Dissertations / Theses on the topic 'Données neuronales'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 42 dissertations / theses for your research on the topic 'Données neuronales.'
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.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Werner, Thilo. "Réseaux de neurones impulsionnels basés sur les mémoires résistives pour l'analyse de données neuronales." Thesis, Université Grenoble Alpes (ComUE), 2017. http://www.theses.fr/2017GREAS028/document.
Full textThe central nervous system of humankind is an astonishing information processing system in terms of its capabilities, versatility, adaptability and low energy consumption. Its complex structure consists of billions of neurons interconnected by trillions of synapses forming specialized clusters. Recently, mimicking those paradigms has attracted a strongly growing interest, triggered by the need for advanced computing approaches to tackle challenges related to the generation of massive amounts of complex data in the Internet of Things (IoT) era. This has led to a new research field, known as cognitive computing or neuromorphic engineering, which relies on the so-called non-von-Neumann architectures (brain-inspired) in contrary to von-Neumann architectures (conventional computers). In this thesis, we explore the use of resistive memory technologies such as oxide vacancy based random access memory (OxRAM) and conductive bridge RAM (CBRAM) for the design of artificial synapses that are a basic building block for neuromorphic networks. Moreover, we develop an artificial spiking neural network (SNN) based on OxRAM synapses dedicated to the analysis of spiking data recorded from the human brain with the goal of using the output of the SNN in a brain-computer interface (BCI) for the treatment of neurological disorders. The impact of reliability issues characteristic to OxRAM on the system performance is studied in detail and potential ways to mitigate penalties related to single device uncertainties are demonstrated. Besides the already well-known spike-timing-dependent plasticity (STDP) implementation with OxRAM and CBRAM which constitutes a form of long term plasticity (LTP), OxRAM devices were also used to mimic short term plasticity (STP). The fundamentally different functionalities of LTP and STP are put in evidence
Merlin, Paul. "Des techniques neuronales dans l'alternatif." Phd thesis, Université Panthéon-Sorbonne - Paris I, 2009. http://tel.archives-ouvertes.fr/tel-00450649.
Full textFuchs, Robin. "Méthodes neuronales et données mixtes : vers une meilleure résolution spatio-temporelle des écosystèmes marins et du phytoplancton." Electronic Thesis or Diss., Aix-Marseille, 2022. http://www.theses.fr/2022AIXM0295.
Full textPhytoplankton are one of the first links in the food web and generate up to 50% of the world's primary production. The study of phytoplankton and their physical environment requires observations with a resolution of less than a day and a kilometer, as well as the consideration of the heterogeneous types of data involved and the spatio-temporal dependency structures of marine ecosystems.This thesis aims to develop statistical methods in this context by using technologies such as automated flow cytometry. Theoretical developments focused on Deep Gaussian Mixture Models (DGMM) introduced by Viroli and McLachlan (2019). To better characterize phytoplankton ecological niches, we extended these models to mixed data (exhibiting continuous and non-continuous variables) often found in oceanography. A clustering method has been proposed as well as an algorithm for generating synthetic mixed data.Regarding the high-frequency study itself, convolutional neural networks have been introduced to process flow cytometry outputs and to study six functional groups of phytoplankton in the littoral zone and the open ocean. Differentiated and reproducible responses of these groups were identified following wind-induced pulse events, highlighting the importance of the coupling between physics and biology. In this regard, a change-point detection method has been proposed to delineate epipelagic and mesopelagic zones, providing a new basis for the calculation of mesopelagic carbon budgets
Martinez, Herrera Miguel. "Inference of non-linear or imperfectly observed Hawkes processes." Electronic Thesis or Diss., Sorbonne université, 2024. http://www.theses.fr/2024SORUS273.
Full textThe Hawkes point process is a popular statistical tool to analyse temporal patterns.Modern applications propose extensions of this model to account for specificities in each field of study, which in turn complexifies the task of inference.In this thesis, we advance different approaches for the parametric estimation of two submodels of the Hawkes process in univariate and multivariate settings.Motivated by the modelling of complex neuronal interactions observed from spike train data,our first study focuses on accounting for both inhibition and excitation effects between neurons, modelled by the non-linear Hawkes process.We derive a closed-form expression of the log-likelihood in order to implement a maximum likelihood procedure.As a consequence of our approach, we gain access to a goodness-of-fit scheme allowing us to establish ad hoc model selection methods to estimate the interaction network in the multivariate setting.The second part of this thesis focuses on studying Hawkes process data noised by two different alterations: adding or removing points.The absence of knowledge on the noise dynamics makes classical inference procedures intractable or computationally expensive.Our solution is to leverage the spectral analysis of point processes to establish an estimator obtained by maximising the spectral log-likelihood.By deriving the spectral densities of the noised processes and by establishing identifiability conditions on our model, we show that the spectral inference method does not necessitate any information on the structure of the noise, effectively circumventing this issue.An additional result of the study of Hawkes processes with missing points is that it gives access to a subsampling paradigm to enhance the estimation methods by introducing a penalisation parameter.We illustrate the efficiency of all of our methods through reproducible numerical implementations
Dora, Matteo. "Mathematical models and signal processing methods to explore biological mechanisms across multiple scales : from intracellular dynamics to neural time series." Electronic Thesis or Diss., Université Paris sciences et lettres, 2022. http://www.theses.fr/2022UPSLE033.
Full textThis dissertation is an investigation of biological phenomena related to the brain by means of mathematical models and quantitative methods. The leitmotiv of this work is the analysis of spatiotemporal series which naturally arise in biological systems at different scales. In the first part of the thesis, we study the finest of such scales. I analyse intracellular protein dynamics in the endoplasmic reticulum (ER), an organelle of eukaryotic cells formed by a network of tubular membrane structures. The ER plays a key role in protein transport, and its dysfunction has been associated with numerous diseases, including, in particular, neurodegenerative disorders. Previous experimental observations suggested a possible deviation of ER luminal transport compared to classical diffusion. Based on this hypothesis, I introduce a graph model to describe ER protein dynamics. I analyse the model and develop numerical simulations, revealing a possible mechanism of aggregated protein transport that deviates from purely diffusive motion. Then, to further test the predictions of the model, we turn to the analysis of experimental data. While protein mobility has been traditionally characterized by fluorescence imaging, the morphological characteristics of the ER pose new challenges to a quantitative analysis of such small scale dynamics. To address these issues, I introduce a novel image processing method to analyse ER dynamics based on photoactivatable fluorescent proteins. By joining analysis and reduction of noise with automatic segmentation of the ER, the technique can provide a robust estimation of the timescale of transport. Moreover, it allows us to characterize the spatial heterogeneity of the protein mixing process. I present and compare results for luminal, membrane, and misfolded proteins in the ER. In the second part of the dissertation, we study neuronal signals at coarser scales. First, at the scale of the single neuron, I present a denoising method suitable for optical recording of single-cell activity in awake, behaving mice via fluorescent voltage indicators. I show how it is possible to reduce instrumental and photon-counting noise in such time series, allowing us to extract spike patterns at lower acquisition frequency. Such results enable simultaneous recording of multiple cells, thus allowing to explore the correlation of spikes and voltage oscillations within ensembles of neurons. Finally, in the last chapters, we reach the coarsest scale with the study of electroencephalograms (EEG) which record the activity of the entire brain. Motivated by the applications of EEG in clinical monitoring, I introduce a new wavelet-based method that can attenuate undesired artefacts which contaminate the recording of the physiological EEG signal. The method is based on the remapping of the wavelet coefficients according to a reference distribution extracted from clean portions of the EEG signal. This technique can provide a flexible alternative to traditional approaches such as wavelet thresholding in the context of real-time clinical monitoring. In conclusion, this thesis illustrates how an interdisciplinary approach combining experimental data with mathematical modelling and signal processing can provide new tools for the understanding of a wide variety of biological mechanisms, ranging from protein transport to EEG monitoring
Leclerc, Gabriel. "Apprendre de données positives et non étiquetées : application à la segmentation et la détection d'évènements calciques." Master's thesis, Université Laval, 2021. http://hdl.handle.net/20.500.11794/69813.
Full textTwo types of neurotransmission occur in brain’s neurons: evoked transmission and spontaneous transmission. Unlike the former, the role of spontaneous transmission on synaptic plasticity –a mechanism used to endow the brain learning and memory abilities – remain unclear. Spontaneous neurotransmissions are localized and randomly happening in neuron’s synapses. When such spontaneous events happen, so-called miniature synaptic Ca²⁺ transients(mSCT), second messenger calcium ions entered the spine, activating downstream signaling pathways of synaptic plasticity. Using calcium imaging of in vitro neuron enable spatiotemporal visual-ization of the entry of calcium ions. Resulting calcium videos enable quantitative study of mSCT’s impact on synaptic plasticity. However, mSCT localization in calcium imaging can be challenging due to their small size, their low intensity compared with the imaging noise and their inherent randomness. In this master’s thesis, we present a method for quantitative high-through put analysis of calcium imaging videos that limits the variability induced by human interventions to obtain evidence for characterizing the impact of mSCTs on synaptic plasticity. Based on a semi-automatic intensity thresholded detection (ITD) tool, we are able to generate data to train a fully convolutional neural network (FCN) to rapidly and automaticaly detect mSCT from calcium videos. Using ITD noisy segmentations as training data combine with a positive and unlabeled (PU) training schema, we leveraged FCN performances and could even detect previously undetected low instensity mSCTs missed by ITD. The FCN also provide better segmentation than ITD. We then characterized the impact of PU parameters such as the number of P and the ratio P:U. The trained FCN is bundled in a all-in-one pipeline to permit a high-thoughtput analysis of mSCT. The pipeline offers detection, segmentation,characterization and visualization of mSCTs as well as a software solution to manage multiple videos with different metadatas.
Lurton, Dominique. "Mécanismes de la mort neuronale lors de l'ischémie cérébrale/substances neuroprotectrices : recueil de données bibliographiques." Bordeaux 2, 1993. http://www.theses.fr/1993BOR23047.
Full textCarrara, Igor. "Méthodes avancées de traitement des BCI-EEG pour améliorer la performance et la reproductibilité de la classification." Electronic Thesis or Diss., Université Côte d'Azur, 2024. http://www.theses.fr/2024COAZ4033.
Full textElectroencephalography (EEG) non-invasively measures the brain's electrical activity through electromagnetic fields generated by synchronized neuronal activity. This allows for the collection of multivariate time series data, capturing a trace of the brain electrical activity at the level of the scalp. At any given time instant, the measurements recorded by these sensors are linear combinations of the electrical activities from a set of underlying sources located in the cerebral cortex. These sources interact with one another according to a complex biophysical model, which remains poorly understood. In certain applications, such as surgical planning, it is crucial to accurately reconstruct these cortical electrical sources, a task known as solving the inverse problem of source reconstruction. While intellectually satisfying and potentially more precise, this approach requires the development and application of a subject-specific model, which is both expensive and technically demanding to achieve.However, it is often possible to directly use the EEG measurements at the level of the sensors and extract information about the brain activity. This significantly reduces the data analysis complexity compared to source-level approaches. These measurements can be used for a variety of applications, including monitoring cognitive states, diagnosing neurological conditions, and developing brain-computer interfaces (BCI). Actually, even though we do not have a complete understanding of brain signals, it is possible to generate direct communication between the brain and an external device using the BCI technology. This work is centered on EEG-based BCIs, which have several applications in various medical fields, like rehabilitation and communication for disabled individuals or in non-medical areas, including gaming and virtual reality.Despite its vast potential, BCI technology has not yet seen widespread use outside of laboratories. The primary objective of this PhD research is to try to address some of the current limitations of the BCI-EEG technology. Autoregressive models, even though they are not completely justified by biology, offer a versatile framework to effectively analyze EEG measurements. By leveraging these models, it is possible to create algorithms that combine nonlinear systems theory with the Riemannian-based approach to classify brain activity. The first contribution of this thesis is in this direction, with the creation of the Augmented Covariance Method (ACM). Building upon this foundation, the Block-Toeplitz Augmented Covariance Method (BT-ACM) represents a notable evolution, enhancing computational efficiency while maintaining its efficacy and versatility. Finally, the Phase-SPDNet work enables the integration of such methodologies into a Deep Learning approach that is particularly effective with a limited number of electrodes.Additionally, we proposed the creation of a pseudo online framework to better characterize the efficacy of BCI methods and the largest EEG-based BCI reproducibility study using the Mother of all BCI Benchmarks (MOABB) framework. This research seeks to promote greater reproducibility and trustworthiness in BCI studies.In conclusion, we address two critical challenges in the field of EEG-based brain-computer interfaces (BCIs): enhancing performance through advanced algorithmic development at the sensor level and improving reproducibility within the BCI community
Carlier, Florent. "Nouvelle technique neuronale de détection multi-utilisateurs : Applications aux systèmes MC-CDMA." Rennes, INSA, 2003. http://www.theses.fr/2003ISAR0019.
Full textLagacherie, Hervé. "L'analyse des données cliniques et biologiques par les réseaux neuronaux." Bordeaux 2, 1997. http://www.theses.fr/1997BOR2P091.
Full textRathelot, Jean-Alban. "Le réseau neuronal du noyau rouge magnocellulaire : exposé bibliographique et données expérimentales chez le chat." Aix-Marseille 1, 1997. http://www.theses.fr/1997AIX11042.
Full textKalathur, Ravi Kiran Reddy. "An integrated systematic approach for storage, analysis and visualization of gene expression data from neuronal tissues acquired through high-throughput techniques." Université Louis Pasteur (Strasbourg) (1971-2008), 2008. https://publication-theses.unistra.fr/public/theses_doctorat/2008/KALATHUR_Ravi_Kiran_Reddy_2008.pdf.
Full textLe travail présenté dans ce manuscrit concerne différents aspects de l'analyse des données d'expression de gènes, qui englobe l'utilisation de méthodes statistiques et de systèmes de stockage et de visualisation, pour exploiter et extraire des informations pertinentes à partir de grands volumes de données. Durant ma thèse j'ai eu l'opportunité de travailler sur ces différents aspects, en contribuant en premier lieu aux tests de nouvelles approches de classification et de méta-analyses à travers la conception d'applications biologiques, puis dans le développement de RETINOBASE (http://alnitak. U-strasbg. Fr/RetinoBase/), une base de données relationnelle qui permet le stockage et l'interrogation performante de données de transcriptomique et qui représente la partie majeure de mon travail
Vielzeuf, Valentin. "Apprentissage neuronal profond pour l'analyse de contenus multimodaux et temporels." Thesis, Normandie, 2019. http://www.theses.fr/2019NORMC229/document.
Full textOur perception is by nature multimodal, i.e. it appeals to many of our senses. To solve certain tasks, it is therefore relevant to use different modalities, such as sound or image.This thesis focuses on this notion in the context of deep learning. For this, it seeks to answer a particular problem: how to merge the different modalities within a deep neural network?We first propose to study a problem of concrete application: the automatic recognition of emotion in audio-visual contents.This leads us to different considerations concerning the modeling of emotions and more particularly of facial expressions. We thus propose an analysis of representations of facial expression learned by a deep neural network.In addition, we observe that each multimodal problem appears to require the use of a different merge strategy.This is why we propose and validate two methods to automatically obtain an efficient fusion neural architecture for a given multimodal problem, the first one being based on a central fusion network and aimed at preserving an easy interpretation of the adopted fusion strategy. While the second adapts a method of neural architecture search in the case of multimodal fusion, exploring a greater number of strategies and therefore achieving better performance.Finally, we are interested in a multimodal view of knowledge transfer. Indeed, we detail a non-traditional method to transfer knowledge from several sources, i.e. from several pre-trained models. For that, a more general neural representation is obtained from a single model, which brings together the knowledge contained in the pre-trained models and leads to state-of-the-art performances on a variety of facial analysis tasks
Lurette, Christophe. "Développement d'une technique neuronale auto-adaptative pour la classification dynamique de données évolutives : application à la supervision d'une presse hydraulique." Lille 1, 2003. https://ori-nuxeo.univ-lille1.fr/nuxeo/site/esupversions/aed48e38-323f-425b-b6ff-c8e75ff5d4b6.
Full textDemartines, Pierre. "Analyse de données par réseaux de neurones auto-organisés." Grenoble INPG, 1994. http://www.theses.fr/1994INPG0129.
Full textZoefel, Benedikt. "Phase entrainment and perceptual cycles in audition and vision." Thesis, Toulouse 3, 2015. http://www.theses.fr/2015TOU30232/document.
Full textRecent research indicates fundamental differences between the auditory and visual systems: Whereas the visual system seems to sample its environment, cycling between "snapshots" at discrete moments in time (creating perceptual cycles), most attempts at discovering discrete perception in the auditory system failed. Here, we show in two psychophysical experiments that subsampling the very input to the visual and auditory systems is indeed more disruptive for audition; however, the existence of perceptual cycles in the auditory system is possible if they operate on a relatively high level of auditory processing. Moreover, we suggest that the auditory system, due to the rapidly fluctuating nature of its input, might rely to a particularly strong degree on phase entrainment, the alignment between neural activity and the rhythmic structure of its input: By using the low and high excitability phases of neural oscillations, the auditory system might actively control the timing of its "snapshots" and thereby amplify relevant information whereas irrelevant events are suppressed. Not only do our results suggest that the oscillatory phase has important consequences on how simultaneous auditory inputs are perceived; additionally, we can show that phase entrainment to speech sound does entail an active high-level mechanism. We do so by using specifically constructed speech/noise sounds in which fluctuations in low-level features (amplitude and spectral content) of speech have been removed, but intelligibility and high-level features (including, but not restricted to phonetic information) have been conserved. We demonstrate, in several experiments, that the auditory system can entrain to these stimuli, as both perception (the detection of a click embedded in the speech/noise stimuli) and neural oscillations (measured with electroencephalography, EEG, and in intracranial recordings in primary auditory cortex of the monkey) follow the conserved "high-level" rhythm of speech. Taken together, the results presented here suggest that, not only in vision, but also in audition, neural oscillations are an important tool for the discretization and processing of the brain's input. However, there seem to be fundamental differences between the two systems: In contrast to the visual system, it is critical for the auditory system to adapt (via phase entrainment) to its environment, and input subsampling is done most likely on a hierarchically high level of stimulus processing
Ammar, Adel. "Restitution de la salinité de surface de l'océan à partir des mesures SMOS : une approche neuronale?" Toulouse 3, 2008. http://thesesups.ups-tlse.fr/475/.
Full textUsing neural networks to retrieve the sea surface salinity from the observed Soil Moisture and Ocean Salinity (SMOS) brightness temperatures (TBs) is an empirical approach that offers the possibility of being independent from any theoretical emissivity model. We prove that this approach is applicable to all pixels over ocean, by designing a set of neural networks with different inputs. Besides, we demonstrate that a judicious distribution of the geophysical parameters in the learning database allows to markedly reduce the systematic regional biases of the retrieved SSS, which are due to the high noise on the TBs. An equalization of the distribution of the geophysical parameters, followed by a new technique for boosting the learning process, makes the regional biases almost disappear for latitudes between 40°S and 40°N, while the global standard deviation remains between 0. 6 psu (at the center of the swath) and 1 psu (at the edges)
Amadou, Boubacar Habiboulaye. "Classification Dynamique de données non-stationnaires :Apprentissage et Suivi de Classes évolutives." Phd thesis, Université des Sciences et Technologie de Lille - Lille I, 2006. http://tel.archives-ouvertes.fr/tel-00106968.
Full textLurette, Christophe Lecœuche Stéphane Vasseur Christian. "Développement d'une technique neuronale auto-adaptative pour la classification dynamique de données évolutives application à la supervision d'une presse hydraulique /." [S.l.] : [s.n.], 2003. http://www.univ-lille1.fr/bustl-grisemine/pdf/extheses/50376-2003-77-78.pdf.
Full textParaschivescu, Cristina. "Le rôle régulateur des cytokines dans le neurodéveloppement et le comportement au début de la période postnatale : Étude de l'impact du TNF sur le comportement de la souris au début de la période postnatale et une nouvelle approche d'analyse de données appliquée au modèle murin de l'autisme basée sur l'activation de l’immunité maternelle." Electronic Thesis or Diss., Université Côte d'Azur (ComUE), 2019. http://www.theses.fr/2019AZUR6027.
Full textBoth preclinical and clinical studies have shown that immune activation and inflammation during the early stages of neurodevelopment increase the risk of neurodevelopment disorders and behaviour abnormalities in adults. While the underlying mechanisms have only been partially elucidated, experiments in the maternal immune activation mouse model (MIA) – in which pregnant dams are injected with the viral mimic poly(I:C) – have demonstrated the critical role of two cytokines: interleukin (IL)-6 and IL-17A. However, the vast majority of the studies performed to date have used behavioural tests in adult mice as a read out to study the impact of cytokines on neurodevelopment. Therefore, it is not clear whether altered levels of other cytokines during the perinatal period could impact neurodevelopment and behaviour in infant mice. To address this issue, we have analysed the progeny of several cohorts of poly(I:C)- and saline-injected mothers for behaviour between postnatal day 5 (P5) and P15 and serum cytokine levels at P15. Because both perinatal neurodevelopment and cytokine production are known or believed to be impacted by many environmental variables, we analysed our data using a multivariable statistical model to identify features associated with being born to a poly(I:C)-injected mother (as opposed to being born to a saline-injected mother). We found that the drop of body weight and temperature of the mother after poly(I:C) injection, the litter size, the pup weight at P15, the number of ultrasonic vocalizations (USV) emitted by the pup at P6, the distance travelled by the pup and the time it spent mobile at P13, as well as serum levels of Tumour Necrosis Factor (TNF), IL-5, IL-15 and C-X-C motif chemokine (CXCL)10 were all associated with altered odds of being born to a poly(I:C)-injected mother. To further explore the role of TNF during the early postnatal period, we injected mouse pups daily from P1 to P5 and assessed these animals for both developmental milestones and behaviour from P8 to P15. Unexpectedly, injection of recombinant TNF did not have a detrimental impact on neurodevelopment but rather promoted sensorimotor reflexes acquisition and exploratory behaviour. Altogether, our results confirm that cytokines play a critical role during neurodevelopment and that altered levels of specific cytokines, and in particular TNF, could regulate the acquisition of developmental milestones and behaviour in infant mice. While we have only obtained preliminary insights into underlying mechanisms, the protocols that we have developed provide a framework for further studies
Legendre, Arnaud. "Modélisation fonctionnelle de l'activité neuronale hippocampique : Applications pharmacologiques." Thesis, Mulhouse, 2015. http://www.theses.fr/2015MULH7271/document.
Full textThe work of this thesis aims to apply modeling and simulation techniques to mechanisms underlying neuronal activity, in order to promote drug discovery for the treatment of nervous system diseases. The models are developed and integrated at different scales: 1) the so-called "elementary models" permit to simulate dynamics of receptors, ion channels and biochemical reactions in intracellular signaling pathways; 2) models at the neuronal level allow to study the electrophysiological activity of these cells; and 3) microcircuits models help to understand the emergent properties of these complex systems, while maintaining the basic mechanisms that are the targets of pharmaceutical molecules. After a bibliographic synthesis of necessary elements of neurobiology, and an outline of the implemented mathematical and computational tools, the manuscript describes the developed models, as well as their validation process, ranging from the neurotransmitter receptor to the microcircuit. Moreover, these developments have been applied to three studies aiming to understand: 1) pharmacological modulation of the long-term potentiation (LTP) of glutamatergic synapses in the hippocampus, 2) mechanisms of neuronal hyperexcitability in the mesial temporal lobe epilepsy (MTLE), based on in vitro and in vivo experimental results, and 3) cholinergic modulation of hippocampal activity, particularly the theta rhythm associated with septo-hippocampal pathway
Derras, Boumédiène. "Estimation des mouvements sismiques et de leur variabilité par approche neuronale : Apport à la compréhension des effets de la source, de propagation et de site." Thesis, Université Grenoble Alpes (ComUE), 2017. http://www.theses.fr/2017GREAU013/document.
Full textThis thesis is devoted to an in-depth analysis of the ability of "Artificial Neural Networks" (ANN) to achieve reliable ground motion predictions. A first important aspect concerns the derivation of "GMPE" (Ground Motion Prediction Equations) with an ANN approach, and the comparison of their performance with those of "classical" GMGEs derived on the basis of empirical regressions with pre-established, more or less complex, functional forms. To perform such a comparison involving the two "betweeen-event" and "within-event" components of the random variability, we adapt the algorithm of the "random effects model" to the neural approach. This approach is tested on various, real and synthetic, datasets: the database compiled from European, Mediterranean and Middle Eastern events (RESORCE: Reference database for Seismic grOund-motion pRediction in Europe), the database NGA West 2 (Next Generation Attenuation West 2 developed in the USA), and the Japanese database derived from the KiK-net accelerometer network. In addition, a comprehensive set of synthetic data is also derived with a stochastic simulation approach. The considered ground motion parameters are those which are most used in earthquake engineering (PGA, PGV, response spectra and also, in some cases, local amplification functions). Such completely "data-driven" neural models, inform us about the respective, and possibly coupled, influences of the amplitude decay with distance, the magnitude scaling effects, and the site conditions, with a particular focus on the detection of non-linearities in site response. Another important aspect is the use of ANNs to test the relevance of different site proxies, through their ability to reduce the random variability of ground motion predictions. The ANN approach allows to use such site proxies either individually or combined, and to investigate their respective impact on the various characteristics of ground motion. The same section also includes an investigation on the links between the non-linear aspects of the site response and the different site proxies. Finally, the third section focuses on a few source-related effects: analysis of the influence of the "style of faulting" on ground motion, and, indirectly, the dependence between magnitude and seismic stress drop
Bougrain, Laurent. "Étude de la construction par réseaux neuromimétiques de représentations interprétables : application à la prédiction dans le domaine des télécommunications." Nancy 1, 2000. http://www.theses.fr/2000NAN10241.
Full textArtificial neural networks constitute good tools for certain types of computational modelling (being potentially efficient, easy to adapt and fast). However, they are often considered difficult to interpret, and are sometimes treated as black boxes. However, whilst this complexity implies that it is difficult to understand the internal organization that develops through learning, it usually encapsulates one of the key factors for obtaining good results. First, to yield a better understanding of how artificial neural networks behave and to validate their use as knowledge discovery tools, we have examined various theoretical works in order to demonstrate the common principles underlying both certain classical artificial neural network, and statistical methods for regression and data analysis. Second, in light of these studies, we have explained the specificities of some more complex artificial neural networks, such as dynamical and modular networks, in order to exploit their respective advantages in constructing a revised model for knowledge extraction, adjusted to the complexity of the phenomena we want to model. The artificial neural networks we have combined (and the subsequent model we developed) can, starting from task data, enhance the understanding of the phenomena modelled through analysing and organising the information for the task. We demonstrate this in a practical prediction task for telecommunication, where the general domain knowledge alone is insufficient to model the phenomena satisfactorily. This leads us to conclude that the possibility for practical application of out work is broad, and that our methods can combine with those already existing in the data mining and the cognitive sciences
Hebart, Martin [Verfasser], John Dylan [Akademischer Betreuer] Haynes, Philipp [Akademischer Betreuer] Sterzer, and Tobias [Akademischer Betreuer] Donner. "On the neuronal systems underlying perceptual decision-making and confidence in humans / Martin Hebart. Gutachter: John - Dylan Haynes ; Philipp Sterzer ; Tobias Donner." Berlin : Humboldt Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät II, 2014. http://d-nb.info/1049237218/34.
Full textMoinnereau, Marc-Antoine. "Encodage d'un signal audio dans un électroencéphalogramme." Mémoire, Université de Sherbrooke, 2017. http://hdl.handle.net/11143/10554.
Full textKalathur, Ravi Kiran Reddy Poch Olivier. "Approche systématique et intégrative pour le stockage, l'analyse et la visualisation des données d'expression génique acquises par des techniques à haut débit, dans des tissus neuronaux An integrated systematic approach for storage, analysis and visualization of gene expression data from neuronal tissues acquired through high-throughput techniques /." Strasbourg : Université Louis Pasteur, 2008. http://eprints-scd-ulp.u-strasbg.fr:8080/920/01/KALATHUR_R_2007.pdf.
Full textChouakri, Nassim. "Identification des paramètres d'un modèle de type Monod a l'aide de réseaux de neurones artificiels." Vandoeuvre-les-Nancy, INPL, 1993. http://www.theses.fr/1993INPL101N.
Full textDonner, Christian [Verfasser], Manfred [Akademischer Betreuer] Opper, Manfred [Gutachter] Opper, Guido [Gutachter] Sanguinetti, and Jakob [Gutachter] Macke. "Bayesian inference of inhomogeneous point process models : methodological advances and modelling of neuronal spiking data / Christian Donner ; Gutachter: Manfred Opper, Guido Sanguinetti, Jakob Macke ; Betreuer: Manfred Opper." Berlin : Technische Universität Berlin, 2019. http://d-nb.info/1187333344/34.
Full textRojas, Castro Dalia Marcela. "The RHIZOME architecture : a hybrid neurobehavioral control architecture for autonomous vision-based indoor robot navigation." Thesis, La Rochelle, 2017. http://www.theses.fr/2017LAROS001/document.
Full textThe work described in this dissertation is a contribution to the problem of autonomous indoor vision-based mobile robot navigation, which is still a vast ongoing research topic. It addresses it by trying to conciliate all differences found among the state-of-the-art control architecture paradigms and navigation strategies. Hence, the author proposes the RHIZOME architecture (Robotic Hybrid Indoor-Zone Operational ModulE) : a unique robotic control architecture capable of creating a synergy of different approaches by merging them into a neural system. The interactions of the robot with its environment and the multiple neural connections allow the whole system to adapt to navigation conditions. The RHIZOME architecture preserves all the advantages of behavior-based architectures such as rapid responses to unforeseen problems in dynamic environments while combining it with the a priori knowledge of the world used indeliberative architectures. However, this knowledge is used to only corroborate the dynamic visual perception information and embedded knowledge, instead of directly controlling the actions of the robot as most hybrid architectures do. The information is represented by a sequence of artificial navigation signs leading to the final destination that are expected to be found in the navigation path. Such sequence is provided to the robot either by means of a program command or by enabling it to extract itself the sequence from a floor plan. This latter implies the execution of a floor plan analysis process. Consequently, in order to take the right decision during navigation, the robot processes both set of information, compares them in real time and reacts accordingly. When navigation signs are not present in the navigation environment as expected, the RHIZOME architecture builds new reference places from landmark constellations, which are extracted from these places and learns them. Thus, during navigation, the robot can use this new information to achieve its final destination by overcoming unforeseen situations.The overall architecture has been implemented on the NAO humanoid robot. Real-time experimental results during indoor navigation under both, deterministic and stochastic scenarios show the feasibility and robustness of the proposed unified approach
Valentin, Nicolas. "Construction d'un capteur logiciel pour le contrôle automatique du procédé de coagulation en traitement d'eau potable." Compiègne, 2000. http://www.theses.fr/2000COMP1314.
Full textZhang, Yujing. "Deep learning-assisted video list decoding in error-prone video transmission systems." Electronic Thesis or Diss., Valenciennes, Université Polytechnique Hauts-de-France, 2024. http://www.theses.fr/2024UPHF0028.
Full textIn recent years, video applications have developed rapidly. At the same time, the video quality experience has improved considerably with the advent of HD video and the emergence of 4K content. As a result, video streams tend to represent a larger amount of data. To reduce the size of these video streams, new video compression solutions such as HEVC have been developed.However, transmission errors that may occur over networks can cause unwanted visual artifacts that significantly degrade the user experience. Various approaches have been proposed in the literature to find efficient and low-complexity solutions to repair video packets containing binary errors, thus avoiding costly retransmission that is incompatible with the low latency constraints of many emerging applications (immersive video, tele-operation). Error correction based on cyclic redundancy check (CRC) is a promising approach that uses readily available information without throughput overhead. However, in practice it can only correct a limited number of errors. Depending on the generating polynomial used, the size of the packets and the maximum number of errors considered, this method can lead not to a single corrected packet but rather to a list of possibly corrected packets. In this case, list decoding becomes relevant in combination with CRC-based error correction as well as methods exploiting information on the reliability of the received bits. However, this has disadvantages in terms of selection of candidate videos. Following the generation of ranked candidates during the state-of-the-art list decoding process, the final selection often considers the first valid candidate in the final list as the reconstructed video. However, this simple selection is arbitrary and not optimal, the candidate video sequence at the top of the list is not necessarily the one which presents the best visual quality. It is therefore necessary to develop a new method to automatically select the video with the highest quality from the list of candidates.We propose to select the best candidate based on the visual quality determined by a deep learning (DL) system. Considering that distortions will be assessed on each frame, we consider image quality assessment rather than video quality assessment. More specifically, each candidate undergoes processing by a reference-free image quality assessment (IQA) method based on deep learning to obtain a score. Subsequently, the system selects the candidate with the highest IQA score. To do this, our system evaluates the quality of videos subject to transmission errors without eliminating lost packets or concealing lost regions. Distortions caused by transmission errors differ from those accounted for by traditional visual quality measures, which typically deal with global, uniform image distortions. Thus, these metrics fail to distinguish the repaired version from different corrupted video versions when local, non-uniform errors occur. Our approach revisits and optimizes the classic list decoding technique by associating it with a CNN architecture first, then with a Transformer to evaluate the visual quality and identify the best candidate. It is unprecedented and offers excellent performance. In particular, we show that when transmission errors occur within an intra frame, our CNN and Transformer-based architectures achieve 100% decision accuracy. For errors in an inter frame, the accuracy is 93% and 95%, respectively
Bertrand, Laurent. "Contribution à la mise en place d'un système d'aide au diagnostic en métallurgie : stockage, analyse et interpolation des diagrammes de transformation en refroidissement continu des aciers." Saint-Etienne, 1995. http://www.theses.fr/1995STET4012.
Full textDeleuze, Carine. "Le chlorhydrate de 1-[1-(2-benzo[b]thiophényl]pipéridine (BTCP), un puissant inhibiteur de capture neuronale de dopamine, donne deux métabolites primaires actifs in vitro et in vivo : Synthèse, identification et quantification des métabolites obtenus à partir de microsomes de foie, de tissus cérébraux, de plasma et d'urines." Montpellier 1, 1998. http://www.theses.fr/1998MON13508.
Full textGaudier, Fabrice. "Modélisation par réseaux de neurones : application à la gestion du combustible dans un réacteur." Cachan, Ecole normale supérieure, 1999. http://www.theses.fr/1999DENS0009.
Full textTiano, Donato. "Learning models on healthcare data with quality indicators." Electronic Thesis or Diss., Lyon 1, 2022. http://www.theses.fr/2022LYO10182.
Full textTime series are collections of data obtained through measurements over time. The purpose of this data is to provide food for thought for event extraction and to represent them in an understandable pattern for later use. The whole process of discovering and extracting patterns from the dataset is carried out with several extraction techniques, including machine learning, statistics, and clustering. This domain is then divided by the number of sources adopted to monitor a phenomenon. Univariate time series when the data source is single and multivariate time series when the data source is multiple. The time series is not a simple structure. Each observation in the series has a strong relationship with the other observations. This interrelationship is the main characteristic of time series, and any time series extraction operation has to deal with it. The solution adopted to manage the interrelationship is related to the extraction operations. The main problem with these techniques is that they do not adopt any pre-processing operation on the time series. Raw time series have many undesirable effects, such as noisy points or the huge memory space required for long series. We propose new data mining techniques based on the adoption of the most representative features of time series to obtain new models from the data. The adoption of features has a profound impact on the scalability of systems. Indeed, the extraction of a feature from the time series allows for the reduction of an entire series to a single value. Therefore, it allows for improving the management of time series, reducing the complexity of solutions in terms of time and space. FeatTS proposes a clustering method for univariate time series that extracts the most representative features of the series. FeatTS aims to adopt the features by converting them into graph networks to extract interrelationships between signals. A co-occurrence matrix merges all detected communities. The intuition is that if two time series are similar, they often belong to the same community, and the co-occurrence matrix reveals this. In Time2Feat, we create a new multivariate time series clustering. Time2Feat offers two different extractions to improve the quality of the features. The first type of extraction is called Intra-Signal Features Extraction and allows to obtain of features from each signal of the multivariate time series. Inter-Signal Features Extraction is used to obtain features by considering pairs of signals belonging to the same multivariate time series. Both methods provide interpretable features, which makes further analysis possible. The whole time series clustering process is lighter, which reduces the time needed to obtain the final cluster. Both solutions represent the state of the art in their field. In AnomalyFeat, we propose an algorithm to reveal anomalies from univariate time series. The characteristic of this algorithm is the ability to work among online time series, i.e. each value of the series is obtained in streaming. In the continuity of previous solutions, we adopt the functionality of revealing anomalies in the series. With AnomalyFeat, we unify the two most popular algorithms for anomaly detection: clustering and recurrent neural network. We seek to discover the density area of the new point obtained with clustering
Zhou, Rongyan. "Exploration of opportunities and challenges brought by Industry 4.0 to the global supply chains and the macroeconomy by integrating Artificial Intelligence and more traditional methods." Electronic Thesis or Diss., université Paris-Saclay, 2021. http://www.theses.fr/2021UPAST037.
Full textIndustry 4.0 is a significant shift and a tremendous challenge for every industrial segment, especially for the manufacturing industry that gave birth to the new industrial revolution. The research first uses literature analysis to sort out the literature, and focuses on the use of “core literature extension method” to enumerate the development direction and application status of different fields, which devotes to showing a leading role for theory and practice of industry 4.0. The research then explores the main trend of multi-tier supply in Industry 4.0 by combining machine learning and traditional methods. Next, the research investigates the relationship of industry 4.0 investment and employment to look into the inter-regional dependence of industry 4.0 so as to present a reasonable clustering based on different criteria and make suggestions and analysis of the global supply chain for enterprises and organizations. Furthermore, our analysis system takes a glance at the macroeconomy. The combination of natural language processing in machine learning to classify research topics and traditional literature review to investigate the multi-tier supply chain significantly improves the study's objectivity and lays a solid foundation for further research. Using complex networks and econometrics to analyze the global supply chain and macroeconomic issues enriches the research methodology at the macro and policy level. This research provides analysis and references to researchers, decision-makers, and companies for their strategic decision-making
Mascarilla, Laurent. "Apprentissage de connaissances pour l'interprétation des images satellite." Toulouse 3, 1996. http://www.theses.fr/1996TOU30300.
Full textAl, Saied Hazem. "Analyse automatique par transitions pour l'identification des expressions polylexicales." Electronic Thesis or Diss., Université de Lorraine, 2019. http://www.theses.fr/2019LORR0206.
Full textThis thesis focuses on the identification of multi-word expressions, addressed through a transition-based system. A multi-word expression (MWE) is a linguistic construct composed of several elements whose combination shows irregularity at one or more linguistic levels. Identifying MWEs in context amounts to annotating the occurrences of MWEs in texts, i.e. to detecting sets of tokens forming such occurrences. For example, in the sentence This has nothing to do with the book, the tokens has, to, do and with would be marked as forming an occurrence of the MWE have to do with. Transition-based analysis is a famous NLP technique to build a structured output from a sequence of elements, applying a sequence of actions (called «transitions») chosen from a predefined set, to incrementally build the output structure. In this thesis, we propose a transition system dedicated to MWE identification within sentences represented as token sequences, and we study various architectures for the classifier which selects the transitions to apply to build the sentence analysis. The first variant of our system uses a linear support vector machine (SVM) classifier. The following variants use neural models: a simple multilayer perceptron (MLP), followed by variants integrating one or more recurrent layers. The preferred scenario is an identification of MWEs without the use of syntactic information, even though we know the two related tasks. We further study a multitasking approach, which jointly performs and take mutual advantage of morphosyntactic tagging, transition-based MWE identification and dependency parsing. The thesis comprises an important experimental part. Firstly, we studied which resampling techniques allow good learning stability despite random initializations. Secondly, we proposed a method for tuning the hyperparameters of our models by trend analysis within a random search for a hyperparameter combination. We produce systems with the constraint of using the same hyperparameter combination for different languages. We use data from the two PARSEME international competitions for verbal MWEs. Our variants produce very good results, including state-of-the-art scores for many languages in the PARSEME 1.0 and 1.1 datasets. One of the variants ranked first for most languages in the PARSEME 1.0 shared task. By the way, our models have poor performance on MWEs that are were not seen at learning time
Toofanee, Mohammud Shaad Ally. "An innovative ecosystem based on deep learning : Contributions for the prevention and prediction of diabetes complications." Electronic Thesis or Diss., Limoges, 2023. https://aurore.unilim.fr/theses/nxfile/default/656b0a1f-2ff2-49c5-bb3e-f34704d6f6b0/blobholder:0/2023LIMO0107.pdf.
Full textIn the year 2021, estimations indicated that approximately 537 million individuals were affected by diabetes, a number anticipated to escalate to 643 million by the year 2030 and further to 783 million by 2045. Diabetes, characterized as a persistent metabolic ailment, necessitates unceasing daily care and management. In the context of Mauritius, as per the most recent report by the International Diabetes Federation, the prevalence of diabetes, specifically Type 2 Diabetes (T2D), stood at 22.6% of the population in 2021, with projections indicating a surge to 26.6% by the year 2045. Amidst this alarming trend, a concurrent advancement has been observed in the realm of technology, with artificial intelligence techniques showcasing promising capabilities in the spheres of medicine and healthcare. This doctoral dissertation embarks on the exploration of the intersection between artificial intelligence and diabetes education, prevention, and management.We initially focused on exploring the potential of artificial intelligence (AI), more specifically, deep learning, to address a critical complication linked to diabetes – Diabetic Foot Ulcer (DFU). The emergence of DFU poses the grave risk of lower limb amputations, consequently leading to severe socio-economic repercussions. In response, we put forth an innovative solution named DFU-HELPER. This tool serves as a preliminary measure for validating the treatment protocols administered by healthcare professionals to individual patients afflicted by DFU. The initial assessment of the proposed tool has exhibited promising performance characteristics, although further refinement and rigorous testing are imperative. Collaborative efforts with public health experts will be pivotal in evaluating the practical efficacy of the tool in real-world scenarios. This approach seeks to bridge the gap between AI technologies and clinical interventions, with the ultimate goal of improving the management of patients with DFU.Our research also addressed the critical aspects of privacy and confidentiality inherent in handling health-related data. Acknowledging the extreme importance of safeguarding sensitive information, we delved into the realm of Peer-to-Peer Federated Learning. This investigation specifically found application in our proposal for the DFU-Helper tool discussed earlier. By exploring this advanced approach, we aimed to ensure that the implementation of our technology aligns with privacy standards, thereby fostering a trustworthy and secure environment for healthcare data management.Finally, our research extended to the development of an intelligent conversational agent designed to offer round-the-clock support for individuals seeking information about diabetes. In pursuit of this goal, the creation of an appropriate dataset was paramount. In this context, we leveraged Natural Language Processing techniques to curate data from online media sources focusing on diabetes-related content
Derras, Boumédiène. "Contribution des données accélérométriques de KiKNet à la prédiction du mouvement sismique par l'approche neuronale avec la prise en compte des effets de site." Phd thesis, 2011. http://tel.archives-ouvertes.fr/tel-00653902.
Full textDiouf, Jean Noël Dibocor. "Classification, apprentissage profond et réseaux de neurones : application en science des données." Thèse, 2020. http://depot-e.uqtr.ca/id/eprint/9555/1/eprint9555.pdf.
Full textSanka, Norbert Bertrand. "Étude comparative et choix optimal du nombre de classes en classification et réseaux de neurones : application en science des données." Thèse, 2021. http://depot-e.uqtr.ca/id/eprint/9662/1/eprint9662.pdf.
Full text