Florent Masseglia – Inria Researcher | Analyse de données, big data et extraction de connaissances…

Home

Bâtiment 5
Université Montpellier 2 – CC 05 018
Campus St Priest – 860 rue St Priest
34095 Montpellier cedex 5

Short Bio

I am a scientific researcher in computer science at Inria since 2002. I work in Montpellier, in the Zenith team of Inria on big scientific data analytics. These data, derived from observations, experiments and simulation are indeed complex, often very large, and are at the heart of important issues to better understand the studied domains (agronomy, biology, medicine).

I defended my Habilitation Thesis in 2009.

I did my PhD in computer science at Montpellier in co-supervision with the University of Saint-Quentin en Yvelines (graduated in 2001), in the area of knowledge discovery from databases. Until 2010 I worked in Sophia Antipolis on the development and application of these techniques for knowledge discovery in areas related to usage (such as navigation on Web sites) and large amounts of data.

News ( < 10 months)

2018 Feb 26. We have a PostDoc position available on Time Series Analytics with SAFRAN in the context of the framework agreement between SAFRAN and Inria.

2018 Feb 15. Our work on “ParCorr: Efficient Parallel Methods to Identify Similar Time Series Pairs across Sliding Windows” (Djamel Edine Yagoubi, Boyan Kolev, Reza Akbarinia, Florent Masseglia and Dennis Shasha) has been accepted as regular paper by the DMKD (DAMI) Journal (rank A).

2017 Dec 15. We have a PhD position available on the topic of “Connected Hives Data Analytics for Beekeepers Decision Support”, partly funded by #DigitAg (partners: ACTA, INRA, Inria, ITSAP). I will be thesis director.

2017 Nov 17. Our work on “Maximally Informative k-Itemset Mining from Massively Distributed Data Streams” (Mehdi Zitouni, Reza Akbarinia, Sadok Ben Yahia and Florent Masseglia) has been accepted as regular paper by the ACM SAC 2018 Conference.

2017 Aug 16. Our work on “DPiSAX: Massively Distributed Partitioned iSAX” (Djamel Edine Yagoubi, Reza Akbarinia, Florent Masseglia, and Themis Palpanas) has been accepted by the IEEE ICDM 2017 Conference (rank A*).

2017 Jul 25. Our work on “RadiusSketch: Massively Distributed Indexing of Time Series” (Djamel Edine Yagoubi, Reza Akbarinia, Florent Masseglia and Dennis Shasha) has been accepted as regular paper by the DSAA 2017 Conference.

Main Interests

Big Data analytics.
Massively Distributed Computing.
Pattern Mining / Clustering / Time series (indexing and mining).
Science Outreach / Science Popularization.

Publications

Complete list of publications
A selection of 3 main publications

Responsibilities

I am:

Leader of the “data analytics” group of Zenith.
In charge of the Science Outreach mission of Inria.
Member of the CRISAM scientific board in charge of managing the computing clusters (NEF, Grid5K, etc.).
Finance chair of IEEE ICDE 2018

I was:

Scientific vice-leader of the “Scientific Data” axis of Numev (2014-2016)
Area-Chair of IEEE ICDM (in 2014 and 2015)
Scientific vice-leader of interstices (2012-2016)
Member of the advisory board of “Les petits débrouillards” in Languedoc-Roussillon (2013-2106)

Current Projects

H2020 CloudDBAppliance (2016-2019). I am Site Leader of this project.
Research contract/grant with SAFRAN: “Large-Scale, High-Dimensional Time Series Correlations for Engine Benchmarks Data Analysis” (2017-2018). I am PI of this project.
Inria ADT “Imitates” (2016-2017). I am PI of this project.

Former Projects

STIC-ASIA BD-Farm (2016-2017). I was PI of this project.
PIA DATASCALE (2014-2015). I was Site Leader of this project.
Research contract/grant with EDF: “Privacy preserving clustering of time series” (2012-2013). I was PI of this project.
Research contract/grant with Orange: “Mobile portal usage mining” (2011-2012). I was PI of this project.
ANR MIDAS (2008-2011). I was Site Leader in this project.
ARC SéSur (funded by Inria, 2007-2008). I was PI of this project.
COLOR Mutan (2008). I was PI of this project.

Committees & Reviewing

Reviewer for the following journals:

1. Annals of Mathematics and Artificial Intelligence (AMAI)
2. Distributed and Parallel Databases (DAPD)
3. Data & Knowledge Engineering (DKE)
4. Data Mining and Knowledge Discovery (DMKD)
5. Expert Systems with Applications (ESWA)
6. Electronics and Telecommunications Research Institute (ETRI)
7. International Journal of Uncertainty Fuzziness and Knowledge-Based Systems (IJUFKS)
8. Information Systems (IS), Information Sciences (INS)
9. Journal of Artificial Intelligence Research (JAIR)
10. Journal of Intelligent Information Systems (JIIS)
11. Journal of Systems and Software (JSS)
12. Knowledge and Information Systems (KAIS)
13. The Proceedings of the VLDB Endowment (PVLDB)
14. IEEE Transactions on Knowledge and Data Engineering (TKDE)
15. Transactions on Large-Scale Data and Knowledge-Centered Systems (TLDKS)
16. Transactions on Parallel and Distributed Systems (TPDS)

Program Committee member of (red < 24 months):

ACM SAC (2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017)
CBMS (2012)
DATA (2014, 2015, 2016)
Discovery Science (2009, 2013)
DSAA (2014, 2016, 2017)
EDBT (2014)
EPIA (2009)
IEEE ICDM (2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018)
ICDM PhD forum (2009, 2010, 2011, 2012, 2013, 2014, 2015)
ICML (2010)
ICTAI (2006)
IJCAI (2018)
ISMIS (2017, 2018)
MCCSIS (2009)
PAKDD (2011, 2012, 2013, 2014, 2015, 2016, 2018)
PKDD (2015, 2018)
PIKM (2007, 2008, 2010)
SimBIG (2016, 2017)
ACM SIGMOD (2016)
UDM (2010, 2012, 2013)
VLDB (2016)

I am regularly PC member of the French major conferences on databases and knowledge discovery (BDA, EGC, Inforsid).

PhD juries

Yann Dauxais (Jury member): defense scheduled on April 13 2018, University of Rennes.
Djamel-Edine Yagoubi (Thesis Director): defense scheduled on March 19 2018, University of Montpellier.
Raef Mousheimish (Reviewer/Rapporteur): October 27 2017, University of Paris-Saclay.
Kenza Kellou-Menouer (Jury member): October 9 2017, University of Paris-Saclay.
Hadi Hashem (Jury member): September 19 2016, University of Paris-Saclay (Telecom SudParis).
Saber Salah (Thesis Director): April 20 106, University of Montpellier.
Manuel Pozo (Reviewer/Rapporteur): October 12 2016, CNAM.
Martin Kirchgessner (Reviewer/Rapporteur): September 26 2016, University of Grenoble.
Moreno Barbosa Andres Dario (Reviewer/Rapporteur): December 10 2014, University of Nice-Sophia Antipolis.
Yasin Amanullah (Reviewer/Rapporteur): October 8 2013, Polytech.
Cassio Melo (Jury Chair) : July 19 2013, Ecole Centrale.
Pierre Nicolas Mougel (Reviewer/Rapporteur): September 14 2012, INSA Lyon.
Chongsheng Zhang (Thesis director): October 21 2011, University of Nice-Sophia Antipolis.
Geoffray Bonnin (Reviewer/Rapporteur): November 23 2010, University of Nancy 2.
Paola Salle (Reviewer/Rapporteur): July 13 2010, University of Montpellier 2.
Alice Marascu (Advisor): September 15 2009, University of Nice-Sophia Antipolis.

Students & Supervising

Current PhD students

Khadidja Meguelati (since 2016). Thesis director. “Massively Distributed Clustering via Dirichlet Process”. Co-advised with Nadine Hilgert (INRA)
Djamel Yagoubi (since 2014). Thesis director. “Massive distribution for indexing and mining time series”. Co-advised with Reza Akbarinia and Themis Palpanas (Univ. Paris-Descartes)
Mehdi Zitouni (since 2014). Thesis co-director. “Pattern mining in highly distributed environments”. Co-advised with Reza Akbarinia and Sadok Ben-Yahia (Univ. Tunis)

Former PhD students

Saber Salah (since 2013). Thesis director. “Optimizing a Cloud for Data Mining Primitives”. Co-advised with Reza Akbarinia.
Chongsheng Zhang. Graduated in 2011. Thesis director. “Managing and Mining Data Streams with Evolving Tuples”.
Alice Marascu. Graduated in 2009. Co-advised with Yves Lechevallier and Brigitte Trousse.
Doru Tanasa. Graduated in 2005. Co-advised with Brigitte Trousse.

Post-docs

Rim Moussa, from 2014 to 2015. PIA “Datascale”.
Mohamed Reda Bouadjenek, in 2014 and 2015. On “Collaborative Filtering using multiple sources”. Part of the “BigDataNet” associate team with UCSB.
Julien Diener, from 2013 to 2014. Numev project “RhizoscanHT”.
Tristan Allard, from 2013 to 2014. EDF research contract “Privacy preserving analysis of time series”.
Eniko Szekely, from 2011 to 2013. Numev project “VIPP”.
Céline Fio from 2008 to 2009. Inria ARC “SéSur”.
Wei Wang. 2008. “intrusion detection in data streams”.

Softwares

Logmagnet: summarizing streaming logs on the fly.
Chiaroscuro: privacy preserving analysis of massive sets of time-series.

Patents

“Procédé et installation de comparaison de consommation d’effluents sans divulgation de données de consommations mesurées”. Tristan Allard, Georges Hébrail, Florent Masseglia, Esther PacittiFrance, N° de brevet: EP 2930471 A1. 2015
“Process for identifying rare events”. Sandra Bringay, Renaud Cezar, Dino Ienco, André Mas, Florent Masseglia, Pascal Poncelet, Pierre Pudlo, Maguelonne Teisseire, Jean-Pierre Vendrell and Eniko Szekely. #EP13153512.2. 2013

Science Outreach (médiation scientifique)

Since october 2016, I am in charge of the Science Outreach mission of Inria (“Chargé de mission pour la médiation scientifique pour la DGDS Inria”). This mission is conducted with the valuable help of colleagues involved in science outreach representing different trades of Inria and, of course, all the colleagues who daily contribute to science popularization.