This article describes an application of the partially observable Markov (POM) model to the analysis of a large scale commercial web search log. Mathematically, POM is a variant o...
—Triggered by a market relevant application that involves making joint predictions of pedestrian and public transit flows in urban areas, we address the question of how to utili...
Marion Neumann, Kristian Kersting, Zhao Xu, Daniel...
We present two machine learning approaches to information extraction from semi-structured documents that can be used if no annotated training data are available, but there does ex...
In this paper we present an original method of analysing the newlyrevised UML2.0 activity diagrams. Our analysis method builds on our formal interpretation of these diagrams with ...
C. Canevet, Stephen Gilmore, Jane Hillston, Le&ium...
In this paper we present a new method, time-striding hidden Markov model (TSHMM), to learn from long-term motion for atomic behaviors and the statistical dependencies among them. T...