Meanings for Fusion Project

First of all, we have to explain what "Meanings for Fusion" means. We work with multimodal applications, which mean applications that use other forms of interaction in addition to the keyboard and mouse. We consider, for example, speech recognition as a modality where a microphone detects sounds that are analyzed and the results can be used for some computer's operations. Realize that, even classified as an input device, a microphone doesn't execute computer's operations by itself.

The main challenge is to extract meanings from the modalities supported by an application and identify how these meanings can be complementary to represent the needs of the user when interacting with the computer. The computer should react according to a decision making process based on machine learning algorithms.

Basically, we aim to extract meanings and fuse them, which justifies the title of the project.

Tools and Frameworks used in the Context of this Project

Testing: TestNG

Version Control System: SVN

Recommended IDE: Netbeans

Ontology Editor: Protege

Supported Languages: Java and C++.

UML Editor: JUDE Community Edition

Project Supported By

CEJUG - Ceará Java User Group - http://www.cejug.org

UCL - Université catholique de Louvain - http://www.uclouvain.be

Community Leaders

The community leaders are those who conceived the project and are available to manage discussions and answer questions from the community. They worked together a whole month (August) to create the first experiment and now, they are together to continue this challenging project. They are (in alphabetic order):

Ao Shen	Daniel Neiberg	David Gomez	Hildberto Mendonça	Olga Vybornova
has a bachelor's degree in Communication Science & Engineering at Fudan University, Shanghai, China and a bachelor's degree in Electronic Communication Engineering at Birmingham University, UK. He is experienced in coding mobile application and won the second prize in Vodafone Betavine Student Competition. Now he has finished his first year of PhD study in Electronic Electrical & Computer Engineering Department, University of Birmingham. His main interests multimodal systems and semantic level applications, knowledge base and ontology creation.	received an Master of Science in field of electrical engineering, KTH (Royal Institute of Technology), Stockholm, Sweden, in 2003. From 2002 to 2006 he worked as a Research engineer at Centre of Speech Technology (CTT) at KTH, were he was doing work in Speaker Verification and Emotion Recognition. From 2006 - 2007 he attended a Trainee Internship at Asahi Kasei, where the working tasks included development and evaluation of Automatic Speech Recognition of Swedish. In 2007, he enrolled as PhD student at Centre of Speech Technology (CTT) at KTH, where the main field of research is methods for automatic speech recognition and speech production.	received a BSc in Computer Systems Engineering in 2002 and a Msc. in Computer Science in 2004 with a specialization in Intelligent Systems and Computer Vision. He obtained these grades from Tec de Monterrey Campus Cuernavaca, Mexico. In 2003 he participated in the Robotic Soccer tournament (FIRA 2003) celebrated in Vienna, Austria in representation of Tec de Monterrey. During 2004 - 2007 he worked as a software developer in several companies (Real Time Services, Infomedia, Banco Azteca, Cognosite) learning and using different software programming technologies. In 2007, he started his PhD in Computer Vision at Télécom SudParis (Evry, France). He is currently studying his second year of his PhD with the thesis subject '3D Human Gesture Acquisition by Computer Vision and Virtual Rendering'.	has a bachelor’s degree in Computer Science at University of Fortaleza, Brazil. During his undergraduate studies he worked in the Laboratory of Human Computer Interaction with distance learning and digital TV projects. Afterwards, he worked in the Laboratory of Knowledge Management with public security and knowledge bases projects. Currently, he has finished his Diploma of Extended Studies in Human Computer Interaction Meta Representation as a requirement for the PhD in Applied Science in the field of Multimodal User Interaction at Catholic University of Louvain, Belgium. He has a rich professional experience in web application development, collaborative systems, and software engineering and software architecture projects. His technical skills are in the Java platform and its main extensions, C++, XML, relational databases, distributed systems, web services, web and desktop user interfaces, and creation and maintenance of ontology.	received a PhD degree in applied and mathematical linguistics from Moscow State Linguistic University, Russia, in October, 2002. From May 2005 she was a post-doctoral researcher and from January 2008 to the present time a research assistant in Université Catholique de Louvain at the Communications and Remote Sensing Lab (UCL-TELE) in Louvain-la-Neuve, Belgium.  Her main research interests are in the fields of multimodal data integration, assistive technology supporting active ageing and social cohesion, semantics-driven multimedia presentation generation, context-based inference, meaning representation, goals, intentions and commitments in communication, dialog modeling; cognitive linguistics; memory and attention, computational semantics.