The development of novel interactive systems for supporting our daily activities (e.g., gym training activities) demands flexible and dynamic ontologies for knowledge representation and application support. In this paper, we propose a soft ontology-based architecture for dealing with decision support and recommendation under dynamic and uncertainty situations, including those related to gym training activities. Our architecture considers users’ characteristics and group’s feedback (e.g., comments, evaluation, sensor data and results) to develop and evolve flexible ontological structures using a Fuzzy RDF approach for implementing soft ontologies. The architecture was implemented by the OntoGymWP application, which provides suggestions of gym workout plans based on users’ features and social feedback represented in Fuzzy RDF ontologies. These ontologies are used to semantically encode: users’ profile; shared concepts from the domain for each group of users; and training plans for each individual. The implemented proof of concept reveals the viability of the architecture, as well as its potentiality in providing suitable gym workout plans based on extensible and flexible ontologies.

Enhancing Peoples’ Training Experience: A Gym Workout Planner Based on Soft Ontologies

The huge mass of data generated continuously leads to information overload which limit the tools available to manage, store and secure this traffic on the web. The situation is paradoxical, a need for timely relevant information and the difficulty to btain this information because it is lost in the mass. The use of fully search engine based on the formulation of the request by users show some limitations. The trend is to improve the information filtering approaches to better answer the user's expectations. In this work, we modelled a collaborative filtering system by Friend Of A Friend (FOAF) formalism for the representation of the users and the Dublin Core (DC) vocabulary to represent the resources " items". In addition, and to ensure the interoperability and openness of this model, we adopted the Resource Description Framework (RDF) syntax to describe the various modules of the system. A hybrid function was introduced for the calculation of prediction. The empirical tests on various real data sets (Book-Crossing, FoafPub) showed satisfactory performances in relevance and precision.

Improvement of Collaborative Filtering Systems through Resource Description Framework

There is a continuous information overload on the Web. The problem treated is how to have relevant information (documents, products, services etc.) at time and without difficulty. Filtering system also called recommender systems have widely used to recommend relevant resources to users by similarity process such as Amazon, MovieLens, Cdnow etc. The trend is to improve the information filtering approaches to better answer the users expectations. In this work, we model a collaborative filtering system by using Friend Of A Friend (FOAF) formalism to represent the users and the Dublin Core (DC) vocabulary to represent the resources “items”. In addition, to ensure the interoperability and openness of this model, we adopt the Resource Description Framework (RDF) syntax to describe the various modules of the system. A hybrid function is introduced for the calculation of prediction. Empirical tests on various real data sets (Book-Crossing, FoafPub) showed satisfactory performances in terms of relevance and precision.

/pdf/a-hybrid-model-to-improve-filtering-systems-540yx9h4hn.pdf

Dahmani youcef

Papers

Improvement of Collaborative Filtering Systems through Resource Description Framework

A Hybrid Model to Improve Filtering Systems