒙古大学图书馆

International Conference on Information Science and Technology (ICIST)

作者： Zhentao Tang Dongbin Zhao Yuanheng Zhu Ping Guo The State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China

StarCraft II is one of the most popular real-time strategy games and has become an important benchmark for AI research as it provides a complex environment with numerous challenges. The build order problem is one of the key challenges which concern the order and type of buildings and units to produce based on current game situation. In contrast to existing hand-craft methods, we propose two reinforcement learning based models: Neural Network Fitted Q-Learning (NNFQ) and Convolutional Neural Network Fitted Q-Learning (CNNFQ). NNFQ and CNNFQ have been applied into a simple bot for fighting against the enemy race. Experimental results show that both these two models are capable of finding the most effective production sequence to defeat the opponent.

关键词： Games Buildings Data structures Boolean functions Training Learning (artificial intelligence) Neural networks

来源：评论

学校读者我要写书评

暂无评论

Pipeline Scene Reconstruction Based on Image Mosaicing

Pipeline Scene Reconstruction Based on Image Mosaicing

引用

第37届中国控制会议

作者： Zishu Gao En Li Lei Yang Zize Liang The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences The University of Chinese Academy of Sciences

Robots should be able to perceive the surroundings in the complicated and unknown environment before carrying out further ***,environmental reconstruction is the premise for the robot autonomous *** this paper,a pipeline scene reconstruction method based on image mosaicing is proposed for cylindrical pipeline *** a wide-angle camera,the image sequence of the pipeline environment is *** order to obtain intuitional environmental information around the pipeline,an unwrapped model is proposed to unfold the distorted raw image to corrected flat surface *** utilizing ORB(Oriented FAST and Rotated BRIEF) and weighted smoothing blending algorithm,image mosaicing with sequence frames are performed to realize scene *** experimental results demonstrate that the proposed algorithm can achieve seamless stitching of pipeline image,and the number of keypoints is prominently decreased in comparison to that of FAST operator,while the quality of keypoints is *** with the classical SIFT and SURF operator,the time-consuming of the algorithm is improved about 2.5 times,which is more suitable for real-time environmental reconstruction.

关键词： scene reconstruction image unwrapping ORB image mosaicing

来源：评论

学校读者我要写书评

暂无评论

Transaction Queuing Game in Bitcoin BlockChain

Transaction Queuing Game in Bitcoin BlockChain

引用

2018 IEEE Intelligent Vehicles Symposium, IV 2018

作者： Li, Juanjuan Yuan, Yong Wang, Shuai Wang, Fei-Yue State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Qingdao Academy of Intelligent Industries Qingdao China University of Chinese Academy of Sciences Beijing China Research Center of Military Computational Experiments and Parallel Systems National University of Defense Technology Changsha China

ISBN: (纸本)9781538644522

Bitcoin is a novel protocol with the potential of enabling a decentralized and trustless cryptographic currency, and its underlying technology named blockchain operates on a worldwide basis via a complex set of rules originally proposed by Nakomoto in 2008. In Bitcoin blockchain, miners provide computational services (i.e. mining) to get profits from the fixed rewards of newly found block and also transaction fees from recording the users' transactions to the blocks. With the decreasing of the fixed new block reward, transaction fees will play the role as the main profit source of miners, thus provide important supports for the sustainability and vitality of the Bitcoin system. Therefore, it is of great necessity to research transaction fees. In this paper, we investigate transaction fees in a queuing game with non-preemptive priority, in which both the miners' mining rewards and the users' time cost are highlighted. Then, we conduct theoretical analysis of the game, getting five types of Nash equilibria of the game. We also find that the over-long waiting time will bring negative marginal profits on transaction fees to some users with low time cost, therefore, they will not be willing to offer transaction fees. © 2018 IEEE.

关键词： Miners

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Scene Text Detection Based on Convolutional Neural Network

Multi-Scale Scene Text Detection Based on Convolutional Neur...

引用

Chinese Automation Congress (CAC)

作者： Yan-Feng Lu Ai-Xuan Zhang Yi Li Qian-Hui Yu Hong Qiao The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China China Academy of Aerospace Standardization and Product Assurance Beijing China School of Information Engineering Nanchang University Nanchang China College of Information and Communication Engineering Harbin Engineering University Harbin China

Faster R-CNN has advantages in object detection task. But in face of the variability of text and interference of the external factors, it cannot achieve perfect detection results in natural scene text detection. Moreover, the text detection algorithms based on deep learning need to use large data sets to train the network, while in some special scenarios where a mass of samples cannot be obtained, the performance of these algorithms is likely to be limited. How to accurately detect text in natural scene based on small data sets is a challenging issue. To address this issue, a multi-scale text feature extraction network with feature pyramid based on Faster R-CNN is proposed, which can accurately and comprehensively express complex and changeable text features in natural scenes even in the small data cases. Experiment results show that the proposed MSTD method is very competitive with existing related architectures.

关键词： Feature extraction Training Proposals Convolutional neural networks Object detection Task analysis Detection algorithms

来源：评论

学校读者我要写书评

暂无评论

An Automatic Labeling Strategy for Locomotion Mode Recognition with Robotic Transtibial Prosthesis

An Automatic Labeling Strategy for Locomotion Mode Recogniti...

引用

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

作者： Enhao Zheng Qining Wang Hong Qiao The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences No. 95 of Zhongguancun East Road Beijing China The Beijing Innovation Center for Engineering Science and Advanced Technology (BIC-ESAT) Peking University Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728107707

ISBN: (纸本)9781728107714

Doffing and Donning the prosthetic socket seriously influenced the performances of the locomotion mode recognition. To make the recognition algorithm adaptive to the disturbances, labeling the new coming data without human intervene was a key step. In this study, we proposed an automatic labeling method with on-prosthesis mechanical signals. The strategy was designed based on the dynamic time warping (DTW) to measure the similarities between the data of a whole completed gait cycle and the pre-defined templates. The automatic labeling algorithm was validated on 6 unilateral transtibial subjects wearing the robotic prosthesis. 2 experimental sessions with 5 locomotion mode and 8 locomotion transition tasks were investigated. Between the sessions, donning and doffing the prosthetic socket were done by the subjects without expertise manual configuration. We evaluated two template generation methods, i.e. the fixed template and the sliding template. The average accuracy of the automatic labeling after re-wearing the socket achieved 96.2% across the subjects, which was comparable to existing sEMG-based studies. The strategy provided a promising tool to accumulate training with inertial signals for locomotion mode recognition.

关键词： Prosthetics Robot sensing systems Labeling Sockets Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

A New Monocular Vision Measurement Method to Estimate 3D Positions of Objects on Floor

引用

International Journal of Automation and computing 2017年第2期14卷 159-168页

作者： Ling-Yi Xu Zhi-Qiang Cao Peng Zhao Chao Zhou State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 101408China

A new visual measurement method is proposed to estimate three-dimensional （3D） position of the object on the floor based on a single camera. The camera fixed on a robot is in an inclined position with respect to the floor. A measurement model with the camera＇s extrinsic parameters such as the height and pitch angle is described. Single image of a chessboard pattern placed on the floor is enough to calibrate the camera＇s extrinsic parameters after the camera＇s intrinsic parameters are calibrated. Then the position of object on the floor can be computed with the measurement model. Furthermore, the height of object can be calculated with the paired-points in the vertical line sharing the same position on the floor. Compared to the conventional method used to estimate the positions on the plane, this method can obtain the 3D positions. The indoor experiment testifies the accuracy and validity of the proposed method.

关键词： Visual measurement, calibration, localization, position estimation monocular vision.

来源：评论

学校读者我要写书评

暂无评论

Amphiphilic Cyclopeptide-Dyes: Smart Self-Assembly Amphiphilic Cyclopeptide-Dye for Near-Infrared Window-II Imaging (Adv. Mater. 16/2021)

引用

Advanced Materials 2021年第16期33卷

作者： Hao Chen Kangquan Shou Si Chen Chunrong Qu Zhiming Wang Lei Jiang Mark Zhu Bingbing Ding Kun Qian Aiyan Ji Hongyue Lou Ling Tong Alexander Hsu Yuebing Wang Dean W. Felsher Zhenhua Hu Jie Tian Zhen Cheng Center for Molecular Imaging Research Shanghai Institute of Materia Medica Chinese Academy of Sciences Shanghai 201203 China Molecular Imaging Program at Stanford (MIPS) Bio-X Program and Department of Radiology Canary Center at Stanford for Cancer Early Detection Stanford University Stanford CA 94305–5344 USA Division of Oncology Departments of Medicine and Pathology Stanford University School of Medicine Stanford CA 94305 USA CAS Key Laboratory of Molecular Imaging The State Key Laboratory of Management and Control for Complex Systems Beijing Key Laboratory of Molecular Imaging Institute of Automation Chinese Academy of Sciences Beijing 100190 China

来源：评论

学校读者我要写书评

暂无评论

DIRAC: HIGH-FIDELITY AUDIO FOR YOUR SMARTPHONE

引用

IEEE SPECTRUM 2018年第4期55卷 19-19页

作者： Koziol, Michael State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

In the years since the iPhone was launched, in 2007, smartphone manufacturers have competed primarily on the size and resolution of their screens, touting display capabilities sometimes to the exclusion of anything else. But as mobile display technology matures, manufacturers are looking to other areas to distinguish themselves, such as sound. This is good news for a company like Dirac, which provides algorithmic audio-optimization tools. A few of the bigger brands around the world that already include Dirac's optimizations are Alcatel, Huawei, Infinix, Motorola, and Tecno. So when Dirac offered IEEE Spectrum a chance to try out its demo suite, I took it. I wanted to see if these tools really made a noticeable difference.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Road Detection for autonomous truck in mine environment

Road Detection for autonomous truck in mine environment

引用

International Conference on Intelligent Transportation

作者： Jianlin Tang Xiaowei Lu Yunfeng Ai Bin Tian Long Chen Jiangsu XCMG Construction Machinery Research Institute LTD Xuzhou China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Beijing China School of Data and Computer Science Sun Yat-Sen University Guangzhou China

ISBN: (纸本)9781538670255

Road boundary line detection provides information of safe driving range and ensures the safety of the vehicles, which is an important part in the sensing system. Due to the mine roads are complicated and the road boundary lines are blurred, the existing road detection methods are not *** this paper, a real-time road boundary detection algorithm is proposed based on Lidar sensors. For the uneven ground of mine roads, this paper proposes a ground detection algorithm called Double Meshing. The elevated point is divided into beam areas after filtering the detected ground. Finally, the road boundary points are extracted in the beam area and the road boundary line is fitted. The performance of the proposed method is verified by experiments, which highlights its accuracy and real-time.

关键词： Roads Three-dimensional displays Laser radar Sensors Data mining Real-time systems Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Deep news event ranker based on user relevant query

Deep news event ranker based on user relevant query

引用

IEEE International Conference on Cloud Computing and Big Data Analysis (ICCCBDA)

作者： Xiangfei Kong Qingchao Kong Wenji Mao Shaoqiang Tang State Key Laboratory of Management and Control for Complex Systems University of Chinese Academy of Sciences College of Engineering Peking University Beijing China

News Event Ranking (NER), which takes event-related news documents as the ranking unit, has been addressed in many research work and implemented in security-oriented applications(e.g. public event monitoring, mining and retrieval). Previous work solely rank news event based on event relevant information, while user relevant information equally important for characterizing news event is totally neglected. In this paper, we depict news event with extra user comments sentiment polarity information, and address news event ranking problem by incorporating user relevant information into the input query. Given an input query, which contains event related objective aspects(e.g. actors, locations, date) and user related subjective aspects(e.g. public attention and opinion polarity), we develop a Deep News Event Ranker model to integrate objective event information and subjective user information. Firstly, a semantic similarity interaction module transforms query keywords, news document and news comments to their semantic vector representation and calculates query\document similarity and query\comment similarity. Then a Feature Extraction Based On CNNs and LSTM module extract query term importance features, query term frequency features and BM25-like relevance features for ranking. Finally, a Feature Aggregation module merges the extracted features with some auxiliary relevance features and produces a global relevance score. Experiments on a large news dataset demonstrate the effectiveness of our proposed model compared to several baseline models.

关键词： Feature extraction Semantics Machine learning Mathematical model Transforms Task analysis Measurement

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：