Search results for "Machine learning"

Analyse des réseaux trophiques et quantification des interactions

2017

Prod 2017-344e SPE équipe EA GESTAD INRA; National audience; L’importante littérature consacrée au sujet suggère une relation positive entre la biodiversité en milieu agricole et la fourniture de services écosystémiques, notamment le service de contrôle des ravageurs par leurs ennemis naturels. Cependant, cette relation n’est que statistique et de nombreux contre-exemples peuvent être trouvés. L’une des raisons principales de l’absence d’additivité des effets des ennemis naturels réside dans la complexité des réseaux d’interactions qui se mettent en place dans les communautés diversifiées. Ainsi, par exemple, des phénomènes de compétition, voire de prédation intra-guilde peuvent conduire à …

Accelerometry - Simple, but challenging

2017

Analisi di test di Immunofluorescenze indiretta per il supporto alla diagnosi di Malattie Autoimmuni basata su Deep Learning.

2019

La diagnosi delle malattie autoimmuni rappresenta un problema molto importante in medicina. Il test più utilizzato a questo scopo è il test anticorpo antinucleo, un test indiretto di immunofluorescenza. Il metodo proposto affronta tale problema sfruttando le metodologie del Machine Learning. In particolare, fa uso di reti neurali pre-addestrate in grado di classificare i pattern auto anticorpali collegati alle patologie autoimmuni. Gli strati delle reti pre-addestrate e vari parametri di sistema sono stati valutati al fine di ottimizzare il processo. Le prestazioni del sistema sono state valutate in termini di accuratezza in un processo di cross validation, mostrando efficienza e robustezza.

Discriminating and simulating actions with the associative self-organising map

2015

We propose a system able to represent others’ actions as well as to internally simulate their likely continuation from a partial observation. The approach presented here is the first step towards a more ambitious goal of endowing an artificial agent with the ability to recognise and predict others’ intentions. Our approach is based on the associative self-organising map, a variant of the self-organising map capable of learning to associate its activity with different inputs over time, where inputs are processed observations of others’ actions. We have evaluated our system in two different experimental scenarios obtaining promising results: the system demonstrated an ability to learn discrim…

A Deep Learning Model for Automatic Sleep Scoring using Multimodality Time Series

2021

Sleep scoring is a fundamental but time-consuming process in any sleep laboratory. Automatic sleep scoring is crucial and urgent to help address the increasing unmet need for sleep research. Therefore, this paper aims to develop an end-to-end deep learning architecture using raw polysomnographic recordings to automate sleep scoring. The proposed model adopts two-dimensional convolutional neural networks (2D-CNN) to automatically learn features from multi-modality signals, together with a "squeeze and excitation" block for recalibrating channel-wise feature responses. The learnt representations are finally fed to a softmax classifier to generate predictions for each sleep stage. The model pe…

Endotyping allergic rhinitis in children: A machine learning approach.

2021

Introduction: The diversity of allergic rhinitis (AR) phenotypes is particularly evident in childhood, suggesting the need to analyze and identify new approaches to capture such clinical heterogeneity. Nasal cytology (NC) is a very useful diagnostic tool for identifying and quantifying nasal inflammation. Data-driven approaches such as latent class analysis (LCA) assign subjects to classes based on their characteristics. We hypothesized that LCA based on NC, including the assessment of neutrophils, eosinophils, and mast cells, may be helpful for identifying AR endotypes in children. Methods: A total of 168 children were enrolled. Sociodemographic characteristics and detailed medical history…

A novel pilot study of automatic identification of EMF radiation effect on brain using computer vision and machine learning

2020

Abstract Electromagnetic field (EMF) radiations from mobile phones and cell tower affect brain of humans and other organisms in many ways. Exposure to EMF could lead to neurological changes causing morphological or chemical changes in the brain and other internal organs. Cellular level analysis to measure and identify the effect of mobile radiations is an expensive and long process as it requires preparing the cell suspension for the analysis. This paper presents a novel pilot study to identify changes in brain morphology under EMF exposure considering drosophila melanogaster as a specimen. The brain is automatically segmented, obtaining microscopic images from which discriminatory geometri…

Robust Automated Assessment of Human Blastocyst Quality using Deep Learning

2018

AbstractMorphology assessment has become the standard method for evaluation of embryo quality and selecting human blastocysts for transfer inin vitro fertilization(IVF). This process is highly subjective for some embryos and thus prone to human bias. As a result, morphological assessment results may vary extensively between embryologists and in some cases may fail to accurately predict embryo implantation and live birth potential. Here we postulated that an artificial intelligence (AI) approach trained on thousands of embryos can reliably predict embryo quality without human intervention.To test this hypothesis, we implemented an AI approach based on deep neural networks (DNNs). Our approac…

Deep learning enables robust assessment and selection of human blastocysts after in vitro fertilization

2019

AbstractVisual morphology assessment is routinely used for evaluating of embryo quality and selecting human blastocysts for transfer after in vitro fertilization (IVF). However, the assessment produces different results between embryologists and as a result, the success rate of IVF remains low. To overcome uncertainties in embryo quality, multiple embryos are often implanted resulting in undesired multiple pregnancies and complications. Unlike in other imaging fields, human embryology and IVF have not yet leveraged artificial intelligence (AI) for unbiased, automated embryo assessment. We postulated that an AI approach trained on thousands of embryos can reliably predict embryo quality with…

Anemia management in end stage renal disease patients undergoing dialysis: a comprehensive approach through machine learning techniques and mathemati…

2016

Kidney impairment has global consequences in the organism homeostasis and a disorder like Chronic Kidney Disease (CKD) might eventually exacerbates into End Stage Renal Disease (ESRD) where a complete renal replacement therapy like dialysis is necessary. Dialysis partially reintegrates the blood ltration process; however, even when it is associated to a pharmacological therapy, this is not su fficient to completely replace the renal endocrine role and causes the development of common complications, like CKD secondary anemia (CKD-anemia) The availability of exogenous Erythropoiesis Stimulating Agents (ESA, synthetic molecules with similar structure and same mechanism of action as human eryth…