Search results for "feature"

2004

This paper presents the use of Support Vector Machines (SVMs) for prediction and analysis of antisense oligonucleotide (AO) efficacy. The collected database comprises 315 AO molecules including 68 features each, inducing a problem well-suited to SVMs. The task of feature selection is crucial given the presence of noisy or redundant features, and the well-known problem of the curse of dimensionality. We propose a two-stage strategy to develop an optimal model: (1) feature selection using correlation analysis, mutual information, and SVM-based recursive feature elimination (SVM-RFE), and (2) AO prediction using standard and profiled SVM formulations. A profiled SVM gives different weights to …

Ensemble Feature Selection Based on Contextual Merit and Correlation Heuristics

2001

Recent research has proven the benefits of using ensembles of classifiers for classification problems. Ensembles of diverse and accurate base classifiers are constructed by machine learning methods manipulating the training sets. One way to manipulate the training set is to use feature selection heuristics generating the base classifiers. In this paper we examine two of them: correlation-based and contextual merit -based heuristics. Both rely on quite similar assumptions concerning heterogeneous classification problems. Experiments are considered on several data sets from UCI Repository. We construct fixed number of base classifiers over selected feature subsets and refine the ensemble iter…

Learning Similarity Scores by Using a Family of Distance Functions in Multiple Feature Spaces

2017

There exist a large number of distance functions that allow one to measure similarity between feature vectors and thus can be used for ranking purposes. When multiple representations of the same object are available, distances in each representation space may be combined to produce a single similarity score. In this paper, we present a method to build such a similarity ranking out of a family of distance functions. Unlike other approaches that aim to select the best distance function for a particular context, we use several distances and combine them in a convenient way. To this end, we adopt a classical similarity learning approach and face the problem as a standard supervised machine lea…

Epigenetic activation of a cryptic TBC1D16 transcript enhances melanoma progression by targeting EGFR

2015

Metastasis is respoMetastasis is responsible for most cancer-related deaths, and, among common tumor types, melanoma is one with great potential to metastasize. Here we study the contribution of epigenetic changes to the dissemination process by analyzing the changes that occur at the DNA methylation level between primary cancer cells and metastases. We found a hypomethylation event that reactivates a cryptic transcript of the Rab GTPase activating protein TBC1D16 (TBC1D16-47 kDa; referred to hereafter as TBC1D16-47KD) to be a characteristic feature of the metastatic cascade. This short isoform of TBC1D16 exacerbates melanoma growth and metastasis both in vitro and in vivo. By combining imm…

Texture analysis with statistical methods for wheat ear extraction

2007

In agronomic domain, the simplification of crop counting, necessary for yield prediction and agronomic studies, is an important project for technical institutes such as Arvalis. Although the main objective of our global project is to conceive a mobile robot for natural image acquisition directly in a field, Arvalis has proposed us first to detect by image processing the number of wheat ears in images before to count them, which will allow to obtain the first component of the yield. In this paper we compare different texture image segmentation techniques based on feature extraction by first and higher order statistical methods which have been applied on our images. The extracted features are…

Tree rings and volcanic cooling

2012

Rapid determination of sterols in vegetable oils by CEC using methacrylate ester-based monolithic columns

2008

A method for the determination of sterols in vegetable oils by CEC with UV-Vis detection, using methacrylate ester-based monolithic columns, has been developed. To prepare the columns, polymerization mixtures containing monomers of different hydrophobicities were tried. The influence of composition of polymerization mixture was optimized in terms of porogenic solvent, monomers/porogens and monomer/crosslinker ratios. The composition of the mobile phase was also studied. The optimum monolith was obtained with lauryl methacrylate monomer at 60:40% (wt:wt) lauryl methacrylate/ethylene dimethacrylate ratio and 60 wt% porogens with 20 wt% of 1,4-butanediol (12 wt% 1,4-butanediol in the polymeriz…

The Constraints of Vehicle Range and Congestion for the Use of Electric Vehicles for Urban Freight in France

2015

The 9th International Conference on City Logistics, Tenerife, Espagne, 17-/06/2015 - 19/06/2015; Electric vehicle is a solution to reduce pollutant emissions from road urban freight. This paper assesses the potential CO2 reduction by transferring urban freight from diesel to electric vehicles while simultaneously looking at the two main technical constraints: electric vehicle range and the impact on congestion linked to change diesel heavy duty vehicles (with a load up to 25 tons) to much smaller electric vehicles. The data used has been computed from a survey (ECHO) that describes in details a very large sample of French shipments. Two scenarios were set up, which differ mainly by the type…

Suspended particulate matter fluxes along with their associated metals, organic matter and carbonates in a coastal Mediterranean area affected by min…

2016

International audience; A study of suspended particulate matter (SPM) fluxes along with their associated metals, organic matter and carbonates, was conducted off the Mejerda River outlet in May 2011 and in March and July 2012 at depths of 10, 20 and 40 m using sediment traps. SPM fluxes are more significant near the Mejerda outlet, especially in winter, but dissipate further offshore. Normalization reveals that the Mejerda is a major source of Pb, Zn, Cd, Cu, Ni, and Co, all of which are the result of human activities. In contrast, Fe, Mn and N are of authigenic origin. The enrichment factor shows that Pb, Zn and especially Cd are the most highly polluting metals off the Mejerda outlet. Thi…

Regional variations in the chemical and helium–carbon isotope composition of geothermal fluids across Tunisia

2011

Abstract Tunisia has numerous thermo-mineral springs. Previous studies have shown that their chemical composition and occurrence are strongly influenced by the regional geology. However little work has been done so far to study the isotopic composition of volatiles associated with these geothermal manifestations. Here, we report on the results of an extensive survey of both natural hot springs and production wells across Tunisia, aimed at investigating the spatial distribution of thermal fluids' geochemical characteristics and He–C isotopic composition. The chemistry of the analyzed samples highlights the heterogeneity of the water mineralization processes in Tunisia, as a consequence of th…