==>"Redirection dans 5 secondes"

Laboratory

Team

SLS

HADAS

Address

46, avenue Félix Viallet
38031 Grenoble Cedex

France

681 rue de la Passerelle, BP72
38402 Saint Martin d'Hères
France

Phone

+(33) 4 76 57 43 00

 

E-mail

sofiane.lagraa(AT)imag.fr

Sofiane LAGRAA

                 

PhD and teaching assistant (ATER) in computer science

·        I received my PhD in Computer Science at Grenoble INP under the supervision of Frédéric Pétrot and Alexandre Termier within TIMA and LIG laboratories, respectively.

·        I received my Master Degree in Computer Science at INSA of Lyon under the supervision of Hamida Seba, within GRAMA team of LIRIS laboratory.                                                                                                                 

                                                                                                                                            

My Thesis:  

The goal of this thesis is to define and design new profiling tools for the evaluation of performance and power for applications mapped on Multi-Processor System-on-Chip. As the number of processors and tasks increases in embedded applications, being able to automatically extract hot spot or spot dysfunctional behaviors from gigabytes of traces becomes both an interesting scientific challenge and a practical issue. The approaches based on Data Mining are the appropriate choice for digging into the large amount of data to process. For example, Frequent Pattern Mining allows to discover patterns having a complex structure (sequences, trees or graphs) occurring frequently in data. The thesis will study the applicability of the Frequent Pattern Mining techniques, clustering to trace data extracted from simulated program executions on the SoC and propose solution to make it practical. It also targets to adapt these techniques in order to discover problematic access patterns such as memory contention or bad temporal locality and scalability bottlenecks.

 

Research Interests

My main research interest is:

·        Pattern recognition using Data Mining and  Graph theory algorithms applied to:

- Data / traces analysis, (Parallel) graph matching,

·        Embedded System: MPSoC, Parallel Application, Profiling.

Teaching Assistantship

Teaching assistant in UFR IM2AG at University of Joseph Fourier.

 

Year

Teaching

Level

Type

Number of hours

Responsible

2013 / 2014

(ATER)

Instrumental computer and multimedia(INF112)

Licence 1

Course /TD/TP

66

Lydie Du-bousquet

Software Engineering

Master 1

TD

15

Yves Ledru

PHP-MySQL Project

Licence 3

Course /TP

12

Christine VERDIER

2012/2013

("moniteur" in french)

Hardware Architectures

3° year engineer Polytech

TD / TP

18

Pascal Sicard

Software Engineering

Master 1

TD

15

Yves Ledru

Instrumental computer and multimedia(INF112)

Licence 1

Course /TD

22

Lydie Du-bousquet

PHP-MySQL Project

Licence 3

Course /TP

12

Christine VERDIER

2011/2012

("moniteur" in french)

Instrumental computer and multimedia(INF112)

Licence 1

Course /TD/TP

64

Lydie Du-bousquet

 

Publications

International conference

·        Sofiane LAGRAA, Alexandre Termier, Frédéric Pétrot. Scalability Bottlenecks Discovery in MPSoC Platforms Using Data Mining on Simulation Traces. DATE 2014 (24-28 / 03/ 2014) Dresden, Germany

·        Sofiane Lagraa, Alexandre Termier, Frédéric Pétrot: Data mining MPSoC simulation traces to identify concurrent memory access patterns. DATE 2013: 755-760

·        Sofiane Lagraa, Alexandre Termier, Frédéric Pétrot: Automatic congestion detection in MPSoC programs using data mining on simulation traces. RSP 2012: 64-70

·        Sofiane Lagraa, Hamida Seba, Hamamache Kheddouci: Matchmaking OWL-S processes: an approach based on path signatures. MEDES 2011: 169-176

·        Sofiane Lagraa, Hamida Seba, Riadh Khennoufa, Hamamache Kheddouci: A Graph Decomposition Approach to Web Service Matchmaking. WEBIST 2011: 31-40s

·        Hamida Seba, Sofiane Lagraa, Hamamache Kheddouci: Web Service Matchmaking by Subgraph Matching. WEBIST (Selected Papers) 2011: 43-56

International Journal

·        Sofiane Lagraa, Hamida Seba, Riadh Khennoufa, A. MBAYA, Hamamache Kheddouci. A Distance Measure for Large Graphs based on Prime Graphs.  Pattern Recognition.   2014. (to appear) 

·        Hamida Seba, Sofiane Lagraa, Hamamache Kheddouci: Alliance-based clustering scheme for group key management in mobile ad hoc networks. The Journal of Supercomputing 61(3): 481-501 (2012)

Award

Best Paper Award at DATE'2014

Project: Authors: Sofiane Lagraa (TIMA and LIG), Alexandre Termier (LIG), Frédéric Pétrot (TIMA)
Title: Scalability Bottlenecks Discovery in MPSoC Platforms Using Data Mining on Simulation Traces

at EDAA/IEEE/ACM 17th Design Automation and Test in Europe (DATE'2014) Conference

Dresden, Germany

 

Reviewing and Organizing Conferences

  • Organizer Committee Member at DATE conference 2013.
  • Co-Reviewer for the following conferences:

·         50th Design Automation Conference (DAC) 2013 (x2 papers)

·         IEEE International Conference on Data Mining series (ICDM2012, ICDM 2011).

·        Knowledge Discovery and Data Mining (KDD 2012)

·        Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD2012).

 

Supervisor of students

  • Project M1 Web, Informatique et Connaissance (WIC) 2013-2014. University of Pierre Mendes France (Grenoble II).
  • Projet tutoré L3-LPbiostat supervised with Christine VERDIER and Olivier Renault. University of Joseph Fourier (Grenoble I).
  • Project at Grenoble School of Management – Technology management and innovation.