检索结果-内蒙古大学图书馆

IEEE/RSJ International Conference on Intelligent Robots and Systems

作者： Procopio Stein Anne Spalanzani Vitor Santos Christian Laugier INRIA Rhone Alpes France Universidade de Aveiro Portugal

ISBN: (纸本)9781479969357

Service and assistance robots that must move in human environment must address the difficult issue of navigating in dynamic environments. As it has been shown in previous works, in such situations the robots can take advantage of the motion of persons by following them, managing to move together with humans in difficult situations. In those circumstances, the problem to be solved is how to choose a human leader to be followed. This work proposes an innovative method for leader selection, based on human experience. A learning framework is developed, where data is acquired, labeled and then used to train an AdaBoost classification algorithm, to determine if a candidate is a bad or a good leader, and also to study the contribution of features to the classification process.

关键词： HUMAN ENVIRONMENT geolocation measurement Human Robot sorting algorithm Persons candidate species

来源：评论

学校读者我要写书评

暂无评论

FAST MARGIN-BASED COST-SENSITIVE CLASSIFICATION

FAST MARGIN-BASED COST-SENSITIVE CLASSIFICATION

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Feng Nan Joseph Wang Kirill Trapeznikov Venkatesh Saligrama Boston University

ISBN: (纸本)9781479928941

We present a novel classification algorithm for learning with test time budgets. In this setting, the goal is to reduce feature acquisition cost while maintaining classification accuracy. For every decision, our approach dynamically selects features based on previously observed information. Once a desired confidence of a decision is achieved, the acquisition stops and the test instance is classified. Our approach can be used in conjunction with many popular margin based classification algorithms. We use margin information from training data in the partial feature neighborhood of a test point to compute a probability of correct classification. This estimate is used to either select the next feature or to stop. We compare our algorithm to other cost-sensitive methods on real world datasets. The experiments demonstrate that our algorithm provides an accurate estimate of classification confidence and outperforms other approaches while being significantly more efficient in computation.

关键词： sorting algorithm Tumor margin status test points Taxonomy confidence algorithms TESTING TIME

来源：评论

学校读者我要写书评

暂无评论

Medical Document Classification Based on MeSH

Medical Document Classification Based on MeSH

引用

Hawaii International Conference on System Sciences

作者： Abdullah Muhammad Alghoson Claremont Graduate University

ISBN: (纸本)9781479925056

One of the most challenging projects in information systems is extracting information from unstructured texts, including medical document classification. I am developing a classification algorithm that classifies a medical document by analyzing its content and categorizing it under predefined topics from the Medical Subject Headings (MeSH). I collected a corpus of 50 full-text journal articles (N=50) from MEDLINE, which were already indexed by experts based on MeSH. Using natural language processing (NLP), my algorithm classifies the collected articles under MeSH subject headings. I evaluated the algorithm's outcome by measuring its precision and recall of resulting subject headings from the algorithm, comparing results to the actual documents' subject headings. The algorithm classified the articles correctly under 45% to 60% of the actual subject headings and got 40% to 53% of the total subject headings correct. This holds promising solutions for the global health arena to index and classify medical documents expeditiously.

关键词： Medical Subject Headings Subject Headings sorting algorithm Classification (Cognitive Process) Medical Natural Language Processing Computer based information systems Mesh Mesh recall Mental Recall MEDLINE

来源：评论

学校读者我要写书评

暂无评论

MR based PET attenuation correction (MRAC) and anatomical localization of human brain using an optimized UTE-mDixon pulse sequence

MR based PET attenuation correction (MRAC) and anatomical lo...

引用

IEEE Nuclear Science Symposium

作者： Lingzhi Hu Christian Stehning Nghi Nguyen Andrew Sher Claudia Martinez Rios Zhiqiang Hu Lingxiong Shao Philips Healthcare Cleveland OH 44124 USA

ISBN: (纸本)9781479960989

MR based Attenuation Correction (MRAC) is essential for PET quantitation and image quality assurance in PET/MR. Ultra-short TE (UTE) sequence is promising in generating positive contrast for cortical bone but its further adoption is limited by prohibitively long scan time, lack of soft tissue contrast, and potential ambiguity in a tissue classification due to MR imaging artifacts. In this investigation, we aimed to develop a new MRAC method that consists an optimized under-sampled UTE-mDixon sequence and an iterative voxel-based tissue classification algorithm to generate 4-compartment μ-map, including water, fat, bone and air cavity. In vivo UTE-mDixon images were acquired on 12 human subjects and the developed segmentation method was employed for tissue classification. Diagnostic quality of MR images and the tissue classification accuracy for MRAC was evaluated by three radiologists independently. As a unique advantage over other MRAC sequences, the under-sampled UTE-mDixon of whole brain with retrospective trajectory delay calibration can be finished within less than 3 minutes providing both high quality water/fat separation images for anatomical localization and UTE images for bone segmentation. Robust tissue classification was achieved in all subjects as evaluated by radiologists. The developed MR scan methodology together with tissue classification algorithm may provide a one-scan solution for attenuation correction and anatomical localization in PET/MR.

关键词： model reference adaptive control human subject air cavity Image quality sorting algorithm

来源：评论

学校读者我要写书评

暂无评论

On Flight Route Planning Method of the Terrain Avoidance System

On Flight Route Planning Method of the Terrain Avoidance Sys...

引用

2014中国制导、导航与控制学术会议

作者： Dongcai Qu Dehai Yu Yuguang Feng Binwen Lu Department of Control Engineering Naval Aeronautical and Astronautical UniversityYantaiShandong ProvinceChina264001 Train DepartmentNaval Aeronautical and Astronautical University YantaiShandong ProvinceChina264001 Department of Ordnance Science and TechnologyNaval Aeronautical and Astronautical UniversityYantaiShandong ProvinceChina264001 College of Mechatronic Engineering and AutomationNational Univerisity of Defense TechnologyChangshaHunan ProvinceChina410000

ISBN: (纸本)9781479946983

It is an important step for flight route planning in the process of air terrain avoidance.A reference air route that can guarantee the flight safety,meet flight quality is the basis to accomplish the flying *** paper research the air route planning for flight terrain avoidance,classify and model to the terrain sampled point by using k mean-value algorithm,and set up the feasible point *** then using the Dijkstra algorithm to find a high quality air route,based on considering the restrained conditions of *** the simulation,the feasibility and rationality of the scheme was verified

关键词： air safety aircraft control collision avoidance pattern clustering Dijkstra algorithm air terrain avoidance feasible point space flight conditions flight quality flight route planning method flight safety flying task high quality air route k mean-value algorithm reference air route terrain avoidance system terrain sampled point Atmospheric modeling Classification algorithms Clustering algorithms Educational institutions Heart Path planning Planning flight safety air safety Aircraft control Atmospheric models flight conditions flight line sorting algorithm Clustering algorithms Educational institutions Dijkstra's algorithm Path planning Collision avoidance Airlines Cluster Analysis Heart

来源：评论

学校读者我要写书评

暂无评论

Intrinsic prior for Bayesian classification of texture images

Intrinsic prior for Bayesian classification of texture image...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Aurelien Schutz Lionel Bombrun Yannick Berthoumieu Universite de Bordeaux Institut Polytechnique de Bordeaux Laboratoire IMS Groupe Signal et Image

ISBN: (纸本)9781479928941

This paper introduces an intrinsic prior distribution for supervised classification of texture images. First, we introduce the intrinsic prior distribution as the normal law on a Riemannian manifold. Next, based on this definition, we derive the estimation and classification schemes. Finally, we propose an application for the classification of texture images. Experiments on the VisTex texture database are conducted and demonstrate the interest of the proposed intrinsic classification algorithm.

关键词： GRAIN PATTERN Prior distribution sorting algorithm Image classification Bayesian inference

来源：评论

学校读者我要写书评

暂无评论

LINEAR DISCRIMINANT MULTIPLE KERNEL LEARNING FOR MULTISPECTRAL IMAGE CLASSIFICATION

LINEAR DISCRIMINANT MULTIPLE KERNEL LEARNING FOR MULTISPECTR...

引用

IEEE International Conference on Image Processing

作者： Yanfeng Gu Qingwang Wang Pigang Liu Deshan Zuo Sch. of Electron. & Inf. Eng. Harbin Inst. of Technol. Harbin China

ISBN: (纸本)9781479957521

In the past decade, with the development of kernel-based machine learning, many different multiple kernel learning (MKL) methods were proposed which focus on selecting the pivotal kernel to be preserved and confirming the optimal kernel combination. In this paper, we address the question mentioned above by using subspace projection method and put forward a linear discriminant based MKL (LDMKL) algorithm. LDMKL algorithm reduces the computational burden and keeps the excellent property of MKL in terms of good classification accuracy by finding the optimal projective direction which makes the intraclass scatter minimum and interclass scatter maximum instead of the time-consuming search for optimal kernel combination. Experimental results indicate that LDMKL algorithm provides the best performances among several the state-of-the-art algorithms while demonstrating satisfactory computational efficiency.

关键词： image classification learning (artificial intelligence) LDMKL algorithm interclass scatter maximum intraclass scatter minimum kernel-based machine learning linear discriminant multiple kernel learning method multispectral image classification subspace projection method Accuracy Classification algorithms Image classification Kernel Remote sensing Support vector machines Training Classification linear discriminant analysis (LDA) multiple kernel learning (MKL) spectral images support vector machine (SVM) Image classification Support Vector Network sorting algorithm Kernel Seeds remote sensing Functional training Linear discriminant analysis multi-spectral image Discriminant

来源：评论

学校读者我要写书评

暂无评论

Spammer Detection on Weibo Social Network

Spammer Detection on Weibo Social Network

引用

IEEE International Conference on Cloud Computing Technology and Science

作者： Zhipeng Zeng Xianghan Zheng Guolong Chen Yuanlong Yu Coll. of Math. & Comput. Sci. Fuzhou Univ. Fuzhou China

ISBN: (纸本)9781479940929

Social network has become a very popular way for internet users to communicate and interact online. Users spend a great deal of time on famous social networks (e.g. Facebook, Twitter, Sina Weibo, etc.), reading news, discussing events and posting their messages. Unfortunately, this popularity also attracts a significant amount of spammers who continuously expose malicious behaviors (e.g. post messages containing commercial topics or URLs, following a larger amount of users, etc.), leading to great inconvenience on normal users' social activities. In this paper, a supervised machine learning based spammer filtering method is proposed. We first collected a dataset from Sina Weibo that includes 30,116 users and more than 16 million messages;then, construct a labeled dataset of users and manually classify users into spammers and non-spammers;after that, abstract a set of novel features from message content and users' social behavior, and apply into SVM based spammer classifier. Our experiments show that true positive rate of spammers and non-spammers could reach 99.1% and 99.9%.

关键词： Internet learning (artificial intelligence) pattern classification social networking (online) support vector machines unsolicited e-mail Internet users SVM based spammer classifier Weibo social network event discussion malicious behaviors message content message posting news reading normal user social activities spammer detection supervised machine learning based spammer filtering method user labeled dataset user social behavior Classification algorithms Crawlers Feature extraction Support vector machines Twitter Unsolicited electronic mail machine learning social network spam spammer support vector machine spammer Support Vector Network Unsolicited electronic mail Social Media Social Networks Crawlers sorting algorithm Consumers Pattern recognition Feature extraction Internets TWITTER

来源：评论

学校读者我要写书评

暂无评论

Implementation of Address-Based Data sorting on Different FPGA Platforms

Implementation of Address-Based Data Sorting on Different FP...

引用

IEEE East-West Design and Test Symposium (EWDTS)

作者： Mihhailov, Dmitri Sudnitson, Alexander Sklyarov, Valery Skliarova, Iouliia Tallinn Univ Technol Dept Comp Engn Tallinn Estonia Univ Aveiro DETI IEETA Aveiro Portugal

ISBN: (纸本)9781479920952;9781479920969

Among numerous tasks that need to be solved, sorting is considered to be one of the most important. Since it is time consuming for large volumes of data, acceleration is greatly required for many practical applications. It is also important to discover such methods that take advantage of the implementation platform (due to its uniqueness) and consider not only the number of the required operations, but also efficiency of their implementation in hardware circuits. This paper evaluates implementations of address-based data sorting algorithms in field-programmable gate array (FPGA) circuits. It is demonstrated that the proposed technique can be used efficiently both in low cost FPGAs as well as in advanced FPGAs, and the number of sorted items (with sizes of up to 32 bits) can reach 2(32).

关键词： Field programmable gate arrays grade Platform sorting programs Electric circuits sorting algorithm uniqueness

来源：评论

学校读者我要写书评

暂无评论

LiCABEDS II. Modeling of Ligand Selectivity for G-Protein-Coupled Cannabinoid Receptors

引用

JOURNAL OF CHEMICAL INFORMATION AND MODELING 2013年第1期53卷 11-26页

作者： Ma, Chao Wang, Lirong Yang, Peng Myint, Kyaw Z. Xie, Xiang-Qun Univ Pittsburgh Sch Pharm Dept Pharmaceut Sci Computat Chem Genom Screening Ctr Pittsburgh PA 15260 USA Univ Pittsburgh Dept Computat & Syst Biol Pittsburgh PA 15260 USA Univ Pittsburgh Ctr Chem Methodol & Lib Dev UPCMLD Pittsburgh PA 15260 USA Univ Pittsburgh Drug Discovery Inst Pittsburgh PA 15260 USA

The cannabinoid receptor subtype 2 (CB2) is a promising therapeutic target for blood cancer, pain relief, osteoporosis, and immune system disease. The recent withdrawal of Rimonabant, which targets another closely related cannabinoid receptor (CB1), accentuates the importance of selectivity for the development of CB2 ligands in order to minimize their effects on the CB1 receptor. In our previous study, LiCABEDS (Ligand Classifier of Adaptively Roosting Ensemble Decision Stumps) was reported as a generic ligand classification algorithm for the prediction of categorical molecular properties. Here, we report extension of the application of LiCABEDS to the modeling of cannabinoid ligand selectivity with molecular fingerprints as descriptors. The performance of LiCABEDS was systematically compared with another popular classification algorithm, support vector machine (SVM), according to prediction precision and recall rate. In addition, the examination of LiCABEDS models revealed the difference in structure diversity of CB1 and CB2 selective ligands. The structure determination from data mining could be useful for the design of novel cannabinoid lead compounds. More importantly, the potential of LiCABEDS was demonstrated through successful identification of newly synthesized CB2 selective compounds.

关键词： selectivity Modeling Receptors, Cannabinoid Retrieval recall Cannabinoids cannabinoid 1 receptor CNR1 gene ligands CNR2 gene rimonabant sorting algorithm

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：