检索结果-内蒙古大学图书馆

Distance range queries in spatialhadoop 21

21st Jornadas de Ingenieria del Software y Bases de Datos, JISBD 2016 - 21st Conference on Software engineering and Databases, JISBD 2016

作者： García-García, Francisco Corral, Antonio Iribarne, Luis Vassilakopoulos, Michael Dept. of Informatics University of Almeria Almeria Spain Dept. of Electrical and Computer Engineering University of Thessaly Volos Greece

Efficient processing of Distance Range Queries (DRQs) is of great importance in spatial databases due to the wide area of applications. This type of spatial query is characterized by a distance range over one or two datasets. The most representative and known DRQs are the Ε Distance Range Query (ΕDRQ) and the Ε Distance Range Join Query (ΕDRJQ). Given the increasing volume of spatial data, it is difficult to perform a DRQ on a centralized machine efficiently. Moreover, the ΕDRJQ is an expensive spatial operation, since it can be considered a combination of the ΕDR and the spatial join queries. For this reason, this paper addresses the problem of computing DRQs on big spatial datasets in SpatialHadoop, an extension of Hadoop that supports spatial operations efficiently, and proposes new algorithms in SpatialHadoop to perform efficient parallel DRQs on large-scale spatial datasets. We have evaluated the performance of the proposed algorithms in several situations with big synthetic and real-world datasets. The experiments have demonstrated the efficiency and scalability of our proposal. © 2016 Sistedes. All rights reserved.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

Deep cross-Modal correlation learning for audio and lyrics in music retrieval

arXiv

引用

arXiv 2017年

作者： Yu, Yi Tang, Suhua Raposo, Francisco Chen, Lei Digital Content and Media Sciences Research Division National Institute of Informatics Tokyo Dept. of Communication Engineering and Informatics University of Electro-Communications Tokyo Japan Instituto Superior Técnico Universidade de Lisboa Lisbon Portugal Department of Computer Science and Engineering Hong Kong University of Science and Technology

Deep cross-modal learning has successfully demonstrated excellent performances in cross-modal multimedia retrieval, with the aim of learning joint representations between different data modalities. Unfortunately, little research focuses on cross-modal correlation learning where temporal structures of different data modalities such as audio and lyrics are taken into account. Stemming from the characteristic of temporal structures of music in nature, we are motivated to learn the deep sequential correlation between audio and lyrics. In this work, we propose a deep cross-modal correlation learning architecture involving two-branch deep neural networks for audio modality and text modality (lyrics). Different modality data are converted to the same canonical space where inter modal canonical correlation analysis is utilized as an objective function to calculate the similarity of temporal structures. This is the first study on understanding the correlation between language and music audio through deep architectures for learning the paired temporal correlation of audio and lyrics. Pre-trained Doc2vec model followed by fully-connected layers (fully-connected deep neural network) is used to represent lyrics. Two significant contributions are made in the audio branch, as follows: i) pretrained CNN followed by fully-connected layers is investigated for representing music audio. ii) We further suggest an end-toend architecture that simultaneously trains convolutional layers and fully-connected layers to better learn temporal structures of music audio. Particularly, our end-to-end deep architecture contains two properties: simultaneously implementing feature learning and cross-modal correlation learning, and learning joint representation by considering temporal structures. Experimental results, using audio to retrieve lyrics or using lyrics to retrieve audio, verify the effectiveness of the proposed deep correlation learning architectures in cross-modal music retrieval. Copyrigh

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Combining Scala with C++ for efficient scientific computation in the context of ScalaLab

Combining Scala with C++ for efficient scientific computatio...

引用

World Congress on engineering 2016, WCE 2016

作者： Papadimitriou, Stergios Moussiades, Lefteris Technology Education Institute of East Macedonia and Thraki Dept of Informatics and Computer Engineering Agios Loukas Kavala65404 Greece

ISBN: (纸本)9789881925305

ScalaLab is a MATLAB-like environment for the Java Virtual Machine (JVM). ScalaLab is based on the Scala programming language. It utilizes an extensive set of Java and Scala scientific libraries and also has access to many native C/C++ scientific libraries by using mainly the Java Native Interface (JNI). The performance of the JVM platform is continuously improved at a fast pace. Today JVM can effectively support demanding high-performance computing and scales well on multicore platforms. However, sometimes optimized native C/C++ code can yield even better performance. That code can exploit the peculiarities of the hardware architecture and of special parallel hardware, as for example Graphical Processing Units. The present work reports some of the experience that we gained with experiments with both JITed JVM code and native code. We compare some aspects of Scala and C++ that concern the requirements of scientific computing. The article describes how ScalaLab tries to combine the best features of the Java Virtual Machine with those of the C/C++ technology, in order to implement an effective scientific computing environment.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

A comparative evaluation of core kernel features of the recent Linux, FreeBSD, solaris and windows operating systems

A comparative evaluation of core kernel features of the rece...

引用

World Congress on engineering 2016, WCE 2016

作者： Papadimitriou, Stergios Moussiades, Lefteris Technology Education Institute of East Macedonia and Thraki Dept of Informatics and Computer Engineering Agios Loukas Kavala65404 Greece

ISBN: (纸本)9789881925305

The paper compares core kernel architecture and functionality of four modern operating systems. The subsystems examined are process/thread architecture, scheduling and interrupt handling. Linux, Solaris and FreeBSD have a lot of similarities, owning Unix roots, but also have some notable differences. However, Windows is significantly different, being a radical non-Unix design. The paper compares some aspects of the Unix-like approaches of Linux/Solaris/FreeBSD with Windows, emphasizing the consequences of their different design decisions, and presents some comparative performance results, using Java benchmarks.

关键词： Linux

来源：评论

学校读者我要写书评

暂无评论

Learning T2D evolving complexity from EMR and administrative data by means of Continuous time Bayesian networks 9

Learning T2D evolving complexity from EMR and administrative...

引用

9th International Conference on Health informatics, HEALTHINF 2016 - Part of 9th International Joint Conference on Biomedical engineering Systems and Technologies, BIOSTEC 2016

作者： Marini, Simone Dagliati, Arianna Sacchi, Lucia Bellazzi, Riccardo Biomedical Informatics Labs Mario Stefanelli Dept. of Electrical Computer and Biomedical Engineering University of Pavia Pavia Italy

ISBN: (纸本)9789897581700

Predicting the complexity level (i.e. the number of complications and their related hospitalizations) in a T2D cohort is a critical step in prevention, resource optimization and overall patient management. Our data set was obtained by monitoring a T2D diabetic cohort along up to 10 years through electronic medical records of a local healthcare agency data warehouse. In order to conveniently handle temporarily sparse data, we designed a model describing the cohort evolution with Continuous Time Bayesian Networks (CTBN). The network structure and its parameters are entirely data driven. Compared to traditional Bayesian Networks, CTBNs admit cycles. As consequence, CTBNs fit the complexity of chronic metabolic syndromes where variables show a reciprocal influence. Network nodes represent metabolic (glycated hemoglobin, lipid profile (cholesterol, triglycerides), and biometric (BMI) data. We observed how these variables directly or indirectly affect the disease level of complexity, and how the variables influence the cumulative adverse events a patient undergoes. Copyright © 2016 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Comparison of point to point and MBSFN transmissions in next generation mobile networks 14

Comparison of point to point and MBSFN transmissions in next...

引用

14th ACM International Symposium on Mobility Management and Wireless Access, MobiWac 2016

作者： Bouras, Christos Kanakis, Nikos Kokkinos, Vasileios Papachristos, Nikolaos Vouyioukas, Demosthenes Computer Technology Institute and Press Diophantus Patras Greece Computer Engineering and Informatics Dept. Univ. of Patras Greece Dept. of Information and Communication System Engineering Univ. of Aegean Greece

ISBN: (纸本)9781450345033

Multicast/Broadcast Multicast Service over Single Frequency Network (MBSFN) technology has introduced advanced broadcast capabilities to cellular systems. In Long Term Evolution Advanced (LTE-A) systems, MBSFN transmission accommodates multicast groups in search of the same data. In this paper we compare the traditional Point-to-Point (PTP) communication with the MBSFN services through simulation experiments for various femtocell distributions and network configurations. The comparison takes into account the average throughput, overhead cost, energy consumption and capacity gain, concluding that MBSFN through multicast transmission may guarantee performance improvement even for users in the cell boundaries. © 2016 ACM.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Polylogarithmic approximation for minimum planarization (almost)

arXiv

引用

arXiv 2017年

作者： Kawarabayashi, Ken-ichi Sidiropoulos, Anastasios National Institute of Informatics 2-1-2 Hitotsubashi Chiyoda-ku Tokyo Japan Dept. of Computer Science and Engineering Dept. of Mathematics Ohio State University ColumbusOH43210 United States

In the minimum planarization problem, given some n-vertex graph, the goal is to find a set of vertices of minimum cardinality whose removal leaves a planar graph. This is a fundamental problem in topological graph theory. We present a logO(1) n-approximation algorithm for this problem on general graphs with running time nO(log n/log log n). We also obtain a O(nΕ)approximation with running time nO(1/Ε) for any arbitrarily small constant Ε > 0. Prior to our work, no non-trivial algorithm was known for this problem on general graphs, and the best known result even on graphs of bounded degree was a nΩ(1)-approximation [CS13]. As an immediate corollary, we also obtain improved approximation algorithms for the crossing number problem on graphs of bounded degree. Specifically, we obtain O(n1/2+Ε)-approximation and n1/2 logO(1) n-approximation algorithms in time nO(1/Ε) and nO(log n/log log n) respectively. The previously best-known result was a polynomial-time n9/10 logO(1) n-approximation algorithm [Chu11]. Our algorithm introduces several new tools including an efficient grid-minor construction for apex graphs, and a new method for computing irrelevant vertices. Analogues of these tools were previously available only for exact algorithms. Our work gives efficient implementations of these ideas in the setting of approximation algorithms, which could be of independent interest. Copyright © 2017, The Authors. All rights reserved.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Model predictive control with state estimation for freeway systems

Model predictive control with state estimation for freeway s...

引用

American Control Conference

作者： A. Brandi A. Ferrara S. Sacone S. Siri C. Vivas F. Rubio the Dept. of Electrical Computer and Biomedical Engineering University of Pavia Italy the Dept. of Informatics Bioengineering Robotics and Systems Engineering University of Genova Italy the Dept. de Ingeniería de Sistemas y Automática Escuela Superior de Ingenieros Universidad de Sevilla Spain

ISBN: (纸本)9781509045839

The objective of the paper is the design of a ramp metering control scheme for freeway systems in which the traffic state estimation is also considered. The development of an approach for estimating the traffic densities is motivated by the fact that traffic flow measurements at some locations are in many cases the only available information obtained by sensors, whereas the knowledge of the traffic density is necessary for determining suitable ramp metering actions. A piecewise-affine version of the Asymmetric Cell Transmission Model is adopted and, on the basis of its operating mode and observability properties, a density estimation mechanism based on switched Luenberger observers is realized. The problem is formulated and solved resorting to Linear Matrix Inequalities. The ramp metering control action is then computed by applying a Model Predictive Control approach that uses state estimates in place of measurements. Some simulation results have been performed to test the effectiveness of the proposed approach.

关键词： estimation freeway systems

来源：评论

学校读者我要写书评

暂无评论

Evaluation of algorithms for multi-modality whole heart segmentation: An open-access grand challenge

arXiv

引用

arXiv 2019年

作者： Zhuang, Xiahai Li, Lei Payer, Christian Štern, Darko Urschler, Martin Heinrich, Mattias P. Oster, Julien Wang, Chunliang Smedby, Örjan Bian, Cheng Yang, Xin Heng, Pheng-Ann Mortazi, Aliasghar Bagci, Ulas Yang, Guanyu Sun, Chenchen Galisot, Gaetan Ramel, Jean-Yves Brouard, Thierry Tong, Qianqian Si, Weixin Liao, Xiangyun Zeng, Guodong Shi, Zenglin Zheng, Guoyan Wang, Chengjia MacGillivray, Tom Newby, David Rhode, Kawal Ourselin, Sebastien Mohiaddin, Raad Keegan, Jennifer Firmin, David Yang, Guang School of Data Science Fudan University Shanghai200433 China Fudan-Xinzailing Joint Research Center for Big Data Fudan University Shanghai200433 China School of Biomedical Engineering Shanghai Jiao Tong University Shanghai200240 China Institute of Computer Graphics and Vision Graz University of Technology Graz8010 Austria Ludwig Boltzmann Institute for Clinical Forensic Imaging Graz8010 Austria Institute of Medical Informatics University of Lubeck Lubeck23562 Germany Inserm Université de Lorraine U1254 IADI Nancy France School for Technology and Health KTH Royal Institute of Technology StockholmSE-10044 Sweden School of Biomed. Eng. Health Science Centre Shenzhen University Shenzhen518060 China Dept. of Comp. Sci. and Eng. Chinese University of Hong Kong Hong Kong China University of Central Florida Orlando32816 United States School of Computer Science and Engineering Southeast University Nanjing210096 China Université de Tours 64 avenue Jean Portalis Tours37200 France School of Computer Science Wuhan University Wuhan430072 China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology SIAT Shenzhen China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Institute for Surgical Technology & Biomechanics University of Bern Bern3014 Switzerland BHF Centre for Cardiovascular Science University of Edinburgh Edinburgh United Kingdom Edinburgh Imaging Facility QMRI University of Edinburgh Edinburgh United Kingdom Department of Imaging Sciences & Biomedical Engineering Kings College London London United Kingdom Cardiovascular Research Centre Royal Brompton Hospital LondonSW3 6NP United Kingdom National Heart and Lung Institute Imperial College London London LondonSW7 2AZ United Kingdom

Knowledge of whole heart anatomy is a prerequisite for many clinical applications. Whole heart segmentation (WHS), which delineates substructures of the heart, can be very valuable for modeling and analysis of the anatomy and functions of the heart. However, automating this segmentation can be arduous due to the large variation of the heart shape, and different image qualities of the clinical data. To achieve this goal, a set of training data is generally needed for constructing priors or for training. In addition, it is difficult to perform comparisons between different methods, largely due to differences in the datasets and evaluation metrics used. This manuscript presents the methodologies and evaluation results for the WHS algorithms selected from the submissions to the Multi-Modality Whole Heart Segmentation (MM-WHS) challenge, in conjunction with MICCAI 2017. The challenge provides 120 three-dimensional cardiac images covering the whole heart, including 60 CT and 60 MRI volumes, all acquired in clinical environments with manual delineation. Ten algorithms for CT data and eleven algorithms for MRI data, submitted from twelve groups, have been evaluated. The results show that many of the deep learning (DL) based methods achieved high accuracy, even though the number of training datasets were limited. A number of them also reported poor results in the blinded evaluation, probably due to overfitting in their training. The conventional algorithms, mainly based on multi-atlas segmentation, demonstrated robust and stable performance, even though the accuracy is not as good as the best DL method in CT segmentation. The challenge, including provision of the annotated training data and the blinded evaluation for submitted algorithms on the test data, continues as an ongoing benchmarking resource via its homepage (***/zhuangxiahai/0/mmwhs/). Copyright © 2019, The Authors. All rights reserved.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Hand-wrist bone assesment for automatic age identification 18

Hand-wrist bone assesment for automatic age identification

引用

18th International Electronics Symposium, IES 2016

作者： Sigit, Riyanto Harsono, Tri Devi Isnanda, Farah Rochmawati, Eva Dwi Triyana, Elvi Nofindarwati, Cicik Setiawati, Rosy Dept. of Informatics and Computer Engineering Electronics Engineering Polytechnic Institute of Surabaya Indonesia Musculoskeletal Division Radiology Departement Faculty of Medicine Airlangga University of Surabaya Indonesia

ISBN: (纸本)9781509016402

Unknown people who have died in suspicious circumstances or in mass disaster often have no evidence to indicate chronological age. Using bone has been being mostly used by an experienced doctor to identify age since it provides the most accurate result compared to other diagnoses. However, due to manual identification, the doctor requires tremendous amount of time and the result is highly subjective to the doctor decisions and experience. In this paper, an automatic identification of person age is performed only from a hand-wrist bone structure. It provides a simpler way and reliable as compared to use full-hand bone structure. An active contour with balloons model is studied to extract hand-wrist bone parts namely epiphysis and metaphysis. From these parts, the width ratio is employed to identify person age. Experiments show encouraging results for the proposed method to automatically identify person age. We believe this can benefit for the future of forensic identification. © 2016 IEEE.

关键词： Bone

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：