다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

On robust estimation of the location parameter

Matrix Factorization Techniques for Recommender Systems

We explore the effect of dimensionality on the nearest neighbor problem. We show that under a broad set of conditions (much broader than independent and identically distributed dimensions), as dimensionality increases, the distance to the nearest data point approaches the distance to the farthest data point. To provide a practical perspective, we present empirical results on both real and synthetic data sets that demonstrate that this effect can occur for as few as 10-15 dimensions. These results should not be interpreted to mean that high-dimensional indexing is never meaningful; we illustrate this point by identifying some high-dimensional workloads for which this effect does not occur. However, our results do emphasize that the methodology used almost universally in the database literature to evaluate high-dimensional indexing techniques is flawed, and should be modified. In particular, most such techniques proposed in the literature are not evaluated versus simple linear scan, and are evaluated over workloads for which nearest neighbor is not meaningful. Often, even the reported experiments, when analyzed carefully, show that linear scan would outperform the techniques being proposed on the workloads studied in high (10-15) dimensionality!.

When is nearest neighbor meaningful

Losses of natural and semi-natural forests, mostly to agriculture, are a significant concern for biodiversity. Against this trend, the area of intensively managed plantation forests increases, and there is much debate about the implications for biodiversity. We provide a comprehensive review of the function of plantation forests as habitat compared with other land cover, examine the effects on biodiversity at the landscape scale, and synthesise context-specific effects of plantation forestry on biodiversity. Natural forests are usually more suitable as habitat for a wider range of native forest species than plantation forests but there is abundant evidence that plantation forests can provide valuable habitat, even for some threatened and endangered species, and may contribute to the conservation of biodiversity by various mechanisms. In landscapes where forest is the natural land cover, plantation forests may represent a low-contrast matrix, and afforestation of agricultural land can assist conservation by providing complementary forest habitat, buffering edge effects, and increasing connectivity. In contrast, conversion of natural forests and afforestation of natural non-forest land is detrimental. However, regional deforestation pressure for agricultural development may render plantation forestry a ‘lesser evil’ if forest managers protect indigenous vegetation remnants. We provide numerous context-specific examples and case studies to assist impact assessments of plantation forestry, and we offer a range of management recommendations. This paper also serves as an introduction and background paper to this special issue on the effects of plantation forests on biodiversity.

Plantation Forests and Biodiversity: Oxymoron or Opportunity?

Grasslands represent a significant source of biodiversity that is important to monitor over large extents. The Spectral Variation Hypothesis (SVH) assumes that the Spectral Heterogeneity (SH) measured from remote sensing data can be used as a proxy for species diversity. Here, we argue the hypothesis that the grassland’s species differ in their phenology and, hence, that the temporal variations can be used in addition to the spectral variations. The purpose of this study is to attempt verifying the SVH in grasslands using the temporal information provided by dense Satellite Image Time Series (SITS) with a high spatial resolution. Our method to assess the spectro-temporal heterogeneity is based on a clustering of grasslands using a robust technique for high dimensional data. We propose new SH measures derived from this clustering and computed at the grassland level. We compare them to the Mean Distance to Centroid (MDC). The method is experimented on 192 grasslands from southwest France using an intra-annual multispectral SPOT5 SITS comprising 18 images and using single images from this SITS. The combination of two of the proposed SH measures—the within-class variability and the entropy—in a multivariate linear model explained the variance of the grasslands’ Shannon index more than the MDC. However, there were no significant differences between the predicted values issued from the best models using multitemporal and monotemporal imagery. We conclude that multitemporal data at a spatial resolution of 10 m do not contribute to estimating the species diversity. The temporal variations may be more related to the effect of management practices.

https://www.mdpi.com/2072-4292/9/10/993/pdf

Spectro-Temporal Heterogeneity Measures from Dense High Spatial Resolution Satellite Image Time Series: Application to Grassland Species Diversity Estimation

In this paper, we study the potential of the new satellite Sentinel-2 (S2) images to identify tree species in temperate forests. Fourteen tree species are classified from eleven S2 images acquired from winter 2015 to autumn 2016 with 2181 reference pixels. Two datasets are compared: (1) the 4-bands dataset including the 10-m VNIR images only and (2) the 10-bands dataset including the red-edge and SWIR bands at 20-m, resampled at 10-m. Three standard supervised algorithms are tested: SVM with three kernel functions, Random Forest, and Gradient Boosted Trees. Depending on the considered dataset and algorithm, we obtain very high performances (Cohen's kappa from 0.92 to 0.97). Black pine and Douglas fir are the most confused species (F1-score of 0.81 and 0.74 respectively). Cultivated tree plantations such as Aspen and Red Oak are the best predicted (F1-score of 0.99 for both). SVM-RBF outperforms systematically the other classifiers. These first results suggest a high potential of the new Sentinel-2 optical images for mapping the distribution of tree species in forest ecosystems.

Mapping tree species of forests in southwest France using Sentinel-2 image time series

With the current expansion of cities, urban trees have an important role for preserving the health of its in- habitants. With their evapotranspiration, they reduce the urban heat island phenomenon, by trapping CO2 emission, improve air quality. In particular, street trees or alignment trees, create shade on the road network, are structuring elements of the cities and decorate the roads. Street trees are also subject to specific conditions as they have little space for growth, are pruned and can be affected by the spread of diseases in single-species plantations. Thus, their detection, identification and monitoring are necessary. In this study, an approach is proposed for mapping these trees that are characteristic of the urban environment. Three areas of the city of Toulouse in the south of France are studied. Airborne hyperspectral data and a Digital Surface Model (DSM) for high vegetation detection are used. Then, contextual information is used to identify the street trees. Indeed, Geographic Information System (GIS) data are considered to detect the vegetation canopies close to the streets. Afterwards, individual street tree crown delineation is carried out by modeling the discriminative contextual features of individual street trees (hypotheses of small angle between the trees and similar heights) based on Marked Point Process (MPP). Compared to a baseline individual tree crown delineation method based on region growing, our method logically provides the best results with F-score values of 91%, 75% and 85% against 70%, 41% and 20% for the three studied areas respectively. Our approach mainly succeeds in identifying the street trees. In addition, the contribution of the angle, the height and the GIS data in the street tree mapping has been studied. The results encourage the use of the angle, the height and the GIS data together. However, with only the angle and the height, the results are similar to those obtained with the inclusion of the GIS data for the first and the second study cases with F-score values of 88%, 79% and 62% against 91%, 75% and 85% for the three study cases respectively. Finally, it is shown that the GIS data only is not sufficient.

Detection of individual trees in urban alignment from airborne data and contextual information: A marked point process approach

Mapping forest composition using multiseasonal optical time series remains a challenge. Highly contrasted results are reported from one study to another suggesting that drivers of classification errors are still under-explored. We evaluated the performances of single-year Formosat-2 time series to discriminate tree species in temperate forests in France and investigated how predictions vary statistically and spatially across multiple years. Our objective was to better estimate the impact of spatial autocorrelation in the validation data on measurement accuracy and to understand which drivers in the time series are responsible for classification errors. The experiments were based on 10 Formosat-2 image time series irregularly acquired during the seasonal vegetation cycle from 2006 to 2014. Due to lot of clouds in the year 2006, an alternative 2006 time series using only cloud-free images has been added. Thirteen tree species were classified in each single-year dataset based on the Support Vector Machine (SVM) algorithm. The performances were assessed using a spatial leave-one-out cross validation (SLOO-CV) strategy, thereby guaranteeing full independence of the validation samples, and compared with standard non-spatial leave-one-out cross-validation (LOO-CV). The results show relatively close statistical performances from one year to the next despite the differences between the annual time series. Good agreements between years were observed in monospecific tree plantations of broadleaf species versus high disparity in other forests composed of different species. A strong positive bias in the accuracy assessment (up to 0.4 of Overall Accuracy (OA)) was also found when spatial dependence in the validation data was not removed. Using the SLOO-CV approach, the average OA values per year ranged from 0.48 for 2006 to 0.60 for 2013, which satisfactorily represents the spatial instability of species prediction between years.

Statistical Stability and Spatial Instability in Mapping Forest Tree Species by Comparing 9 Years of Satellite Image Time Series

This study aims at identifying the best object-based fusion strategy that takes advantage of the complementarity of several heterogeneous airborne data sources for improving the classification of 1...

Mathieu Fauvel

Papers

Spectro-Temporal Heterogeneity Measures from Dense High Spatial Resolution Satellite Image Time Series: Application to Grassland Species Diversity Estimation

Mapping tree species of forests in southwest France using Sentinel-2 image time series

Detection of individual trees in urban alignment from airborne data and contextual information: A marked point process approach

Statistical Stability and Spatial Instability in Mapping Forest Tree Species by Comparing 9 Years of Satellite Image Time Series

Object-based fusion for urban tree species classification from hyperspectral, panchromatic and nDSM data