Abstract
Gramene (http://www.gramene.org) is an online resource for comparative functional genomics in crops and model plant species. Its two main frameworks are genomes (collaboration with Ensembl Plants) and pathways (The Plant Reactome and archival BioCyc databases). Since our last NAR update, the database website adopted a new Drupal management platform. The genomes section features 39 fully assembled reference genomes that are integrated using ontology-based annotation and comparative analyses, and accessed through both visual and programmatic interfaces. Additional community data, such as genetic variation, expression and methylation, are also mapped for a subset of genomes. The Plant Reactome pathway portal (http://plantreactome.gramene.org) provides a reference resource for analyzing plant metabolic and regulatory pathways. In addition to similar to 200 curated rice reference pathways, the portal hosts gene homology-based pathway projections for 33 plant species. Both the genome and pathway browsers interface with the EMBL-EBI's Expression Atlas to enable the projection of baseline and differential expression data from curated expression studies in plants. Gramene's archive website (http://archive.gramene.org) continues to pro-vide previously reported resources on comparative maps, markers and QTL. To further aid our users, we have also introduced a live monthly educational webinar series and a Gramene YouTube channel carrying video tutorials.

Abstract
Telecommunication companies are acknowledging the existing connection between customer satisfaction and company revenues. Customer churn in telecom refers to a customer that ceases his relationship with a company. Churn prediction in telecom has recently gained substantial interest of stakeholders, who noticed that retaining a customer is substantially cheaper that gaining a new one. This research compares six approaches using different algorithms that identify the clients who are closer to abandon their telecom provider. Those algorithms are: KNN, Naive Rayes, C4.5, Random Forest, AdaBoost and ANN. The use of real data provided by WeDo technologies extended the refinement time necessary, but ensured that the developed algorithm and model can be applied to real world situations. The models are evaluated according to three criteria: are under curve, sensitivity and specificity, with special weight to the first two criteria. The Random Forest algorithm proved to be the most adequate in all the test cases.

Abstract

Abstract

Abstract
An estimated 214 million cases of malaria were detected in 2015, which caused approximately 438 000 deaths. Around 90% of those cases occurred in Africa, where the lack of access to malaria diagnosis is largely due to shortage of expertise and equipment. Thus, the importance to develop new tools that facilitate the rapid and easy diagnosis of malaria for areas with limited access to healthcare services cannot be overstated. This paper presents an image processing and analysis methodology using supervised classification to assess the presence of P. falciparum trophozoites and white blood cells in Giemsa stained thick blood smears. The main differential factor is the usage of microscopic images exclusively acquired with low cost and accessible tools such as smartphones, using a dataset of 194 images manually annotated by an experienced parasilogist. Using a SVM classifier and a total of 314 image features extracted for each candidate, the automatic detection of trophozoites detection achieved a sensitivity of 80.5% and a specificity of 93.8%, while the white blood cells achieved 98.2% of sensitivity and 72.1% specificity. (C) 2016 The Authors. Published by Elsevier B.V.

Abstract
Widespread adoption of Electric Vehicles (EVs) could bring social and economic benefits. The effort of promoting the use of EVs in transportation is indispensable to meet the climate change related targets and to reduce the dependency on the ever unstable prices of diminishing fossil fuels. However, there are still many uncertainties in the market regarding the acceptability of EVs by the final consumers. As a new contribution with respect to earlier studies, this paper assesses the impact of EV charging load on the dielectric oil deterioration of two real Power Distribution Transformers (PDTs), one residential and one industrial, located in the insular grid of Sao Miguel. A PDT thermal model is used to estimate the hot-spot temperature given the load ratio. Real data are used for the main inputs of the model, namely, the daily residential load curve, the daily private industrial client load curve, the PDT parameters, time-of-use rates and EV parameters.