A Pattern Language for Knowledge Discovery in a Semantic Web Context

Author(s):  
Mehdi Adda

Ontologies are used to represent data and share knowledge of a specific domain, and in recent years they tend to be used in many applications such as database integration, peer-to-peer systems, e-commerce, semantic web services, bioinformatics, or social networks. Feeding ontological domain knowledge into those applications has proven to increase flexibility and inter-operability and interpretability of data and knowledge. As more data is gathered/generated by those applications, it becomes important to analyze and transform it to meaningful information. One possibility is to use data mining techniques to extract patterns from those large amounts of data. One challenging general problem in mining ontological data is taking into account not only domain concepts, properties and instances, but also hierarchical structures of those concepts and properties. In this paper, the authors research the specific problem of extracting ontology-based sequential patterns.

Author(s):  
Mehdi Adda

Ontologies are used to represent data and share knowledge of a specific domain, and in recent years they tend to be used in many applications such as database integration, peer-to-peer systems, e-commerce, semantic web services, bioinformatics, or social networks. Feeding ontological domain knowledge into those applications has proven to increase flexibility and inter-operability and interpretability of data and knowledge. As more data is gathered/generated by those applications, it becomes important to analyze and transform it to meaningful information. One possibility is to use data mining techniques to extract patterns from those large amounts of data. One challenging general problem in mining ontological data is taking into account not only domain concepts, properties and instances, but also hierarchical structures of those concepts and properties. In this paper, the authors research the specific problem of extracting ontology-based sequential patterns.


Author(s):  
Dong (Haoyuan) Li ◽  
Anne Laurent ◽  
Pascal Poncelet

As common criteria in data mining methods, the frequency-based interestingness measures provide a statistical view of the correlation in the data, such as sequential patterns. However, when the authors consider domain knowledge within the mining process, the unexpected information that contradicts existing knowledge on the data has never less importance than the regularly frequent information. For this purpose, the authors present the approach USER for mining unexpected sequential rules in sequence databases. They propose a belief-driven formalization of the unexpectedness contained in sequential data, with which we propose 3 forms of unexpected sequences. They further propose the notion of unexpected sequential patterns and implication rules for determining the structures and implications of the unexpectedness. The experimental results on various types of data sets show the usefulness and effectiveness of our approach.


2011 ◽  
Vol 20 (04) ◽  
pp. 357-370 ◽  
Author(s):  
D. PAULRAJ ◽  
S. SWAMYNATHAN ◽  
M. MADHAIYAN

One of the key challenges of the Service Oriented Architecture is the discovery of relevant services for a given task. In Semantic Web Services, service discovery is generally achieved by using the service profile ontology of OWL-S. Profile of a service is a derived, concise description and not a functional part of the semantic web service. There is no schema present in the service profile to describe the input, output (IO), and the IOs in the service profile are not always annotated with ontology concepts, whereas the process model has such a schema to describe the IOs which are always annotated with ontology concepts. In this paper, we propose a complementary sophisticated matchmaking approach which uses the concrete process model ontology of OWL-S instead of the concise service profile ontology. Empirical analysis shows that high precision and recall can be achieved by using the process model-based service discovery.


Sign in / Sign up

Export Citation Format

Share Document