Hai Bang Truong

A HYBRID METHOD FOR FUZZY ONTOLOGY INTEGRATION

The main contribution of this work consists of combining a heuristic method for propagation of matchable concepts and using consensus techniques for conflict resolution for fuzzy ontology integration. Two central observations behind this approach are as follows: (1) if two concepts across different source ontologies equivalently match each other, then their neighboring concepts will be often matched as well; and (2) conflicts regarding integration of multiple ontologies can be resolved by creating a consensus among the conflict ontological entities. The key idea of the first observation is to start from an aligned pair of concepts (called medoids) to determine so-called potentially common parts to provide additional suggestions for possible matching concepts. This approach is used to obtain pairs of matchable concepts and to avoid pairs of mismatching concepts. On the other hand, the second observation is used to discover a new merged concept from matched concepts by making a consensus among conflict ontological entities. This idea is to determine the best representative as the merged version of the component ones. A combination of both observations for fuzzy ontology integration is a significant contribution of this work. The results of the experiments imply that the proposed approach is effective with regard to both completeness and accuracy.

A Preliminary Analysis of the Influence of the Inconsistency Degree on the Quality of Collective Knowledge

ABSTRACT Collective knowledge is often determined on the basis of the knowledge states of members of a collective about a subject in the real world. The real knowledge state about this subject exists, but it’s not known by the collective members. With the objective case, we assume that the real knowledge state about this subject exists independently of the knowledge states given by the collective members, whose knowledge states reflect the real knowledge state to some degree because of incompleteness and uncertainty. The inconsistency degree is understood as the coherence level of the knowledge states of the collective members. In this study we analyze the influence of the inconsistency degree of a collective on the quality of collective knowledge for the objective case. The quality measure is based on the distance from the collective knowledge to the real knowledge state. For this aim, based on the Euclidean space, the hypothesis “the higher the inconsistency, the better the quality of collective knowledge” will be proved. Also, the upper limit of the difference between the real knowledge state and the collective knowledge is also investigated. The upper limit means the maximal value that the difference between them does not exceed.

A consensus-based method for fuzzy ontology integration

Ontology can be treated as the background of a knowledge-based system. Fuzzy ontologies in many cases seem to be more useful than nonfuzzy ontologies because of the possibility for distinguish the degrees to which concepts describe a real world, or relations between them. This paper includes a framework of consensus-based method for fuzzy ontology integration. For this aim a conception for fuzzy ontology definition is proposed and three problems for fuzzy ontology integration on concept and relation levels are presented. For these problems several algorithms have been proposed.

A framework of an effective fuzzy ontology alignment technique

Fuzzy ontology integration is important for handling uncertain information on the Semantic web. However, current ontology integration technologies are not sufficient for fuzzy ontologies. The main contribution of the approach presented here is to propose a novel framework of an effective method for fuzzy ontology alignment. The key concept of the approach is to start from an aligned pair of concepts (called a medoid pair) to determine Potentially Common Parts in different fuzzy ontologies. The distance between the Potentially Common Parts is the sum of the distances between weights of their corresponding concepts. The weight of each concept is estimated by taking into account its attributes and relations to other concepts. Concepts belonging to the common parts are often similar, as they are either sub-concepts/super-concepts of or related concepts to the medoid concepts. Therefore, the distance between Potentially Common Parts is minimized to identify possible matching concepts. New aligned pairs are collected across the potentially common parts by computing similarities between the corresponding concepts belonging to the minimum Potentially Common Parts.

Local neighbor enrichment for ontology integration

The main aim of this research is to deal with enriching conceptual semantic by expanding local conceptual neighbor. The approach consists of two phases: neighbor enrichment phase and matching phase. The enrichment phase is based on analysis of the extension semantic the ontologies have. The extension we make use of in this work is generated an contextually expanded neighbor of each concept from external knowledge sources such as WordNet, ODP, and Wikimedia. Outputs of the enrichment phase are two sets of contextually expanded neighbors belonging to these two corresponding ontologies, respectively. The matching phase calculates similarities between these contextually expended neighbors, which yields decisions which concepts are to be matched.

A new graph-based flooding matching method for ontology integration

Ontology integration is a well-known problem, a crucial mechanism for semantic interoperability and knowledge reusing, and a backbone of Semantic Web. In this paper, a graph-based method, which combines similarity flooding and concept classification for ontology integration, is proposed. This method consists of three main steps: model ontologies into directed labeled graph, concept classification, and similarity flooding for computing fix-points of pairwise connectivity graph. The main issue presented here is how to shrink spreading scale before we use similarity flooding. Experimental results demonstrate that our method is more effective and obtain better results than original similarity flooding algorithm.

A Comparative Study of Methods for Collective Prediction Determination Using Interval Estimates

Recently, research on the Wisdom of Crowd (WoC) has been widely expanded by supporting interval values as an additional representation of underlying predictions. Accordingly, instead of giving single values, ones can express their predictions on a given cognition problem in the form of interval values1. For such a representation, many methods have been proposed for aggregating underlying predictions based on their midpoints. In this case, of course, the outputs of the proposed methods are single values. In some situations, however, the aggregated prediction in the form of interval value can be better representation of underlying predictions. In the current study, we present a comparison of the use of different approaches for aggregating individual predictions including Interval Aggregation and MidPoint Aggregation. Experimental studies have been conducted to determine how do different aggregation methods influence the quality of the obtained collective prediction.

Intelligent Collectives: Impact of Diversity on Susceptibility to Consensus and Collective Performance.

In this paper, we present an approach to analyzing the impact of diversity, one of the most crucial determinants of intelligent collectives, on susceptibility to consensus and collective performance. In the common understanding, susceptibility to consensus refers to the situation in which the obtained collective prediction determined on the basis of individual predictions can be accepted as the representative for the collective as a whole. Computational experiments have indicated that when collectives are small, it is difficult to obtain a high probability of susceptibility to consensus. For large collectives, however, diversity seems not to matter susceptibility to consensus. Furthermore, the findings have also shown that higher collective performances can be the consequence of more diverse collectives. In other words, diversity is positively correlated with collective performance.