BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.2.3.1//EN TZID:Europe/Paris X-WR-TIMEZONE:Europe/Paris BEGIN:VEVENT UID:5857@i2m.univ-amu.fr DTSTART;TZID=Europe/Paris:20221201T094500 DTEND;TZID=Europe/Paris:20221201T170000 DTSTAMP:20241120T200639Z URL:https://www.i2m.univ-amu.fr/evenements/journee-thematique-processus-po nctuels-en-traitement-du-signal-et-image/ SUMMARY:Journée (FRUMAM\, St Charles\, Marseille): Journée thématique "P rocessus ponctuels en traitement du signal et image" DESCRIPTION:Journée: Journée thématique \nSignal Thematic Day: Point Pro cesses\n\nProgram\n\n\n\n\n9:45-10:00\n\n\nCoffee and introduction\n\n\n10 :00-12:00\nFrédéric Lavancier\n\nCrash-course \nModélisation et infére nce des processus ponctuels spatiaux\n\nAbstract: Les processus ponctuels spatiaux modélisent la répartition aléatoire de points dans l’espace (le plan dans la plupart des applications). Nous verrons comment ils sont définis mathématiquement et les principaux exemples de modèles employé s en pratique\, selon que la répartition des points est spatialement homo gène ou inhomogène\, et que l’interaction entre points voisins est nul le\, attractive\, répulsive ou plus complexe.\nEtant donné une réalisat ion d’un processus ponctuel spatial\, c’est à dire l’observation d' un ensemble de points dans un certain domaine\, nous détaillerons les out ils d’analyse descriptive classiques qui permettent de qualifier la rép artition observée et d’éventuellement s’orienter vers une modélisat ion plus fine. Nous évoquerons également les méthodes d’inférence di sponibles pour calibrer les modèles standards.\n\n\n\n\n\n\n12:00 - 1:30\ n\n\nLunch\n\n\n1:30 - 2:30\nAgnès Desolneux\n\nResearch talk\nDeterminan tal Point Processes and applications in imaging\nAbstract: In this talk\, I will start by presenting the general framework of discrete determinantal point processes (DPP). Then I will show how they can be adapted to the ca se of the pixels of an image (with some applications in texture synthesis) and to the case of patches of an image (with some applications in compres sion/reconstruction).\n\n\n\n\n\n2:30-3:30\nCédric Allain\n\nResearch tal k\nDriPP: Driven Point Processes to Model Stimuli Induced Patterns in M/EE G Signals\nAbstract: The quantitative analysis of non-invasive electrophys iology signals from electroencephalography (EEG) and magnetoencephalograph y (MEG) boils down to the identification of temporal patterns such as evok ed responses\, transient bursts of neural oscillations but also blinks or heartbeats for data cleaning. Several works have shown that these patterns can be extracted efficiently in an unsupervised way\, e.g.\, using Convol utional Dictionary Learning. This leads to an event-based description of t he data. Given these events\, a natural question is to estimate how their occurrences are modulated by certain cognitive tasks and experimental mani pulations. To address it\, we propose a point process approach. While poin t processes have been used in neuroscience in the past\, in particular for single cell recordings (spike trains)\, techniques such as Convolutional Dictionary Learning make them amenable to human studies based on EEG/MEG s ignals. We develop a novel statistical point process model-called driven t emporal point processes (DriPP)-where the intensity function of the point process model is linked to a set of point processes corresponding to stimu lation events. We derive a fast and principled expectation-maximization (E M) algorithm to estimate the parameters of this model. Simulations reveal that model parameters can be identified from long enough signals. Results on standard MEG datasets demonstrate that our methodology reveals event-re lated neural responses-both evoked and induced-and isolates non-task speci fic temporal patterns.\nArticle sur https://arxiv.org/abs/2112.06652\n\n\n \n\n\n4:00-5:00\nFrédéric Lavancier\n\nResearch talk\nSpatial birth-deat h-move processes : basic properties and estimation of their intensity func tions\nAbstract: Various spatio-temporal data record the time of birth and death of individuals\, along with their spatial trajectories during their lifetime\, whether through continuous-time observations or discrete-time observations. The data at hand can be viewed as a random set of points\, t he cardinality and the position of which evolve stochastically through tim e. Natural applications include epidemiology\, individual-based modelling in ecology\, spatio-temporal dynamics observed in bio-imaging\, and comput er vision. To model this kind of data\, we introduce spatial birth-death-m ove processes\, where the birth and death dynamics depends on the current spatial state of all alive individuals and where individuals can move duri ng their lifetime according to a continuous Markov process. We present som e of the basic probabilistic properties of these processes and we consider the non-parametric estimation of their birth and death intensity function s. We prove the consistency of kernel estimators in presence of continuous -time or discrete-time observations\, under fairly simple conditions. We m oreover discuss how we can take advantage in practice of structural assump tions made on the intensity functions and we explain how data-driven bandw idth selection can be conducted\, despite the unknown (and sometimes undef ined) second order moments of the estimators. We finally apply our statist ical method to the analysis of the spatio-temporal dynamics of proteins in volved in exocytosis in cells.\nThis is a joint work with Ronan Le Guével (Rennes 2).\n\n\n\n\n\n\n\nSpeakers\nFrédéric Lavancier (Univ. Nantes)\ nAgnès Desolneux (CNRS Centre Borelli\, Paris)\nCédric Allain (INRIA Sac lay).\n\n\n\nOrganizers\nSandrine Anthoine\nClothilde Mélot\n \;\n ATTACH;FMTTYPE=image/jpeg:https://www.i2m.univ-amu.fr/wp-content/uploads/2 019/11/image-alea_si-signal-binar-numbers-x450.jpg CATEGORIES:Journée(s),Manifestation scientifique LOCATION:Saint-Charles - FRUMAM (2ème étage)\, 3 Place Victor Hugo\, Mar seille\, 13003\, France X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=3 Place Victor Hugo\, Marse ille\, 13003\, France;X-APPLE-RADIUS=100;X-TITLE=Saint-Charles - FRUMAM ( 2ème étage):geo:0,0 END:VEVENT BEGIN:VTIMEZONE TZID:Europe/Paris X-LIC-LOCATION:Europe/Paris BEGIN:STANDARD DTSTART:20221030T020000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 TZNAME:CET END:STANDARD END:VTIMEZONE END:VCALENDAR