检索结果-内蒙古大学图书馆

conference on Pattern Recognition and Computer Vision

作者： Liu, Ming Xu, Xun Huang, Thomas S. Univ Illinois Beckman Inst Image Format Grp Urbana IL 61801 USA

ISBN: (纸本)9780819469526

Combining different modalities for pattern recognition task is a very promising field. Basically, human always fuse information from different modalities to recognize object and perform inference, etc. Audio-Visual gender recognition is one of the most common task in human social communication. Human can identify the gender by facial appearance, by speech and also by body gait. Indeed, human gender recognition is a multi-modal data acquisition and processing procedure. However, computational multimodal gender recognition has not been extensively investigated in the literature. In this paper, speech and facial image are fused to perform a mutli-modal gender recognition for exploring the improvement of combining different modalities.

关键词： visualization Acoustics Binary data databases Pattern recognition Neural networks Computer vision technology data acquisition Gait analysis Machine vision

来源：评论

学校读者我要写书评

暂无评论

Use of circle-segments as a data visualization technique for feature selection in pattern classification

Use of circle-segments as a data visualization technique for...

引用

14th International conference on Neural Information Processing (ICONIP 2007)

作者： Wang, Shir Li Loy, Chen Change Lim, Chee Peng Lai, Weng Kin Tan, Kay Sin Univ Sci Malaysia Sch Elect & Elect Engn Engn Campus14300 Nibong Tebal George Town Malaysia MIMOS Berhad Ctr Adv Informat Kuala Lumpur 57000 Malaysia Univ Malaya Fac Med Dept Med Kuala Lumpur 50603 Malaysia

ISBN: (纸本)9783540691549

One of the issues associated with pattern classification using databased machine learning systems is the "curse of dimensionality". In this paper, the circle-segments method is proposed as a feature selection rnethod to identify important input features before the entire data set is provided for learning with machine learning systems. Specifically, four machine learning systems are deployed for classification, viz. Multilayer Perceptron (MLP), Support Vector Machine (SVM), Fuzzy ARTMAP (FAM), and k-Nearest Neighbour(kNN). The integration between the circle-segments method and the machine learning systems has been applied to two case studies comprising one benchmark and one real data sets. Overall, the results after feature selection using the circle-segments method demonstrate improvements in performance even with more than 50% of the input features eliminated from the original data sets.

关键词： feature selection circle-segments data visualization principal component analysis machine learning techniques

来源：评论

学校读者我要写书评

暂无评论

Optimal clustering of kinetic patterns on malignant breast lesions: Comparison between K-means clustering and three-time-points method in dynamic contrast-enhanced MRI

Optimal clustering of kinetic patterns on malignant breast l...

引用

29th Annual International conference of the IEEE-Engineering-in-Medicine-and-Biology-Society

作者： Lee, S. H. Kim, J. H. Kim, K. G. Park, J. S. Park, S. J. Moon, W. K. Seoul Natl Univ Coll Med Interdisciplinary Program Radiat Appl Life Sci Seoul 151 South Korea Seoul Natl Univ Hosp Dept Radiol Seoul South Korea Seoul Natl Univ Med Res Ctr Inst Radiat Med Seoul South Korea

ISBN: (纸本)9781424407873

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is useful for breast cancer diagnosis and treatment planning. Nevertheless, due to the multi-temporal nature of DCE-MRI data, the assessment of early stage breast cancer is a challenging task. In this study, we applied an unsupervised clustering approach and cluster validation technique to the analysis of malignant intral-tumoral kinetic curves in DCE-MRI. K-means cluster analysis was performed from real world malignant tumor cases and the data were transformed into an optimal number of reference patterns representative each cluster. The optimal number of clusters was estimated by a cluster validation index, which was calculated with the ratio of inter-class scatter to intra-class scatter. This technique then classifies tumor specific patterns from a given MRI data by measuring the vector distances from the reference pattern seta and compared the result from the k-means clustering with that from three-time-points (3TP) method, which represents a clinical standard protocol for analysis of tumor kinetics. The evaluation of twenty five cases indicates that optimal k-means clustering reflects partitioning intra-tumoral kinetic patterns better than the 3TP technique. This method will greatly enhance the capability of radiologists to identify and characterize internal kinetic heterogeneity and vascular change of a tumor in breast DCE-MRI.

关键词： DCE-MRI breast cancer kinetics k-means clustering 3TP method visualization

来源：评论

学校读者我要写书评

暂无评论

Evolution of the Socio-cognitive Structure of Knowledge Management(1986–2015): An Author Co-citation analysis

引用

Journal of data and Information Science 2019年第2期4卷 36-55页

作者： Carlos Luis González-Valiente Magda León Santos Ricardo Arencibia-Jorge Biblioteca Nacional de Cuba "José Martí" ave.Independencia Facultad de Comunicación Universidad de la Habana San Pedro entre Ermita y Avenida Independencia Empresa de Tecnologías de la Información

Purpose: The evolution of the socio-cognitive structure of the field of knowledge management(KM) during the period 1986–2015 is described. Design/methodology/approach: Records retrieved from Web of Science were submitted to author co-citation analysis(ACA) following a longitudinal perspective as of the following time slices: 1986–1996, 1997–2006, and 2007–2015. The top 10% of most cited first authors by sub-periods were mapped in bibliometric networks in order to interpret the communities formed and their ***: KM is a homogeneous field as indicated by networks results. Nine classical authors are identified since they are highly co-cited in each sub-period, highlighting Ikujiro Nonaka as the most influential authors in the field. The most significant communities in KM are devoted to strategic management, KM foundations, organisational learning and behaviour, and organisational theories. Major trends in the evolution of the intellectual structure of KM evidence a technological influence in 1986–1996, a strategic influence in 1997–2006, and finally a sociological influence in 2007–*** limitations: Describing a field from a single database can offer biases in terms of output coverage. Likewise, the conference proceedings and books were not used and the analysis was only based on first authors. However, the results obtained can be very useful to understand the evolution of KM *** implications: These results might be useful for managers and academicians to understand the evolution of KM field and to(re)define research activities and organisational ***/value: The novelty of this paper lies in considering ACA as a bibliometric technique to study KM research. In addition, our investigation has a wider time coverage than earlier articles.

关键词： Knowledge management Bibliometrics Author co-citation analysis Knowledge domain visualization Social network analysis Intellectual structure

来源：评论

学校读者我要写书评

暂无评论

analysis of the MPI-IO optimization levels with the PIOViz jumpshot enhancement

引用

14th EuroPVM/MPI conference

作者： Ludwig, Thomas Krempel, Stephan Kuhn, Michael Kunkel, Julian Lohse, Christian Ruprecht Karls Univ Heidelberg D-69120 Heidelberg Germany

ISBN: (纸本)9783540754152

With MPI-IO we see various alternatives for programming file I/O. The overall program performance depends on many different factors. A new trace analysis environment provides deeper insight into the client/server behavior and visualizes events of both process types. We investigate the influence of making independent vs. collective calls together with access to contiguous and non-contiguous data regions in our MPI-IO program. Combined client and server traces exhibit reasons for observed I/O performance.

关键词： parallel I/O MPI-IO performance visualization Trace-Based tools

来源：评论

学校读者我要写书评

暂无评论

Facilitating interdisciplinary PLM through usage of Hub methodology and 3D lightweight visualisation data

Facilitating interdisciplinary PLM through usage of Hub meth...

引用

16th International conference on Engineering Design, ICED 2007

作者： Zimmerman, Trond Malmqvist, Johan Volvo Information Technology PLM Solution Center Dept. 9143 PVV3:1 SE-405 08 Göteborg Sweden Chalmers University of Technology Göteborg Sweden

ISBN: (纸本)1904670024

Demands on shortened development leadtimes in many branches of the manufacturing industry has implied earlier and more intense efforts of sales, manufacturing and aftermarket preparations than before. Thus, the need of sharing emerging pieces of the product definition from product development to downstream processes such as manufacturing and aftermarket has received more attention in later times. An important view of the product definition is its geometrical representation. Distribution and use of 3D visualisation data is a critical ability for an effective downstream development. This work relates to a study in the commercial vehicle industry and concern issues on how to efficiently distribute configured visualisation data to the aftermarket preparation process throughout the product development process, including the conceptual design phases. This includes utilisation of visualisation data for production of service and repair methods, service information, parts assortment and spare parts information. The results unfold information needs from, and requirements on the Product Lifecycle Management (PLM) system, from an aftermarket perspective. These prerequisites are set in relation to available information technology and utilised or evolved architectural concepts. The analysis comprise an exploitation of 3D lightweight formats as a mean for carrying geometrical definitions between processes and organisations, as well as different standards and techniques for establishing a working application and infrastructure architecture in support. The principal element is an architectural design for an Engineering Portal (Hub) and adherent feasibility analysis.

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

An integrated visual intrusion detection and analysis system

An integrated visual intrusion detection and analysis system

引用

Proceedings of the International conference on Internet Computing, IC'04

作者： Rana, Aurangzieb Zieh Huang, Mao Lin Faculty of Information Technology University of Technology Sydney Broadway 2007 Australia

The existing Intrusion Detection Systems often convey intrusion detection by using either or combination of network intrusion detection sensors, and host intrusion detection sensors. They do not integrate other devices such as firewalls, routers, mail, web, and DNS servers to extend the data collection resources. As a result of limited data resources, the higher correlation among intrusion data cannot be achieved and higher accurate results cannot be produced. There is also an issue of security between IDS sensors and central console. The intrusion results are also often represented as textual log files and hence are more difficult to analyze by a human user. This paper discusses a need and proposes a framework for an Integrated Intrusion detection system with inbuilt visual analysis tool. This system will provide various logs, audit trails, policy violations and alerts. All of this data could be collected and aggregated into a single database. The database could then be analyzed by using data mining and information visualization methods to determine and verify if an intrusion has occurred.

关键词： World Wide Web

来源：评论

学校读者我要写书评

暂无评论

Visual representation of construction progress monitoring metrics on time-lapse photographs

Visual representation of construction progress monitoring me...

引用

25th Inaugural Construction Management and Economics: 'Past, Present and Future' conference, CME 2007

作者： Fard, Mani Golparvar Sridharan, Aravind Lee, Sanghyun Peña-Mora, Feniosky Construction Management Group Department of Civil and Environmental Engineering University of Illinois Urbana-Champaign 205 N. Mathews Ave. Urbana IL 61801 United States Department of Civil and Environmental Engineering University of Alberta CNRL Natural Resources Engineering Facility Edmonton 3-133 Markin AB T6G 2W2 Canada

ISBN: (纸本)9780415460590

A low cost progress data collection technique for construction projects using time-lapse photography or real-time videotaping can provide a wealth of spatial and temporal information for progress data collection. The benefits of using photographs would be maximized if the progress deviations between planned and actual (as-built) performance are visually shown on these photographs. The importance of such visual representation of construction progress is well understood when the participation of diverse parties with different levels of expertise (from owners to subcontractors) is considered. Current formats of monitoring reports (e.g. textual progress reports, progress graphs or charts) may not properly and quickly communicate progress situations and would make understanding of the progress situation difficult. Current methods of monitoring require manual data collection and extensive data extraction from construction documents making progress monitoring a time-consuming process and distracts managers from the important task of decision making. As an effort to address this issue, a visual representation of construction progress is proposed that aims to picture the progress situation on time-lapse photographs (representing actual progress), superimpose the planned progress (obtained from the 4D as-planned model), and provide the clear comparison in an augmented reality environment between as-planned and as-built progress. A series of visualization techniques (e.g. colour and colour gradient) is developed to communicate and visualize detected discrepancies and progress performance metrics. Schedule deviations, construction sequence, budget distribution and earned value analysis metrics (cost performance and schedule performance indices) are also visualized. These techniques if automated could accurately and quickly communicate the progress situation on photographs and provide a powerful tool for prompt progress control decision making.

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

Adaptation of video game UVW mapping to 3D visualization of gene expression patterns

Adaptation of video game UVW mapping to 3D visualization of ...

引用

conference on Multimedia Content Access - Algorithms and Systems

作者： Vize, Peter D. Gerth, Victor E. Univ Calgary Dept Biol Sci 2500 Univ Dr 1 NW Calgary AB T2N 1N4 Canada Univ Calgary Dept Comp Sci Calgary AB T2N 1N4 Canada

ISBN: (纸本)9780819466198

analysis of gene expression patterns within an organism plays a critical role in associating genes with biological processes in both health and disease. During embryonic development the analysis and comparison of different gene expression patterns allows biologists to identify candidate genes that may regulate the formation of normal tissues and organs and to search for genes associated with congenital diseases. No two individual embryos, or organs, are exactly the same shape or size so comparing spatial gene expression in one embryo to that in another is difficult. We will present our efforts in comparing gene expression data collected using both volumetric and projection approaches. Volumetric data is highly accurate but difficult to process and compare. Projection methods use UV mapping to align texture maps to standardized spatial frameworks. This approach is less accurate but is very rapid and requires very little processing. We have built a database of over 180 3D models depicting gene expression patterns mapped onto the surface of spline based embryo models. Gene expression data in different models can easily be compared to determine common regions of activity. visualization software, both Java and OpenGL optimized for viewing 3D gene expression data will also be demonstrated.

关键词： UVW mapping in situ hybridization gene expression

来源：评论

学校读者我要写书评

暂无评论

A network algorithm to discover sequential patterns

A network algorithm to discover sequential patterns

引用

13th Portuguese conference on Artificial Intelligence

作者： Cavique, Luis ESCS-IPL Portugal

ISBN: (纸本)9783540770008

This paper addresses the discovery of sequential patterns in very large databases. Most of the existing algorithms use lattice structures in the space search that are very demanding computationally. The output of these algorithms generates a large number of rules. The aim of this work is to create a swift algorithm for the discovery of sequential patterns with a low time complexity. In this work, we also want to define tools that allow us to simplify the work of the final user, by offering a new visualization of the sequences, while bypassing the analysis of thousands of association rules.

关键词： data mining frequent sequence mining graph theory.

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：