Nhan Le Thanh

Bio: Nhan Le Thanh is an academic researcher from University of Nice Sophia Antipolis. The author has contributed to research in topics: Ontology (information science) & Semantic Web. The author has an hindex of 9, co-authored 38 publications receiving 250 citations. Previous affiliations of Nhan Le Thanh include Centre national de la recherche scientifique.

Semantic Web Approach to Ease Regulation Compliance Checking in Construction Industry

Abstract: Regulations in the Building Industry are becoming increasingly complex and involve more than one technical area. They cover products, components and project implementations. They also play an important role to ensure the quality of a building, and to minimize its environmental impact. Control or compliance checking are becoming more complex every day for industrials but also for organizations in charge of assessing the conformity of new products or processes. This paper will detail the approach taken by the CSTB in order to simplify this compliance control task. The approach and the solutions proposed are based on semantic web technologies. For this purpose, we first elaborate a domain-ontology, which defines the main concepts involved and the relationships among them based on OWL. We rely on SBVR and SPARQL to reformulate the regulatory requirements written in natural language in a controlled and formal language. We structure then our control process based on expert practices. Each elementary control step is defined as a SPARQL query and assembled into complex control processes " on demand " according to the component tested and its semantic definition. Finally, we represent in RDF the association between the SBVR rules and SPARQL queries representing the same regulatory constraints.

Graph-based Event Extraction from Twitter

Abstract: Event detection on Twitter has become an attractive and challenging research field due to the popularity and the peculiarities of tweets. Detecting which tweets describe a specific event and clustering them is one of the main challenging tasks related to Social Media currently addressed in the NLP community. Existing approaches have mainly focused on detecting spikes in clusters around specific keywords or Named Entities (NE). However, one of the main drawbacks of such approaches is the difficulty in understanding when the same keywords describe different events. In this paper, we propose a novel approach that exploits NE mentions in tweets and their entity context to create a temporal event graph. Then, using simple graph theory techniques and a PageRank-like algorithm, we process the event graphs to detect clusters of tweets describing the same events. Experiments on two gold standard datasets show that our approach achieves state-of-the-art results both in terms of evaluation performances and the quality of the detected events.

Detecting depression using multimodal approach of emotion recognition

Abstract: Depression is a growing problem in our society. It causes pain and suffering not only to patients but also to those who care about them. This paper presents a multimodal emotion recognition system that is capable of preventing depression. It consists of detecting persistent negative emotions for early detection of depression. Our proposal is based on an algebraic representation of emotional states using multidimensional vectors. This algebraic model provides powerful mathematical tools for the analysis and the processing of emotions and permits the fusion of complementary information such as facial expression, voice, physiological signals, etc. Experiments results show the efficiency of the proposed method in detecting negative emotions by giving high recognition rate.

Towards an Ontology-enabled Approach for Modeling the Process of Conformity Checking in Construction.

Abstract: This paper presents an ontological method aimed at semi-automatic checking the conformity of a construction project represented by RDF graph against a set of construction norms formalized as SPARQL queries. The reasoning is modeled by the matching of RDF representations of construction projects to SPARQL conformity queries. We integrate meta-knowledge relative to the checking process by annotating the conformity queries themselves and organize them according to their annotations. The queries annotations also help to guide the information/knowledge extraction and reasoning process and explain the results of the validation process, especially in case of failure.

Towards an Algebraic Modeling of Emotional States

Abstract: In this study, we present a new vision of modeling emotional states. Indeed, the proposed model is different from traditional approaches like ontological representation. It is based on an algebraic representation of emotions. We represent every emotion as a vector in a space of 8 dimensions where every axis represents a basic emotion. This multidimensional model provides to represent infinity of emotion and provides powerful mathematical tools for the analysis and the processing of these emotions. Therefore, our model permits to model not only the basic emotions (e.g., anger, sadness, fear) but also different types of complex emotions like simulated and masked emotions. Moreover, it permits the exchange of emotional states between heterogeneous applications regardless to the modalities and sensors used in the detection step.

Tacit knowledge transfer and the knowledge disconnect

Abstract: Purpose – The purpose of this paper is to look at some of the factors that influence the transfer of tacit knowledge between two product development partners.Design/methodology/approach – Research involved the collection of both qualitative and quantitative data. The qualitative data was based on 13 interviews with various individuals, representing three companies, charged with integrating external technology. The quantitative portion of the data was collected through an online survey. The survey was executed by soliciting responses from managers of 39 discreet projects involving various types of external technology integration, representing five different companies.Findings – The paper provides evidence that trust, early involvement, and due diligence influence the extent of meeting technology transfer expectations and tacit knowledge transfer expectations. It also finds that the subject of tacit knowledge transfer, content and process, is poorly understood. While managers and project leaders saw the val...