Modeling Rules Fission and Modality Selection Using Ontology

Atef Zaguia, Ahmad Wahbi, Moeiz Miraoui, Chakib Tadj, Amar Ramdane-Cherif
2013 Journal of Software Engineering and Applications  
Researchers in computer science and computer engineering devote a significant part of their efforts on communication and interaction between man and machine. Indeed, with the advent of multimedia and multimodal processing in real time, the computer is no longer considered only as a computational tool, but as a machine for processing, communication, collection and control. Many machines assist and support many activities in daily life. The main objective of this paper is to propose a new
more » ... opose a new methodological solution by modeling an architecture that facilitates the work of multimodal system especially for a fission module. To realize such systems, we rely on ontology to integrate data semantically. Ontologies provide a structured vocabulary usedas support for data representation. This paper provides a better understanding of the fission system and multimodal interaction. We present our architecture and the description of the detection of optimal modalities. This is done by using an ontological model that contains different applicable scenarios and describes the environment where a multimodal system exists. Fusion Fission Multimodal System Environment Environment Command Modality In1 Modality In2 Modality Inn Modality Ou1 Modality Ou2 Modality Oun Figure 1. Multimodal system. JSEA Modeling Rules Fission and Modality Selection Using Ontology 355 eve the annotation of the data, such as it can be performed by experts in a particular field. Several studies have focused on the improvement of intelligent systems and especially the creation of systems that enable semantic interoperability, which means the systems will not only exchange data with each other in a given format (e.g. the string "Canada") but also must have the same meaning for both parties (a Country). So the main goal is to find a way to present data so that the machines, the users, the applications can understand. The most adequate solution is ontology [8] . The ontology will have a good impact in multimodal systems and specially for fission module [9] . The fission module is a fundamental component of multimodal interactive system. It is mainly used at the output. Its role is to subdivide the requests/commands made by the user to elementary subtasks, then associate them to the appropriate modalities and to present them in the available output media [10] . The meaning of the command may vary according to the context, the task and the services. This paper is focused on the fission process. We propose a new methodological solution by modeling an architecture that facilitates the work of a fission module, by defining an ontology that contains different applicable scenarios and describes the environment where a multimodal system exists. The proposed architecture has three main characteristics:  Openness: handling a large number of modalities that prevents the restriction in its application to specific domains.  Flexibility: the use of ontology makes the description of an environment and its scenarios easier.  Consistency: the description of the most potential objects and scenarios of the environment. This paper discusses these characteristics by explaining the architectural design of the proposed solution. The rest of this paper is structured as follows. Section 2 presents the problems related to the fission processand highlights the novelty of our work. Section 3 presents related researches. Sections 4 to 6 present the design of the architecture, the interaction context and the ontology which we will use to solve the problem "How to present fission rules and modality selection for multimodal systems?". Sections 7 and 8 describe our proposed fission algorithm and a scenario respectively. Conclusion is presented in Section 9.  Class Average Object={microwave, box, desk, computer, chair, television, table, Copyright © 2013 SciRes. JSEA Modeling Rules Fission and Modality Selection Using Ontology 360 b) Electronic Object: it presents the electronic objects. For instance: AFNMO has Next NMO has Next LO For instance "close the door of the kitchen". These models enable us to process a large variety and complex commands.
doi:10.4236/jsea.2013.67045 fatcat:ekwiz4delzh5dod5dr2niatgji