Academic literature on the topic 'Apprentissage automatique – Dissertation universitaire'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Apprentissage automatique – Dissertation universitaire.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Dissertations / Theses on the topic "Apprentissage automatique – Dissertation universitaire":
Selingue, Maxime. "amélioration de la précision de structures sérielles poly-articulées par des méthodes d'apprentissage automatique économes en données." Electronic Thesis or Diss., Paris, HESAM, 2023. http://www.theses.fr/2023HESAE085.
The evolution of production methods in the context of Industry 4.0 has led to the use of collaborative and industrial robots for tasks such as drilling, machining, and assembly. These tasks require an accuracy of around a tenth of a millimeter, whereas the precision of these robots is in the range of one to two millimeters. Robotic integrators had to propose calibration methods aimed at establishing a more reliable and representative model of the robot's behavior in the real world.As a result, analytical calibration methods model the defects affecting the accuracy of industrial robots, including geometric defects, joint compliance, transmission errors, and thermal drift. Given the complexity of experimentally identifying the parameters of some of these analytical models, hybrid calibration methods have been developed. These methods combine an analytical model with a machine learning approach whose role is to accurately predict residual positioning errors (caused by the inaccuracies of the analytical model). These defects can then be compensated for in advance through a compensation algorithm.However, these methods require a significant amount of time and data and are no longer valid when the robot's payload changes. The objective of this thesis is to improve hybrid calibration methods to make them applicable in industrial contexts. In this regard, several contributions have been made.First, two methods based on neural networks that allow the adaptation of the hybrid model to a new payload within a robot's workspace with very little data. These two methods respectively rely on transfer learning and prediction interpolation.Then, a hybrid calibration method using active learning with Gaussian process regression is presented. Through this approach, in an iterative process, the system autonomously decides on relevant data to acquire, enabling optimized calibration in terms of data and time
Ali, Aminata. "Méthodes de fouille de données en épidémiologie psychiatrique : application à l’analyse des facteurs et marqueurs de risque de la symptomatologie dépressive à l’adolescence." Thesis, université Paris-Saclay, 2021. http://www.theses.fr/2021UPASR003.
Adolescence is a vulnerable period for depression, both psychologically and biologically. The literature on depression in adolescence is very extensive on risk and protective factors and on the various externalized manifestations that can serve as warning sign. However, prediction models remain poorly performing. Systematic and in-depth research into the combinations of risk factors/markers could improving these models. Techniques derived from data mining/Machine Learning methods (DMML) now seem to be more and more used on similar issues. This work will focus on the application of DMML methods to depression during adolescence. In this context, the objective will be i) to map the actual use of these methods in epidemiology and public health ii) to analyze the associations between risk factors/markers of depression in adolescence in order to develop new useful leads in the identification of this population. First, a bibliometric analysis of Medline will be conducted in order to quantify the development of DMML methods in public health and epidemiology and to characterize their major fields of application. Secondly, a comparison of the contribution of two classification methods in terms of their capacity to model the risk of depression: boosted regression trees, random forests compared to a logistic LASSO regression without interaction will be carried out. Finally, a supervised partitioning method, called «Bayesian Profile regression", will be used to create clusters of adolescents from the explanatory variables of depression and depression. Data from the cross-sectional school survey "Processus adolescence" will be used. It includes 15235 adolescents, responding to an anonymous self-administered questionnaire containing depression via the Adolescent Depression Rating Scale and the explanatory variables for depression present in the survey. This work showed the interests and difficulties of DMML to analysis relevant associations in psychiatric epidemiology
Fovet, Thomas. "Détection automatisée des hallucinations auditives en IRM fonctionnelle et perspectives thérapeutiques dans la schizophrénie." Thesis, Lille 2, 2017. http://www.theses.fr/2017LIL2S036/document.
Hallucination is a transient subjective experience perceived as real, but occurring in the absence of an appropriate stimulation coming from the external environment. Hallucinatory events, which can occur across every sensory modality, are observed in various neurological and psychiatric disorders but also among “non-clinical” populations. The most frequent disorder associated with hallucinations in the field of psychiatry is schizophrenia. Auditory-verbal experiences are particularly frequent, with a lifetime-prevalence of 60 to 80% in patients suffering from schizophrenia. Hallucinations may cause long-term disability and poorer quality of life.In this context, the management of auditory-verbal hallucinations in patients with schizophrenia constitutes a major challenge. However, despite the increasing sophistication of biological and psychosocial research methods in the field, no significant therapeutic breakthrough has occurred in the last decade and a consensus exists that a significant proportion of patients with schizophrenia (i.e., around 25 %), exhibit drug-resistant auditory-verbal hallucinations. Non-pharmacological treatments, such as repetitive transcranial magnetic stimulation (rTMS) or transcranial direct current stimulation (tDCS) have been proposed as an option for addressing the unmet medical needs described above. However, these neuromodulation techniques show a moderate effect in alleviating drug-resistant auditory-verbal hallucinations and the development of innovative therapeutic strategies remains a major challenge.In recent years, the number of brain imaging studies in the field of auditory-verbal hallucinations has grown substantially, leading to a better pathophysiological understanding of this subjective phenomenon. Recent progress in deciphering the neural underpinnings of AVHs has strengthened transdiagnostic neurocognitive models that characterize auditory-verbal hallucinations, but more specifically these findings built the bases for new therapeutic strategies. In this regards the development of auditory hallucinations “capture" brain-imaging studies (i.e. the identification of functional patterns associated with the occurrence of auditory hallucinations), was the main topic of this thesis.The first part of this work is devoted to the automatized detection of auditory-verbal hallucinations using functional MRI (fMRI). The identification of hallucinatory periods occurring during a fMRI session is now possible using a semi-automatized procedure based on an independent component analysis applied to resting fMRI data combined with a post-fMRI interview (i.e. the patient is asked to report auditory-verbal hallucinations immediately after acquisition). This “two-steps method” allows for the identification of hallucination periods (ON) and non-hallucination ones (OFF). However, the time-consuming nature of this a posteriori labelling procedure considerably limits its use. In these regards, we show how machine-learning, especially support vector machine (SVM), allows the automation of hallucinations capture. We present new results of accurate and generalizable classifiers which could be used in real-time because of their low computational-cost. We also highlight that algorithms able to identify the "pre-hallucinatory" period exhibit significant performances. Finally, we propose the use of an alternative learning-machine strategy, based on TV-Elastic-net, which achieves slightly better performances and more interpretable discriminative maps than SVM [...]
Bauvin, Pierre. "Modélisation de la stéatose hépatique (NAFLD) et de ses facteurs de risque par apprentissage sur des données de santé." Thesis, Lille 2, 2020. http://www.theses.fr/2020LIL2S028.
Non-alcoholic fatty liver disease (NAFLD) is a chronic liver disease which is a combination of simple, slowly progressing steatosis, and non-alcoholic steatohepatitis (NASH), an inflammatory form which accelerates its progression. It is estimated that one in four people in the world is affected by NAFLD, and its prevalence is increasing rapidly, in parallel with the prevalence of its main risk factors: overweight, obesity and type 2 diabetes.This pathology is asymptomatic up to the complications, cirrhosis and liver cancer (hepatocellular carcinoma, HCC), which leads to late diagnosis and a negative impact on the associated morbidity and mortality. Furthermore, the reference diagnosis requires a liver biopsy, an invasive examination that cannot be performed routinely. As a result, the progression of the disease is poorly known and its estimation may suffer from a selection bias, towards patients with significant risk factors, who require a biopsy in the first place. A better understanding would allow the implementation of strategies to reduce its burden.The modelling approach is appropriate to take into account all susceptible patients, without having to carry out a large-scale follow-up study using liver biopsies in patients who are mostly asymptomatic. The objectives of this thesis are to describe and quantify the progression of NAFLD, to predict the associated morbidity and mortality, and to identify the population at risk, using Markov models. To do this, it is necessary to fill in some of the progression parameters via a literature review, to characterise the initial states (population likely to develop NAFLD) and the final states (mortality due to NAFLD), in order to deduce the missing progression parameters between the onset of the disease and mortality, by back-calculation.To exhaustively characterise NAFLD mortality, we identified all patients with cirrhosis or HCC from national hospital databases, representing more than 380,000 patients. We then developed an identification algorithm to determine the etiology underlying the hepatic complication, based on all the stays of the identified patients. This algorithm requires the identification of patients with cirrhosis or HCC of alcoholic or viral origin, to obtain by elimination only NAFLD patients. Once the specific mortality data had been obtained, we estimated the population likely to develop NAFLD, defined as all individuals with overweight or type 2 diabetes, excluding the population of excessive drinkers. We estimated the prevalence and incidence of this population, and modelled its evolution with age and years, based on individual data from surveys representative of the French population.Finally, we quantified the progression of NAFLD, and the impact of risk factors, using two approaches: from the literature, and from biopsy data from more than 1,800 obese patients who were candidates for bariatric surgery, resulting in a tool for predicting the progression of NAFLD in this population. We chose to back-calculate the progression parameters corresponding to the asymptomatic states, which are the most susceptible to selection bias.We obtained a model of the progression of NAFLD, taking into account the dynamic distribution of the population among weight classes and diabetes status, and resulting in the observed statistics of NAFLD deaths. The model takes into account gender, age, year, BMI (body mass index) class, diabetes status and the presence of a genetic polymorphism (PNPLA3 rs738409, C→G) as covariates of progression. It is a tool for assessing the impact of a possible treatment or public health policy on morbidity and mortality
Houzé, de l'Aulnoit Agathe. "Acquisition du rythme cardiaque fœtal et analyse de données pour la recherche de facteurs prédictifs de l’acidose fœtale." Thesis, Lille, 2019. http://www.theses.fr/2019LIL2S007.
Visual analysis of the fetal heart rate FHR is a good method for screening for fetal hypoxia but is not sufficiently specific. The visual morphological analysis of the FHR during labor is subject to inter- and intra-observer variability – particularly when the FHR is abnormal. Underestimating the severity of an FHR leads to undue risk-taking for the fetus with an increase in morbidity and mortality and overvaluation leads to unnecessary obstetric intervention with an increased rate of caesarean section. This last point also induces a French public health problem.FHR automated analysis reduces inter and intra-individual variability and accesses other calculated parameters aimed at increasing the diagnostic value. The FHR morphological analysis parameters (baseline, number of accelerations, number and typing of decelerations, long-term variability (LTV)) were described as well as others such as the decelerations surfaces, short-term variability (STV) and frequency analyzes. Nevertheless, when attempting to analyze the FHR automatically, the main problem is computation of the baseline against which all the other parameters are determined.Automatic analysis provides information on parameters that cannot be derived in a visual analysis and that are likely to improve screening for fetal acidosis during labor.The main objective of the thesis is to establish a predictive model of fetal acidosis from a FHR automated analysis. The secondary objective is to determine the relevance of the classical basic parameters (CNGOF 2007) (baseline, variability, accelerations, decelerations) and that of other parameters inaccessible to the eye (indices of short-term variability, surfaces of decelerations, frequency analysis ...). Later, we want to identify decision criteria that will help in the obstetric care management.We propose to validate FHR automated analysis during labor through a case-control study; cases were FHR recordings of neonatal acidosis (arterial cord pH less than or equal to 7.15) and controls, FHR recordings of neonatal without acidosis (arterial cord pH upper than or equal to 7.25). This is a monocentric study at the maternity hospital of Saint Vincent de Paul Hospital, GHICL - Lille, on our « Well Born » database (digital archiving of RCF plots since 2011), with a sufficient number of cases on this only center. Since 2011, the Saint Vincent de Paul hospital (GHICL) has had about 70 cases per year of neonatal acidosis (pHa less than or equal to 7.10) (3.41%). The R software will be used for statistical analysis
Congnard, Florian. "Méthodologie et physiopathologie des mesures de pressions artérielles périphériques chez le sujet sain : aspects cliniques, méthodologiques et pédagogiques." Thesis, Angers, 2017. http://www.theses.fr/2017ANGE0049/document.
The measurement of ankle to brachial pressure index (ABPI) is a simple and non-invasive diagnostic tool for detecting arterial involvement of the lower limbs. If the methodology and interpretation of this index have been standardized, there remain some discrepancies about some aspects of its measurement. Thus, the present thesis reports the investigations of three of these aspects. First, the objective was to study the physiological relationship between ABPI and age among healthy and physically active subjects. The results show a positive relationship. This trend is consistent with structural modifications of arterial wall with ageing. Second, our aim was to investigate the use of automatic blood pressure measurement tools for the calculation of ABPI during the recovery of a maximal physical exercise. We found that the use of anoscillometric blood pressure device allowed to obtain a faster postexercise ABPI faster than a manual recording and also to reduce the standard error of the measurement. Finally, we discussed the learning strategies of this peripheral vascular measurement. Indeed, it appears that the measurement of arterial systolic blood pressure at the ankle (ASBPa) is largely under-taught compared to the humeral measurement. The purpose was to objectively assess, by a simulator, the effect of an additional practical and pedagogical intervention on the ability of novice students to perform ASBP a measurement. The results suggest that a one-hour practical learning allows to significantly reduce the measurement error but is not sufficient to harmonize all of the measurement parameters according to the measurement standards
Books on the topic "Apprentissage automatique – Dissertation universitaire":
Enseignement Apprentissage De La Dissertation Franaise En Classe Universitaire De Fle Etude De Cas Universit Europenne Viadrina Allemagne. Grin Verlag, 2013.
Book chapters on the topic "Apprentissage automatique – Dissertation universitaire":
Okome Engouang, Liliane, and Liza Gladys Boukandou Kombila. "La TA et la TAO dans le processus d’enseignement/apprentissage de l’espagnol et du français en classe universitaire au Gabon." In L’enseignement-apprentissage en/des langues européennes dans les systèmes éducatifs africains : place, fonctions, défis et perspectives, 319–35. Observatoire européen du plurilinguisme, 2020. http://dx.doi.org/10.3917/oep.kouam.2020.01.0319.