Abstract
[abstract]

Abstract
Virtual environments for driving simulations aimed to scientific purposes require three-dimensional road models that must obey to detailed standards of specification and realism. The creation of road models with this level of quality requires previous definition of the road networks and the road paths. Each road path is usually obtained through the dedicated work of roadway design specialists, resulting in a long time consuming process. The driving simulation for scientific purposes also requires a semantic description of all elements within the environment in order to provide the parameterization of actors during the simulation and the production of simulation reports. This paper presents a methodology to automatically generate road environments suitable to the implementation of driving simulation experiences. This methodology integrates every required step for modelling road environments, from the determination of interchanges nodes to the generation of the geometric and the semantic models. The human supervisor can interact with the model generation process at any stage, in order to meet every specific requirement of the experimental work. The proposed methodology reduces workload involved in the initial specification of the road network and significantly reduces the use of specialists for preparing the road paths of all roadways. The generated semantic description allows procedural placing of actors in the simulated environment. The models are suitable for conducting scientific work in a driving simulator. Copyright

Abstract

Abstract
The data produced by Internet applications have increased substantially. Big data is a flaring field that deals with this deluge of data by using storage techniques, dedicated infrastructures and development frameworks for the parallelization of defined tasks and its consequent reduction. These solutions however fall short in online and highly data demanding scenarios, since users expect swift feedback. Reduction techniques are efficiently used in big data online applications to improve classification problems. Reduction in big data usually falls in one of two main methods: (i) reduce the dimensionality by pruning or reformulating the feature set; (ii) reduce the sample size by choosing the most relevant examples. Both approaches have benefits, not only of time consumed to build a model, but eventually also performance-wise, usually by reducing overfitting and improving generalization capabilities. In this paper we investigate reduction techniques that tackle both dimensionality and size of big data. We propose a framework that combines a manifold learning approach to reduce dimensionality and an active learning SVM-based strategy to reduce the size of labeled sample. Results on Twitter data show the potential of the proposed active manifold learning approach.

Abstract

Abstract