Etienne Côme

Researcher at Université Gustave Eiffel

Main topics:

Some sharing

Code

Some random code available on my github account.

Course

Some pedagogical materials around data-science.

Publications

A selection of publications pre-prints are available for download.

Galerie

A selection of visual projects made with .

En:

I’m researcher at the Gustave Eiffel University. I mainly work on applications of pattern recognition tools to transportations problems. I share here some informations on my scientific and other activities.

Fr:

Je suis chargé de recherche à l’Université Gustave Eiffel et je travail principalement sur l'aplication d'outils de type reconnaissances des formes sur des problèmes de transports. Je partage ici des informations sur mes travaux scientifique et autres.

Etienne Côme
Grettia
14-20 Boulevard Newton
Cité Descartes, Champs sur Marne
F-77447 Marne la Vallée Cedex 2
etienne.come[@]univ-eiffel.fr
etienne.come[@]gmail.com

Bibliography

Recent Publications

International journals

E. Côme, N. Jouvin, P. Latouche, C. Bouveyron. Hierarchical Clustering with Discrete Latent Variable Models and the Integrated Clas- sification Likelihhod. Advances in Data Analysis and Classification. 2021, 15(4), 957-986

P. de Nailly, E. Côme, A. Samé, L. Oukhellou, J. Ferriere, Y Merad-Boudia. What can we learn from 9 years of ticketing data at a major transport hub? A struc- tural time series decomposition. Transportmetrica A: Transport Science, 2021, 1-25, https://doi.org/10.1080/23249935.2021.1948626

T. Bapaume, E. Côme, J. Roos, M. Ameli, L. Oukhellou. Image inpainting and deep learning to forecast short-term train loads. IEEE Access vol. 9, pp. 98506-98522, 2021, doi: 10.1109/ACCESS.2021.3093987

N. Roelandt F. Bahoken, G. Le Campion, L. Jegou, E. Côme. One Arabesque in the small world of od webmaps. ISPRS-The International Archives of the Photogrammetry, Remote Sensing and Spatial In- formation Sciences, XLVI-4/W2-2021, 147–154, 2021

F. Bahoken, A.C. Bronner, E. Côme, L. Jégou. Le palmarès du Mapathon du colloque Tous (im) mobiles, tous cartographes. Mappemonde 131 | 2021, DOI : https://doi.org/10.4000/mappemonde.6284

F. Bahoken, G. Le Campion, M. Maisonobe, L. Jégou, E. Côme. Typologie d’un geoweb des flux et réseaux / Typology of a flow and network geoweb. Geomatica, 2020, 74 (3), 15

S. Midenet, E. Côme, F. Papon. Modal shift potential of improvements in cycle access to exurban train stations, Case Studies on Transport Policy, 2018 DOI 10.1016/j.cstp.2018.09.004

C. Richer, E. Côme, M.K. El Mahrsi, L. Oukhellou La mobilité intermodale par les données billettiques. Analyses spatio-temporelles du réseau bus-métro de Rennes Métropole. Cybergeo : Revue européenne de géographie / European journal of geography, 2018, DOI 10.4000/cybergeo.29132

A. S., Briand, E. Côme, M.Trepanier, L. Oukhellou. Analyzing year-to-year changes in public transport passenger behaviour using smart card data. Transportation research - Part C : Emerging technologies, 2017, DOI 10.1016/j.trc.2017.03.021

A-S. Briand, E. Côme, M. K. El Mahrsi & .L Oukhellou. A mixture model clustering approach for temporal passenger pattern characterization in public transport. In International Journal of Data Science and Analytics Volume 1, Issue 1, pp 37–50, 2016.

M K. El Mahrsi, E. Côme, L. Oukhellou & M. Verleysen. Clustering Smart Card Data for Urban Mobility Analysis. In IEEE Transactions on Intelligent Transportation Systems ( Volume: PP, Issue: 99 ), pp 1 – 17, 2016 (DOI: 10.1109/TITS.2016.2600515)

C. Bouveyron, Etienne Côme, J. Jacques. The Discriminative Functional Mixture Model for the Analysis of Bike Sharing Systems [hal]

E. Côme, P. Latouche. Model selection and clustering in stochastic block models with the exact integrated complete data likelihood. To appear in Statistical Modelling.[arXiv], [pdf]

P.A. Laharotte, R. Billot, E. Côme, L. Oukhellou, A. Nantes, N.E. El Faouzi. Spatiotemporal Analysis of Bluetooth Data: Application to a Large Urban Network. Transactions on Intelligent Transportation Systems (99) : 1-10, 2014.

E. Côme, L. Oukhellou. Model-based count series clustering for Bike-sharing system usage mining, a case study with the Vélib’ system of Paris. ACM TIST 5(3), 21014. [pdf]

A. Randriamanamihaga, E. Côme, L. Oukhellou and G. Govaert. Clustering the Vélib’ origin-destinations flows by means of Poisson mixture models. Neurocomputing 141(2) : 124–138, 2014. [preprint]

E. Côme and E. Diemert. The Noise Cluster Model, a Greedy Solution to the Network Community Extraction Problem. I3, 11(3), 2011. [pdf]

Z. Cherfi, E. Côme, L. Oukhellou, T. Denoeux and P. Aknin. Partially supervised Independent Factor Analysis using soft labels elicited from multiple experts: application to railway track circuit diagnosis. Soft Computing, 16(5) :741-754, 2012.

E. Côme, L. Oukhellou, T. Denoeux and P. Aknin. Fault diagnosis of a railway device using semi-supervised independent factor analysis with mixing constraints. Pattern Analysis and Applications, 15(3) :313-326, 2012. [pdf]

E. Côme, L. Oukhellou, T. Denoeux and P. Aknin. Learning from partially supervised data using mixture models and belief functions. Pattern Recognition,42(3) :334–348, 2009. [pdf]

L. Oukhellou, E. Côme, L. Bouillaut and P. Aknin. Combined use of sensor data and structural data processed by bayesian network. application to a railway diagnosis aid scheme. Transportation Research Part C,16(6) :755–767, 2008.

A. Samé, L. Oukhellou, E. Côme, and P. Aknin. Mixture-model-based signal denoising. Advances in Data Analysis and Classification (ADAC), 1(1):39–51, 2007. [pdf]


International Conferences

C. Andrieu, M.K. El Mahrsi, E. Côme, Z. Bezza, L. Oukhellou, F. Rossi. Traffic Characterization on Airport Surface Using Aircraft Ground Trajectories, The 21st IEEE International Conference on Intelligent Transportation Systems, 2018

A. S., Briand, E. Côme, M.Trepanier, L. Oukhellou. Smart Card clustering to extract typical temporal passenger habits in Transit network. Two case studies: Rennes in France and Gatineau in Canada, 3rd International Workshop and Symposium Research and applications on the use of passive data from public transport, 2017.

P. Borgnat, E. Côme, L. Oukhellou. Processing, mining and visualizing massive urban data. ESANN2017, 25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, 2017

E. Côme, A. Remy. Multiscale Spatio-Temporal Data Aggregation and Mapping for Urban Data Exploration. ESANN2017, 25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, 2017

F. Toqué, E. Côme, M.K. El Mahrsi, L. Oukhellou. Forecasting Dynamic Public Transport Origin-Destination Matrices with Long-Short Term Memory Recurrent Neural Networks. IEEE 19th International Conference on Intelligent Transportation Systems, 2016.

A.S. Briand, E. Côme, MK. El Mahrsi, L.Oukhellou. Classification à base de Modèle de mélange pour l’identification de profils temporels types d’usagers de transport public. In proceedings of AAFD & SFC'16 - Francophone International Conference on Data Science , Marrakech , MAROC , 2016 (Prix du meilleur papier jeune chercheur).

F. Toqué, E. Côme, M. K. El Mahrsi, L. Oukhellou. Forecasting Dynamic Public Transport Origin-Destination Matrices with Long-Short Term Memory Recurrent Neural Networks. In Proceedings of IEEE 19th International Conference on Intelligent Transportation Systems , Rio de Janeiro , BRESIL 2016.

A. Randriamanamihaga, E. Côme, L. Oukhellou. Dynamic Origin/Destination modeling with Gravity-Latent Dirichlet Allocation (G-LDA). In proceedings of TRISTAN IX - 9th Triennial Symposium on Transportation Analysis, Oranjestad, Aruba , PAYS-BAS , 2016.

F. Papon, J.M. Beauvais, S. Midenet, E. Côme, N. Polombo, S. Abours, L. Belton-Chevallier, C. Soulas. Evaluation of the bicycle as a feeder mode to regional train stations, Transportation research Procedia, WCTR2016 - World Conference on Transport Research, Shanghai, CHINE, 2016, Elsevier, 20p.

A.S. Briand, M.K. El Mahrsi, E. Côme, J. Baro & L. Oukhellou. A Mixture Model Clustering Approach for Temporal Passenger Pattern Characterization in Public Transport. In proceedings of the 2nd IEEE International Conference on Data Science & Advance Data analytics, Paris 2015 (Séléctionné pour publication dans une revue).

E. Côme. Analysing Spatio Temporal Behaviours of Bike Sharing Systems Through Clustering and topic modelling, In proceedings of the 14th International Conference on Travel Behaviour Research, p. 1-20, Windsor 2015.

E. Côme, M.K. El Mahrsi, L. Oukhellou. Cartographie interactive de matrices Origines / Destinations. In proceedings of Spatial Analysis and GEOmatics, 2014, Grenoble.

M.K. El Mahrsi, E. Côme, J. Baro and L. Oukhellou . Understanding Passenger Patterns in Public Transit Through Smart Card and Socioeconomic Data. In 3rd International Workshop on Urban Computing (SigKDD), 2014. [pdf]

E. Côme, A. Randriamanamihaga, L. Oukhellou and P. Aknin. Spatio-temporal analysis of Dynamic Origin-Destination data using Latent Dirichlet Allocation. Application to the Vélib’ Bike Sharing System of Paris. In Proceedings of 93rd Annual Meeting of the Transportation Research Board, 2014. [pdf]

Y. Han, E. Côme and L. Oukhellou. Towards bicycle demand prediction of large-scale bicycle sharing system. In Proceedings of 93rd Annual Meeting of the Transportation Research Board, 2014. [pdf]

A. Randriamanamihaga, E. Côme, L. Oukhellou and G. Govaert. Clustering the Vélib’ origin-destinations flows by means of Poisson mixture models. In Proceedings of the European Symposium on Artificial Neural Networks, 2013. [pdf]

J. Baro, E. Côme, P. Aknin and O. Bonin. Hierarchical and multiscale Mean Shift segmentation of population grid. In Proceedings of the European Symposium on Artificial Neural Networks, 2013. [pdf]

E. Côme, M. Cottrell, M. Verleyssen and J. Lacaille. Self Organizing Star (SOS) for health monitoring. In Proceedings of the European Symposium on Artificial Neural Networks, 2010.

E. Côme, L. Oukhellou, T. Denoeux and P. Aknin Noiseless Independent Factor Analysis with mixing constraints in a semi-supervised framework. Application to railway device fault diagnosis. In Proceedings of the 7th International Conference on Artificial Neural Networks (ICANN), Accepté, 2009. [pdf]

Z.L Cherfi, L. Oukhellou, E. Côme, and P. Aknin. Railway device diagnosis using sparse independent component analysis. In Proceedings of the European Signal Processing Conference, Accepté, 2009.

E. Côme, L. Oukhellou, P. Aknin. and T. Denoeux. Partially-supervised learning in Independent Factor Analysis. In Proceedings of the European Symposium on Artificial Neural Networks, Accepté, 2009.

E. Côme, Z.L Cherfi, L. Oukhellou, T. Denoeux, and P. Aknin. Semi-supervised IFA with prior knowledge on the mixing process An application to a railway device diagnosis. In International Conference on Machine Learning and Applications,December 11-13, San-Diego, 2008.

E. Côme, L. Oukhellou, T. Denoeux, and P. Aknin. Mixture model estimation with soft labels. In Proceedings of the 4st Soft Methods in Probability and Statistics, June 13-15, Toulouse, 2008. [pdf]

E. Côme, L. Bouillaut, P. Aknin, and L. Oukhellou. Hidden markov random field, an application to railway infrastructure diagnosis. In Proceedings of the 1st IFAC Workshop on dependable control of discret systems (DCDS), June 13-15, Paris, pages 155–160, 2007. [pdf]

Portfolio

Recent Projects

Courses & Talks

Recent Courses & Talks

Introduction to data-science M2 UPEM

github repository of the course

Introduction to data-science M2-IM Paris 5

repository of the course

Cartostats : itinéraire d'un pseudo-cartographe

slides

Summer school, Massive spatial data

github repository of the course

Summer school, Geo-viz

slides

satRday, 2019 : Spatial data and cartography

github repository of the workshop