Ontological Knowledge Integration Research Articles

Study on Ontological Knowledge Integration of Micromachining for Collaborative Process

In collaborative manufacturing environment, the knowledge integration in collaborative process is very crucial, especially the heterogeneous information distributed among various cooperative suppliers. To tackle the optimization of knowledge consolidation in co-manufacturing, a knowledge integration with ontological framework is proposed in this study. First, by representing the collaborative business activities for cooperative suppliers, an architecture of knowledge integration with ontological schema is generated. The ontological model of knowledge concepts is explored in terms of the analysis of the ontological structure of knowledge. Aiming at the concept, an approach of ontology integration on the basis of ontological similarity is promoted. There are two portions included in this approach, mapping and combination, which are implemented through the analysis of similarity in two ontologies namely universal and regional. To integrate the two ontologies, the relations and restrictions among fields are definitely depicted by the Semantic Web Rule Language. Eventually, the presented framework is illustrated through a case study, and the outcomes satisfy the needs of knowledge combination to assure that the effectiveness of the presented method is confirmed.

C-Norm: a neural approach to few-shot entity normalization

BackgroundEntity normalization is an important information extraction task which has gained renewed attention in the last decade, particularly in the biomedical and life science domains. In these domains, and more generally in all specialized domains, this task is still challenging for the latest machine learning-based approaches, which have difficulty handling highly multi-class and few-shot learning problems. To address this issue, we propose C-Norm, a new neural approach which synergistically combines standard and weak supervision, ontological knowledge integration and distributional semantics.ResultsOur approach greatly outperforms all methods evaluated on the Bacteria Biotope datasets of BioNLP Open Shared Tasks 2019, without integrating any manually-designed domain-specific rules.ConclusionsOur results show that relatively shallow neural network methods can perform well in domains that present highly multi-class and few-shot learning problems.

Ontological knowledge integration and sharing for collaborative product development

ABSTRACTThe product development process is knowledge intensive, involving the retrieval and reuse of sometimes heterogeneous knowledge. As the exchange of this knowledge can be challenging in a distributed environment, this paper presents a two-stage approach to integrate and share product knowledge effectively. The first stage is ontology integration. Through ontology mapping and merging, product knowledge from the local ontologies is integrated into a global ontology, and any repetitive knowledge is removed. The second stage is knowledge sharing. In the multiple ontologies, product knowledge is exchanged through multi-agents, and all the knowledge is retrieved. As a result, product knowledge is shared between the global and local ontologies, and among the local ontologies. A case on the Nose Landing Gear (NLG) product development is presented to highlight the potential of the proposed method.

Architecting Multimedia Content Publish/Subscribe Applications: A Graph-Oriented Approach

This paper presents an approach, called GOM, for modeling and implementing the architecture of multimedia content publish/subscribe (Pub/Sub) applications using a graph-oriented multimedia (GOM) model. The GOM unites three of the applications aspects, namely the content aspect, the semantic aspect, and the functional aspect, and provides means for the integration of ontological knowledge within the GOM graph structure. A formal definition is proposed for the GOM. Performance is evaluated. The results show that the GOM can easily be constructed, while enabling an efficient management by the publishing and subscribing of multimedia content.

Discovery of functional protein groups by clustering community links and integration of ontological knowledge

In this paper we cluster data from protein networks and integrate the results with chemical databases and ontologies to investigate functional links between related disease states. It is well know that certain genes participate in more than one function and if they are defective are likely to be responsible for several health problems. Furthermore, genes tend to cooperate in associated networks or cascades often with ’crosstalk’ between networks which can subtly alter cellular functions. Understanding the complexity and role of the various cell functions and mechanisms requires the use of computational models to make inferences and link together the interplay between genes, proteins and chemical interactions. A deeper understanding of the mechanisms of diseases will eventually be of benefit for the development new and improved therapies. The particular disease state we investigate in this work is cystinosis which is characterized by the widespread deposition of the amino acid cystine in cells due to a defect in cystine transport. In cystinosis, cystine accumulates in the lysosomes and eventually forms crystals throughout the body causing problems in the kidneys and the eyes. The defect is caused by a mutation in the CTNS gene and this forms the starting point for our investigation.

Integration of ontological knowledge within the authoring and retrieval of multimedia metaobjects

To enable efficient authoring, management and access to multimedia content, media data has to be augmented by semantic metadata and functionality. Semantic representation has to be integrated with domain ontologies to fully exploit domain-specific knowledge. This knowledge can be used within the authoring process and for the efficient management of multimedia content. Also, this knowledge can be used for refining ambiguous user queries by closing the conceptual gap between the user and the information to be retrieved. In our previous research, we have introduced Enhanced Multimedia Metaobjects (EMMOs) as a new approach for semantic multimedia meta modelling, as well as the query algebra EMMA, which is adequate and complete with regard to the EMMO model. This paper illustrates how ontological knowledge can be used within the authoring process of EMMOs, integrated into the EMMO knowledge structures and exploited for refining EMMA queries.

Extracting focused knowledge from the semantic web

Ontologies are increasingly being recognized as a critical component in making networked knowledge accessible. Software architectures which can assemble knowledge from networked sources coherently according to the requirements of a particular task or perspective will be at a premium in the next generation of web services. We argue that the ability to generate task-relevant ontologies efficiently and relate them to web resources will be essential for creating a machine-inferencable “semantic web”. The Internet-based multi-agent problem solving (IMPS) architecture described here is designed to facilitate the retrieval, restructuring, integration and formalization of task-relevant ontological knowledge from the web. There are rich structured and semi-structured sources of knowledge available on the web that present implicit or explicit ontologies of domains. Knowledge-level models of tasks have an important role to play in extracting and structuring useful focused problem-solving knowledge from these web sources. IMPS uses a multi-agent architecture to combine these models with a selection of web knowledge extraction heuristics to provide clean syntactic integration of ontological knowledge from diverse sources and support a range of ontology merging operations at the semantic level. Whilst our specific aim is to enable on-line knowledge acquisition from web sources to support knowledge-based problem solving by a community of software agents encapsulating problem-sloving inferences, the techniques described here can be applied to more general task-based integration of knowledge from diverse web sources, and the provision of services such as the critical comparison, fusion, maintenance and update of both formal informal ontologies.