Particle Competition and Cooperation in Networks for Semi-Supervised Learning

Semi-supervised learning is one of the important topics in machine learning, concerning with pattern classification where only a small subset of data is labeled. In this paper, a new network-based (or graph-based) semi-supervised classification model is proposed. It employs a combined random-greedy walk of particles, with competition and cooperation mechanisms, to propagate class labels to the whole network. Due to the competition mechanism, the proposed model has a local label spreading fashion, i.e., each particle only visits a portion of nodes potentially belonging to it, while it is not allowed to visit those nodes definitely occupied by particles of other classes. In this way, a "divide-and-conquer" effect is naturally embedded in the model. As a result, the proposed model can achieve a good classification rate while exhibiting low computational complexity order in comparison to other network-based semi-supervised algorithms. Computer simulations carried out for synthetic and real-world data sets provide a numeric quantification of the performance of the method.

Commentary on "The Impact of Family Stressors on the Social Development of Adolescents in Residential Facilities"

This is a commentary on “The impact of family stressors on the social development of adolescents admitted to a residential treatment facility,” by Cynthia Harr. This article examines the important but relatively understudied relationship of family dynamics in the social development of high risk teens in residential treatment facility (RTF) care. The commentary supports the author’s calls for a continuum of care involving greater cooperation with parents, and critiques and expands on some of the recommendations.

Flow and wakes in complex terrain and offshore. Model development and verification in UPWIND

The paper presents research conducted in the Flow workpackage of the EU funded UPWIND project which focuses on improving models for flow within and downwind of large wind farms in complex terrain and offshore. The main activity is modelling the behaviour of wind turbine wakes in order to improve power output predictions.

Ultraviolet-B Radiation Effects on Water Relations, Leaf Development, and Photosynthesis in Droughted Pea Plants1

The effects of ultraviolet-B (UV-B) radiation on water relations, leaf development, and gas-exchange characteristics in pea (Pisum sativum L. cv Meteor) plants subjected to drought were investigated. Plants grown throughout their development under a high irradiance of UV-B radiation (0.63 W m−2) were compared with those grown without UV-B radiation, and after 12 d one-half of the plants were subjected to 24 d of drought that resulted in mild water stress. UV-B radiation resulted in a decrease of adaxial stomatal conductance by approximately 65%, increasing stomatal limitation of CO2 uptake by 10 to 15%. However, there was no loss of mesophyll light-saturated photosynthetic activity. Growth in UV-B radiation resulted in large reductions of leaf area and plant biomass, which were associated with a decline in leaf cell numbers and cell division. UV-B radiation also inhibited epidermal cell expansion of the exposed surface of leaves. There was an interaction between UV-B radiation and drought treatments: UV-B radiation both delayed and reduced the severity of drought stress through reductions in plant water-loss rates, stomatal conductance, and leaf area.