检索结果-内蒙古大学图书馆

IEEE International Geoscience and Remote Sensing Symposium

作者： Xiayuan Huang Xiangli Nie Hong Qiao Bo Zhang State Key Lab of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China State Key Lab of Scientific and Engineering Computing and Institute of Applied Mathematics AMSS Chinese Academy of Sciences Beijing China

Spatial information helps improve the performance of polarimetric synthetic aperture radar (PolSAR) image classification. Some existing methods have combined the spatial information and polarimetric features by the third-order tensor representation for feature extraction. They describe a pixel with the patch centered on this pixel. But they neglect the spatial heterogeneity, which may influence the classification performance. Therefore, we firstly seek k nearest samples based on the polarimetric feature similarity for each pixel to construct the second-order tensor, whose first order denotes the nearest samples and the second order denotes the polarimetric features. Moreover, k nearest samples are searched in a spatial local region rather than the full image, which can exploit the spatial information and reduce the computational burden. Then we employ tensor principal component analysis (TPCA) to extract low-dimensional features. Experimental results demonstrate that the proposed method can improve the classification performance compared with other methods.

关键词： Feature extraction Principal component analysis Visualization Euclidean distance Eigenvalues and eigenfunctions Roads

来源：评论

学校读者我要写书评

暂无评论

Traffic Congestion Prediction using Decision Tree, Logistic Regression and Neural Networks

引用

IFAC-PapersOnLine 2020年第5期53卷 512-517页

作者： Tariku Sinshaw Tamir Gang Xiong Zhishuai Li Hao Tao Zhen Shen Bin Hu Heruye Mulugeta Menkir State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing 100049 China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan 523808 China China Ship Development and Design Center Wuhan 430064 China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing 100190 China Debremarkos University Institute of Technology Debremarkos 269 Ethiopia

Traffic congestion is a serious problem around the world and to a great extent influences urban communities in various manners including increased stress levels, delayed deliveries, fuel wastage, and monetary losses. Therefore, an accurate congestion prediction algorithm to limit these misfortunes is fundamental. This paper presents a comparative study of traffic congestion prediction systems including decision tree, logistic regression, and neural networks. Five days of traffic information (1,231,200 samples) are utilized to drive the prediction model. The TensorFlow and the Clementine machine learning platforms are used for data preprocessing, training, and testing of the model. The confusion matrix clears that decision tree has better prediction performance and leads the other two methods with accuracy (97%), macro-average precision (95%), macro-average recall (96%), and macro-average F1_score (96%) in the python programming environment. Moreover, performance of the three prediction models is verified in Clementine environment and decision tree outperforms all other models with an accuracy of 97.65%.

关键词： Confusion matrix Data preprocessing Python TensorFlow Clementine environment ITS

来源：评论

学校读者我要写书评

暂无评论

Effect of compliant passive joint on swimming performance for a multi-joint robotic fish

Effect of compliant passive joint on swimming performance fo...

引用

2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

作者： Chen, Di Wu, Zhengxing Yu, Junzhi Institute of Automation CAS State Key Lab Management and Control for Complex Systems Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Dept. Mech. Eng. Sci. BIC-ESAT College of Engineering Peking University Beijing100871 China

ISBN: (纸本)9781728163215

In this paper, a novel compliant passive joint with two torsion springs is designed for a multi-joint robotic fish to improve propulsive performance. The motion of the multi-joint robotic fish is governed by the central pattern generator (CPG) control method. Using this multi-joint robotic fish as a testbed, the effect of compliant passive joint on swimming speed with changes in spring constant and CPG parameters such as oscillation frequency and phase difference is explored. As for the multi-joint robotic fish with a compliant passive joint, the swimming speed increases directly with the increase of oscillation frequency and the swimming speed achieved at maximum oscillation frequency increases with the decrease of phase difference. In addition, the comparison of swimming performance between robotic fish with a compliant passive joint and a fixed passive joint is made. Remarkably, the maximum swimming speed after improvement increases approximately 9.43 cm/s, corresponding to 0.17 BL/s. Experimental results reveal that adding an extra compliant passive joint can not always bring an improvement in swimming performance. Appropriate stiffness of passive joint and control parameters are needed to achieve better swimming performance. © 2019 IEEE.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-based Educational Digital Assets management System

引用

IFAC-PapersOnLine 2020年第5期53卷 47-52页

作者： Junqing Li Mo Lan Ying Tang Shichao Chen Fei-Yue Wang Wei Wei Shandong University of Science and Technology Qingdao China 266590 The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China 100190 Southwest University Chongqing China 400715 Beijing Achievelearn Education Technology Group Beijing China 100095 Electrical and Computer Engineering Rowan University Glassboro NJ 08003 USA Qingdao Academy of Intelligent Industries Qingdao China 266042 3E Smart Education Beijing China 100083

A variety of heterogeneous information is produced after the application of various emerging technologies in education, which is of great research value as educational assets. The traditional educational asset management system has emerged. In view of the disadvantages of traditional system centralization process, people begin to use decentralized blockchain technology for innovation. This paper proposes an educational digital asset management system architecture based on blockchain 3.0 technology system, which forms various data formed by students in and out of class learning process, courseware and experience data generated by teachers in the process of teaching into educational digital assets, and carries out the right confirmation and storage on the blockchain. The system can use a variety of heterogeneous data in digital assets to analyze the development status of school users, achieve the teaching purpose of teaching students according to their aptitude and different people.

关键词： blockchain blockchain system digital assets educational technology decentralized systems

来源：评论

学校读者我要写书评

暂无评论

Weakly Paired Multimodal Fusion for Object Recognition

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2018年第2期15卷 784-795页

作者： Liu, Huaping Wu, Yupei Sun, Fuchun Fang, Bin Guo, Di Tsinghua Univ Dept Comp Sci & Technol Beijing 100084 Peoples R China Tsinghua Univ Tsinghua Natl Lab Informat Sci & Technol State Key Lab Intelligent Technol & Syst Beijing 100084 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

The ever-growing development of sensor technology has led to the use of multimodal sensors to develop robotics and automation systems. It is therefore highly expected to develop methodologies capable of integrating information from multimodal sensors with the goal of improving the performance of surveillance, diagnosis, prediction, and so on. However, real multimodal data often suffer from significant weak-pairing characteristics, i.e., the full pairing between data samples may not be known, while pairing of a group of samples from one modality to a group of samples in another modality is known. In this paper, we establish a novel projective dictionary learning framework for weakly paired multimodal data fusion. By introducing a latent pairing matrix, we realize the simultaneous dictionary learning and the pairing matrix estimation, and therefore improve the fusion effect. In addition, the kernelized version and the optimization algorithms are also addressed. Extensive experimental validations on some existing data sets are performed to show the advantages of the proposed method. Note to Practitioners-In many industrial environments, we usually use multiple heterogeneous sensors, which provide multimodal information. Such multimodal data usually lead to two technical challenges. First, different sensors may provide different patterns of data. Second, the full-pairing information between modalities may not be known. In this paper, we develop a unified model to tackle such problems. This model is based on a projective dictionary learning method, which efficiently produces the representation vector for the original data by an explicit form. In addition, the latent pairing relation between samples can be learned automatically and be used to improve the classification performance. Such a method can be flexibly used for multimodal fusion with full-pairing, partial-pairing and weak-pairing cases.

关键词： intelligent robot system manipulation and grasping multimodal data projective dictionary learning weakly paired data

来源：评论

学校读者我要写书评

暂无评论

A hierarchical framework for ad inventory allocation in programmatic advertising markets

引用

ELECTRONIC COMMERCE RESEARCH AND APPLICATIONS 2018年 31卷 40-51页

作者： Li, Juanjuan Ni, Xiaochun Yuan, Yong Wang, Fei-Yue Beijing Inst Technol Sch Automat Beijing Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China Qingdao Acad Intelligent Ind Qingdao Peoples R China

Enabled by the big data driven user profiling and precision bidding techniques, online programmatic advertising markets have evolved from the traditional website-buying or ad-slot-buying models to a fine-grained and realtime trading model at the level of ad impressions (i.e., ad inventory). As a result, Web publishers are now facing a challenging decision of allocating the ad inventory across multiple advertising models, which has a direct and important influence on both their individual revenues, and the market-wide supply-demand balance. In this paper, we propose a novel hierarchical ad inventory allocation framework (AIAF), taking into consideration the possible scenarios of ad inventory allocation in programmatic advertising markets. AIAF explicitly captures the specific features of ad inventory allocation in each of three levels (i.e., channel level, market level and platform level), and also their influence-feedback effects. We present the general solution process for solving this model on the basis of its property analysis. An illustrative instantiation of our AIAF model is formulated to demonstrate its applications in supporting publishers' decision-making on the ad inventory allocation. We also conduct experiments based on empirical data so as to validate the model and analysis. Our research findings indicate that 1) our AIAF model outperforms other single-level and two-level allocation strategies;2) the fine-grained optimization is superior to that of the coarse-grained level;3) allocation decisions should be made on the basis of the comparative marginal revenue instead of the absolute marginal revenue.

关键词： Programmatic advertising Ad inventory Real-time bidding Private marketplace Header bidding

来源：评论

学校读者我要写书评

暂无评论

3D Deep Learning for 3D Printing of Tooth Model

3D Deep Learning for 3D Printing of Tooth Model

引用

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

作者： Yiwen Liu Xiuqin Shang Zhen Shen Bin Hu Zhihai Wang Gang Xiong Faculty of Information The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing University of Technology Beijing China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Beijing Engineering Research Center of Intelligent Systems and Technology Chinese Academy of Sciences Beijing China Faculty of Information Beijing University of Technology Beijing China

Recently, with the development of both 3D sensors and 3D virtual network that bring the needs of interaction with the real world, many 3D applications burst out. However, it is difficult to understanding these three-dimensional scenes with a fixed program. Then, a data-driven method is required to process these 3D data, which brings a strong demand of 3D Deep Learning in 3D data. Towards this goal, with an end-to-end deep learning, the experiment is based on PointNet++, a well proposed method for feature extraction. The experiment optimizes the network structure and parameters to improve the classification results. Finally, the network is applied to tooth model for classification and identification so that the dental model can be found from different perspectives.

关键词： Three-dimensional displays Deep learning Transforms Cameras Object segmentation Image segmentation Sensors

来源：评论

学校读者我要写书评

暂无评论

Forest Representation Learning with Multiscale Contour Feature Learning for Leaf Cultivar Classification

Forest Representation Learning with Multiscale Contour Featu...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zheng, Wenbo Gou, Chao Yan, Lan Xi An Jiao Tong Univ Sch Software Engn Xian Shaanxi Peoples R China Sun Yat Sen Univ Sch Intelligent Syst Engn Guangzhou Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China

ISBN: (纸本)9781728118673

Automated plant species identification system could help botanists and layman in identifying plant species rapidly. Deep learning is robust for feature extraction as it is superior in providing deeper information of images. However, deep neural networks based leaf cultivar classification model can not deeply mine the contour features of leaf images. Besides, the deep neural networks are very data-hungry due to the large complexity of the models, which means that the model's performance can decrease significantly when the size of the training data decreases. In this paper, we propose the leaf cultivar classification model based on forest representation learning and multiscale contour feature learning. Firstly, we build the multiscale contour feature learning to extract the contour features of leaf images. Then, the original input features are transformed by the data augmentation method to enhance the ability of feature expression, and the autoencoder by forest performs the data of dimensionality reduction on the features. Finally, we use the improved deep forest algorithm and autoencoder by forest to build forest representation learning for classification. The experimental results show that the proposed algorithm has higher performance than the original deep forest (gcForest) algorithm and other existing start-of-art algorithms, and has higher performance and efficiency than other deep learning algorithms.

关键词： Leaf Cultivar Classification Deep Learning Deep Forest AutoEncoder by Forest Data Augmentation

来源：评论

学校读者我要写书评

暂无评论

A Relation Hashing Network Embedded with Prior Features for Skin Lesion Classification 1

引用

10th International Workshop on Machine Learning in Medical Imaging (MLMI) / 22nd International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)

作者： Zheng, Wenbo Gou, Chao Yan, Lan Xi An Jiao Tong Univ Sch Software Engn Xian Peoples R China Sun Yat Sen Univ Sch Intelligent Syst Engn Guangzhou Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China

ISBN: (数字)9783030326920

ISBN: (纸本)9783030326920;9783030326913

Deep neural networks have become an effective tool for solving end-to-end classification problems and are suitable for many diagnostic settings. However, the success of such deep models often depends on a large number of training samples with annotations. Moreover, deep networks do not leverage the power of domain knowledge which is usually essential for diagnostic decision. Here we propose a novel relation hashing network via meta-learning to address the problem of skin lesion classification with prior features. In particular, we present a deep relation network to capture and memorize the relation among different samples. To employ the prior domain knowledge, we construct the hybrid-prior feature representation via joint meta-learning based on handcrafted models and deep-learned features. In order to utilize the fast and efficient computation of representation learning, we further create a hashing hybrid-prior feature representation by incorporating deep hashing into hybrid-prior representation learning, and then integrating it into our proposed network. Final recognition is obtained from our hashing relation network by learning to compare among the hashing hybrid-prior features of samples. Experimental results on ISIC Skin 2017 dataset demonstrate that our hashing relation network can achieve the state-of-the-art performance for the task of skin lesion classification.

关键词： Skin lesion classification Meta-learning Prior feature Deep-hashing

来源：评论

学校读者我要写书评

暂无评论

A GPU Based Parallel Genetic Algorithm for the Orientation Optimization Problem in 3D Printing

A GPU Based Parallel Genetic Algorithm for the Orientation O...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Li, Zhishuai Xiong, Gang Zhang, Xipeng Shen, Zhen Luo, Can Shang, Xiuqin Dong, Xisong Bian, Gui-Bin Wang, Xiao Wang, Fei-Yue Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Chinese Acad Sci Cloud Comp Ctr Dongguan 523808 Peoples R China Qingdao Acad Intelligent Ind Qingdao 266113 Shandong Peoples R China

ISBN: (纸本)9781538660263

The choice of model orientation is a very important issue in Additive Manufacturing (AM). In this paper, the model orientation problem is formulated as a multi-objective optimization problem, aiming at minimizing the building time, the surface quality, and the supporting area. Then we convert the problem into a single-objective optimization in the linear-weighted way. After that, the Genetic Algorithm (GA) is used to solve the optimization problem and the process of GA is parallelized and implemented on GPU. Experimental results show that when dealing with complex models in AM, compared with CPU only implementation, the GPU based GA can speed up the process by about 50 times, which helps to significantly reduce the optimization time and ensure the quality of solutions. The GPU based parallel methods we proposed can help to reduce the execution time and improve the efficiency greatly, making the processes more efficient.

关键词： Orientation Optimization GPU parallel computing genetic algorithm Additive Manufacturing

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：