Learn More
The measurement of distance is one of the key steps in the unsupervised learning process, as it is through these distance measurements that patterns and correlations are discovered. We examined the characteristics of both non-Euclidean norms and data normalisation within the unsupervised learning environment. We empirically assessed the performance of the(More)
BACKGROUND Many studies have quantified the indirect effect of hydrocarbon-based economies on climate change and biodiversity, concluding that a significant proportion of species will be threatened with extinction. However, few studies have measured the direct effect of new energy production infrastructure on species persistence. METHODOLOGY/PRINCIPAL(More)
Wind energy offers the potential to reduce carbon emissions while increasing energy independence and bolstering economic development. However, wind energy has a larger land footprint per Gigawatt (GW) than most other forms of energy production, making appropriate siting and mitigation particularly important. Species that require large unfragmented habitats(More)
Emerging infectious diseases pose a serious threat to wildlife conservation (Daszak et al. 2000), yet often little is known about consequences of emerging infectious diseases for populations of sensitive or declining native species. Evaluating impacts of emerging infectious diseases to wildlife populations is difficult because monitoring strategies rarely(More)
This paper discusses some of the key design drivers for the next generation of the Oyster wave energy converter which is being developed by Aquamarine Power Ltd. The paper presents a general overview of the Oyster technology including the nearshore wave energy resource, the power capture characteristics of bottom-hinged flap type oscillators and the(More)
BACKGROUND Biodiversity offsets provide a mechanism to compensate for unavoidable damages from new energy development as the U.S. increases its domestic production. Proponents argue that offsets provide a partial solution for funding conservation while opponents contend the practice is flawed because offsets are negotiated without the science necessary to(More)
We present a novel formulation of Hilbert mapping in which we construct a global occupancy map by incrementally fusing local overlapping Hilbert maps. Rather than maintain a single supervised learning model for the entire map, a new model is trained with each of a robot's range scans, and queried at all points within the robot's perceptual field. We treat(More)
Given the significance of animal dispersal to population dynamics and geographic variability, understanding how dispersal is impacted by landscape patterns has major ecological and conservation importance. Speaking to the importance of dispersal, the use of linear mixed models to compare genetic differentiation with pairwise resistance derived from(More)