Abstract-With the fast growing demand of location-based services in indoor environments, indoor positioning based on fingerprinting has attracted a lot of interest due to its high accuracy. In this paper, we present a novel deep learning based indoor fingerprinting system using Channel State Information (CSI), which is termed DeepFi. Based on three hypotheses on CSI, the DeepFi system architecture includes an off-line training phase and an on-line localization phase. In the off-line training phase, deep learning is utilized to train all the weights of a deep network as fingerprints. Moreover, a greedy learning algorithm is used to train the weights layer-by-layer to reduce complexity. In the on-line localization phase, we use a probabilistic method based on the radial basis function to obtain the estimated location. Experimental results are presented to confirm that DeepFi can effectively reduce location error compared with three existing methods in two representative indoor environments.
Protected areas are the cornerstone of biodiversity conservation. However, alien species invasion is an increasing threat to biodiversity, and the extent to which protected areas worldwide are resistant to incursions of alien species remains poorly understood. Here, we investigate establishment by 894 terrestrial alien animals from 11 taxonomic groups including vertebrates and invertebrates across 199,957 protected areas at the global scale. We find that <10% of protected areas are home to any of the alien animals, but there is at least one established population within 10-100 km of the boundaries of 89%-99% of protected areas, while >95% of protected areas are environmentally suitable for establishment. Higher alien richness is observed in IUCN category-II national parks supposedly with stricter protection, and in larger protected areas with higher human footprint and more recent designation. Our results demonstrate that protected areas provide important protection from biological invasions, but invasions may become an increasingly dominant problem in the near future.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.