New evidence for the origin and behaviour of deep ocean 'crusts'

In situ tests in deep waterWest African clays show crust-like shear strengths within the top few metres of sediment. Typical strength profiles show su rising from mud-line to 10 kPa to 15 kPa before dropping back to normally consolidated strengths of 3 kPa to 4 kPa by 1.5m to 2m depth. A Cam-shear device is used to better understand the mechanical behaviour of undisturbed crust samples under pipelines. Extremely variable peak and residual shear strengths are observed for a range of pipeline consolidation stresses and test shear rates, with residual strengths approximating zero. ESEM of undisturbed samples and wet-sieved samples from various core depths show the presence of numerous randomly-located groups of invertebrate faecal pellets. It is therefore proposed that the cause of strength variability during shear testing and, indeed, of the crust's origin, is the presence of random groups of faecal pellets within the sediment. © 2011 Taylor & Francis Group, London.

Probabilistic graphical models for semi-supervised traffic classification

Traffic classification using machine learning continues to be an active research area. The majority of work in this area uses off-the-shelf machine learning tools and treats them as black-box classifiers. This approach turns all the modelling complexity into a feature selection problem. In this paper, we build a problem-specific solution to the traffic classification problem by designing a custom probabilistic graphical model. Graphical models are a modular framework to design classifiers which incorporate domain-specific knowledge. More specifically, our solution introduces semi-supervised learning which means we learn from both labelled and unlabelled traffic flows. We show that our solution performs competitively compared to previous approaches while using less data and simpler features. Copyright © 2010 ACM.