一种模型驱动的交互式信息可视化开发方法

设计与实现面向领域应用的交互式信息可视化软件十分困难．缺乏统一的开发方法与支撑工具箱，为非专家用户提供对层次、网络、多维等数据类型的统一支持，对各种可视化技术与交互技术的统一支持，以及对信息可视化任务的统一支持．针对此问题，提出了一种模型驱动的交互式信息可视化开发方法Daisy．首先，提出了交互式信息可视化界面模型IIVM（interactive information visualization interface model）；然后，提出了基于IIVM的交互式信息可视化开发方法Daisy,讨论了该方法的两个核心技术：IIVM建模与描述文件生成方法、系统自动生成方法．同时，给出了Daisy工具箱，包括Daisy建模工具、Daisy系统自动生成工具以及运行时框架与组件库．最后，给出了该开发方法与工具箱的应用实例．实例表明，该方法能够为交互式信息可视化开发的统一支撑方法问题提供一种有效的解决方案．

信息可视化中的交互技术研究

随着计算技术的发展，使海量信息得以存在并迅猛增长。近年来商务智能、生物信息学、社会网络分析等新兴应用领域的迅速发展，对海量信息的有效利用提出了迫切的要求。我们正处于信息爆炸的时代，纷繁复杂的信息给人们理解、查询和获取知识带来沉重的负担。信息可视化通过对抽象信息提供计算机支持的、交互式的、可视化的表示形式，不断增强人们对于复杂信息的认知能力，成为人们解释现象、发现规律、辅助决策的强有力工具。 人机交互是信息可视化的重要研究领域。然而，对于信息可视化中的人机交互的研究仍存在以下挑战：一是传统的信息可视化研究主要关注数据转换过程并以可视编码为核心，缺乏从人的角度出发对任务进行全面分析，对于新出现的交互任务提供的理论支持不足，需要对传统信息可视化模型予以扩展。二是针对海量信息在小界面中的可视化与交互问题，如何为用户提供真正符合认知规律的新的交互式可视化技术，使用户能够高效地进行交互探索以洞悉知识。三是针对领域应用中的非专家用户需要构建具有个性化用户界面的交互式信息可视化系统的问题，如何提供一套统一的开发方法。本文正是从上述问题出发，围绕着信息可视化中的交互技术，从理论、方法与应用等方面展开研究。 本文首先论述了信息爆炸带来的挑战以及信息可视化的发展趋势，继而对信息可视化、人机交互、模型驱动架构等相关研究进行了综述。在此基础上构建了交互式信息可视化框架，建立了交互式信息可视化的用户界面模型IIVM。然后，针对海量信息在小界面中的可视化与交互问题，提出了嵌套圆鱼眼视图技术、基于嵌套圆鱼眼视图的Focus+Context交互式可视化技术、基于网络关注度模型的Focus+Context交互式可视化技术。针对非专家用户构建具有个性化用户界面的交互式信息可视化应用的问题，提出了基于模型IIVM的交互式信息可视化系统开发方法Daisy。最后，将上述研究成果应用于制造企业交互式信息可视化系统与计算机文件系统的开发，给出了两个应用实例。 本文的创新点主要包括： 1. 构建了一个交互式信息可视化框架。 本文在信息可视化的经典模型基础上对其进行扩展，构建了一个交互式信息可视化框架。该框架从用户、任务、信息三个方面对信息可视化进行描述，深入分析了信息的转换过程、任务的层次树模型、用户的认知规律，并讨论了三者之间相互影响的关系。该框架提炼了信息可视化中人的特征、计算机表示的信息的特征以及相互之间的关系，能够为信息可视化中的人机交互理论提供支撑。 2. 建立了交互式信息可视化的用户界面模型IIVM。 本文围绕着交互式信息可视化框架中的用户的特征、任务的特征、信息的特征及其相互之间的关系，基于Puerta提出的基于模型的界面开发通用框架中的界面模型，建立了交互式信息可视化的用户界面模型IIVM。讨论了IIVM的抽象组成元素即用户模型、任务模型、领域信息模型，以及具体组成元素即可视化表征模型与对话模型，建立了各个模型间的映射关系，并给出了IIVM的形式化定义。IIVM能够有效地描述具有个性化用户界面的交互式信息可视化系统。 3. 提出了两种新的Focus+Context交互式可视化技术。 针对海量信息在小界面中的可视化与交互问题，在认知心理学规律基础上，提出了嵌套圆鱼眼视图技术；提出了一种基于嵌套圆鱼眼视图的Focus+Context交互式可视化技术；提出了一种基于网络关注度模型的Focus+Context交互式可视化技术。实验结果表明：上述方法能够有效解决在小界面内对海量信息的交互式可视化的问题，具有较高任务完成效率和用户满意度。 4. 提出了一种基于模型的交互式信息可视化系统开发方法Daisy。 提出了一种基于模型IIVM的交互式信息可视化系统开发方法Daisy。描述了该方法的软件生命周期，论述了其中两项关键技术：IIVM建模与描述文件生成方法、系统自动生成方法。讨论了支撑该方法的Daisy平台的体系结构，给出了Daisy工具箱。实验表明，该方法可以为非专家用户构建交互式信息可视化的特定领域应用提供一种有效的解决方案。 5. 基于上述研究成果完成了制造业交互式信息可视化系统和计算机文件可视化系统等两个实际系统的开发。 将研究成果应用于两个系统。一方面，将Daisy方法及Focus+Context交互可视化技术应用于制造业领域，构建了制造业企业交互式信息可视化系统。实例表明，Daisy能够面向非专家用户、为交互式信息可视化系统的开发提供一种统一的解决方案。另一方面，将基于嵌套圆鱼眼视图的Focus+Context交互式可视化技术应用于计算机文件系统，开发了基于嵌套圆的计算机文件可视化系统。应用实例表明，本文研究成果既具有理论价值又具有应用价值。

人口统计信息空间可视化系统研究

Population research is a front area concerned by domestic and overseas, especially its researches on its spatial visualization and its geo-visualization system design, which provides a sound base for understanding and analysis of the regional difference in population distribution and its spatial rules. With the development of GIS, the theory of geo-visualization more and more plays an important role in many research fields, especially in population information visualization, and has been made the big achievements recently. Nevertheless, the current research is less attention paid to the system design for statistical-geo visualization for population information. This paper tries to explore the design theories and methodologies for statistical-geo-visualization system for population information. The researches are mainly focused on the framework, the methodologies and techniques for the system design and construction. The purpose of the research is developed a platform for population atlas by the integration of the former owned copy software of the research group in statistical mapping system. As a modern tool, the system will provide a spatial visual environment for user to analyze the characteristics of population distribution and differentiate the interrelations of the population components. Firstly, the paper discusses the essentiality of geo-visualization for population information and brings forward the key issue in statistical-geo visualization system design based on the analysis of inland and international trends. Secondly, the geo-visualization system for population design, including its structure, functionality, module, user interface design, is studied based on the concepts of theory and technology of geo-visualization. The system design is proposed and further divided into three parts: support layer, technical layer, user layer. The support layer is a basic operation module and main part of the system. The technical layer is a core part of the system, supported by database and function modules. The database module mainly include the integrated population database (comprises spatial data, attribute data and geographical features information), the cartographic symbol library, the color library, the statistical analysis model. The function module of the system consists of thematic map maker component, statistical graph maker component, database management component and statistical analysis component. The user layer is an integrated platform, which provides the functions to design and implement a visual interface for user to query, analysis and management the statistic data and the electronic map. Based on the above, China's E-atlas for population was designed and developed by the integration of the national fifth census data with 1:400 million scaled spatial data. The atlas illustrates the actual development level of the population nowadays in China by about 200 thematic maps relating with 10 map categories(environment, population distribution, sex and age, immigration, nation, family and marriage, birth, education, employment, house). As a scientific reference tool, China's E-atlas for population has already received the high evaluation after published in early 2005. Finally, the paper makes the deep analysis of the sex ratio in China, to show how to use the functions of the system to analyze the specific population problem and how to make the data mining. The analysis results showed that: 1. The sex ratio has been increased in many regions after fourth census in 1990 except the cities in the east region, and the high sex ratio is highly located in hilly and low mountain areas where with the high illiteracy rate and the high poor rate; 2. The statistical-geo visualization system is a powerful tool to handle population information, which can be used to reflect the regional differences and the regional variations of population in China and indicate the interrelations of the population with other environment factors. Although the author tries to bring up a integrate design frame of the statistical-geo visualization system, there are still many problems needed to be resolved with the development of geo-visualization studies.

Web-based spatiotemporal visualization of marine environment data

With long-term marine surveys and research, and especially with the development of new marine environment monitoring technologies, prodigious amounts of complex marine environmental data are generated, and continuously increase rapidly. Features of these data include massive volume, widespread distribution, multiple-sources, heterogeneous, multi-dimensional and dynamic in structure and time. The present study recommends an integrative visualization solution for these data, to enhance the visual display of data and data archives, and to develop a joint use of these data distributed among different organizations or communities. This study also analyses the web services technologies and defines the concept of the marine information gird, then focuses on the spatiotemporal visualization method and proposes a process-oriented spatiotemporal visualization method. We discuss how marine environmental data can be organized based on the spatiotemporal visualization method, and how organized data are represented for use with web services and stored in a reusable fashion. In addition, we provide an original visualization architecture that is integrative and based on the explored technologies. In the end, we propose a prototype system of marine environmental data of the South China Sea for visualizations of Argo floats, sea surface temperature fields, sea current fields, salinity, in-situ investigation data, and ocean stations. An integration visualization architecture is illustrated on the prototype system, which highlights the process-oriented temporal visualization method and demonstrates the benefit of the architecture and the methods described in this study.