检索结果-内蒙古大学图书馆

2011 International Conference on Image Processing, computer Vision, and Pattern Recognition, IPCV 2011

作者： Bae, Tae-Wuk Choi, Won-Hyung Kim, Byoung-Ik Kim, Young-Choon Ahn, Sang-Ho School of Electrical Engineering and Computer Science Kyungpook National University Korea Republic of Dept. of Information and Communication Engineering Youngdong University Korea Republic of School of Electronic Telecommunication Inje University Korea Republic of

ISBN: (纸本)9781601321916

In this paper, we propose a recursive multi-scale new white top-hat (NWTH) filter for small target detection in the infrared (IR) images. At first, NWTH filter based on white top-hat (WTH) transformation is performed for three scales (structure elements) with wide scale interval. For the discrimination of candidate target and background region, Threshold is calculated by using maximum value of the summation image by NWTH filter. By using this threshold, a structure element is selected by candidate target clutter ratio (CTCR), modification of signal to clutter ratio gain (SCRG). Based on the selected structure element, the other two structure elements are updated with middle scale interval. Through recursive process of procedure mentioned above, optimum three structure elements are obtained. The experimental results show that the proposed method is robust and effective than existing morphological methods for the small target detection.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

A rapid texture-based moving object detection method

A rapid texture-based moving object detection method

引用

作者： Huang, Yea-Shuan Ou, Zhi-Hong Hsieh, Hsiang-Wen Yu, Hung-Hsiu Dept. of Computer Science and Information Engineering Chung-Hua University Hsinchu Taiwan Mechanical and System Laboratory Industrial Technology Research Institute Hsinchu Taiwan

ISBN: (纸本)9788995605646

This paper presents a moving object detection method based on texture information extracted from images. Every image captured from the camera is converted into Local Binary Pattern (LBP). Salient feature points extracted from previous LBP are compared with those features found from the current LBP with a block matching approach so that the corresponding feature points from the successive image frames can be identified. If multiple correspondences exist between feature points, the motion vectors of each feature points are then calculated to determine the best corresponding features on the current LBP. Finally, with clustering of motion vectors, all the moving objects on image frames can be successfully detected and identified. Experimental results show that the average matching accuracy rate is 95.12%, and the average processing time for moving object detection is 46.2ms. © 2011 Asian Control Association.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Securing vehicular ad-hoc networks against malicious drivers: A probabilistic approach

Securing vehicular ad-hoc networks against malicious drivers...

引用

5th International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2011

作者： Rawat, Danda B. Bista, Bhed B. Yan, Gongjun Weigle, Michele C. Dept. of Electrical and Computer Engineering Old Dominion University Norfolk VA United States Faculty of Software and Information Science Iwate Prefectural University 020-0193 Japan Department of NMIS Indiana University Kokomo Kokomo IN United States Dept. of Computer Science Old Dominion University Norfolk VA United States

ISBN: (纸本)9780769543734

Future development of Intelligent Transportation Systems (ITS) depends on Vehicular Ad-hoc Networks (VANETs) in which communications will help to improve traffic safety and efficiency through exchanging information among vehicles. As each vehicle cannot be a source of all messages in VANET, most communications depend on the information received from other vehicles. To protect VANET from malicious action, each vehicle must be able to evaluate, decide and react locally on information received from other vehicles. Message verification is more challenging in VANETs since the security and privacy of the participating vehicles, in general, and of the drivers and passengers specifically is of major concern. Each vehicle needs to verify the accuracy of the message and needs to verify that the received message is from a legitimate vehicle. In this paper, we propose a new algorithm to secure vehicular communication with the help of trust measured for the given period using a probabilistic approach. The proposed algorithm secures VANETs against the untrustworthy drivers. The proposed algorithm is illustrated through numerical results obtained from simulations. © 2011 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Ordinal hyperplanes ranker with cost sensitivities for age estimation

Ordinal hyperplanes ranker with cost sensitivities for age e...

引用

作者： Chang, Kuang-Yu Chen, Chu-Song Hung, Yi-Ping Institute of Information Science Academia Sinica Taipei Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan Dept. of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Graduate Institute of Networking and Multimedia National Taiwan University Taipei Taiwan

ISBN: (纸本)9781457703942

In this paper, we propose an ordinal hyperplane ranking algorithm called OHRank, which estimates human ages via facial images. The design of the algorithm is based on the relative order information among the age labels in a database. Each ordinal hyperplane separates all the facial images into two groups according to the relative order, and a cost-sensitive property is exploited to find better hyperplanes based on the classification costs. Human ages are inferred by aggregating a set of preferences from the ordinal hyperplanes with their cost sensitivities. Our experimental results demonstrate that the proposed approach outperforms conventional multiclass-based and regression-based approaches as well as recently developed ranking-based age estimation approaches. © 2011 IEEE.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Digital microfluidic biochips: Recent research and emerging challenges 11

Digital microfluidic biochips: Recent research and emerging ...

引用

Embedded Systems Week 2011, ESWEEK 2011 - 9th IEEE/ACM International Conference on Hardware/Software-Codesign and System Synthesis, CODES+ISSS'11

作者： Ho, Tsung-Yi Chakrabarty, Krishnendu Pop, Paul Dept. of Computer Science and Information Engineering National Cheng Kung Univ. Tainan Taiwan Department of Electrical and Computer Engineering Duke University Durham NC United States Technical University of Denmark DTU Informatics Kgs. Lyngby Denmark

ISBN: (纸本)9781450307154

Microfluidic biochips are replacing the conventional biochemical analyzers, and are able to integrate on-chip all the basic functions for biochemical analysis. The "digital" microfluidic biochips (DMFBs) are manipulating liquids not as a continuous flow, but as discrete droplets on a two-dimensional array of electrodes. Basic microfluidic operations, such as mixing and dilution, are performed on the array, by routing the corresponding droplets on a series of electrodes. The challenges facing biochips are similar to those faced by microelectronics some decades ago. To meet the challenges of increasing design complexity, computer-aided-design (CAD) tools are being developed for DMFBs. This paper provides an overview of DMFBs and describes emerging CAD tools for the automated synthesis and optimization of DMFB designs, from fluidic-level synthesis and chip-level design to testing. Design automations are expected to alleviate the burden of manual optimization of bioassays, time-consuming chip designs, and costly testing and maintenance procedures. With the assistance of CAD tools, users can concentrate on the development and abstraction of nanoscale bioassays while leaving chip optimization and implementation details to CAD tools. Copyright 2011 ACM.

关键词： Biochips

来源：评论

学校读者我要写书评

暂无评论

Path optimization for software testing: An intelligent approach using cuckoo search

Path optimization for software testing: An intelligent appro...

引用

5th Indian International Conference on Artificial Intelligence, IICAI 2011

作者： Srivastava, Praveen Ranjan Chis, Monica Deb, Suash Yang, Xin-She Computer Science and Information System Department BITS Pilani - 333031 India FREQUENTIS Romania Dept. of Computer Science and Engineering C.V. Raman College of Engineering Bhubaneswar India Department of Engineering University of Cambridge Trumpington Street Cambridge CB2 1PZ United Kingdom

ISBN: (纸本)9780972741286

Software Testing is one of the main important and complex steps in the software development lifecycle. To fully test a newly developed software package, either black box (specification based) or white box (code based) testing must be performed. White box testing depends upon structure of code and its control flow graph. Identification of independent path is a complex problem, so the aim of the current paper is to present a simple algorithm for independent path generation, based on the recently developed cuckoo search. The proposed approach has some additional set of rules for the effective paths generation and prioritization of the basic paths. It can be shown that the proposed approach guarantees full path coverage.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Novel Mastrovito Multiplier over GF(2m) Using Trinomial

Novel Mastrovito Multiplier over GF(2m) Using Trinomial

引用

International Conference on Genetic and Evolutionary Computing (ICGEC)

作者： Che Wun Chiou Jim-Min Lin Chiou-Yng Lee Chi-Ting Ma Dept. of Computer Science and Information Engineering Ching Yun University Chung-Li Taiwan Dept. of Information Engineering and Computer Science Feng Chia University Taichung City Taiwan

In recent years, mobile communication becomes more and more popular. Thus, information security on electronic commerce is an important issue for mobile communication. The finite field arithmetic operations are applied in modern public-key cryptosystems such as elliptic curve cryptosystem (ECC). In this article, a novel systolic polynomial basis multiplier based on Mastrovito multiplier is presented. The proposed systolic Mastrovito multiplier has low hardware cost by employing reused components. As m=81, the proposed systolic Mastrovito multiplier saves about 50% space complexity as comparing with other similar multipliers.

关键词： computer architecture Polynomials Elliptic curve cryptography Galois fields Educational institutions Hardware Microprocessors

来源：评论

学校读者我要写书评

暂无评论

Construction labor production rates modeling using artificial neural network

引用

Electronic Journal of information Technology in Construction 2011年 16卷 713-726页

作者： Muqeem, Sana Idrus, Arazi Khamidi, M. Faris Bin Ahmad, Jale Bin Zakaria, Saiful Civil Engineering Dept. Universiti Teknologi PETRONAS Malaysia Computer Information Science Dept. Universiti Teknologi PETRONAS Malaysia

Construction productivity is constantly declining over a decade due to the lack of standard productivity database system and the ignorance of impact of various factors influencing labor productivity. Prediction models developed earlier usually neglect the influencing factors which are subjective in nature such as weather, site conditions etc. Many modeling techniques have been developed for predicting production rates for labor that incorporate the influence of various factors but artificial neural network (ANN) has been found to have strong pattern recognition and learning capabilities to get reliable results. Therefore the objective of this research is to develop a neural network prediction model for predicting labor production rates that takes into account the factors which are in qualitative form. The objectives of the research have been achieved by collecting production rates data for formwork of beams from different high rise concrete building structures by direct observation. Reliable values of production rates have been successfully predicted by ANN. The average value of 1.45xE-04 has been obtained for Mean Square Error (MSE) after testing the network. These results indicate that the ANN has predicted production rates values for beam formwork successfully with least range of errors. © 2011 The authors.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Automated extraction of nested sulcus features from human brain MRI data

Automated extraction of nested sulcus features from human br...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society

作者： Forrest Sheng Bao Joachim Giard Jason Tourville Arno Klein F. S. Bao is with Depts. of Computer Science and Electrical Engineering Texas Tech University Lubbock Texas J. Giard is with Institute of Information and Communication Technologies Electronics and Applied Mathematics Université Catholique de Louvain Louvain Belgium J. Tourville is with Dept. of Speech Language and Hearing Sciences and Center for Computational Neuroscience and Neural Technology Boston University Boston Massachusetts A. Klein is with New York Psychiatric Institute Columbia University New York New York

ISBN: (纸本)9781424441198

Extracting objects related to a fold in the cerebral cortex ("sulcus features") from human brain magnetic resonance imaging data has applications in morphometry, landmark-based registration, and anatomical labeling. In prior work, sulcus features such as surfaces, fundi and pits have been extracted separately. Here we define and extract nested sulcus features in a hierarchical manner from a cortical surface mesh having curvature or dept. values. Our experimental results show that the nested features are comparable to features extracted separately using other methods, and that they are consistent across subjects and with manual label boundaries. Our open source feature extraction software will be made freely available as part of the Mindboggle project ().

关键词： Automated extraction MRI data sulcus features

来源：评论

学校读者我要写书评

暂无评论

Consistency maintenance in prosodic labeling for reliable prediction of prosodic breaks

Consistency maintenance in prosodic labeling for reliable pr...

引用

5th Linguistic Annotation Workshop, LAW 2011

作者： Jung, Youngim Kwon, Hyuk-Chul Dept. Knowledge Resources Korea Institute of Science and Technology Information 245 Daehang-no Yuseong-gu 305-806 Daejeon Korea Republic of Dept. Computer Science and Engineering Pusan National University San 30 Jangjeon-dong Geumjeon-gu 609-735 Korea Republic of

ISBN: (纸本)9781932432930

For the implementation of the prosody prediction model, large scale annotated speech corpora have been widely applied. Reliability among transcribers, however, was too low for successful learning of an automatic prosodic prediction. This paper reveals our observations on performance deterioration of the learning model due to inconsistent tagging of prosodic breaks in the established corpora. Then, we suggest a method for consistent prosodic labeling among multiple transcribers. As a result, we obtain a corpus with consistent annotation of prosodic breaks. The estimated pairwise agreement of annotation of the main corpus is between 0.7477 and 0.7916, and the value of K is between 0.7057 and 0.7569. Considering the estimated K, annotation of the main corpus has reliable consistency among multiple transcribers. © 2011 Association for Computational Linguistics.

关键词： Forecasting

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：