面向多网多终端协同的内容适配服务

目前的内容适配技术主要从单网络单终端角度出发,未考虑当前及未来可能的网络运营模式。为解决设备能力和多媒体内容/服务不匹配问题,引入内容适配技术,提出一种面向多网多终端协同的内容适配技术。通过引入本体建模技术,将复杂的多网多终端环境化分为单网单终端、单网多终端和多网单终端3种情况,并采用逻辑决策和物理决策的两级决策方案,实现多网多终端协同的内容适配服务,从而完善单网单终端向多网多终端的过渡。应用结果表明,该内容适配模型可解决终端能力和多媒体内容/服务不匹配问题。     

内容适配技术研究综述

内容适配技术是实现通用多媒体接入的技术体系。MPEG-21标准提出了内容适配技术框架和服务环境描述技术规范。针对MPEG-21内容适配框架,从内容适配系统、服务环境数据交换、适配决策等方面,介绍国内外相关研究现状。     

MPEG-21中的数字项适配技术研究

数字项适配是MPEG-21标准中一项非常重要的关键技术.本文研究MPEG-21中的数字项适配技术以及媒体独立格式的资源适配机制,实现一套基于MPEG-21 DIA的图像适配系统,提供了数字项解析、适配决策形成以及资源适配等功能.并在此基础之上试验了新的基于感兴趣区域的适配方法.试验结果表明该系统是完整和有效的,采用的新的适配方法是新颖的.     

内容适配系统设计及性能评价研究

内容适配技术是实现通用多媒体访问的主流技术,如何实现内容适配系统是内容适配技术研究中的重要问题。基于SOA架构设计并实现内容适配系统。系统具有数据管理、服务管理、内容适配和内容服务功能。采用客观和主观指标结合的评价体系,对内容适配系统的服务质量进行评价。     

数字媒体适配过程的一般框架、模型及应用研究

丰富的媒体内容和格式、异构的网络以及多样的终端设备,成为通用媒体访问的巨大障碍,媒体适配成为必要.文中分析了MPEG-21数字媒体适配DIA各实体之间的抽象关系,讨论了数字媒体适配的一般框架,建立了基于混合变量的约束优化模型.该模型统一了现有的媒体适配应用研究,能够用一致的算法进行求解.同时,文中从图像理解和视频分析角度,建立了媒体适配的层次结构,对媒体适配应用进行分类,并以当前的主要应用研究如图像适配、视频转码、位率适配、视频对象适配等举例说明.文中也探讨了混合媒体的多模态适配,指出了今后的研究热点和难点,如媒体语义抽取和适配、用户主观测度和媒体访问体验最大化等.     

Java类库演化过程中客户端代码适配方法

类库技术使得程序员无需了解实现细节,直接调用类库暴露的接口就可以组织软件产品的业务逻辑。由于类库的版本不断演化,将客户端代码适配到新类库的时间与成本将大幅增加。为此,提出一个代码适配层自动化生成的解决方案,来应对Java语言类库的类库演化问题。分析Java类库演化的常见模式,针对每一种类库演化模式给出相应的适配方案,在此基础上开发适配层代码生成器。针对特定的客户端代码,适配层代码生成器为客户端代码自动产生适配层代码,以完成客户端代码对新类库的兼容。最后,通过一个案例研究,展示了该方法的可行性。     

决策树在贷款客户信用评估中的应用

针对如何在贷款过程中尽可能地降低风险,提出利用决策树理论对客户的基本情况进行分析,建立银行贷款客户信用评估决策树模型。为防止过拟合问题的产生,对最初生成的决策树又利用基于规则的方法进行裁剪修正,使得决策模型不只在训练集上的信用度决策获正确率较高,在相互独立的不同测试集和验证集上都取得令人满意的效果。     

构件交互模型与组合适配方法研究

构件交互操作与构件适配是基于构件的软件开发方法(CBD)中的关键问题。如何更有效地解决构件适配问题以提高软件的开发质量是一个永久的热点。而构件间的交互操作又是解决构件适配问题的关键所在。在已有的研究成果的基础上、基于自动机理论提出了一种构件交互模型。它将构件接口根据所提供的服务不同分为调用接口和使用接口,使得对构件间的交互操作描述的更为准确。在此基础上,对构件组合适配方法进行了分析。     

基于迁移学习的信用评分预测

在互联网金融机构有很多信贷业务, 部分新开展的业务由于客户数据较少, 无法建立有效的信用评分模型. 本文研究将迁移学习思想应用到该问题中, 利用已有其他业务的客户数据帮助新开展的业务建立有效的信用评分模型. 本文提出一种联合Triplet-Loss表征学习和领域适配的深度学习方法对已有业务数据进行重新编码, 并将重新编码后所得的知识迁移到新开展业务的模型中, 最后使用XGBoost做为分类器. 针对上述问题, 本文提出的模型相对传统机器学习方法在效果上有一定提升, 在一定程度上解决了该问题.     

动态Web服务行为适配方法初探

面向服务的计算是当前软件工程领域和软件产业界的研究热点之一。随着Web服务组合技术的广泛应用,服务间的行为交互日趋复杂,已存在的静态Web服务行为适配方法难以支持复杂Web服务间的行为适配。以此为背景,首先介绍Web服务适配的相关概念,然后分析现有的静态Web服务行为适配方法的研究现状和存在的主要问题,最后探讨动态Web服务行为适配的基本原理、一般方法和技术优势。     

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.     

Seamless video access for mobile devices by content-aware utility-based adaptation

Today’s Internet multimedia services are characterized by heterogeneous networks, a wide range of terminals, diverse user preferences, and varying natural environment conditions. Heterogeneity of terminals, networks, and user preferences impose nontrivial challenges to the Internet multimedia services for providing seamless multimedia access particularly for mobile devices (e.g., laptops, tablet PCs, PDAs, mobile phones, etc.). Thus, it is essential that advanced multimedia technologies are developed to deal with these challenges. One of these technologies is video adaptation, which has gained significant importance with its main objective of enabling seamless access to video contents available over the Internet. Adaptation decision taking, which can be considered as the “brain” of video adaptation, assists video adaptation to achieve this objective. Scalable Video Coding (SVC) offers flexibility for video adaptation through providing a comprehensive set of scalability parameters (i.e., temporal, spatial, and quality) for producing scalable video streams. Deciding the best combination of scalability parameters to adapt a scalable video stream while satisfying a set of constraints (e.g., device specifics, network bandwidth, etc.) poses challenges for the existing adaptation services to enable seamless video access. To ease such challenges, an adaptation decision taking technique employing a utility-based approach to decide on the most adequate scalability parameters for adaptation operations is developed. A Utility Function (UF), which models the relationships among the scalability parameters and weights specifying the relative importance of these parameters considering video content characteristics (i.e., motion activity and structural feature), is proposed to assist the developed technique. In order to perform the developed adaptation decision taking technique, a video adaptation framework is also proposed in this paper. The adaptation experiments performed using the proposed framework prove the effectiveness of the framework to provide an important step towards enabling seamless video access for mobile devices to enhance viewing experience of users.     

Digital item adaptation: overview of standardization and research activities

MPEG-21 Digital Item Adaptation (DIA) has recently been finalized as part of the MPEG-21 Multimedia Framework. DIA specifies metadata for assisting the adaptation of Digital Items according to constraints on the storage, transmission and consumption, thereby enabling various types of quality of service management. This paper provides an overview of DIA, describes its use in multimedia applications, and reports on some of the ongoing activities in MPEG on extending DIA for use in rights governed environments.     

Optimal adaptation decision-taking for terminal and network quality-of-service

In order to cater to the diversity of terminals and networks, efficient, and flexible adaptation of multimedia content in the delivery path to end consumers is required. To this end, it is necessary to associate the content with metadata that provides the relationship between feasible adaptation choices and various media characteristics obtained as a function of these choices. Furthermore, adaptation is driven by specification of terminal, network, user preference or rights based constraints on media characteristics that are to be satisfied by the adaptation process. Using the metadata and the constraint specification, an adaptation engine can take an appropriate decision for adaptation, efficiently and flexibly. MPEG-21 Part 7 entitled Digital Item Adaptation standardizes among other things the metadata and constraint specifications that act as interfaces to the decision-taking component of an adaptation engine. This paper presents the concepts behind these tools in the standard, shows universal methods based on pattern search to process the information in the tools to make decisions, and presents some adaptation use cases where these tools can be used.     

普适个性化多媒体服务技术综述*

随着数字技术和通信技术的快速发展,越来越多的普适设备能够接收和处理更多的多媒体信息。提供面向普适环境的多媒体个性化服务成为今天研究的热点。从普适个性化多媒体服务研究的不同侧面对其进行了综述,介绍了普适个性化多媒体服务的通用体系结构;对实现普适个性化多媒体服务的关键技术进行了详细的描述,包括描述模型、媒体代码转换与适应技术、用户喜好获取与更新和多媒体推荐技术;最后总结了现有的研究及其不足,指出进一步需要研究的方向。     

Feature pattern based representation of multimedia documents for efficient knowledge discovery

The rapid growth of multimedia documents has raised huge demand for sophisticated multimedia knowledge discovery systems. The knowledge extraction of the documents mainly relies on the data representation model and the document representation model. As the multimedia document comprised of multimodal multimedia objects, the data representation depends on modality of the objects. The multimodal objects require distinct processing and feature extraction methods resulting in different features with different dimensionalities. Managing multiple types of features is challenging for knowledge extraction tasks. The unified representation of multimedia document benefits the knowledge extraction process, as they are represented by same type of features. The appropriate document representation will benefit the overall decision making process by reducing the search time and memory requirements. In this paper, we propose a domain converting method known as Multimedia to Signal converter (MSC) to represent the multimodal multimedia document in an unified representation by converting multimodal objects as signal objects. A tree based approach known as Multimedia Feature Pattern (MFP) tree is proposed for the compact representation of multimedia documents in terms of features of multimedia objects. The effectiveness of the proposed framework is evaluated by performing the experiments on four multimodal datasets. Experimental results show that the unified representation of multimedia documents helped in improving the classification accuracy for the documents. The MFP tree based representation of multimedia documents not only reduces the search time and memory requirements, also outperforms the competitive approaches for search and retrieval of multimedia documents.