Age and Gender Identification using Stacking for Classification⋆ Notebook for PAN at CLEF 2016

This paper presents our approach of identifying the profile of an unknown user based on the activities of known users. The aim of author profiling task of PAN@CLEF 2016 is cross-genre identification of the gender and age of an unknown user. This means training the system using the behavior of different users from one social media platform and identifying the profile of other user on some different platform. Instead of using single classifier to build the system we used a combination of different classifiers, also known as stacking. This approach allowed us explore the strength of all the classifiers and minimize the bias or error enforced by a single classifier.

O que o estado português quis conservar: a avaliação e aquisição de documentos de arquivo em Portugal nos séculos XIX e XX

Esta dissertação procura identificar os desígnios que orientaram as decisões do Estado português em relação à aquisição de documentos de arquivo, com o objectivo de verificar se esses desígnios se formalizaram numa política de avaliação e aquisição de documentos de arquivo coerente e sistemática. A análise incidiu no Arquivo Nacional e nos arquivos distritais durante o período cronológico que abrange o século XIX e a primeira metade do século XX. Partindo da discussão teórica presente nos discursos de arquivistas e investigadores, da evolução das práticas no Arquivo Nacional e das incorporações realizadas nos arquivos distritais, esta tese defende que existiu uma visão constitutiva dos arquivos enquanto repositórios documentais da memória da nação. No entanto, esta visão não se concretizou numa política arquivística articulada e estrutural; ABSTRACT:This dissertation aims to identify portuguese state’s goals that guided its intervention on acquisition of archival records. Our purpose is to verify if those goals meant a coherent and systematic appraisal and acquisition policy. Our analysis took as object Portugal’s national and regional archives from nineteenth to twentieth century’s first half. Beginning from theoretical discussion that can be seen on archivists and investigators speeches, National Archive’s practices and acquisitions occurred in regional archives, this thesis sustains that there was a vision on the archives as national memory documental repositories. However, this vision was not translated on an articulated and structured archival policy.

Assessment of the spatial variability in Tall wheatgrass forage using LANDSAT 8 satellite imagery to delineate potential management zones

Little information is available on the degree of within-field variability of potential production of Tall wheatgrass (Thinopyrum ponticum) forage under unirrigated conditions. The aim of this study was to characterize the spatial variability of the accumulated biomass (AB) without nutritional limitations through vegetation indexes, and then use this information to determine potential management zones. A 27-×-27-m grid cell size was chosen and 84 biomass sampling areas (BSA), each 2 m(2) in size, were georeferenced. Nitrogen and phosphorus fertilizers were applied after an initial cut at 3 cm height. At 500 °C day, the AB from each sampling area, was collected and evaluated. The spatial variability of AB was estimated more accurately using the Normalized Difference Vegetation Index (NDVI), calculated from LANDSAT 8 images obtained on 24 November 2014 (NDVInov) and 10 December 2014 (NDVIdec) because the potential AB was highly associated with NDVInov and NDVIdec (r (2) = 0.85 and 0.83, respectively). These models between the potential AB data and NDVI were evaluated by root mean squared error (RMSE) and relative root mean squared error (RRMSE). This last coefficient was 12 and 15 % for NDVInov and NDVIdec, respectively. Potential AB and NDVI spatial correlation were quantified with semivariograms. The spatial dependence of AB was low. Six classes of NDVI were analyzed for comparison, and two management zones (MZ) were established with them. In order to evaluate if the NDVI method allows us to delimit MZ with different attainable yields, the AB estimated for these MZ were compared through an ANOVA test. The potential AB had significant differences among MZ. Based on these findings, it can be concluded that NDVI obtained from LANDSAT 8 images can be reliably used for creating MZ in soils under permanent pastures dominated by Tall wheatgrass.