SAMOVAR - SAMOVAR
Telecom SudParis
9 rue Charles Fourier
91011 EVRY CEDEX

Fax : +33 (0) 1 60 76 20 80

Yohan PETETIN

Maßtre de Conférences
SOP

yohan.petetin[@-Code to remove to avoid SPAM-]telecom-sudparis.eu

Article dans une revue

2024

ref_biblio
Yazid Janati, Sylvain Le Corff, Yohan Petetin. Variance estimation for Sequential Monte Carlo Algorithms: a backward sampling approach. Bernoulli, 2024, 30 (2), ⟨10.3150/23-BEJ1586⟩. ⟨hal-03630333v2⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-03630333/file/arxivpaper.pdf BibTex

2023

ref_biblio
François Desbouvries, Yohan Petetin, Achille SalaĂŒn. Expressivity of hidden Markov chains vs. Recurrent neural networks from a system theoretic viewpoint. IEEE Transactions on Signal Processing, 2023, 71, pp.4178-4191. ⟨10.1109/TSP.2023.3328108⟩. ⟨hal-03746170⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-03746170/file/main.pdf BibTex
ref_biblio
Hugo Gangloff, Katherine Morales, Yohan Petetin. Deep parameterizations of pairwise and triplet Markov models for unsupervised classification of sequential data. Computational Statistics and Data Analysis, 2023, 180, pp.107663. ⟨10.1016/j.csda.2022.107663⟩. ⟨hal-03584314⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-03584314/file/Deep%20parameterizations%20of%20pairwise%20and%20triplet%20Markov%20models.pdf BibTex

2021

ref_biblio
Yohan Petetin, Yazid Janati, François Desbouvries. Structured variational Bayesian inference for Gaussian state-space models with regime switching. IEEE Signal Processing Letters, 2021, 28, pp.1953-1957. ⟨10.1109/LSP.2021.3113279⟩. ⟨hal-03348244⟩
AccĂšs au bibtex
BibTex

2018

ref_biblio
Roland Lamberti, Yohan Petetin, François Desbouvries, François Septier. Semi-independent resampling for particle filtering. IEEE Signal Processing Letters, 2018, 25 (1), pp.130 - 134. ⟨10.1109/LSP.2017.2775150⟩. ⟨hal-01670395⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-01670395/file/1710.05407.pdf BibTex

2017

ref_biblio
Roland Lamberti, Yohan Petetin, François Desbouvries, François Septier. Independent resampling sequential Monte Carlo algorithms. IEEE Transactions on Signal Processing, 2017, 65 (20), pp.5318 - 5333. ⟨10.1109/TSP.2017.2726971⟩. ⟨hal-01593422⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-01593422/file/1607.05758.pdf BibTex

2015

ref_biblio
Yohan Petetin, François Desbouvries. Bayesian conditional Monte Carlo Algorithm for nonlinear time-series state estimation. IEEE Transactions on Signal Processing, 2015, 63 (14), pp.3586 - 3598. ⟨10.1109/TSP.2015.2423251⟩. ⟨hal-01255022⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-01255022/file/article_YohanPetetin.pdf BibTex

2014

ref_biblio
Noufel Abbassi, StĂ©phane Derrode, François Desbouvries, Yohan Petetin, Wojciech Pieczynski. Filtrage statistique optimal rapide dans des systĂšmes linĂ©aires Ă  sauts non stationnaires. Traitement du Signal, 2014, 31 (3-4), pp.339-361. ⟨10.3166/TS.31.1-23⟩. ⟨hal-01157813⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-01157813/file/TS2014.pdf BibTex
ref_biblio
Yohan Petetin, François Desbouvries. A class of fast exact Bayesian filters in dynamical models with jumps. IEEE Transactions on Signal Processing, 2014, 62 (14), pp.3643 - 3653. ⟨10.1109/TSP.2014.2329265⟩. ⟨hal-01262437⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-01262437/file/arXiv_1310.0226.pdf BibTex
ref_biblio
Yohan Petetin, Mark Morelande, François Desbouvries. Marginalized particle PHD filters for multiple object Bayesian filtering. IEEE Transactions on Aerospace and Electronic Systems, 2014, 50 (2), pp.1182 - 1196 ⟨10.1109/TAES.2014.120805⟩. ⟨hal-01264791⟩
AccĂšs au bibtex
BibTex

2013

ref_biblio
Yohan Petetin, François Desbouvries. Bayesian multi-object filtering for pairwise Markov chains. IEEE Transactions on Signal Processing, 2013, 61 (18), pp.4481 - 4490. ⟨10.1109/TSP.2013.2271751⟩. ⟨hal-01263075⟩
AccĂšs au bibtex
BibTex
ref_biblio
Yohan Petetin, François Desbouvries. Optimal SIR algorithm vs. fully adapted auxiliary particle filter : a non asymptotic analysis. Statistics and Computing, 2013, 23 (6), pp.759-775. ⟨10.1007/s11222-012-9345-5⟩. ⟨hal-00862193⟩
AccĂšs au bibtex
BibTex

2011

ref_biblio
François Desbouvries, Yohan Petetin, Boujemaa Ait-El-Fquih. Direct, prediction- and smoothing-based Kalman and particle filter algorithms. Signal Processing, 2011, 91 (8), pp.2064 - 2077. ⟨10.1016/j.sigpro.2011.03.013⟩. ⟨hal-01354694⟩
AccĂšs au bibtex
BibTex

Communication dans un congrĂšs

2019

ref_biblio
Nicolas Aussel, Fabian Dubourvieux, Yohan Petetin. Spatio-temporal convolutional neural networks for failure prediction. GRETSI 2019: XXVIIĂšme colloque francophone de traitement du signal et des images, Aug 2019, Lille, France. pp.1-5. ⟨hal-02282219⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-02282219/file/gretsi_2019_YP.pdf BibTex
ref_biblio
Achille SalaĂŒn, Yohan Petetin, François Desbouvries. Comparing the modeling powers of RNN and HMM. ICMLA 2019: 18th International Conference on Machine Learning and Applications, Dec 2019, Boca Raton, FL, United States. pp.1496-1499. ⟨hal-02387002⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-02387002/file/2019-icmla.pdf BibTex

2018

ref_biblio
Nicolas Aussel, Yohan Petetin, Sophie Chabridon. Improving performances of log mining for anomaly prediction through NLP-based log parsing. MASCOTS 2018: 26th International Symposium on the Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, Sep 2018, Milwaukee, United States. pp.237 - 243, ⟨10.1109/MASCOTS.2018.00031⟩. ⟨hal-01919820⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-01919820/file/2018_hal-01919820.pdf BibTex
ref_biblio
Roland Lamberti, Yohan Petetin, François Septier, François Desbouvries. A double proposal normalized importance sampling estimator. SSP 2018: IEEE Statistical Signal Processing Workshop, Jun 2018, Freiburg, Germany. pp.238 - 242, ⟨10.1109/SSP.2018.8450849⟩. ⟨hal-01870199⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-01870199/file/2018-ssp-roland.pdf BibTex

2017

ref_biblio
Nicolas Aussel, Samuel Jaulin, Guillaume Gandon, Yohan Petetin, Eriza Fazli, et al.. Predictive models of hard drive failures based on operational data. ICMLA 2017 : 16th IEEE International Conference On Machine Learning And Applications, Dec 2017, Cancun, Mexico. pp.619 - 625, ⟨10.1109/ICMLA.2017.00-92⟩. ⟨hal-01703140⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-01703140/file/article_preprint.pdf BibTex
ref_biblio
Roland Lamberti, François Desbouvries, François Septier, Yohan Petetin. RĂ©Ă©chantillonnage indĂ©pendant et semi-indĂ©pendant pour le filtrage particulaire. XXVIĂšme Colloque GRETSI, Sep 2017, Juan-Les-Pins, France. ⟨hal-01679000⟩
AccĂšs au bibtex
BibTex

2016

ref_biblio
Roland Lamberti, Yohan Petetin, François Septier, François Desbouvries. Particle filters with independent resampling. ICASSP 2016 : 41st International Conference on Acoustics, Speech and Signal Processing, Mar 2016, Shanghai, China. pp.3994 - 3998, ⟨10.1109/ICASSP.2016.7472427⟩. ⟨hal-01341157⟩
AccĂšs au bibtex
BibTex
ref_biblio
Roland Lamberti, Yohan Petetin, François Septier, François Desbouvries. An improved SIR-based sequential Monte Carlo algorithm. 2016 IEEE Workshop on Statistical Signal Processing (SSP 16), Jun 2016, Palma de Mallorca, Spain. ⟨hal-01359095⟩
AccĂšs au bibtex
BibTex

2015

ref_biblio
Yohan Petetin, François Desbouvries. Un algorithme d'estimation non supervisĂ©e dans des modĂšles Markoviens Ă  sauts. Gretsi 2015 : XXVe colloque Gretsi, Sep 2015, Lyon, France. ⟨hal-01255026⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-01255026/file/article_YohanPetetin_2015-gretsi.pdf BibTex
ref_biblio
Yohan Petetin, Cyrille Laroche, Aurelien Mayoue. Deep neural networks for audio scene recognition. 2015 23rd European Signal Processing Conference (EUSIPCO), Aug 2015, Nice, France. pp.7362358, ⟨10.1109/EUSIPCO.2015.7362358⟩. ⟨hal-01888746⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-01888746/file/article_YohanPetetin_Deepneuralnetworks.pdf BibTex

2014

ref_biblio
Yohan Petetin, François Desbouvries. Exact Bayesian estimation in constrained Triplet Markov Chains. 2014 MLSP : IEEE International Workshop on Machine Learning for Signal Processing, Sep 2014, Reims, France. ⟨10.1109/MLSP.2014.6958847⟩. ⟨hal-01262438⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-01262438/file/article_YohanPetetin_Exact%20Bayesian%20estimation.pdf BibTex

2013

ref_biblio
Marc Blanc-Patin, Marion Chevalier, Audrey Dupont, Emmanuel Monfrini, Yohan Petetin. Poursuite de cible par un senseur mobile ; repĂ©rage multisenseur de la position du senseur mobile. XXIVĂšme Colloque Gretsi, Sep 2013, Brest, France. ⟨hal-00867150⟩
AccĂšs au bibtex
BibTex
ref_biblio
Yohan Petetin, François Desbouvries. Un nouvel algorithme de filtrage dans les modĂšles de Markov Ă  saut linĂ©aires et Gaussiens. XXIVĂšme Colloque Gretsi, Sep 2013, Brest, France. ⟨hal-00867111⟩
AccĂšs au bibtex
BibTex
ref_biblio
Yohan Petetin, Mark Morelande, François Desbouvries. Filtrage particulaire marginalisĂ© pour la poursuite multi-objets. XXIVĂšme Colloque Gretsi, Sep 2013, Brest, France. ⟨hal-00867104⟩
AccĂšs au bibtex
BibTex
ref_biblio
Wojciech Pieczynski, StĂ©phane Derrode, Noufel Abbassi, Yohan Petetin, François Desbouvries. Exact optimal filtering in an approximating switching system. TAIMA 2013 : Traitement et Analyse de l'Information MĂ©thodes et Applications, May 2013, Hammamet, Tunisia. ⟨hal-01461574⟩
AccĂšs au bibtex
BibTex

2012

ref_biblio
Yohan Petetin, François Desbouvries. A semi-exact sequential Monte Carlo filtering algorithm in hidden Markov chains. ISSPA '12 : The 11th International Conference on Information Sciences, Signal Processing and their Applications, Jul 2012, Montreal, Canada. pp.595-600, ⟨10.1109/ISSPA.2012.6310621⟩. ⟨hal-00765899⟩
AccĂšs au bibtex
BibTex
ref_biblio
Yohan Petetin, François Desbouvries. A mixed GM/SMC implementation of the probability hypothesis density filter. ISSPA '12 : The 11th International Conference on Information Sciences, Signal Processing and their Applications, Jul 2012, Montreal, Canada. pp.425-430, ⟨10.1109/ISSPA.2012.6310588⟩. ⟨hal-00765490⟩
AccĂšs au bibtex
BibTex
ref_biblio
Yohan Petetin, François Desbouvries. Further Rao-Blackwellizing an already Rao-Blackwellized algorithm for jump Markov state space systems. ISSPA '12 : The 11th International Conference on Information Sciences, Signal Processing and their Applications, Jul 2012, Montreal, Canada. pp.706-711, ⟨10.1109/ISSPA.2012.6310644⟩. ⟨hal-00765888⟩
AccĂšs au bibtex
BibTex
ref_biblio
Yohan Petetin, François Desbouvries. Multi-object filtering for pairwise Markov chains. ISSPA '12 : The 11th International Conference on Information Sciences, Signal Processing and their Applications, Jul 2012, Montreal, Canada. pp.348 -353, ⟨10.1109/ISSPA.2012.6310573⟩. ⟨hal-00765497⟩
AccĂšs au bibtex
BibTex
ref_biblio
Yohan Petetin, François Desbouvries. Marginalized PHD filters for multi-target filtering. ISSPA '12 : The 11th International Conference on Information Sciences, Signal Processing and their Applications, Jul 2012, Montreal, Canada. pp.419-424, ⟨10.1109/ISSPA.2012.6310587⟩. ⟨hal-00765488⟩
AccĂšs au bibtex
BibTex

2011

ref_biblio
François Desbouvries, Yohan Petetin, Emmanuel Monfrini. Filtrage particulaire optimal et filtrage particulaire auxiliaire adaptĂ© : une analyse non asymptotique. GRETSI 2011 : XXIIIe Colloque, Sep 2011, Bordeaux, France. ⟨hal-01347966⟩
AccĂšs au bibtex
BibTex
ref_biblio
François Desbouvries, Yohan Petetin, Emmanuel Monfrini. A non asymptotical analysis of the optimal SIR algorithm vs. the fully adapted auxiliary particle filter. SSP 2011 : Statistical Signal Processing Workshop, Jun 2011, Nice, France. pp.213 - 216, ⟨10.1109/SSP.2011.5967662⟩. ⟨hal-01354690⟩
AccĂšs au bibtex
BibTex
ref_biblio
François Desbouvries, Yohan Petetin, Emmanuel Monfrini. Optimal SIR algorithm vs. fully adapted auxiliary particle filter : a matter of conditional independence. ICASSP 2011 : International Conference on Acoustics, Speech and Signal Processing, May 2011, Prague, Czech Republic. pp.3992 - 3995, ⟨10.1109/ICASSP.2011.5947227⟩. ⟨hal-01304056⟩
AccĂšs au bibtex
BibTex
ref_biblio
Yohan Petetin, François Desbouvries. A particle smoothing implementation of the fully-adapted auxiliary particle filter : an alternative to auxiliary particle filters. SSP 2011 : Statistical Signal Processing Workshop, Jun 2011, Nice, France. pp.217 - 220, ⟨10.1109/SSP.2011.5967663⟩. ⟨hal-01354688⟩
AccĂšs au bibtex
BibTex

2010

ref_biblio
Yohan Petetin, François Desbouvries. Direct vs. indirect sequential Monte-Carlo filters. SMTDA 2010 : Stochastic Modeling Techniques and Data Analysis International Conference, Jun 2010, Chania, Greece. pp.121 - 128. ⟨hal-01306303⟩
AccĂšs au bibtex
BibTex

HDR

2023

ref_biblio
Yohan Petetin. Generative models for times series data. Statistiques [math.ST]. Institut polytechnique de Paris, 2023. ⟨tel-04414619⟩
AccÚs au texte intégral et bibtex
https://hal.science/tel-04414619/file/HDR_Yohan.P.pdf BibTex

Poster de conférence

2014

ref_biblio
Roland Lamberti, Thomas Durier, Frederic Lehmann, Yohan Petetin, Dominique Maltese. Track-before-detect and PHD filter for multi-object tracking in infrared image sequences. SENSO 2014 : Sensors, Energy harvesting, wireless Network and Smart Objects, Oct 2014, Gardanne, France. ⟨hal-01332943⟩
AccĂšs au bibtex
BibTex

ThĂšse

2013

ref_biblio
Yohan Petetin. Algorithmes de restauration BayĂ©sienne mono- et multiobjet(s) dans des modĂšles Markoviens. MathĂ©matiques [math]. Telecom SudParis, 2013. Français. ⟨NNT : ⟩. ⟨tel-04414609⟩
AccÚs au texte intégral et bibtex
https://hal.science/tel-04414609/file/These_Yohan.P.pdf BibTex
ref_biblio
Yohan Petetin. Algorithmes de restauration bayĂ©sienne mono- et multi-objets dans des modĂšles markoviens. MathĂ©matiques gĂ©nĂ©rales [math.GM]. Institut National des TĂ©lĂ©communications, 2013. Français. ⟨NNT : 2013TELE0032⟩. ⟨tel-00939083⟩
AccÚs au texte intégral et bibtex
https://theses.hal.science/tel-00939083/file/PETETIN_Yohan-SMPC.pdf BibTex

Pré-publication, Document de travail

2022

ref_biblio
Hugo Gangloff, Katherine Morales, Yohan Petetin. ChaĂźnes de Markov cachĂ©es Ă  bruit gĂ©nĂ©ralisĂ©. 2022. ⟨hal-03698101⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-03698101/file/mtmc_gretsi.pdf BibTex

2021

ref_biblio
Hugo Gangloff, Katherine Morales, Yohan Petetin. A GENERAL PARAMETRIZATION FRAMEWORK FOR PAIRWISE MARKOV MODELS: AN APPLICATION TO UNSUPERVISED IMAGE SEGMENTATION. 2021. ⟨hal-03181237v2⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-03181237/file/general_pmc_new.pdf BibTex
ref_biblio
Katherine Morales, Yohan Petetin. Variational Bayesian inference for pairwise Markov models. 2021. ⟨hal-03237172⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-03237172/file/Morales_Petetin_ssp_2021.pdf BibTex

2019

ref_biblio
Nicolas Aussel, Sophie Chabridon, Yohan Petetin. Combining federated and active learning for communication-efficient distributed failure prediction in aeronautics. 2019. ⟨hal-02446200⟩
AccÚs au texte intégral et bibtex
https://hal.science/hal-02446200/file/article.pdf BibTex