Ontology Merging Research Articles

Open biomedical pluralism: formalising knowledge about breast cancer phenotypes

We demonstrate a heterogeneity of representation types for breast cancer phenotypes and stress that the characterisation of a tumour phenotype often includes parameters that go beyond the representation of a corresponding empirically observed tumour, thus reflecting significant functional features of the phenotypes as well as epistemic interests that drive the modes of representation. Accordingly, the represented features of cancer phenotypes function as epistemic vehicles aiding various classifications, explanations, and predictions. In order to clarify how the plurality of epistemic motivations can be integrated on a formal level, we give a distinction between six categories of human agents as individuals and groups focused around particular epistemic interests. We analyse the corresponding impact of these groups and individuals on representation types, mapping and reasoning scenarios. Respecting the plurality of representations, related formalisms, expressivities and aims, as they are found across diverse scientific communities, we argue for a pluralistic ontology integration. Moreover, we discuss and illustrate to what extent such a pluralistic integration is supported by the distributed ontology language DOL, a meta-language for heterogeneous ontology representation that is currently under standardisation as ISO WD 17347 within the OntoIOp (Ontology Integration and Interoperability) activity of ISO/TC 37/SC 3. We particularly illustrate how DOL supports representations of parthood on various levels of logical expressivity, mapping of terms, merging of ontologies, as well as non-monotonic extensions based on circumscription allowing a transparent formal modelling of the normal/abnormal distinction in phenotypes.

Joint Perception in Agent Communication

Correctness of agent communication requires that the communicatingagents share a common ontology. Most of the ontology merging approaches assumethat there is a global, god's eye view which is a combination of theconcepts in the ontology of the individual agents. These approaches admitthat the agents may have different views and try to resolve the differenceswithin the limits of the global view which contains only the concepts based onthe individual perceptions of the agents. In this paper we introduce the notionof joint perception in order to enrich the available concepts in the global viewand we introduce the notion of conceptualization based on joint perceptionin order to enable the agents to resolve the differences of their views byintroducing new concepts. We propose an incremental ontology negotiation protocolfor the conceptualization based on joint perception and demonstrate it in ablocks world. With this work we develop new insights into ontology merging andnegotiation for agent communication by defining a formal realization proposalfor emergent semantics.

Imprecise Ontology Merging Framework Design

Precision is selected unwillingly by human being when dealing with imprecise objects because of the limitation of human cognitive ability, which deviates from the substance of the processed object when it gets the feasible way of solution. Nowadays, in terms of the research in the Ontology and the Semantic Web, the time for the transformation from the “precise phase” to the “imprecise phase” is ripe. The interoperability among ontologies is seriously blocked by the heterogeneity of ontologies constructed under distributed environment. In this case, Ontology merging in the same domain is the most effective method to solve ontology heterogeneity. Firstly, the improved fuzziness and the R-improved roughness are respectively defined and verified as the more efficient measure way for the fuzziness and roughness. Secondly, a composite appraisal method of fuzzy-rough relevancy in combination of the fuzzy set theory and the rough set theory is proposed, which can serve as the basis of the inquiry and reasoning of the imprecise ontology, the transformation reference of the fuzzy roughness set or the rough fuzziness set. Lastly, by employing semantic bridge generator and conflict processor, a novel multiple-mapping-based imprecise ontology merging framework is proposed. The example verification reveals that both the imprecise ontology merging efficiency can be improved and the merging source imprecise ontologies into object imprecise ontology can be done automatically under the semantic web environment.

An Ontology Learning Method Based on Document Clustering

Ontology learning is a series method and technology of semi-automatic ontology construction, which uses various data sources to create or expand in-built ontology by semi-automatic method to build a new ontology. Existing ontology construction methods are to collect a large number of conceptual terms based on a large number of field text and background corpus, and then to select field concepts to construct a body. The proposed Cluster-Merge algorithm is to use k-means clustering algorithm in the field document at first, then according to document clustering results to construct body by themself, at last accoring to the ontology similarity for ontology merging to get final output ontology. The experiment may prove that Cluster-Merge algorithm can improve the body resulting recall and precision.

Research on domain ontology in different granulations based on concept lattice

This paper introduces concept lattice and granular computing into ontology learning, and presents a unified research model for ontology building, ontology merging and ontology connection based on the domain ontology base in different granulations. In this model, as the knowledge in the lowest and most basic level, the domain ontology base is presented firstly, which provides a uniform technology for ontology learning on the whole; secondly, in order to better understand problems rather than be overwhelmed unnecessary details, granular computing is introduced to abstract and simplify domain ontology bases in complex domains. Moreover, the similarly of concepts in different granulations is introduced to help domain experts judging relations except for inheritance relation, and the similarity of ontologies in multi-granulations is introduced to measure the degree of connection of ontologies; finally, based on similarity models mentioned above, the ontology building, ontology merging and ontology connection can be obtained in different granulations with the help of domain experts. It is shown by instances that the application of the model presented in this paper is valid and practicable. Although there are still some problems in applications of this model (for example, ontology learning cannot dispense with the intervention of domain experts yet), this paper offers a new way for combining ontology learning and concept lattice.

Constructing and Merging Ontology of E-business based on Fuzzy Rough Concept Sets

Ontology, regarded as a basic knowledge structure for information on the Semantic Web, often captures a semantic network and represents it by a graph. The domain ontology model of e-business is built combined with knowledge of domain expert. The domain ontology model of e-business is built combined with knowledge of domain expert. Ontology provides common understanding of the domain knowledge and confirms common approbatory vocabulary in the domain. The project probes into building and merging of e-business domain ontology based on fuzzy rough concept sets in order to constructing the ontology model of e-commerce recommendation system, and to suffice the needs of theory and application in E-commerce recommendation system. Finally, ontology merging is carried out. The experimental results indicate that this method has great promise.

Using Fuzzy Rough Concept Lattices Merging and Presenting Domain Ontology

As the foundation of the semantic web, ontology is a formal, explicit specification of a shared conceptual model. It becomes an important problem on ontology application to merg and present ontology. However, there are some defects between several kinds of existing ontology application methods in many aspects. The paper offers a methodology of ontology merging for knowledge sharing and reusing based on fuzzy concept concept lattice union in order to makes up these defects.This paper proposes the means of ontology presenting based on the form of concept lattices visualizing in three-dimensional space. The experimental results indicate that this method has great validity.

On the Merging of Domain-Specific Heterogeneous Ontologies Using WordNet and Web Pattern-Based Queries

Ontologies are a basic interest in various computer science disciplines such as semantic web, information retrieval, database design, etc. They aim at providing a formal, explicit and shared conceptualisation and understanding of common domains between different communities. In addition, they allow for concepts and their constraints of a specific domain to be explicitly defined. However, the distributed nature of ontology development and the differences in viewpoints of ontology engineers have resulted in the so-called "semantic heterogeneity" between ontologies. Semantic heterogeneity constitutes the major obstacle against achieving interoperability between ontologies. To overcome this obstacle, we present a multipurpose framework which exploits the WordNet generic knowledge base for the following purposes: (i) discovering and correcting the incorrect semantic relations between the concepts of the ontology in a specific domain, this step is a primary step of ontology merging; (ii) merging domain-specific ontologies through computing semantic relations between their concepts; (iii) handling the issue of missing concepts in WordNet through the acquisition of statistical information on the Web; (iv) enriching WordNet with these missing concepts. An experimental instantiation of the framework and comparisons with state-of-the-art syntactic- and semantic-based systems validate our proposal.

Extending description logics with uncertainty reasoning in possibilistic logic

Possibilistic logic provides a convenient tool for dealing with uncertainty and handling inconsistency. In this paper, we propose possibilistic description logics as an extension of description logics, which are a family of well-known ontology languages. We first give the syntax and semantics of possibilistic description logics and define several inference services in possibilistic description logics. We show that these inference serviced can be reduced to the task of computing the inconsistency degree of a knowledge base in possibilistic description logics. Since possibilistic inference services suffer from the drowning problem, that is, axioms whose confidence degrees are less than or equal to the inconsistency are not used, we consider a drowning-free variant of possibilistic inference, called linear order inference. We propose an algorithm for computing the inconsistency degree of a possibilistic description logic knowledge base and an algorithm for the linear order inference. We consider the impact of our possibilistic description logics on ontology learning and ontology merging. Finally, we implement these algorithms and provide some interesting evaluation results. © 2011 Wiley Periodicals, Inc.

Selected Papers from the MIE 2009 Conference, Sarajevo, Bosnia-Herzegovina

It is quite a long tradition that the best papers presented at Medical Informatics Europe (MIE) conferences are selected and invited to submit as an extended paper to be published as journal article in a special issue. For the former years these selected papers have been published in the International Journal of Medical Informatics. Due to change of the publication policy, European Federation of Medical Informatics (EFMI) made an agreement with the edi tors to move to Methods of Information in Medicine. This applies first for MIE 2009 held in Sarajevo, Bosnia-Herzegovina. This was not just a formal change, since the whole selection procedure had to be reshaped due to the stronger volume restrictions. From about 150 oral presentations more than 25 had been invited to submit an extended paper and finally four of them could be published. This is a really strong competition, which on one side is beneficial allowing to maintain a really high quality. On the other side this makes it very hard for the editor to give a representative picture about the ongoing research activity in the field. Somewhat luckily, the finally selected four papers cover quite large part of our domain. The group from UMIT (Universitat fur Gesundheitswissenschaften, Medizinische Informatik und Technik – Tirol) [1] asks a question about the justification of all activity in medical informatics: Can users accept the developed systems? At health policy level it is a commonplace that the use of electronic health records is essential for keeping the quality and cost effectiveness of health care delivery, also for evidencebased health system planning. But health policy makers rarely use EHR systems directly and the opinion of doctors working on the “battlefield” should not be disregarded. Systems that do not serve the real needs of their users are likely to fail. Hackl and his co-authors conclude however that the success of system implementation very much depends on the way how end users are informed about the system and how their concerns are treated. For centuries, life science researchers had some reason to be jealous to the success of physics. The advantage of physics seems to be related – among others – to the relative easiness of the formalization of the descriptions of phenomena, because this made the deployment of the whole arsenal of mathematics possible. As biomedical ontologies appeared on the horizon just in the last decades, nowadays we more and more can believe that medical phenomena also can be formally described. While a number of theoretical and pragmatic problems are waiting for solution, the way towards practical applications is already open. In the second paper [2] Ceusters and his co-workers present the development of an ontology for adverse events. They used a number of “feeder ontologies”, that are already at the disposal of researches, demonstrating that reuse and merging of ontologies is both desired and feasible but by no means an easy enterprise. But this paper also demonstrates that there is a quite long way ahead us. The authors cope with three levels of reality: what exists, what Methods Inf Med 2011; 50: 51–52

Data Management Practices for Collaborative Research

The success of research in the field of maternal–infant health, or in any scientific field, relies on the adoption of best practices for data and knowledge management. Prior work by our group and others has identified evidence-based solutions to many of the data management challenges that exist, including cost–effective practices for ensuring high-quality data entry and proper construction and maintenance of data standards and ontologies. Quality assurance practices for data entry and processing are necessary to ensure that data are not denigrated during processing, but the use of these practices has not been widely adopted in the fields of psychology and biology. Furthermore, collaborative research is becoming more common. Collaborative research often involves multiple laboratories, different scientific disciplines, numerous data sources, large data sets, and data sets from public and commercial sources. These factors present new challenges for data and knowledge management. Data security and privacy concerns are increased as data may be accessed by investigators affiliated with different institutions. Collaborative groups must address the challenges associated with federating data access between the data-collecting sites and a centralized data management site. The merging of ontologies between different data sets can become formidable, especially in fields with evolving ontologies. The increased use of automated data acquisition can yield more data, but it can also increase the risk of introducing error or systematic biases into data. In addition, the integration of data collected from different assay types often requires the development of new tools to analyze the data. All of these challenges act to increase the costs and time spent on data management for a given project, and they increase the likelihood of decreasing the quality of the data. In this paper, we review these issues and discuss theoretical and practical approaches for addressing these issues.

A New Bidirectional Method for Ontologies Matching

Recently, much research has focused on developing techniques for schema/ontology matching and mapping as it is required in many areas e.g. heterogeneous database integration, merging of ontologies, semantic query processing. In this paper, we present a novel method to detect and repair the list of homologs concepts; this last is based on the bidirectional comparison (Checking) between the two matched ontologies to filter this list of concepts. The used measures are classical just to show the reliability and realisability of our method, but we can generalize it for supporting other advanced measures.

Towards ensuring Satisfiability of Merged Ontology

Abstract The last decade has seen researchers developing efficient algorithms for the mapping and merging of ontologies to meet the demands of interoperability between heterogeneous and distributed information systems. But, still state-of-the-art ontology mapping and merging systems is semi-automatic that reduces the burden of manual creation and maintenance of mappings, and need human intervention for their validation. The contribution presented in this paper makes human intervention one step more down by automatically identifying semantic inconsistencies in the early stages of ontology merging. Our methodology detects inconsistencies based on structural mismatches that occur due to conflicts among the set of Generalized Concept Inclusions, and Disjoint Relations due to the differences between disjoint partitions in the local heterogeneous ontologies. We present novel methodologies to detect and repair semantic inconsistencies from the list of initial mappings. This results in global merged ontology free from ‘circulatory error in class/property hierarchy’, „common class/instance between disjoint classes error’, ‘redundancy of subclass/subproperty relations’, ‘redundancy of disjoint relations’ and other types of „semantic inconsistency’ errors. In this way, our methodology saves time and cost of traversing local ontologies for the validation of mappings, improves performance by producing only consistent accurate mappings, and reduces the user dependability for ensuring the satisfiability and consistency of merged ontology. The experiments show that the newer approach with automatic inconsistency detection yields a significantly higher precision.

A new algebraic structure for formal concept analysis

Formal concept analysis (FCA) originally proposed by Wille [39], is an important theory for data analysis and knowledge discovery. Concept lattice is the core of the mathematical theory of formal concept analysis. To address the requirements of real word applications, concept lattice has been extended to many other forms from the theoretical point of view and possible applications. In this paper, with the aim of deriving the mathematical properties of formal concepts from the point of algebra, we propose a new algebra system for the formal context. Under the frame of the proposed system, some interesting properties of formal concepts are explored, which could be applied to explore concept hierarchy and ontology merging.

Evaluating ontology extraction tools using a comprehensive evaluation framework

Ontologies are a key component of the Semantic Web; thus, they are widely used in various applications. However, most ontologies are still built manually, a time-consuming activity which requires many resources. Several tools such as ontology editing tools, ontology merging tools, and ontology extraction tools have therefore been proposed to speed up ontology development. To minimize building time, one promising solution is the automation of the ontology development process. Consequently, the need for an automatic ontology extraction tool has increased in the last two decades and many tools have been developed for this purpose. However, there is still no comprehensive framework for evaluating such tools. In this paper, we proposed a set of criteria for evaluating ontology extraction tools and carried out an evaluation experiment on four ontology extraction tools (i.e., OntoLT, Text2Onto, OntoBuilder, and DODDLE-OWL) using our proposed evaluation framework. Based on the results of our experiment, we concluded that ontology extraction tools still lack the ability to automate the extraction process fully and thus require functional performance improvement.

Merging domain ontologies based on the WordNet system and Fuzzy Formal Concept Analysis techniques

Many different contents and structures exist in constructed ontologies, including those that exist in the same domain. If extant domain ontologies can be used, time and money can be saved. However, domain knowledge changes fast. In addition, the extant domain ontologies may require updates to solve domain problems. The reuse of extant ontologies is an important topic for their application. Thus, the integration of extant domain ontologies is of considerable importance. In this paper, we propose a new method for combining the WordNet and Fuzzy Formal Concept Analysis (FFCA) techniques for merging ontologies with the same domain, called FFCA-Merge. Through the method, two extant ontologies can be converted into a fuzzy ontology. The new fuzzy ontology is more flexible than a general ontology. The experimental results indicate that our method can merge domain ontologies effectively.

Dealing with Uncertainty in Lexical Annotation

We present ALA, a tool for the automatic lexical annotation (i.e. annotation w.r.t. a thesaurus/lexical resource) of structured and semi-structured data sources and the discovery of probabilistic lexical relationships in a data integration environment. ALA performs automatic lexical annotation through the use of probabilistic annotations, i.e. an annotation is associated to a probability value. By performing probabilistic lexical annotation, we discover probabilistic inter-sources lexical relationships among schema elements. ALA extends the lexical annotation module of the MOMIS data integration system. However, it may be applied in general in the context of schema mapping discovery, ontology merging and data integration system and it is particularly suitable for performing “on-the-fly” data integration or probabilistic ontology matching.

Automatic fusion of knowledge stored in ontologies

A person adds new knowledge to his/her mind, taking into account new information, additional details, better precision, synonyms, homonyms, redundancies, apparent contradictions, and inconsistencies between what he/she knows and new knowledge that he/she acquires. This way, he/she incrementally acquires information keeping it at all times consistent. This information can be represented by Ontologies. In contrast to human approach, algorithms of Ontologies fusion lack these features, merely being computer-aided editors where a person solves the details and inconsistencies. This article presents a method for Ontology Merging (OM), its algorithm and implementation to fuse or join two ontologies (obtained from Web documents) in an automatic fashion (without human intervention), producing a third ontology, and taking into account the inconsistencies, contradictions, and redundancies between both ontologies, thus delivering a result close to reality. The repeated use of OM allows acquisition of much information about the same topic.

Research on ontology-based integration of product knowledge for collaborative manufacturing

One of the most important research subjects germane to knowledge management in collaborative manufacturing is the integration of heterogeneous product knowledge distributed among different collaborative enterprises. To deal with the problem of optimization of knowledge integration in collaborative manufacturing, an ontology-based framework of knowledge integration is presented to transform the problem of knowledge integration into a problem of ontology integration. First of all, a collaborative business process for collaborative enterprises is described, and then an ontology-based framework of knowledge integration is established. Under the condition of analyzing the structure of knowledge ontology, an ontology schema of knowledge concept is discussed. Aiming at the ontology schema, a method of ontology integration based on ontology similarity is improved. The method is composed of ontology mapping and ontology merging, which is based on calculated result of ontology similarity between local ontology and global ontology. Finally, the implementation of the framework of knowledge integration is described, and the application results meet the requirement of the knowledge integration to ensure that validity of the ontology integration method was proved.

Merging Architectural, Engineering, and Construction Ontologies

Ontologies have emerged as a means of facilitating semantic interoperability among computer systems. However, recognizing that no single universally agreed-on ontology can ever be defined for a domain, a tool that allows ontologies to interoperate becomes essential to semantic interoperability. This paper presents an ontology integrator (Onto-Integrator) for facilitating ontology interoperability within the architectural, engineering, and construction (AEC) domain. The Onto-Integrator offers a heuristic for ontology merging, including the merging of concept taxonomies, relations, and axioms. Unlike existing tools, the integrator addresses ontology merging requirements that are specific to the AEC domain. The integrator heuristic was implemented into a prototype Web-based tool and was evaluated through a focus group.