Suchergebnisse

The Rotation Forest classifier is a successful ensemble method for a wide variety of data mining applications. However, the way in which Rotation Forest transforms the feature space through PCA, although powerful, penalizes training and prediction times, making it unfeasible for Big Data. In this paper, a MapReduce Rotation Forest and its implementation under the Spark framework are presented. The proposed MapReduce Rotation Forest behaves in the same way as the standard Rotation Forest, training the base classifiers on a rotated space, but using a functional implementation of the rotation that enables its execution in Big Data frameworks. Experimental results are obtained using different cloud-based cluster configurations. Bayesian tests are used to validate the method against two ensembles for Big Data: Random Forest and PCARDE classifiers. Our proposal incorporates the parallelization of both the PCA calculation and the tree training, providing a scalable solution that retains the performance of the original Rotation Forest and achieves a competitive execution time (in average, at training, more than 3 times faster than other PCA-based alternatives). In addition, extensive experimentation shows that by setting some parameters of the classifier (i.e., bootstrap sample size, number of trees, and number of rotations), the execution time is reduced with no significant loss of performance using a small ensemble. ; This work was supported through project TIN2015-67534-P (MINECO/FEDER, UE) of the Ministerio de Economía y Competitividad of the Spanish Government, projects BU085P17 and BU055P20 (JCyL/FEDER, UE) of the Junta de Castilla y León, Spain (both projects co-financed through European Union FEDER funds), and by the Consejería de Educación of the Junta de Castilla y León, Spain and the European Social Fund through a pre-doctoral grant (EDU/1100/2017). The project leading to these results has received also funding from "la Caixa" Foundation, Spain , under agreement LCF/PR/PR18/51130007. This material is based upon work supported by Google Cloud.

International audience ; Detailed and timely information on crop area, production and yield isimportant for the assessment of environmental impacts of agriculture,for the monitoring of the land use and management practices, and forfood security early warning systems. A machine learningapproach is proposed to model crop rotations which can predict with good accuracy,at the beginning of the agricultural season, the crops most likely tobe present in a given field using the crop sequence of the previous 3to 5 years. The approach is able to learn from data and to integrateexpert knowledge represented as first-order logic rules. Itsaccuracy is assessed using the French Land Parcel Information System implementedin the frame of the EU's Common Agricultural Policy. This assessmentis done using different settings in terms of temporal depth andspatial generalization coverage. The obtained results show that theproposed approach is able to predict the crop type of each field,before the beginning of the crop season, with an accuracy as high as 60\%, which is better than the results obtained with currentapproaches based on remote sensing imagery.

International audience ; Detailed and timely information on crop area, production and yield isimportant for the assessment of environmental impacts of agriculture,for the monitoring of the land use and management practices, and forfood security early warning systems. A machine learningapproach is proposed to model crop rotations which can predict with good accuracy,at the beginning of the agricultural season, the crops most likely tobe present in a given field using the crop sequence of the previous 3to 5 years. The approach is able to learn from data and to integrateexpert knowledge represented as first-order logic rules. Itsaccuracy is assessed using the French Land Parcel Information System implementedin the frame of the EU's Common Agricultural Policy. This assessmentis done using different settings in terms of temporal depth andspatial generalization coverage. The obtained results show that theproposed approach is able to predict the crop type of each field,before the beginning of the crop season, with an accuracy as high as 60\%, which is better than the results obtained with currentapproaches based on remote sensing imagery.

International audience ; Detailed and timely information on crop area, production and yield isimportant for the assessment of environmental impacts of agriculture,for the monitoring of the land use and management practices, and forfood security early warning systems. A machine learningapproach is proposed to model crop rotations which can predict with good accuracy,at the beginning of the agricultural season, the crops most likely tobe present in a given field using the crop sequence of the previous 3to 5 years. The approach is able to learn from data and to integrateexpert knowledge represented as first-order logic rules. Itsaccuracy is assessed using the French Land Parcel Information System implementedin the frame of the EU's Common Agricultural Policy. This assessmentis done using different settings in terms of temporal depth andspatial generalization coverage. The obtained results show that theproposed approach is able to predict the crop type of each field,before the beginning of the crop season, with an accuracy as high as 60\%, which is better than the results obtained with currentapproaches based on remote sensing imagery.

International audience ; Detailed and timely information on crop area, production and yield isimportant for the assessment of environmental impacts of agriculture,for the monitoring of the land use and management practices, and forfood security early warning systems. A machine learningapproach is proposed to model crop rotations which can predict with good accuracy,at the beginning of the agricultural season, the crops most likely tobe present in a given field using the crop sequence of the previous 3to 5 years. The approach is able to learn from data and to integrateexpert knowledge represented as first-order logic rules. Itsaccuracy is assessed using the French Land Parcel Information System implementedin the frame of the EU's Common Agricultural Policy. This assessmentis done using different settings in terms of temporal depth andspatial generalization coverage. The obtained results show that theproposed approach is able to predict the crop type of each field,before the beginning of the crop season, with an accuracy as high as 60\%, which is better than the results obtained with currentapproaches based on remote sensing imagery.

Background: An estimated 6,000 to 18,000 additional hospice and palliative medicine (HPM) physicians are needed in the United States. A source could be the military graduate medical education system where 15% of U.S. medical residents are trained. A community-based hospice and palliative care organization created a one-week rotation for military residents including participation in interdisciplinary group visits at patients' homes, facilities, and an inpatient hospice unit.

A general approach for constructing filters to produce trend estimates from a repeated survey is described. This approach accounts for the correlation structure induced by the rotation pattern used in the survey. Different filters are developed depending on whether the trend analysis is based on elementary estimates available for each rotation group or overall estimates obtained by combining the rotation group estimates. The properties of trend estimates obtained directly from the elementary estimates, those obtained from the simple average of the rotation group estimates and trend estimates obtained from the best linear unbiased estimates of the population characteristics of interest are compared. These comparisons are done for a number of rotation pattern, enabling an assessment of the impact of the choice of rotation patterns on trend estimation.

This work is from the project titled Modelling Economic Impact and Strategies to Increase Resilience Against Tree Disease Outbreaks, which is funded jointly by a grant from BBSRC, Defra, ESRC, the Forestry Commission, NERC and the Scottish Government, under the Tree Health and Plant Biosecurity Initiative. ; Forests deliver multiple benefits both to their owners and to wider society. However, a wave of forest pests and pathogens is threatening this worldwide. In this paper we examine the effect of disease on the optimal rotation length of a single-aged, single rotation forest when a payment for non-timber benefits, which is offered to private forest owners to partly internalise the social values of forest management, is included. Using a generalisable bioeconomic framework we show how this payment counteracts the negative economic effect of disease by increasing the optimal rotation length, and under some restrictive conditions, even makes it optimal to never harvest the forest. The analysis shows a range of complex interactions between factors including the rate of spread of infection and the impact of disease on the value of harvested timber and non-timber benefits. A key result is that the effect of disease on the optimal rotation length is dependent on whether the disease affects the timber benefit only compared to when it affects both timber and non-timber benefits. Our framework can be extended to incorporate multiple ecosystem services delivered by forests and details of how disease can affect their production, thus facilitating a wide range of applications. ; Publisher PDF ; Peer reviewed