MOVE: A Distributed Framework for Materialized Ontology View Extraction

The use of ontologies lies at the very heart of the newly emerging era of semantic web. Ontologies provide a shared conceptualization of some domain that may be communicated between people and application systems. As information on the web increases significantly in size, web ontologies also tend to grow bigger, to such an extent that they become too large to be used in their entirety by any single application. Moreover, because of the size of the original ontology, the process of repeatedly iterating the millions of nodes and relationships to form an optimized sub-ontology becomes very computationally extensive. Therefore, it is imperative that parallel and distributed computing techniques be utilized to implement the extraction process. These problems have stimulated our work in the area of sub-ontology extraction where each user may extract optimized sub-ontologies from an existing base ontology. The extraction process consists of a number of independent optimization schemes that cover various aspects of the optimization process, such as ensuring consistency of the user-specified requirements for the sub-ontology, ensuring semantic completeness of the sub-ontology, etc. Sub-ontologies are valid independent ontologies, known as materialized ontologies, that are specifically extracted to meet certain needs. Our proposed and implemented framework for the extraction process, referred to as Materialized Ontology View Extractor (MOVE), has addressed this problem by proposing a distributed architecture for the extraction/optimization of a sub-ontology from a large-scale base ontology. We utilize coarse-grained data-level parallelism inherent in the problem domain. Such an architecture serves two purposes: (a) facilitates the utilization of a cluster environment typical in business organizations, which is in line with our envisaged application of the proposed system, and (b) enhances the performance of the computationally extensive extraction process when dealing with massively sized realistic ontologies. As ontologies are currently widely used, our proposed approach for distributed ontology extraction will play an important role in improving the efficiency of ontology-based information retrieval.     

基于领域本体的用户模型的研究*

目前大多数知识管理系统采用基于关键词或关键词向量空间模型表示用户的兴趣偏好。针对该方法不包含语义信息,很难准确表示用户感兴趣的信息,并且难于扩展,提出一种基于领域本体的用户模型。该模型利用用户访问量,采用改进的相似度算法,实现用户分类建立用户模型,体现用户个人偏好。最后将该模型应用于齐齐哈尔货车快速设计系统中,应用表明该模型能准确地反映用户兴趣,且提高了信息检索效率。     

DICOM数据的语义查询及优化

医学信息领域用DICOM类型的数据存储由各类检查设备产生的医学图像信息。DICOM标准的优点是标准化和语义化,它使各类医学图像设备和医学图像处理系统之间有了统一的数据交换模式。一个DICOM图像包含丰富的语义信息,包括患者相关、检查相关和图像相关的信息,但目前各类系统对其应用得还不够,尤其是数据挖掘方面,大多系统是通过构建关系数据库来存储和描述图像相关的信息。针对DICOM图像本身所携带的语义信息进行的挖掘还不够多,这违背了当初创建DICOM标准的初衷。造成这个应用现状的主要原因是国内系统厂商只利用了DICOM标准信息交换的功能,却对其语义的理解有欠缺。为了解决上述问题,对基于DICOM语义信息的数据检索模型、检索方法及检索优化方法进行了研究。根据目前国内业界的应用偏好,对DICOM标准的语义模型进行了扩展,在扩展模型下应用了文本模糊和数据模糊查询方法,最后提出了DICOM语义查询智能Agent的概念。     

基于领域本体的贝叶斯网络检索模型研究

针对传统的信息检索方法无法实现用户查询的语义理解、检索效率低等问题,本文提出基于领域本体进行查询扩展的贝叶斯网络检索模型。该模型首先将用户查询通过领域本体进行语义扩展,然后将扩展后的查询作为证据在贝叶斯网络检索模型中进行传播,进而得到查询结果,实验表明本文提出的贝叶斯网络检索模型能提高检索效率。     

一种基于领域本体的资源反馈检索模型研究

针对现有资源平台无法互通共享资源,资源库检索系统仅依靠用户输入的单词关键字描述检索资源而无法挖 掘用户需求中的语义信息的问题,提出了一种基于本体的资源反馈检索模型。该模型通过构建本体、概念相似度计算、查询关 键字扩展等关键技术,利用了用户多次反馈中的包含语义知识,满足了用户的查询需求。实验表明,该模型能够有效提高检索 的性能。     

Enhancing electronic medical record retrieval through semantic query expansion

There are currently many active movements towards computerizing patient healthcare information. As Electronic Medical Record (EMR) systems are being increasingly adopted in healthcare facilities, however, there is a big challenge in effectively utilizing this massive information source. It is very time-consuming for healthcare providers to dig into the voluminous medical records of a patient to find the few that are indeed relevant to the patient’s current problem. Due to the complex semantic relationships among medical concepts and use of many synonyms, antonyms, and hypernym/hyponym, simple word-based information retrieval does not produce satisfactory results. In this paper, we propose an EMR retrieval system that leverages semantic query expansion to retrieve medical records that are relevant to the patient’s current symptom/problem. The proposed framework integrates various technologies, including information retrieval, domain ontologies, automatic semantic relationship learning, as well as a body of domain knowledge elicited from healthcare experts. Knowledge of semantic relationships among medical concepts, such as symptoms, exams and tests, diagnoses, and treatments, as well as knowledge of synonyms and hypernym/hyponyms, is used to expand and enhance initial queries posed by a user. We have implemented a preliminary prototype and conducted a pilot testing using sample nursing notes drawn from the EMR system of a community health center.     

An ontology-based retrieval system using semantic indexing

In this paper, we present an ontology-based information extraction and retrieval system and its application in the soccer domain. In general, we deal with three issues in semantic search, namely, usability, scalability and retrieval performance. We propose a keyword-based semantic retrieval approach. The performance of the system is improved considerably using domain-specific information extraction, inferencing and rules. Scalability is achieved by adapting a semantic indexing approach and representing the whole world as small independent models. The system is implemented using the state-of-the-art technologies in Semantic Web and its performance is evaluated against traditional systems as well as the query expansion methods. Furthermore, a detailed evaluation is provided to observe the performance gain due to domain-specific information extraction and inferencing. Finally, we show how we use semantic indexing to solve simple structural ambiguities.     

语义图像检索研究进展

语义图像检索已成为解决图像简单视觉特征和用户检索丰富语义之间存在的“语义鸿沟”问题的关键。从图像语义描述方式、图像语义抽取方法和语义检索系统设计3个方面对语义图像检索的研究状况进行了分析和研究;讨论了面向对象的图像内容模型和图像语义表示问题;对利用系统知识的提取、根据用户交互的提取和利用外部信息源的语义生成等具有代表性的语义处理方法进行了阐述;介绍了系统设计中用户界面和语义处理的不同方式,最后从对象识别、语义抽取规则、用户检索模型和图像检索性能评价标准4个方面剖析了实现图像语义处理所面临的困难,并提出了一些初步解决思路。     

A personalized query expansion approach for engineering document retrieval

Engineers create engineering documents with their own terminologies, and want to search existing engineering documents quickly and accurately during a product development process. Keyword-based search methods have been widely used due to their ease of use, but their search accuracy has been often problematic because of the semantic ambiguity of terminologies in engineering documents and queries. The semantic ambiguity can be alleviated by using a domain ontology. Also, if queries are expanded to incorporate the engineer’s personalized information needs, the accuracy of the search result would be improved. Therefore, we propose a framework to search engineering documents with less semantic ambiguity and more focus on each engineer’s personalized information needs. The framework includes four processes: (1) developing a domain ontology, (2) indexing engineering documents, (3) learning user profiles, and (4) performing personalized query expansion and retrieval. A domain ontology is developed based on product structure information and engineering documents. Using the domain ontology, terminologies in documents are disambiguated and indexed. Also, a user profile is generated from the domain ontology. By user profile learning, user’s interests are captured from the relevant documents. During a personalized query expansion process, the learned user profile is used to reflect user’s interests. Simultaneously, user’s searching intent, which is implicitly inferred from the user’s task context, is also considered. To retrieve relevant documents, an expanded query in which both user’s interests and intents are reflected is then matched against the document collection. The experimental results show that the proposed approach can substantially outperform both the keyword-based approach and the existing query expansion method in retrieving engineering documents. Reflecting a user’s information needs precisely has been identified to be the most important factor underlying this notable improvement.     

An application of metadata-based image retrieval system for facility management

For facility management, photography is an efficient and accurate method of recording the physical state of infrastructure. However, without an effective organizational scheme, the difficulty of retrieving relevant photos from historical databases can become overly burdensome for highly complex or long-lived assets. To make strategic decisions, it is crucial to retrieve the right information from a plurality of sources in a timely manner. The main objective of this paper is to present a method for organizing and retrieving photos from massive facility management photo databases using photo-metadata: photographed location, camera perspective, and image semantic content information. Indoor localization experiments were performed using Bluetooth technology to infer the location information. Perspective is inferred from the device’s on-board inertial measurement unit (IMU). Image semantic content is inferred using a Convolutional Neural Network (CNN)-based deep learning algorithm. Fusing these three features, seven query options were provided for the user when retrieving images. Leveraging Building Information Modeling (BIM) as a process and Geographic Information Systems (GIS) as a framework, this paper also envisions a federated information management by connecting 2D and 3D facility assets with our real-world map which can be smoothly bridged with our image retrieval system. The realization of the integrated application with BIM and GIS is significantly beneficial for the facility management domain by advancing the understanding of projects in a broader view with a federated data platform. In this research, the framework is illustrated with 21 institutional buildings within the University of Texas at Austin’s main campus, and the authors conclude that the proposed metadata-based image retrieval system can ultimately enhance the better-informed decision-making process through rapid information retrieval.     

Architecture of a semantic data integration system based on a semantically complete model and a semantically complete query language

The availability of numerous sources of structured data on the Internet poses the problem of their integration into a unified information space just as the unstructured data and weakly structured data sources are integrated in the framework of the WWW. The main requirement for such an information space is the simplicity of operation for the users that are not trained IT experts. The architecture of a system of semantic integration of distributed and heterogeneous data sources is proposed in the framework of a unified semantic access interface. The semantic nature of this interface lies in the fact that one can interact with such a system in terms of the concepts of the application domain completely ignoring the implementation details of the systems being integrated. The proposed architecture simplifies the users’ work, the integration process, and the development of user forms with a rich functionality including a semantic navigation between the forms. A distinctive feature of this architecture is that the system integration and the development of user forms are performed declaratively in the interactive mode without programming. The simplification of the users’ work with the system is achieved due to some special properties of the semantically complete model (SCM) and of the semantically complete query language (SCQL), which provide a basis for the system. A prototype of the system under study is briefly described. The prototype is implemented as a type of the client-server technology based on the SCM-SCQL.     

基于本体的教育资源库的研究与设计

目前,我国的教育资源建设在共享性、重用性、资源检索查全率和查准率等问题上依然存在某些不足,为了解决当前检索系统中同义词难以识别、相关查找困难等问题,把本体引入到教育资源建设中,并提出了基于本体的语义检索系统的体系结构,该系统旨在实现对领域内资源的语义分析,赋予检索系统足够的语义信息。研究的重点是资源的元数据描述、领域本体的构建及语义查询,而这也是进行语义检索的理论基础。     

Automatic localization and annotation of facial features using machine learning techniques

Content-based image retrieval (CBIR) systems traditionally find images within a database that are similar to query image using low level features, such as colour histograms. However, this requires a user to provide an image to the system. It is easier for a user to query the CBIR system using search terms which requires the image content to be described by semantic labels. However, finding a relationship between the image features and semantic labels is a challenging problem to solve. This paper aims to discover semantic labels for facial features for use in a face image retrieval system. Face image retrieval traditionally uses global face-image information to determine similarity between images. However little has been done in the field of face image retrieval to use local face-features and semantic labelling. Our work aims to develop a clustering method for the discovery of semantic labels of face-features. We also present a machine learning based face-feature localization mechanism which we show has promise in providing accurate localization.     

界模型信息检索及其参数优化

信息检索中,如何较好地理解和表达用户的信息需求是提高信息检索效果的关键。从语言的内涵和外延出发,挖掘、计算信息需求的上边界、下边界,确定信息需求的需求域,建立了一种表达用户信息需求的界模型。引入文档与信息需求域的相似度,在信息检索时计算各文档的相似度,并根据相似度对文档进行排序。使用Lemur工具进行的对比分析实验表明,界模型具有较理想的检索效果。进一步对相似度中的参数进行了优化,得到了更优的检索效果。     

基于整体区域相似的互动式图象检索模型

高效的基于内容的图象检索在许多领域得到了广泛的应用 ,基于内容的图象检索研究领域已经建立了一些系统 ,但在实际使用中 ,这些系统均有如下欠缺 :(1)这些系统均期望以相同的方法来处理各种不同类型的图象检索 ;(2 )这些系统在设计时 ,均缺乏从使用者的需求出发 .实际上 ,由于不同的检索方式是针对不同类型的图象 ,为此 ,提出了一个基于整体区域相似匹配的图象互动式检索系统 ,该系统是一个基于小波变换的特征提取和图象整体区域相似的、语义分类和互动方法的图象检索系统 .与其他检索方法相比较 ,此方法允许自适应查找和互动 ,因此可缩小查找范围 ,以提高检索效率 .实验结果表明 ,该系统比其他一些系统精确和高效     

Fast semantic object search and detection for vegetable trading information using Steiner tree

We propose an approach to speed up the semantic object search and detection for vegetable trading information using Steiner Tree. Through analysis, comparing the relevant ontology construction method, we present a set of ontology construction methods based on domain ontology for vegetables transaction information. With Jena2 provides rule-based reasoning engine, More related information could be searched with the help of ontology database and ontology reasoning, query expansion is to achieve sub-vocabulary of user input, the parent class of words, equivalence class of extensions, and use of ontology reasoning to get some hidden information to use of these technologies, we design and implementation of ontology-based semantic vegetables transaction information retrieval system, and through compare to keyword-based matching of large-scale vegetable trading site retrieval systems, the results show that the recall and precision rate of ontology-based information retrieval system much better than keyword-based information retrieval system, and has some practical value.