在线草图识别中的用户适应性研究

提出一种在线草图识别用户适应性解决方法，该方法分别采用支撑向量机主动式增量学习和动态用户建模技术进行笔划和复杂图形的识别．支撑向量机主动式增量学习方法通过主动“分析”用户增量数据，并根据用户反馈从中选择重要数据作为训练样本，可有效地鉴别用户手绘笔划特征，快速地识别用户输入笔划．动态用户建模技术则采用增量决策树记录草图的笔划构成及其手绘过程，有效捕捉用户的复杂图形手绘习惯，进而利用模糊匹配在草图绘制过程中预测和识别复杂图形．实验表明：该方法具有很好的效果，为解决在线草图识别及其用户适应性问题提供参考．     

在线手绘草图识别中的用户建模方法

提出了一种在线手绘草图识别的用户建模方法。该方法首先利用用户输入笔划的速率和曲率特性进行笔划特征点抽取和笔划分段,从而将用户的输入草图分解成基本图元表示;进而,利用决策树收集和记录用户输入草图的时序信息,实现对复杂手绘草图的用户建模和在线识别,并通过对用户输入模式使用频率的统计实现对用户模型的动态管理和更新。实验表明:该方法不仅能显著提高复杂图形的识别效率,而且具有在线训练能力。     

基于用户建模的手绘草图识别

在线草图识别包括预处理、特征提取、图形规整和用户建模等几个方面的问题。其中用户建模是手绘草图识别的核心和关键问题。提出了一种在线草图识别用户建模方法,方法用动态用户建模技术进行笔划和复杂图形的识别。方法采用增量决策树记录草图的笔划构成及其手绘过程,实现对复杂手绘草图的用户建模和在线识别。实验表明所提出的方法不仅能得到较好的检索结果,而且具有较好的用户适用性     

基于自适应HMM的在线草图识别方法

用户适应性是在线手绘草图识别的一个关键问题。本文以实现草图识别的自适应性为目标,对草图识别中的用户适应性问题进行了深入的研究和实验,提出了一种自适应草图识别解决方法,并针对在线草图识别的特点,提出了一种基于笔划曲率,速率以及整体几何特性的组合特征。本文重点研究并实现了基于自适应HMM的草图识别,在已有HMM的基础上,针对在线草图识别的特点,提出了状态数可变自适应HMM的学习方法。实验表明本文所提出的方法具有很好的效果。     

在线草图识别中用户手绘习惯建模方法

手绘草图是概念设计和思路外化的一种高效的表达方式。用户绘制草图时存在的多种形式，及其随意性和模糊性使得用户适应性问题逐渐成为草图识别的核心课题。本文提出了一种在线草图识别的用户建模方法来捕捉绘制草图时的用户习惯，主要包括两个方面的内容：一是基于SVM的主动式增量学习方法，二是基于动态用户建模的手绘复杂图形的识别方法。前者与传统的增量式学习方法相比，在识别精度相同的情况下所需的训练时间和训练数据集要少得多。后者则是基于笔划信息以及笔划间的顺序和空间关系信息，采用增量式决策树捕捉用户的输入习惯和过程信息。实验证明了本文方法在在线草图识别中的有效性和高效性。     

基于轮廓的手绘草图检索研究

利用傅利叶形状描述方法来统一描述手绘草图图像库和用户输入的手绘草图形状信息,该方法解决了基于笔划描述的计算效率和输入顺序敏感性问题。实验表明所提出的方法不仅能得到较好的检索结果,且具有较好的用户适应性。     

手绘草图的在线分段识别

提出了一种在线手绘草图快速分段识别方法。先对草绘笔划进行平滑预处理,以减少噪声干扰和冗余点的数目;然后利用草绘笔划的动静态特性,以及用户的草绘习惯等特性找出笔划的关键分段点,将笔划分为多个笔划子段;最后利用基于二次曲线的方法对笔划子段进行分段识别和特征参数计算,并通过构造面向对象的图形数据结构对识别出的几何图元进行重构。实例表明,该方法具有较好的识别能力和系统稳定性,能够应用于二维概念草图的快速表达,以及后续三维草绘建模的特征笔划智能识别过程中。     

基于草图的人机交互技术研究进展

从草图识别和语义理解这两个方面对基于草图的人机交互技术的研究状况进行了分析和总结．对草图识别方法按其模式单元定义（笔划、图元、特征和组合图形）进行了分类和剖析;对草图语义理解所涉及的语义获取、语义解释和语义应用这三个关键问题及其解决方法进行了分析和阐述;并分别从基于草图的人机交互技术的几何模糊性、用户适应性和应用独旁性及其关系角度提出了这一领域的主要研究课题及其解决思路．     

手绘草图识别中的相关反馈方法

手绘草图是人类思维外化和表达设计意图的有效工具之一,手绘草图的模糊性和用户适应性问题是草图识别中的关键问题。本文提出了将相关反馈机制引入到手绘草图识别中以捕捉用户意图的方法,该方法以抽取手绘草图的向量化特征为基础,首先利用基于图形特征的相似度计算,给出手绘草图候选识别结果集,然后借助用户对识别结果的相关性评价,通过逐渐调整图形构成特征的权重来捕捉用户输入意图,并提高识别效果。实验表明本文所提出的方法具有很好的效果。     

草图理解技术研究进展

本文概述了草图理解技术(包括草图识别和语义理解)的现状。首先，草图识别包括预处理和图形识别．根据各种图形处理机制，介绍了四种图形识别方法：基于笔划的、基于图元的、基于几何特征的、基于组合图形的。其次．深入分析了几个语义理解方法，一般包括三个环节：语义获取关系分析和高层应用。最后，本文提出了几何模型、用户模型和领域模型。讨论了草图理解中的主要问题并给出初步解决方案。     

A novel model of adaptation decision-taking engine in multimedia adaptation

In heterogeneous environments, universal multimedia access (UMA) is proposed to provide multimedia content services. Multimedia adaptation is one of technologies to perform UMA, in which adaptation decision-taking engine (ADTE) is a key component. Though there are many models of ADTE existing, it needs to be reconsidered for personalized content services. In this paper, a novel model of ADTE is proposed based on decision tree termed adaptation decision tree (ADT) in which adaptation decision is viewed as sequence decision: modality decision and format decision. Correspondingly, user preferences are divided into two types: user modality preferences and user format preferences. By utilizing user preferences, the ADT model is built up. Before making decision, an optimal multimedia variation set (OMVS) with respect to user modality preferences is constructed and any element here is with the shortest distance to user format preferences for every modality. Therefore, adaptation decision can be executed by letting the element in OMVS travel along the ADT one by one. Finally, the first element that reaches the leaf with the logical value true is the decision result, or the one with the smallest value in distance is the decision variation if no elements get to proper leaf. Quantitative analysis and experimental simulation prove that the model is effective and efficient to cope with adaptation decision in multimedia adaptation especially in dynamic user preferences and resource-limited cases.     

Integrating adaptation rules for people with special needs in model-based UI development process

The adaptation of user interfaces for people with special needs is a promising approach in order to enable their access to digital services. Model-based user interfaces provide a useful approach for this purpose since they allow tailoring final user interfaces with a high degree of flexibility. This paper describes a system called Adaptation Integration System aimed at providing Cameleon Reference Framework model-based tools with a mechanism to integrate adaptation rules in the development process. Thus, more accessible user-tailored interfaces can be automatically generated. The services provided by the system can be applied at both design time and runtime. At design time, a user interface can be tailored at any abstraction level in the development process. At runtime, changes in the context of use trigger the adaptation process. Adaptation rules are stored in a repository tagged with meta-information useful for the adaptation process, such as the granularity of the adaptations and the abstraction level. As case studies, two applications have been developed using the services provided by the system. One of them exploits the benefits at design time, whereas the other application is devoted to describe the adaptation process at runtime. The results obtained in these two scenarios demonstrate the viability and potential of the adaption integration system since even inexperienced designers may efficiently produce accessible user interfaces.     

Mobile access to real-time information—the case of autonomous stock brokering

When services providing real-time information are accessible from mobile devices, functionality is often restricted and no adaptation of the user interface to the mobile device is attempted. Mobile access to real-time information requires designs for multi-device access and automated facilities for the adaptation of user interfaces. We present TapBroker, a push update service that provides mobile and stationary access to information on autonomous agents trading stocks. TapBroker is developed for the Ubiquitous Interactor system and is accessible from Java Swing user interfaces and Web user interfaces on desktop computers, and from a Java Awt user interface on mobile phones. New user interfaces can easily be added without changes in the service logic.     

A new approach to automatic and a priori mesh adaptation around circular holes for finite element analysis

Through our research on the integration of finite element analysis in the design and manufacturing process with CAD, we have proposed the concept of mesh pre-optimization. This concept consists in converting shape and analysis information in a size map (a mesh sizing function) with respect to various adaptation criteria (refining the mesh around geometric form features, minimizing the geometric discretization error, boundary conditions, etc.). This size map then represents a constraint that has to be respected by automatic mesh generation procedures. This paper introduces a new approach to automatic mesh adaptation around circular holes. This tool aims at optimizing, before any FEA, the mesh of a CAD model around circular holes. This approach, referred to as “a priori” mesh adaptation, should not be regarded as an alternative to adaptive a posteriori mesh refinement but as an efficient way to obtain reasonably accurate FEA results before a posteriori adaptation, which is particularly interesting when evaluating design scenarios. The approach is based on performing many offline FEA analyses on a reference case and deriving, from results and error distributions obtained, a relationship between mesh size and FEA error. This relationship can then be extended to target user specified FEA accuracy objectives in a priori mesh adaptation for any distribution of circular holes. The approach being purely heuristic, fulfilling FEA accuracy objectives, in all cases, cannot be theoretically guaranteed. However, results obtained using varying hole diameters and distributions in 2D show that this heuristic approach is reliable and useful. Preliminary results also show that extension of the method can be foreseen towards a priori mesh adaptation in 3D and mesh adaptation around other types of 2D features.     

Adapting Web content to mobile user agents

In this article, we describe an adaptation proxy we developed as a part of a Kontti research project at VTT Information Technology that lets mobile users access Web content that's not directly targeted to mobile user agents. More and more content is now available on the Internet, and there's a growing need for mobile users to be able to access it. Thus the authors describe the adaptation proxy, which lets mobile users access Web content that's not directly targeted to user agents of mobile devices. The adaptation proxy can adapt Extensible Hypertext Markup Language (XHTML) documents into XHTML mobile profile (XHTML MP) and Wireless Markup Language (WML), and can perform media adaptation. At the system's core is an adaptation framework to which new source and target XML languages can be introduced with relatively little effort.     

Contributions of Dichotomic View of plasticity to seamlessly embed accessibility and adaptivity support in user interfaces

Recent legal changes have increased the need for developing accessible user interfaces in computer-based systems. In this sense, previously existing user interfaces are intended to be modified and new user interfaces are intended to be designed taking accessibility guidelines into account. Typically, model-based approaches have been used when developing accessible user interfaces or redefining existing ones. But the use of static models leads to the development of not dynamically adaptable user interfaces. Dynamic adaptation in accessible user interfaces is important due to the fact that interaction difficulties on people with disabilities may change through use. In this paper, we present some contributions that can be obtained from the application of the Dichotomic View of plasticity in the personalization of user interfaces. With the double perspective defined in this approach, it is intended to go further from a mere adaptation to certain user stereotypes, offering also a dynamic support to real limitations or difficulties users can encounter during the use of the UI. This goal is achieved analyzing user logs by an inference engine that dynamically infers modifications in the user interface to adjust it to varying user needs. A case study is presented in order to show how the guidelines and software support defined in the Dichotomic View of plasticity can be applied to develop a component for a particular system aimed at performing dynamic user interface adaptations with accessibility purposes. This approach includes some innovations that make it different from conventional adaptable mechanisms applied to accessibility in some important aspects.     

Personalized video adaptation framework (PIAF): high-level semantic adaptation

Despite much work on Universal Multimedia Experience (UME), existing video adaptation approaches cannot yet be considered as truly user-centric, mostly due to their poor handling of semantic user preferences. Indeed, these works mainly concentrate on lower-level user preferences but do neither consider any fine-grained object-level adaptation nor evaluate different adaptation options based on predicted user expectations. Moreover, these works do not provide owners with property rights that enable them to place restrictions on the types of modifications to be made to the video content. To address these shortcomings, we propose the Personalized vIdeo Adaptation Framework (PIAF) for high-level semantic video adaptation. PIAF is a fully integrated framework providing all the requirements for a semantic video adaptation. It defines a video annotation model and a user profile model comprising semantic constraints that are delineated in a consistent way, based on the standards MPEG-7 and MPEG-21. At the heart of the framework, the Adaptation Decision Taking Engine (ADTE) computes utility values for different adaptation options, considering each shot separately. The corresponding utility function evaluates the possible choices by evaluating multiple parameters that capture different dimensions of a multimedia experience: amount of modified content, modifications to key objects and shots with respect to the semantic integrity of the original content, expected processing cost of the adaptation, and the anticipated visual and temporal quality of the adapted content. Furthermore, the ADTE can deal with intellectual property issues by selecting an adaptation plan of good quality that also satisfies constraints specified by the content owner. This paper places a significant emphasis on theoretical details of the utility function and the computation of the adaptation plan. It also presents the results and evaluation of the adaptation process both in simulation and user study.