Palestra: Machine Learning For Data Fusion And The Big Data Question
Criada em 21/11/2012 12:05 por maperna | Marcadores: eventofen
PALESTRA PROF. FABIO RAMOS DATA: 23 de novembro de 2012 LOCAL: sala 401L. Prédio Cardeal Leme, PUC-Rio HORÁRIO: 10 às 12h
Title: Machine learning for data fusion and the Big Data question
Abstract: Recent years have seen an enormous proliferation and availability of data typically collected from sensors embedded in computer devices. Most people have mobile phones with an integrated camera, GPS and accelerometers. Mobile robots can possess radars, 3D laser scanners, and hyperspectral cameras. Larger -scale examples include the mining industry where several sources of information (core drilling, cone logging, spectrometry) are available to predict the ore concentration and assess the quality of the product. However, immense quantities of data are not necessarily useful unless we develop methods to interpret and represent multi-modal information efficiently. In this talk I will present methods to jointly infer multiple quantities from various sensor modalities, at different space and time resolutions. As an example, consider the problem of estimating a real-time spatial-temporal model of pollution dispersion in a river using mobile platforms. Given the technology available, the vehicle can sense biomass, temperature, PH and many other chemical/physical quantities. Understanding the relationships between these quantities can significantly improve the accuracy of the method while reducing the uncertainty about the phenomenon. I will show a set of techniques for nonparametric Bayesian modelling that address the challenges in spatial-temporal modelling with heterogenous sensors. In particular: 1) how to define exact and sparse models that are scalable to large datasets; 2) how to integrate data collected at different support and resolutions; and 3) how to automatically learn relationships between different quantities in real -time, from mobile platforms. I will show applications of these methods to a number of problems in robotics, mining exploration and environmental monitoring.
Short bio: Fabio Ramos is a Senior Lecturer at the School of Information Technologies, University of Sydney, and an ARC Discovery Early Career Fellow. He received the B.Sc. and the M.Sc. degrees in Mechatronics Engineering at University of Sao Paulo, Brazil, in 2001 and 2003 respectively, and the Ph.D. degree at University of Sydney, Australia, in 2007. From 2007 to 2010 he was an ARC research fellow at the Australian Centre for Field Robotics (ACFR). He has over 80 peer -reviewed publications and received the Best Paper Award at the International Conference on Intelligent Robots and Systems (IROS) and at the Australian Conference on Robotics and Automation (ACRA). He is an associate editor for ICRA, IROS, RSS and a program committee member AAAI, IJCAI and IPSN. His research focuses on statistical machine learning for large-scale data fusion problems with applications to robotics, mining, environmental monitoring and healthcare.
(Para perguntas, verifique acima a forma de contato na notícia)
Todos os campos são obrigatórios
Regras para comentários:
Comentários anônimos serão excluídos;
A postagem de comentários com links externos será excluída;
Não publicamos denúncias. Nestes casos, você deve encaminhar aos órgãos cabíveis ou indicados na notícia;
Comentários que fujam ao teor da matéria serão excluídos;
Ofensas e quaisquer outras formas de difamação não serão publicadas;
Os autores da notícia não monitoram os comentários, portanto não há garantias que serão lidos e/ou respondidos. Procure a forma de contato na própria notícia