Groupe de travail MINERS

Description :
Data Mining Team of LIMOS

Responsable communication :
MBOUOPDA Michael Franklin


Journée Perspectives et Défis de l'IA (PDIA) - April 2, 2021 - SEMINAIRE

L’Association Française pour l’Intelligence Artificielle (AFIA) organise sa septième journée PERSPECTIVES ET DEFIS DE l’IA sur le thème de l’EXPLICABILITE.

L’utilisation des systèmes d’apprentissage et d’aide à la décision est devenue courante. L’étude de la fiabilité et de la précision des systèmes concernés est devenue un sujet d’intérêt majeur, et le besoin de comprendre comment de tels systèmes fonctionnent, apprennent ou prennent des décisions est devenu primordial. L’objectif de cette journée est d’étudier et de discuter toutes ces questions, et de rassembler les chercheurs qui s’y intéressent.

La journée est construite autour d’exposés accessibles, de retours d’expériences et de tables rondes favorisant une grande interaction.

 

Plus d'info ici: https://afia.asso.fr/pdia21/


Photographs from IJCAI 2020 - Yokohama (virtual) - Jan. 18, 2021 - GENERAL

 Sit in the garden


Three papers accepted at the national conference EGC'2020 - Nov. 30, 2020 - PUBLICATION

GPoID : Extraction de Motifs Graduels pour les Bases de Données Imprécises

By: Michael Chirmeni Boujike, Jerry Lonlac, Norbert Tsopze and Engelbert Mephu Nguifo 

Apport de l'entropie pour les c-moyennes floues sur des données catégoriques (French version of Fuzz-IEEE'2020)

By: Abdoul Jalil Djiberou Mahamadou, Violaine Antoine, Engelbert Mephu Nguifo and Sylvain Moreno

Ontology-based data integration in a distributed context of coalition air missions

By: Karima Ennaoui, Mathieu Faivre, Md Shahriar Hassan, Christophe Rey, Lauren Dargent, Hervé Girod and Engelbert Mephu Nguifo


Accepted Paper at ICDMW 2020: Uncertain Time Series Classification with Shapelet Transform - Nov. 16, 2020 - PUBLICATION

Authors: Michael F. MBOUOPDA and Engelbert MEPHU NGUIFO

Abstract: Time series classification is a task that aims at classifying chronological data. It is used in a diverse range of domains such as meteorology, medicine and physics. In the last decade, many algorithms have been built to perform this task with very appreciable accuracy. However, applications where time series have uncertainty has been under-explored. Using uncertainty propagation techniques, we propose a new uncertain dissimilarity measure based on Euclidean distance. We then propose the uncertain shapelet transform algorithm for the classification of uncertain time series. The large experiments we conducted on state of the art datasets show the effectiveness of our contribution. The source code of our contribution and the datasets we used are all available on a public repository.

 

Model overview

 

 


A novel algorithm for searching frequent gradual patterns from an ordered data set - Oct. 8, 2020 - PUBLICATION

Accepted Paper at WUML2020 (workshop at ECMLPKDD 2020): Classification of Uncertain Time Series by Propagating Uncertainty in Shapelet Transform - July 24, 2020 - PUBLICATION

Author: Michael F. MBOUOPDA and Engelbert MEPHU NGUIFO

Abstract: Time series classification is a task that aims at classifying chronological data. It is used in a diverse range of domains such as meteorology, medicine and physics. In the last decade, many algorithms have been built to perform this task with very appreciable accuracy. However, the uncertainty in data is not explicitly taken into account by these methods. Using uncertainty propagation techniques, we propose a new uncertain dissimilarity measure based on euclidean distance. We also show how to classify uncertain time series using the proposed dissimilarity measure and shapelet transform, one of the best time series classification methods. An experimental assessment of our contribution is done on the well known UCR dataset.


Accepted Paper at FUZZ-IEEE2020: Categorical fuzzy entropy c-means - May 8, 2020 - PUBLICATION

Authors: Abdoul Jalil Djiberou Mahamadou, Violaine Antoine and Engelbert Mephu Nguifo and Sylvain Moreno

Abstract: Hard and fuzzy clustering algorithms are part of the partition-based clustering family. They are widely used in real-world applications to cluster numerical and categorical data. While in hard clustering an object is assigned to a cluster with certainty, in fuzzy clustering an object can be assigned to different clusters given a membership degree. For both types of method an entropy can be incorporated into the objective function, mostly to avoid solutions raising too much uncertainties. In this paper, we present an extension of a fuzzy clustering method for categorical data using fuzzy centroids. The new algorithm, referred to as Categorical Fuzzy Entropy (CFE), integrates an entropy term in the objective function. This allows a better fuzzification of the cluster prototypes. Experiments on ten real-world data sets and statistical comparisons show that the new method can efficiently handle categorical data.


Acticle accepté à CNIA2020: Classification des Séries Temporelles Incertaines par Transformation Shapelet - May 6, 2020 - PUBLICATION

Auteurs: Michael Franklin MBOUOPDA et Engelbert MEPHU NGUIFO

Résumé: La classification des séries temporelles est une tâche qui consiste à classifier les données chronologiques. Elle est utilisée dans divers domaines tels que la météorologie, la médecine et la physique. Plusieurs techniques performantes ont été proposées durant les dix dernières années pour accomplir cette tâche. Cependant, elles ne prennent pas explicitement en compte l’incertitude dans les données. En utilisant la propagation de l’incertitude, nous proposons une nouvelle mesure de dissimilarité incertaine basée sur la distance euclidienne. Nous montrons également comment faire la classification de séries temporelles incertaines en couplant cette mesure avec la méthode de transformation shapelet, l’une des méthodes les plus performantes pour cette tâche. Une évaluation expérimentale de notre contribution est faite sur le dépôt de données temporelles UCR.


Accepted Paper at FUZZ-IEEE 2019: Evidential clustering for categorical data - May 6, 2020 - PUBLICATION

Author: A. J. Djiberou Mahamadou, V. Antoine, G. J. Christie and S. Moreno

Abstract: Evidential clustering methods assign objects to clusters with a degree of belief, allowing for better representation of cluster overlap and outliers. Based on the theoretical framework of belief functions, they generate credal partitions which extend crisp, fuzzy and possibilistic partitions. Despite their ability to provide rich information about the partition, no evidential clustering algorithm for categorical data has yet been proposed. This paper presents a categorical version of ECM, an evidential variant of k-means. The proposed algorithm, referred to as catECM, considers a new dissimilarity measure and introduces an alternating minimization scheme in order to obtain a credal partition. Experimental results with real and synthetic data sets show the potential and the efficiency of cat-ECM for clustering categorical data.

https://ieeexplore.ieee.org/abstract/document/8858972


NeuroDeRisk - Semi annual meeting - April 28, 2020 - SEMINAIRE

Semi-annual face-to-face meeting of the European project NeuroDeRisk , initially planned in Brussels, but held in web conference because of COVID-19.
A meeting to discuss the last 6 months deliverables and futur ones.


Nouvel article publié dans la revue Pattern Recognition - March 20, 2020 - PUBLICATION


Remise des écharpes docteurs 2020 - Feb. 4, 2020 - SEMINAIRE

Nos nouveaux docteurs en informatique Dr. Angeline PLAUD et Dr. Jocelyn DE GOËR, tous deux encadrés par Prof. Engelbert MEPHU NGUIFO


BIOSS : Groupe de travail sur la biologie systémique symbolique - Dec. 20, 2018 - PUBLICATION

Groupe de travail financé par le GdrIA, Monsieur Engelbert Nguifo Mephu, a réalisé une présentation Mercredi 19 décembre 2018. Cette présentation avait pour thème :A Novel Computational Approach for Global Alignment for Multiple Biological Networks.


mephu_expose_IA_multiformes_2.pdf - Nov. 22, 2018 - PUBLICATION


mephu_expose_IA_multiformes_2.pdf.zip


AALTD'18 Accepted Paper - Sept. 19, 2018 - PUBLICATION

Time Series Classification with Recurrent Neural Networks

by Denis Smirnov and Engelbert Mephu Nguifo

doc


IMG_2530 - Sept. 19, 2018 - PUBLICATION


IMG_2530.jpeg


IMG_2530 - Sept. 19, 2018 - PUBLICATION


IMG_25301.jpeg


IMG_2530 - Sept. 19, 2018 - PUBLICATION


IMG_25302.jpeg


ECML PhD Forum 2018 Presentation - July 26, 2018 - PUBLICATION

Title: Classification of multivariate time series based on bihistograms Authors : Angéline PLAUD, Engelbert Mephu, Jacques Charreyron This paper will be present during the PhD Forum of the ECML conference 10-14 septembre 2018 in Dublin.  


Grasp heuristic for time series compression with piecewise aggregate approximation - July 22, 2018 - PUBLICATION

Vanel Steve Siyou Fotso, Engelbert Mephu Nguifo, Philippe Vaslin published a new research paper entitled Grasp heuristic for time series compression with piecewise aggregate approximation in Journal : RAIRO, Operations Research


L’intelligence Artificielle est-elle multiforme ? - May 4, 2018 - PUBLICATION

doc

Présentation effectuée à l'Université Ouverte de Clermont-Ferrand


mephu_expose_IA_multiformes_180403-ilovepdf-compressed - May 4, 2018 - PUBLICATION


mephu_expose_IA_multiformes_180403-ilovepdf-compressed.pdf


LintelligenceArtificielleEst-elle-multiforme - May 3, 2018 - PUBLICATION


LintelligenceArtificielleEst-elle-multiforme.png


Paper - FUZZ-IEEE 2018 - March 28, 2018 - PUBLICATION

 Author(s):  Jerry Lonlac, Yannick Miras, Aude Beauger, Vincent Mazenod, Jean-Luc Peiry and Engelbert Mephu Nguifo Title:      An Approach for Extracting Frequent (Closed) Gradual Patterns Under Temporal Constraint has been accepted for presentation at the FUZZ-IEEE 2018 and for publication in the conference proceedings published by IEEE. This email provides you with all the information you require to complete your paper and submit it for inclusion in the proceedings.


Presentation - Denis Smirnov - Deeplearning - March 28, 2018 - PUBLICATION

doc  


slide - March 28, 2018 - PUBLICATION


slide.png


DL_interpretability - March 28, 2018 - PUBLICATION


DL_interpretability.pdf


Nomination as Senior Member of the ACM - Jan. 15, 2018 - PUBLICATION

Dear Engelbert Mephu Nguifo: On behalf of the ACM Senior Member Committee, I am pleased to inform you that your nomination as Senior Member of the ACM has been accepted. The Senior Member Committee gratefully acknowledges your efforts in submitting a nomination for review and hopes that your interest in the advanced member program will continue. As part of your recognition, you will be receiving a certificate and pin, and an annotated membership card with the designation of Senior Member. Your certificate and pin will be mailed to you within three to four weeks. Also, your name will appear on the ACM Senior Member page, http://awards.acm.org/senior-members. On behalf of ACM, we are delighted that you will be among the inductees honored with this designation and wish to congratulate you on this well-deserved recognition. Sincerely, Nancy M. Amato Chair, ACM Senior Member Committee


An Experimental Survey on Big Data Frameworks - Nov. 22, 2017 - PUBLICATION

Réunion MINERS du 22/11/2017, W. Inoubli présente une comparaison des outils de Big Data doc  


Slides-meeting-LIMOS-22-11-2017 - Nov. 22, 2017 - PUBLICATION


Slides-meeting-LIMOS-22-11-2017.pptx


presentation_miners_22112017 - Nov. 22, 2017 - PUBLICATION


presentation_miners_22112017.png


Slides-meeting-LIMOS-22-11-2017 - Nov. 22, 2017 - PUBLICATION


Slides-meeting-LIMOS-22-11-2017.pdf


Time Series Workshop @ ICML , August 2017 - Sydney, Australia - Sept. 20, 2017 - PUBLICATION

doc


Harbin Institute of technology - August 2017 - Shen Zhen, China - Sept. 20, 2017 - PUBLICATION

doc


ECMLPKDD, September 2017- SKOPJE, MACEDONIA - Sept. 20, 2017 - PUBLICATION

doc


Harbin_institute - Sept. 20, 2017 - PUBLICATION


Harbin_institute.jpeg


TSW@ICML2017 - Sept. 20, 2017 - PUBLICATION


TSW@ICML2017.jpeg


Ecml_pkdd_2017 - Sept. 20, 2017 - PUBLICATION


Ecml_pkdd_2017.jpeg


TSW@ICML2017 - Sept. 20, 2017 - PUBLICATION


TSW@ICML20171.jpeg


Réunion de l'équipe MINERS 26/27 Juillet 2017 - July 27, 2017 - PUBLICATION

[gallery]


WhatsApp Image 2017-07-26 at 18.26.05 - July 27, 2017 - PUBLICATION


WhatsApp-Image-2017-07-26-at-18.26.05.jpeg


WhatsApp Image 2017-07-26 at 18.26.04 - July 27, 2017 - PUBLICATION


WhatsApp-Image-2017-07-26-at-18.26.04.jpeg


WhatsApp Image 2017-07-26 at 17.12.45 - July 27, 2017 - PUBLICATION


WhatsApp-Image-2017-07-26-at-17.12.45.jpeg


WhatsApp Image 2017-07-26 at 17.12.43 - July 27, 2017 - PUBLICATION


WhatsApp-Image-2017-07-26-at-17.12.43.jpeg


WhatsApp Image 2017-07-26 at 17.12.41 - July 27, 2017 - PUBLICATION


WhatsApp-Image-2017-07-26-at-17.12.41.jpeg


WhatsApp Image 2017-07-26 at 17.12.38 - July 27, 2017 - PUBLICATION


WhatsApp-Image-2017-07-26-at-17.12.38.jpeg


WhatsApp Image 2017-07-26 at 17.12.36 - July 27, 2017 - PUBLICATION


WhatsApp-Image-2017-07-26-at-17.12.36.jpeg


WhatsApp Image 2017-07-26 at 17.12.34 - July 27, 2017 - PUBLICATION


WhatsApp-Image-2017-07-26-at-17.12.34.jpeg


WhatsApp Image 2017-07-26 at 17.12.31 - July 27, 2017 - PUBLICATION


WhatsApp-Image-2017-07-26-at-17.12.31.jpeg


WhatsApp Image 2017-07-26 at 17.12.27 - July 27, 2017 - PUBLICATION


WhatsApp-Image-2017-07-26-at-17.12.27.jpeg


WhatsApp Image 2017-07-26 at 17.12.25 - July 27, 2017 - PUBLICATION


WhatsApp-Image-2017-07-26-at-17.12.25.jpeg


WhatsApp Image 2017-07-26 at 17.12.24 - July 27, 2017 - PUBLICATION


WhatsApp-Image-2017-07-26-at-17.12.24.jpeg


WhatsApp Image 2017-07-27 at 13.57.39 - July 27, 2017 - PUBLICATION


WhatsApp-Image-2017-07-27-at-13.57.39.jpeg


WhatsApp Image 2017-07-27 at 13.57.39 (1) - July 27, 2017 - PUBLICATION


WhatsApp-Image-2017-07-27-at-13.57.39-1.jpeg


cropped-WhatsApp-Image-2017-07-26-at-18.26.051.jpg - July 27, 2017 - PUBLICATION

http://home.isima.fr/miners/wp-content/uploads/2017/07/cropped-WhatsApp-Image-2017-07-26-at-18.26.051.jpg
cropped-WhatsApp-Image-2017-07-26-at-18.26.051.jpg


hoto-Z redshift reconstruction using a constructive multilayer perceptron - April 27, 2017 - PUBLICATION
EWASS 2017, Prague, Czech republic
Title: Photo-Z redshift reconstruction using a constructive multilayer perceptron.
Authors: Cyrine Arouri, Nina Pelagie Bekono, Jean-Calvin Fopa, Rim Shayakhmetov, Sabeur Aridhi, Gaëlle Loosli-Bonnet, Cécile Roucelle, Norbert Tsopzé, Engelbert Mephu Nguifo
 

On Containment of Triclusters Collections Generated by Quantified Box Operators - April 27, 2017 - PUBLICATION
ISMIS 2017, Poland
TITLE: On Containment of Triclusters Collections Generated by Quantified Box Operators AUTHORS: Dmitrii Egurnov, Dmitry Ignatov and Engelbert Mephu Nguifo

Clustering flou non-supervisé sur de grands volumes de séquences d'ADN - April 27, 2017 - PUBLICATION

TITLE: Clustering flou non-supervisé sur de grands volumes de séquences d'ADN AUTHORS: Alexandre Bazin, Didier Debroas and Engelbert Mephu Nguifo


Mining Triclusters of Similar Values in Triadic Real-Valued Contexts - April 15, 2017 - PUBLICATION

Dmitry Egurnov, Dmitry Ignatov and Engelbert Mephu Nguifo, "Mining Triclusters of Similar Values in Triadic Real-Valued Contexts" International Conference on Formal Concept Analysis, Rennes, 2017


Vers une stratégie de réduction de la base de clauses apprises fondée sur la relation de dominance - April 15, 2017 - PUBLICATION

Jerry Lonlac and Engelbert Mephu Nguifo, "Vers une stratégie de réduction de la base de clauses apprises fondée sur la relation de dominance", Treizièmes Journées Francophones de Programmation par Contraintes, Lens, juin 2017.


Big Graph Mining : Frameworks and Techniques - Feb. 28, 2017 - PUBLICATION
Invited talk at BigSkyEarth Workshop, Sopron (Hungary), February 23-24, 2017
Title : Big Graph Mining - Frameworks and Techniques
Speaker : Engelbert Mephu Nguifo
doc

aridhi_mephu_slides_part1 - Feb. 28, 2017 - PUBLICATION


aridhi_mephu_slides_part1.pdf


aridhi_mephu_slides_part2 - Feb. 28, 2017 - PUBLICATION


aridhi_mephu_slides_part2.pdf


Extraction de Motifs Graduels (Fermés) Fréquents Sous Contrainte de la Temporalité - EGC 2017 - Feb. 27, 2017 - PUBLICATION


Parameter Free Dynamic Time Warping - ROADEF 2017 - Feb. 27, 2017 - PUBLICATION

doc


slides_EGC_Jerry - Feb. 27, 2017 - PUBLICATION


slides_EGC_Jerry-1.pdf


extraction_de_motifs_graduels - Feb. 27, 2017 - PUBLICATION


extraction_de_motifs_graduels.png


parameter_free_piecewise_dtw - Feb. 27, 2017 - PUBLICATION


parameter_free_piecewise_dtw.png


Vanel_presentation_roadef-2017 - Feb. 27, 2017 - PUBLICATION


Vanel_presentation_roadef-2017.pdf


big_graph_mining - Feb. 27, 2017 - PUBLICATION


big_graph_mining.png


Dmitrii Egurnov, lauréat of the competition of research papers in Computer Science among Masters students - Feb. 8, 2017 - PUBLICATION

doc


nirs - Feb. 8, 2017 - PUBLICATION


nirs.jpg


nirs - Feb. 8, 2017 - PUBLICATION


nirs1.jpg


About Miners - Feb. 8, 2017 - PUBLICATION

Equipe MINERS 2017

Superviseur

  • Pr. Engelbert Mephu Nguifo

Post-Doctorant

  • Dr. Alexandre Bazin
  • Dr. Jerry Lonlac

Doctorants

  • Jocelyn De Goer
  • Vanel SIYOU
  • Nestor Koueya
  • Angeline Pauld

 


Remise des diplômes de Doctorat, chercheurs de l'équipe MINERS - Jan. 30, 2017 - PUBLICATION

[gallery]


20131213_190627 - Jan. 30, 2017 - PUBLICATION


20131213_190627-e1485804351817.jpg


20131213_190658 - Jan. 30, 2017 - PUBLICATION


20131213_190658-e1485804432308.jpg


20131213_190707 - Jan. 30, 2017 - PUBLICATION


20131213_190707-e1485804473418.jpg


20131213_190817-ConvertImage - Jan. 30, 2017 - PUBLICATION


20131213_190817-ConvertImage-e1485805040102.jpg


Presentation du Pr. Mehpu au seminaire UFMG à BeloHorizonte - Dec. 2, 2016 - PUBLICATION

Première partie Deuxième partie


mephu_seminaire_UFMG_BeloHorizonte_021216_compact - Dec. 2, 2016 - PUBLICATION


mephu_seminaire_UFMG_BeloHorizonte_021216_compact.pdf


mephu_seminaire_UFMG_BeloHorizonte_021216_part1_compact - Dec. 2, 2016 - PUBLICATION


mephu_seminaire_UFMG_BeloHorizonte_021216_part1_compact.pdf


baniere.png - Nov. 28, 2016 - PUBLICATION

http://home.isima.fr/miners/wp-content/uploads/2016/11/baniere.png
baniere.png


From Bioinformacs to Astroinformacs curriculum : A French experience - Oct. 28, 2016 - PUBLICATION

Engelbert MEPHU NGUIFO BigSkyEarth Cost Action meeting Sorrento (Italy), October 24-­‐25, 2016 La présentation est disponible ici : partie 1 partie2


WhatsApp Image 2016-09-01 at 20.05.554 - Oct. 28, 2016 - PUBLICATION


WhatsApp-Image-2016-09-01-at-20.05.554.jpeg


WhatsApp Image 2016-09-01 at 20.05.553 - Oct. 28, 2016 - PUBLICATION


WhatsApp-Image-2016-09-01-at-20.05.553.jpeg


WhatsApp Image 2016-09-01 at 20.05.552 - Oct. 28, 2016 - PUBLICATION


WhatsApp-Image-2016-09-01-at-20.05.552.jpeg


WhatsApp Image 2016-09-01 at 20.05.55 - Oct. 28, 2016 - PUBLICATION


WhatsApp-Image-2016-09-01-at-20.05.55.jpeg


mephu_slides_From_Bio_To_Astro_Informatics_part1 - Oct. 28, 2016 - PUBLICATION


mephu_slides_From_Bio_To_Astro_Informatics_part1.pdf


mephu_slides_From_Bio_To_Astro_Informatics_part2 - Oct. 28, 2016 - PUBLICATION


mephu_slides_From_Bio_To_Astro_Informatics_part2.pdf


Soutenance des étudiants en master année académique 2015/2016 - Sept. 8, 2016 - PUBLICATION

[gallery]


Big Graph Mining: Frameworks and Techniques - July 26, 2016 - PUBLICATION

Sabeur Aridhi and Engelbert Mephu Nguifo published a new research paper entitled Big Graph Mining: Frameworks and Techniques in Journal: Big Data Research, Elsevier  


Papier de Manel présenté à JOBIM - June 10, 2016 - PUBLICATION

Le papier de Manel a été accepté pour une présentation à JOBIM 2016


workshop : Big Data, Large-Scale Optimization and Applications - June 9, 2016 - PUBLICATION

This workshop first intends to bring together, on June 06 and 07, mathematicians and computer scientists from Vancouver, British Columbia and Clermont-Ferrand, France, to exchange new ideas and discuss research directions in the fields of big-data analytics and large-scale optimization. Through an industrial day, organized on June 09, the workshop will also gather together mathematicians and computer scientist from both academia and industry to confront challenging problems in industrial big data and large-scale optimization. The goals of this workshop are twofold. First, it aims to set up a collaborative network of Canadian and French researchers in mathematics and computer science. Secondly, it intends to identify promising new research projects with an emphasis on big data, optimization problems of increasingly greater scale and their applications. Banniere


MINERS intervient au comité scientifique et pédagogique et au mini-forum d'Exposciences le 26/05/2016 @ Poyldôme @ Clermont-Ferrand - May 28, 2016 - PUBLICATION

Cette année Alexandre Bazin et Jerry Lonlac deux postdoctorants en informatique appartenant au groupe de travail MINERS ont participé aux journées scientifiques organisées à Clermont-Ferrand.

  •  Alexandre a animé le comité scientifique et pédagogique le jeudi matin de 9h à 12h, il a échangé avec des jeunes sur leurs projets et la démarche scientifique à utiliser;
  •  Jerry a  animé avec deux autres enseignants-chercheurs de L'UBP le mini-forum  le jeudi de 14h30 à 16h00 : il s'agissait d'un échange libre avec les jeunes sur le thème "intelligence artificielle" .

Ce fut un moment privilégié d'échange qui, nous l'espérons, a planté la petite graine de l'amour de la science dans le cœur des jeunes collégiens et lycéens présents./>


wwwAfrica2016 - April 21, 2016 - PUBLICATION

Aims and scope

wwwAfrica2016  is a special event of www2016 with three main objectives:

  1. provide a meeting platform for African web developers and researchers;
  2. stimulate the development of e-Gov, e-Health, e-Education and Smart-cities via the link between African web actors and deciders in African countries;
  3. stimulate the research publication on web related topics to African issues and help African scientists access to world-class conferences.

Resources are being solicited to support the fees for a limited number of African students and scientists.


Boolean Factors Based Artificial Neural Network - April 21, 2016 - PUBLICATION

Paper accepted to IJCNN'2016 for Oral presentation International Joint Conference on Neural Networks "Boolean Factors Based Artificial Neural Network" Lauraine Tiogning Kueti, Norbert Tsopze, Cezar Mbiethieu, Engelbert Mephu-Nguifo and Laure Pauline Fotso


Conférence francophone en Apprentissage 2016 - Feb. 10, 2016 - PUBLICATION

Depuis 1999, la conférence francophone sur l’apprentissage automatique (CAp) est le rendez-vous annuel incontournable de la communauté scientifique travaillant dans le domaine de l’Apprentissage Automatique. L'édition 2016 aura lieu à Marseille du 4 au 7 juillet. Les articles doivent être soumis avant le 10 avril 2016 via le système easychair (pas encore ouvert). L’Apprentissage Automatique est une discipline de l’informatique, liée à l'intelligence artificielle, qui s’intéresse au développement de modèles et d’algorithmes permettant à la machine d’évoluer par apprentissage et ainsi de remplir des tâches qu'il est difficile ou impossible de remplir par des moyens algorithmiques plus classiques. L’Apprentissage Automatique est au cœur de la science des données qui a émergé ces dernières années comme un secteur industriel en très forte progression intimement lié à l’explosion des données et des besoins associés (phénomène résumé sous la dénomination de Big Data).


Journées Ouvertes en Biologie, Informatique et Mathématiques - Feb. 10, 2016 - PUBLICATION

La 17ème édition des Journées Ouvertes en Biologie, Informatique et Mathématiques (JOBIM) se déroulera du 28 au 30 juin sur le site Jacques Monod du campus de l'ENS à Lyon. Cette conférence, placée sous l'égide de la Société Française de Bioinformatique (SFBI), constitue le rendez-vous annuel de la communauté francophone en bioinformatique. Le service en ligne de soumission des résumés ouvrira le 1er mars et la clôture des soumissions est fixée au 14 avril. Toutes les soumission doivent être effectuées sur le site de la conférence et nécessitent de disposer au préalable d'un compte sur le service Sciencesconf.org. La procédure de création de compte peut etre accédéee à partir de ce lien.


Award - Jan. 26, 2016 - PUBLICATION

Ekaterina was awarded the third prize for her Master's thesis (all disciplines) by the  High School of Economics - Russia   in 2015. [caption id="attachment_449" align="aligncenter" width="223" caption="Award - Ekaterina"]doc[/caption]  

 

photo_Ekaterina_Award_Master_HSE - Jan. 26, 2016 - PUBLICATION


photo_Ekaterina_Award_Master_HSE.jpg


photo_Ekaterina_Award_Master_HSE (1) - Jan. 26, 2016 - PUBLICATION


photo_Ekaterina_Award_Master_HSE-1.jpg


EGC 2016 - Jan. 13, 2016 - PUBLICATION

Le 19 janvier 2016, dans le cadre de EGC à Reims, la deuxième journée EXTRACTION ET GESTION DES CONNAISSANCES et INTELLIGENCE ARTIFICIELLE réunit les deux communautés autour du thème des « Données Participatives et Sociales ». Ces données sont au coeur de nouveaux défis tant au niveau de la fouille de données que de l'intelligence artificielle. Les travaux de la littérature sont généralement associés à l'une des deux communautés, sans montrer le lien entre elles. Cet atelier cherche particulièrement à focaliser sur ce lien du point de vue représentation qu'analyse. L’atelier se tient dans le cadre de la conférence EGC 2016 à à IUT de Reims-Chalons-Charleville, Chemin des Rouliers, 51100 Reims. Les inscriptions se font sur le site de la conférence (http://egc2016.univ-reims.fr/index.php/Inscription). Plus d’information sur le programme : http://www.afia.asso.fr/tiki-download_file.php?fileId=268

 

The miners meeting is scheduled on Thursday, September 24 at 3pm (French time). Room D010 - Sept. 22, 2015 - PUBLICATION

For those abroad, here is a link to join the meeting. http://classevirtuelle.univ-bpclermont.fr/connect/3d24328df05891e468444b85263b6957


ICDM 2015 IEEE International Conference on Data Mining - Sept. 11, 2015 - PUBLICATION

The IEEE International Conference on Data Mining series (ICDM) has established itself as the world's premier research conference in data mining. It provides an international forum for presentation of original research results, as well as exchange and dissemination of innovative, practical development experiences. The conference covers all aspects of data mining, including algorithms, software and systems, and applications. ICDM draws researchers and application developers from a wide range of data mining related areas such as statistics, machine learning, pattern recognition, databases and data warehousing, data visualization, knowledge-based systems, and high performance computing. By promoting novel, high quality research findings, and innovative solutions to challenging data mining problems, the conference seeks to continuously advance the state-of-the-art in data mining. Besides the technical program, the conference features workshops, tutorials, panels.

Contest Starts: Jun 01, 2015 Paper submission: Jun 03, 2015 Tutorial proposals: Jul 13, 2015 Workshop and demo submission: Jul 20, 2015


SFC 2015 : XXII ÈMES RENCONTRES DE LA SOCIÉTÉ FRANCOPHONE DE CLASSIFICATION 9-11 SEPT. 2015 NANTES (FRANCE) - Sept. 6, 2015 - PUBLICATION

PRÉSENTATION La SFC organise chaque année les Rencontres de la Société Francophone de Classification qui ont pour objectifs de présenter des résultats récents, des applications originales en classification ou dans des domaines connexes, de favoriser les échanges scientifiques à l'intérieur de la société et de faire connaître à divers partenaires extérieurs les travaux de ses membres. Soumission L’acceptation des exposés se fait sur des résumés étendus [ici]. La date limite d’envoi est le 13 mai 21 mai 2015. Une publication sous forme de post-actes est prévue. Une publication sous forme de post-actes est prévue dans la Revue des Nouvelles Technologies de l'nformation (RNTI). L'appel à communication pour les post-actes sera fait à l'issue du colloque. Programme


Programme_provisoire - Sept. 6, 2015 - PUBLICATION


Programme_provisoire.pdf


EDBT 2016 CALL FOR PAPERS - July 19, 2015 - PUBLICATION

EDBT 2016 March 15-18, 2016 - Bordeaux, France CALL FOR PAPERS ================ The International Conference on Extending Database Technology is a leading international forum for database researchers, practitioners, developers, and users to discuss cutting-edge ideas, and to exchange techniques, tools, and experiences related to data management. We encourage submissions or research contribution relating to all aspects of data management defined broadly, and particularly encourage work on topics of emerging interest in the research and development communities. Topics of Interest —————————————————— We welcome papers on topics including, but not limited to, the following: o Availability, Reliability, and Scalability o Tuning, Monitoring, Benchmarking and Performance Evaluation o Big Data Storage, Processing and Transformation o Data Curation, Annotation and Provenance o Data Management in Clouds o Complex Event Processing and Data Streams o Data Mining and Knowledge Discovery o Data Warehousing, Large-Scale Analytics, and ETL Tools o Emerging Hardware and In-memory Database Architecture and Systems o Heterogeneous Databases, Data Integration and Interoperability o Middleware and Workflow Management o Parallel, Distributed and Grid Data Management o Privacy, Trust and Security in Databases o Indexing, Query Processing and Optimization o Semantic Web and Knowledge Management o Sensor and Mobile Data Management o Scientific and Statistical Databases o Social Networks and Crowdsourcing o Graph Databases o Spatial, Temporal, and Geographic Databases o Text Databases and Information Retrieval o Semi-Structured and Linked Data Management o Modeling, Mining and Querying User Generated Content o Data Quality o User Interfaces and Data Visualization Research papers will be selected for inclusion in the program on the basis of their originality, significance and rigor. Selected best papers will be considered for submission to a special issue of TODS. Important Dates for Research and Vision Papers —————————————————————————————————————————————— o Abstract submission deadline: September 21, 2015, 4:59pm CET o Paper submission deadline: September 28, 2015, 4:59pm CET o Notification: December 10, 2015 Submission Guidelines ————————————————————— All aspects of the submission and notification process will be handled electronically. All papers should be submitted in electronic format using the conference submission site  Research papers should be submitted to the Research Track, while vision papers to the Vision Track. EDBT 2016 submissions are reviewed following a single blind review process, meaning, you do not need to hide authors’ names and affiliations. EDBT Program Committee Chair ————————————————————————————— Evaggelia Pitoura, University of Ioannina, Greece EDBT Program Committee Members ———————————————————————————————— Bernd           Amann   Universite Pierre et Marie Curie, France Walid           Aref    Purdue University, USA Sourav  S       Bhowmick        Nayang Technology University, Singapore Michael         Bohlen  University of Zurich, Switzerland Klemens         Bohm    Karlsruhe Institute of Technology, Germany Francesco               Bonchi  Yahoo! Labs, Spain Angela          Bonifati        Lille 1 University, France Philippe                Bonnet  ITU, Copenhagen, Denmark Luc             Bouganim        INRIA, France Nieves          Brisaboa        Universidad de La Coruna, Spain Reynold         Cheng   University og Hong Kong Beng            Chin Ooi        National University of Singapore, Singapore Vassilis                Christophides   University of Crete, Greece Panos   K       Chrysanthis     University of Pittsburgh, USA Paolo           Ciaccia University of Bologna, Italy Philippe                Cudre-Mauroux   University of Freibourg, Switzerland Bin             Cui     Peking University, China Khuzaima                Daudjee University of Waterloo, Canada Antonios                Deligiannakis   Technical University of Crete, Greece Elena           Ferrari University of Insubria, Italy Peter           Fischer Uni Freiburg, Germany Helena          Galhardas       University of Lisbon. Portugal Johann          Gamper  Free University of Bolzen-Bolzano, Italy Minos           Garofalakis     Technical University of Crete, Greece Floris          Geerts  University of Antwerp, Belgium Jiawei          Han     UI Urbana Champaign, USA Takahiro                Hara    Osaka University, Japan Thomas          Heinis  Imperial College, UK Arantza         Illarramendi    Universidad del Paes Vasco, Spain George          Kollios Boston University, USA Georgia         Koloniari       University of Macedonia, Greece Yiannis         Kotidis Athens University of Business and Economics, Greece Nick            Koudas  University of Toronto, Canada Georg           Lausen  Uni Freiburg, Germany Wang-Chien              Lee     Penn State University, USA Wolfgang                Lehner  TU Dresden, Germany Hong-Va         Leong   Hong Kong Polytechnik University, China Roy             Levin   IBM Research, Israel Feifei          Li      University of Utah, USA Xuemin          Lin     University of New South Wales, Australia Eric            Lo      Honk Kong Polytechnik, China Norman                  May     SAP, Germany Sebastian               Michel  TU Kaiserslautern, Germany Kjetil          Norvag  Norwegian University of Science and Technology, Norway Ippokratis              Pandis  Cloudera, USA Paolo           Papotti         QCRI, Qatar Marta           Patino  Polit?cnica de Madrid, Spain Torben  B       Pedersen        University of Aalborg, Denmark Peter           Pietzuch        Imperial College, UK Maya            Ramanath        IIT Delhi, India Matthias                Renz    Ludwig-Maximilians-University, Germany Rodolfo         Resende Universidade Federale de Minas Gerais, Brazil Tore            Risch   Uppsala University, Sweden Pierangela              Samarati        Universita degli Studi di Milano, Italy Mohamed         Sarwat  Arizona State University, USA Kai-Uwe         Sattler TU Ilmenau, Germany Marc            Scholl  University of Konstanz, Germany Heiko           Schuldt University of Basel, Switzerland Assaf           Schuster        Technion, Israel Thomas          Seidl   RWTH Aachen University, Germany Jianwen                 Su      UC Santa Barbara, USA Peter           Triantafillou   University of Glasgow, UK Yannis          Velegrakis      University of Trento, Italy Stratis         Viglas  University of Edinburgh, UK Jef             Wijsen  University of Mons (UMONS), Belgium Yoshitaka               Yamamoto        University of Yamanashi, Japan Carlo           Zaniolo         UCLA, USA Demetrios               Zeinalipour-Yazti       University of Cyprus, Cyprus Wenjie          Zhang   University of New South Wales, Australia


Réunion du groupe miner Jeudi16-07-2015 à 14:00 en D010 - July 16, 2015 - PUBLICATION

Vous êtes cordialement invités à la réunion de fin d'année du groupe miner qui aura lieu Jeudi le 16-07-2015 à 14H en D010 (ISIMA)


Seminaire LIMOS, Mardi 30 juin à 10h30 en Amphi Garcia - June 19, 2015 - PUBLICATION

Quand ? --  Mardi 30 juin à 10h30 Où ? -- Amphi Garcia (Batiment E, ISIMA) Quoi ? --  Séminaire donné par le Professeur Philippe LENCA  de Telecom Bretagne, Brest Titre : Sur quelques propriétés des mesure de qualité des règles d'association Résumé : Nous présenterons une synthèse, nécessairement partielle, de travaux concernant les mesures de qualité des règles d’association et des règles d’association de classe en présentant les principaux critères d’évaluation des mesures et en illustrant le rôle de chacun de ces critères dans le comportement des mesures. Nous illustrerons le lien qui existe entre les propriétés des mesures sur les critères retenus et leur comportement sur un certain nombre de bases de règles. Une attention particulière sera portée aux propriétés algorithmiques des mesures afin de pouvoir extraire les motifs intéressants en travaillant directement sur la mesure considérée, sans fixer de seuil de support, ce qui permet d’accéder aux pépites de connaissances. Nous exhiberons des conditions algébriques sur la formule d’une mesure qui assurent de pouvoir associer un critère d’élagage à la mesure considérée.


Towards an efficient estimation of ECM parameters - June 19, 2015 - PUBLICATION


Presentation-Intelligent-ECM.pdf


Réunion du groupe miner Mercredi 17-06-2015 à 14:00 en D010 - June 17, 2015 - PUBLICATION
Vous êtes cordialement invités à la présentation du travail de Ekaterina et Hayfa Mercredi 17 juin 2015 à 14:00  dans la salle D010.
 
Sujet:
Ekaterina :  "Vers une estimation efficace des paramètres de ECM" Hayfa : "Un algorithme de hachage perceptuel pour l'indexation et la recherche de similarités dans une base de données de séquences ADN"

-- You are cordially invited to the presentation of Ekaterina and Hayfa , which will take place on Wednesday, June 17, 2015 at 14:00 a.m. in room D010 Topic: Ekaterina :"Towards an efficient estimation of ECM parameters" Hayfa : "A perceptual hash algorithm for indexing and similarity search in a database of DNA sequences"


AAAI-16 — Thirtieth AAAI Conference on Artificial Intelligence - June 2, 2015 - PUBLICATION

AAAI-16  welcomes submissions reporting research that advances artificial intelligence, broadly conceived. The conference scope includes all subareas of AI, including (but not limited to) traditional topics such as search, machine learning, planning, knowledge representation, reasoning, natural language processing, robotics and perception, and multiagent systems.

Timetable for Authors

  • July 1, 2015 – September 10, 2015: Authors register on the AAAI web site
  • September 10, 2015: Electronic abstracts due
  • September 15, 2015: Electronic papers due
  • October 28-30, 2015: Author feedback about initial reviews
  • November 12, 2015: Notification of acceptance or rejection
  • December 1, 2015: Camera-ready copy due

Etat d'avancement du travail de thèse - May 21, 2015 - PUBLICATION

Quand ?  --  Jeudi 21/05/2015 Où ? --  ISIMA D010 Quoi ? -- Présentation de l'état d'avancement du tavail de thèse de Vanel SIYOU Sujet : Extraction de connaissances et incertitudes à partir de mesures effectuées lors de la locomotion en Fauteuil Roulant Manuel Encadrant : Englebert Mephu-Nguifo et Philippe Vaslin


etatD'avancement-21-05-2015 - May 21, 2015 - PUBLICATION


etatDavancement-21-05-2015.pdf


IEEE Big Data 2015 Call for Paper - May 18, 2015 - PUBLICATION
Call for Papers
Oct 29-Nov 1  2015,  Santa Clara, CA, USA
 
Paper Submission:
Please submit a full-length paper (upto 10 page IEEE 2-column format) through the online submission system.
Papers should be formatted to IEEE Computer Society Proceedings Manuscript Formatting Guidelines (see link to "formatting instructions" below).
 
Formatting Instructions, 8.5" x 11" (DOC, PDF), LaTex Formatting Macros
 
Important Dates:
Electronic submission of full papers: July 1, 2015
Notification of paper acceptance: Sept 4, 2015
Camera-ready of accepted papers: Sept 25, 2015
Conference: October 29-Nov 1, 2015
 
 

Towards more targeted recommendations in folksonomies - May 11, 2015 - PUBLICATION

Présentation de Mohamed Nader Jelassi lors de la conférence CaRR@ICIR15 Encadrant :  Engelbert Mephu-Nguifo,  Sadok Ben Yahia


expose carr 2015 - May 11, 2015 - PUBLICATION


expose-carr-2015.pdf


PFIA 2015 : Rennes, au coeur de l’intelligence de demain - May 8, 2015 - PUBLICATION

Du 29 juin au 3 juillet, à Rennes, se tiendra l’édition 2015 de Plate-Forme Intelligence Artificielle (PFIA), un événement organisé par Inria et l’AFIA (l’Association Française pour l’Intelligence Artificielle). Communiqué de presse


PFIA 2015 Communiqué de presse - May 8, 2015 - PUBLICATION


PFIA-2015-Communiqué-de-presse.pdf


ICML - 06/11 July 2015 Lille Grand Palais - April 28, 2015 - PUBLICATION

ICML is the leading international machine learning conference and is supported by the International Machine Learning Society (IMLS). Important Dates

  • 6 Feb. Paper submission deadline
  • 27-31 Mar. Author feedback period
  • 25 Apr. Decision notification
  • 6 jul. Tutorials
  • 7-9 jul. Main Conference
  • 10-11 Jul. Workshops

IJCAI, Buenos Aires, 27th July 2015 - April 10, 2015 - PUBLICATION

The aim of this workshop called Bioinformatics and Artificial Intelligence (BAI) is to bring together active scholars and practionners in the frontier of Artificial Intelligence (AI) and Bioinformatics.


Etude de la scabilité des méthodes d'optimisation d'architecture des réseaux de neurones. Application à l'estimation des redshifts photométriques - April 9, 2015 - PUBLICATION

Etat d'avancement du travail - 09/04/2015 -  Nina Bekono Encadrant : Engelbert Mephu-Nguifo Presentation


International Conference on Machine Learning - (11-15) July 2015 - LILLE GRAND PALAIS - April 9, 2015 - PUBLICATION

ICML is the leading international machine learning conference and is supported by the International Machine Learning Society (IMLS).


Expose - April 9, 2015 - PUBLICATION


Expose.pdf


Call for Papers - IEEE DSAA (Data Science and Advanced Annalytics) 2015 - March 26, 2015 - PUBLICATION

Please find below the Call for Papers for the IEEE 2015 International Conference on Data Science and Advanced Analytics (DSAA'2015), to be held on 19-21 October 2015 in Paris, France. Website


ECMLPKDD 2015 : Call for Papers, Tutorials and Workshops - Feb. 20, 2015 - PUBLICATION

The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD) will take place in Porto, Portugal, from September 7th to 11th, 2015


Méthodologie de la recherche - Feb. 19, 2015 - PUBLICATION

Conseils sur la méthodologie de la recherche, la rédaction scientifique et la présentation de ses résultats


Réunion MINERS - Feb. 13, 2015 - PUBLICATION

État d'avancement du travail de Thèse de J. DE GOËR
2015-02-12-MINERS.pdf


Réunion MINERS du 12 février 2015 - Feb. 13, 2015 - PUBLICATION

Point d'avancement du travail de Thèse de Jocelyn DE GOËR Titre: "Stockage, indexation et comparaison d’une grande quantité́ de données génomiques à l’aide d’algorithmes de traitement d’images dans un environnement d’exécution NoSQL et GPU" Présenté par: Jocelyn DE GOËR Sous la direction de: Pr. Engelbert Mephu Nguifo et Pr. Myoung-Ah KANG Consulter la présentation au format PDF ICI  


mephu_seminaire_UQAM_LATECE_10dec14_vf.compressed - Dec. 11, 2014 - PUBLICATION


mephu_seminaire_UQAM_LATECE_10dec14_vf.compressed.pdf


Fouille de motifs et Préférences - Dec. 10, 2014 - PUBLICATION

Contexte : dixième séminaire de l'automne 2014   du LATECE (Laboratory for research on Technology on Ecommerce; Montreal, Quebec, Canada) Orateur : M. Engelbert Mephu Nguifo, professeur d'informatique à l'université Blaise Pascal (Clermont-Ferrand II, France)   Titre : Fouille de motifs et Préférences Résumé Pattern mining is still a challenging task in data mining and machine learning, with many applications in biology, physics, chemistry, marketing, etc. One of the bottleneck in such problem comes from the huge number of output generated by any of the several standard algorithms. Introducing user preferences is a direction to tackle such limitations. In this talk, I will review state of the art on preferences in pattern mining. I will put more focus on skyline pattern mining, and more precisely on undominated association rules   slides de la présentation qui a eu lieu  Mer. 10 Décembre 2014 à 12:15 au PK 5115


Mephu_Debroas_CPER2014-appelCandidature-PostDoc - Oct. 22, 2014 - PUBLICATION


Mephu_Debroas_CPER2014-appelCandidature-PostDoc.pdf


ALLOCATION POST-DOCTORALE – 18 mois - Oct. 22, 2014 - PUBLICATION

Étude de la biosphère rare microbienne par une approche in silico : nouvelle méthode de classification ensembliste et modélisation   La détermination de la structure des communautés (richesse, abondance, diversité, composition) d'un écosystème est un enjeu central en écologie et donc en écologie microbienne. Elle repose sur la détermination des OTUs (i.e. espèces microbienne). Or, cette détermination varie en fonction des méthodes de classification et n'est pas associée à une probabilité d’appartenance à une classe. La difficulté réside généralement soit dans le langage de représentation associé, soit dans le mécanisme d’inférence mis en œuvre. Le LMGE peut être considéré par la nature de sa production scientifique comme un laboratoire leader au niveau international dans la description de la biosphère rare. Le LIMOS a développé ces dernières années des méthodes originales pour traiter le problème de la classification non supervisée en présence d’incertitudes, et pour la prise en compte des préférences de l’utilisateur pour l’extraction de connaissances. L'association de l'expertise d'un laboratoire reconnu dans l'utilisation du séquençage haut débit pour étudier les communautés microbiennes (LMGE) à celle d'un laboratoire d'informatique (LIMOS) est un atout original dans ce domaine de recherche. La diffusion du travail se fera sous la forme de communications académiques. Les avancées technologiques  (i.e. classification) seront intégrées au site web ePANAM  en cours d'élaboration. La mise en place de tels sites internet a un fort impact sur la communauté scientifique et donc sur la promotion du savoirfaire d'une région comme le montre l'utilisation du site METAVIR  dans le monde entier. La coordination sera assurée par Engelbert Mephu-Nguifo et Didier Debroas et se traduira par des réunions régulières organisées par le post-doctorant recruté. Une Présentation du sujet de recherche, des objectifs à atteindre et du calendrier prévisionnel de réalisation est disponible  ici


THE 19TH PACIFIC-ASIA CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING - Sept. 22, 2014 - PUBLICATION

The Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD) is a leading international conference in the areas of knowledge discovery and data mining (KDD).


2015 SIAM International Conference on DATA MINING - Sept. 22, 2014 - PUBLICATION

The SDM conference provides a venue for researchers who are addressing these problems to present their work in a peer-reviewed forum. It also provides an ideal setting for graduate students and others new to the field to learn about cutting-edge research by hearing outstanding invited speakers and attending presentations and tutorials (included with conference registration). A set of focused workshops is also held on the last day of the conference. The proceedings of the conference are published in archival form, and are also made available on the SIAM web site.


Conférences 2014 - Aug. 26, 2014 - PUBLICATION

Neural Information Processing Systems Foundation 2014 The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2014 ECCB'14, the 13th European Conference on Computational Biology

 


graphx - July 19, 2014 - PUBLICATION


graphx.pdf


Etat d'avancement du travail - July 19, 2014 - PUBLICATION

Présenté par: Takwa Ben Smida Sous la direction de:  Dr. Sabeur Aridhi Sous la supervision de :   Pr. Engelbert Mephu Nguifo   présentation


CLA Presentation_GRISSA - July 15, 2014 - PUBLICATION


CLA-Presentation_GRISSA.pdf


Boolean factors as a means of clustering of interestingness measures of association rules - July 15, 2014 - PUBLICATION

Authors: Radim Belohlavek, Dhouha Grissa, Sylvie Guillaume, Engelbert Mephu Nguifo, Jan Outrata presentation


Présentation_PetaSky Cyrine2_partie1 - July 12, 2014 - PUBLICATION


Présentation_PetaSky-Cyrine2_partie1.pdf


Présentation_PetaSky Cyrine2_partie2 - July 12, 2014 - PUBLICATION


Présentation_PetaSky-Cyrine2_partie2.pdf


Présentation_PetaSky Cyrine2_partie3 - July 12, 2014 - PUBLICATION


Présentation_PetaSky-Cyrine2_partie3.pdf


ESTIMATION DES REDSHIFTS PHOTOMERIQUES AVEC LES RESEAUX DE NEURONES - July 12, 2014 - PUBLICATION

Présentée par : Cyrine  AROURI Participants :  Engelbert MEPHU NGUIFO, Cécile ROUCELLE,  Gaëlle BONNET LOOSLI, Sabeur ARIDHI présentation : partie 1 présentation : partie 2 présentation : partie 3


Presentation_miner - July 11, 2014 - PUBLICATION


Presentation_miner.pdf


Modèle paramétrique et non paramétrique de locomotion en Fauteuil Roulant Manuel - July 11, 2014 - PUBLICATION

présentation


communityDection - July 8, 2014 - PUBLICATION


communityDection.pdf


analyseDiversiteMicrobienneParSequencage_1 - July 8, 2014 - PUBLICATION


analyseDiversiteMicrobienneParSequencage_1.pdf


analyseDiversiteMicrobienneParSequencage_2 - July 8, 2014 - PUBLICATION


analyseDiversiteMicrobienneParSequencage_2.pdf


analyseDiversiteMicrobienneParSequencage_3 - July 8, 2014 - PUBLICATION


analyseDiversiteMicrobienneParSequencage_3.pdf


Aridhi et al., 2014_1 - July 8, 2014 - PUBLICATION


Aridhi-et-al.-2014_1.pdf


Aridhi et al., 2014_2 - July 8, 2014 - PUBLICATION


Aridhi-et-al.-2014_2.pdf


A novel MapReduce-based approach for distributed frequent subgraph mining - July 8, 2014 - PUBLICATION
 Authors : Sabeur Aridhi, Laurent d’Orazio, Mondher Maddouri and Engelbert Mephu Nguifo
Date : July 04, 2014
 

Miners Seminar on July 8, 2014 - July 8, 2014 - PUBLICATION

The following master's students will give a 20-30mn talk (French or English). 09:30am-  Takwa Ben Smida 10:00am-  Vanel Steve Siyou Fotso

10:30am-  break

11:00am-  Andrey Shestakov 11:30am-  Cyrine Arouri 12:00am-  Nestor Koueya (distance talk) 12:30am-  Lunch 02:00 - 05:00pm-  Opening hours for PhD talk proposal Najwa TAIB, Jocelyn DE GOER, Dhouha GRISSA


Analyse de la diversité microbienne par séquençage massif - July 8, 2014 - PUBLICATION

Auteur : Najwa TAIB presentation, partie 1 presentation, partie 2 presentation, partie 3  


Semi-average criterion in community detection problems - July 8, 2014 - PUBLICATION

Author : Shestakov Andrey Scientific Supervisors: Boris Mirkin (HSE), Engelbert Mephu Nguifo (LIMOS) file : community detection        


exposeIC5-5-14 - June 16, 2014 - PUBLICATION


exposeIC5-5-14.pdf


exposeIC5-5-14 - June 16, 2014 - PUBLICATION


exposeIC5-5-141.pdf


exposeIC5-5-14 - June 16, 2014 - PUBLICATION


exposeIC5-5-142.pdf


exposeIC5-5-14 - June 16, 2014 - PUBLICATION


exposeIC5-5-143.pdf


exposeIC5-5-14 - June 16, 2014 - PUBLICATION


exposeIC5-5-144.pdf


Vers des recommandations plus personnalisées dans les folksonomies - June 16, 2014 - PUBLICATION

Plusieurs approches ont été proposées dans la littérature pour personnaliser les recommandations dans les folksonomiesDans ce papier, nous considérons une nouvelle dimension dans les folksonomies comme information supplémentaire pour offrir aux utilisateurs une recommandation plus ciblée et mieux conforme à leurs besoins. Cela passe par un regroupement des utilisateurs ayant des intérêts communs sous forme de structures appelées quadri-concepts. Notre approche, dans laquelle nous répondons également au challenge de cold start, est ensuite évaluée sur deux jeux de données du monde réel, MovieLens et BookCrossing. Cette évaluation comprend une mesure de la précision et du rappel, une évaluation sociale ainsi que plusieurs métriques d'évaluation comme la diversité, la couverture ou la scalabilité.   exposeIC5-5-14.


Talk at French conference on DataWarehouse 2014 - June 2, 2014 - PUBLICATION

Nestor Koueya, Sandro Bimonte, Engelbert Mephu Nguifo: Une nouvelle approche d’estimation pour les entrepôts de données multi-granulaires incomplètes. EDA 2014, Vichy (France)


mephu_panelSession_NICST2014 - May 28, 2014 - PUBLICATION


mephu_panelSession_NICST2014_v3.pdf


Presentation of Engelbert Mephu Nguifo - NICST 2014 workshop, Weihai (China) - Panel session - May 28, 2014 - PUBLICATION

Title : Smarter Compuing & ICT for Sustainable Development of Human Society and Industry in Big Data Environment mephu_panelSession_NICST2014


Talk of Sabeur Aridhi - Big Data Forum - May 19, 2014 - PUBLICATION

Title : Mining large datasets : case of mining frequent subgraph in the cloud Date : May 16, 2014


Paper - To appear in "Information Systems" - May 19, 2014 - PUBLICATION

S. Aridhi, L. d'Orazio, M. Maddouri and E. Mephu Nguifo. Density-based data partitioning strategy to approximate large-scale subgraph mining. Information Systems, Elsevier, 2013, ISSN 0306-4379, http://dx.doi.org/10.1016/j.is.2013.08.005.  


Paper - Accepted in "Technique et science informatiques" - May 19, 2014 - PUBLICATION

S. Aridhi, L. d'Orazio, M. Maddouri and E. Mephu Nguifo. Un partitionnement basé sur la densité de graphe pour approcher la fouille distribuée de sous-graphes fréquents. Technique et Science Informatiques, Lavoisier.


Paper - Accepted in "RFIA 2014" for oral presentation - May 19, 2014 - PUBLICATION

S. Aridhi, L. d'Orazio, M. Maddouri et E. Mephu Nguifo. A Novel MapReduce-based approach for distributed frequent subgraph mining. 19ème congrès national sur la Reconnaissance de Formes et l'Intelligence Artificielle (RFIA'14), Rouen, France, 2014.


expose_26-03-14 - April 10, 2014 - PUBLICATION


expose_26-03-141.pdf


Towards more targeted recommendations in folksonomies - April 7, 2014 - PUBLICATION


expose_26-03-14.pdf


Towards more targeted recommendations in folksonomies - April 7, 2014 - PUBLICATION

expose_26-03-14 Recommender systems are now popular both commercially as well as within the research community, where many approaches have been suggested for providing recommendations. Folksonomies’ users are sharing items (e.g.,movies,books,bookmarks, etc.) by annotating them with freely chosen tags. Within the Web 2:0 age, users become the core of the system since they are both the contributors and the creators of the information. In this respect, it is of paramount importance to intercept their needs by considering their respective profiles to use this information for providing a more targeted recommendation. In this paper, we consider users’ profile as a new dimension of a folksonomy classically composed of three dimensions <users,tags,ressources> and propose an approach to group users with close profiles and interests through quadri-concepts. Then, we use such structures in order to propose our personalized recommendation system of users, tags and resources. Carried out extensive experiments on two real-life datasets,i.e.,MOVIELENS and BOOKCROSSING highlight encouraging results in terms of precision as well as a good social evaluation. Moreover, we study some of the key assessment metrics such as coverage, diversity and scalability.


ClaSeek_Luckas - Feb. 21, 2014 - PUBLICATION


claseek.pdf


Talk of PhD student Lukas Havrlant - Feb. 18, 2014 - PUBLICATION

Title: Search engine based on FCA

Abstract: A search engine can help a user to find required documents by suggesting similar queries. I will present a search engine with a simple web interface which works with static or dynamic set of documents. The key feature is that after sending a query the search engine suggests generalisations, specialisations and categorisations based on the formal concept analysis.
 
Date: Febrary, 21, 2014, 11:00 am
 
Room: A102 (ISIMA)
 

bitvector_Lukas - Feb. 15, 2014 - PUBLICATION


bitvector_Lukas.pdf


Slides - Feb. 15, 2014 - PUBLICATION


bitvector_Lukas1.pdf


Presentation of Lukas Havrlant (Palacky University of Olomouc) - Feb. 15, 2014 - PUBLICATION

Title: Bit-vector encoding and matrix decomposition Date: Febrary 12, 2014 Slides


Presentation of Sabeur Aridhi - Feb. 15, 2014 - PUBLICATION

Title: Distribued graph mining and cloud computing Date: Ferbrary 04, 2014  


ECAI'14, The Twenty-first European Conference on Artificial Intelligence, Prague, Czech Republic, 18-22 aout 2014 - Dec. 27, 2013 - PUBLICATION

The Twenty-first European Conference on Artificial Intelligence 18-22 August 2014, Prague, Czech Republic http://www.ecai2014.org The biennial European Conference  on Artificial Intelligence (ECAI) is Europe's premier  archival venue for presenting  scientific results in AI.  Organised by the European  Coordinating Committee for AI (ECCAI), the ECAI conference provides an opportunity for researchers to present and hear about the very best research in contemporary AI. As well as a full  programme   of  technical  papers,  ECAI'14   will  include  the Prestigious Applications of Intelligent Systems conference (PAIS), the Starting AI Researcher Symposium  (STAIRS), the International Web Rule Symposium (RuleML) and an extensive programme of  workshops, tutorials,  and invited  speakers. (Separate  calls are issued for PAIS, STAIRS, tutorials, and workshops.)ECAI'14 will be held in the beautiful and historic city of Prague, the capital  of  the Czech  Republic.   With  excellent opportunities  for sightseeing and  gastronomy, Prague promises  to be a  wonderful venue for a memorable conference. This  call  invites the  submission  of  papers  and posters  for  the technical programme of ECAI'14. High-quality original  submissions are welcome  from all areas  of AI; the following list of topics is indicative only. - Agent-based and Multi-agent Systems - Constraints, Satisfiability, and Search - Knowledge Representation, Reasoning, and Logic - Machine Learning and Data Mining - Natural Language Processing - Planning and Scheduling - Robotics, Sensing, and Vision - Uncertainty in AI - Web and Knowledge-based Information Systems - Multidisciplinary Topics Both  long  (6-page)  and  short (2-page)  papers  can  be  submitted. Whereas  long papers  should report  on substantial  research results, short  papers are  intended  for highly  promising  but possibly  more preliminary  work. Short  papers  will be  presented  in poster  form. Rejected long papers will be considered for the short paper track. Submitted papers must be formatted according to ECAI'14 guidelines and submitted electronically through the ECAI'14 paper submission site. Full  instructions  including  formatting  guidelines  and  electronic templates are available on the ECAI'14 website. Paper submission: 1 March 2014 Author feedback: 14-18 April 2014 Notification of acceptance/rejection: 9 May 2014 Camera-ready copy due: 30 May 2014 The proceedings of ECAI'14 will be published by IOS Press. Best papers go AIJ The authors of the best papers (and runner ups) of ECAI'14 will be  invited to submit an extended version of their paper to the Artificial  Intelligence Journal.


PhD Thesis Defense of Wajdi Dhifli - Dec. 10, 2013 - PUBLICATION

Place: ISIMA, Campus des Cézeaux (Clermont-Ferrand), Room A102 Date: Wednesday December 11th 2013 at 2:30pm. Examiners Board : -Reviewers :

  • Pr. Mohammed Javeed Zaki (Rensselaer Polytechnic Institute, USA)
  • Pr. Abdoulaye Baniré Diallo (Université du Québec à Montréal, Canada)
  • Pr. Jan Ramon (Katholieke Universiteit Leuven, Belgium)
-Examinators :
  • DR. David W. Ritchie (INRIA, Nancy, France)
  • DR. Jean Sallantin (LIRMM, Montpellier, France)
  • DR. Jean-François Gibrat (INRA, Jouy-en-Josas, France)
  • Dr. Annegret Wagler (LIMOS, Clermont-Ferrand, France)
-Advisor : Prof. MEPHU NGUIFO Engelbert (LIMOS, Clermont-Ferrand, France)
 
-----------------------------------------------------------------------------------------------------------------------------------------------------
Title: Topological and Domain Knowledge-based Subgraph Mining: Application on Protein 3D-Structures Abstract: This thesis is in the intersection of two proliferating research fields, namely data mining and bioinformatics. With the emergence of graph data in the last few years, many efforts have been devoted to mining frequent subgraphs from graph databases. Yet, the number of discovered frequent subgraphs is usually exponential, mainly because of the combinatorial nature of graphs. Many frequent subgraphs are irrelevant because they are redundant or just useless for the user. Besides, their high number may hinder and even makes further explorations unfeasible. Redundancy in frequent subgraphs is mainly caused by structural and/or semantic similarities, since most discovered subgraphs differ slightly in structure and may infer similar or even identical meanings. In this thesis, we propose two approaches for selecting representative subgraphs among frequent ones in order to remove redundancy. Each of the proposed approaches addresses a specific type of redundancy. The first approach focuses on semantic redundancy where similarity between subgraphs is measured based on the similarity between their nodes' labels, using prior domain knowledge. The second approach focuses on structural redundancy where subgraphs are represented by a set of user-defined topological descriptors, and similarity between subgraphs is measured based on the distance between their corresponding topological descriptions. The main application data of this thesis are protein 3D-structures. This choice is based on biological and computational reasons. From a biological perspective, proteins play crucial roles in almost every biological process. They are responsible of a variety of physiological functions. From a computational perspective, we are interested in mining complex data. Proteins are a perfect example of such data as they are made of complex structures composed of interconnected amino acids which themselves are composed of interconnected atoms. Large amounts of protein structures are currently available in online databases, in computer analyzable formats. Protein 3D-structures can be transformed into graphs where amino acids are the graph nodes and their connections are the graph edges. This enables using graph mining techniques to study them. The biological importance of proteins, their complexity, and their availability in computer analyzable formats made them a perfect application data for this thesis.
 
-----------------------------------------------------------------------------------------------------------------------------------------------------
Titre de la thèse: Fouille de Sous-graphes Basée sur la Topologie et la Connaissance du Domaine: Application sur les Structures 3D de Protéines Résumé:Cette thèse est à l'intersection de deux domaines de recherche en plein expansion, à savoir la fouille de données et la bioinformatique. Avec l'émergence des bases de graphes au cours des dernières années, de nombreux efforts ont été consacrés à la fouille des sous-graphes fréquents. Mais le nombre de sous-graphes fréquents découverts est exponentiel, cela est due principalement à la nature combinatoire des graphes. Beaucoup de sous-graphes fréquents ne sont pas pertinents parce qu'ils sont redondants ou tout simplement inutiles pour l'utilisateur. En outre, leur nombre élevé peut nuire ou même rendre parfois irréalisable toute utilisation ultérieure. La redondance dans les sous-graphes fréquents est principalement due à la similarité structurelle et / ou sémantique, puisque la plupart des sous-graphes découverts diffèrent légèrement dans leur structures et peuvent exprimer des significations similaires ou même identiques.
Dans cette thèse, nous proposons deux approches de sélection des sous-graphes représentatifs parmi les fréquents afin d'éliminer la redondance. Chacune des approches proposées s'intéresse à un type spécifique de redondance. La première approche s'adresse à la redondance sémantique où la similarité entre les sous-graphes est mesurée en fonction de la similarité entre les étiquettes de leurs nœuds, en utilisant les connaissances de domaine. La deuxième approche s'adresse à la redondance structurelle où les sous-graphes sont représentés par des descripteurs topologiques définis par l'utilisateur, et la similarité entre les sous-graphes est mesurée en fonction de la distance entre leurs descriptions topologiques respectives. Les principales données d'application de cette thèse sont les structures 3D des protéines. Ce choix repose sur des raisons biologiques et informatiques. D'un point de vue biologique, les protéines jouent un rôle crucial dans presque tous les processus biologiques. Ils sont responsables d'une variété de fonctions physiologiques. D'un point de vue informatique, nous sommes intéressés à la fouille de données complexes. Les protéines sont un exemple parfait de ces données car elles sont faites de structures complexes composées d'acides aminés interconnectés qui sont eux-mêmes composées d'atomes interconnectés. Des grandes quantités de structures protéiques sont actuellement disponibles dans les bases de données en ligne. Les structures 3D des protéines peuvent être transformées en graphes où les acides aminés représentent les nœuds du graphe et leurs connexions représentent les arêtes. Cela permet d'utiliser des techniques de fouille de graphes pour les étudier. L'importance biologique des protéines et leur complexité ont fait d'elles des données d'application appropriées pour cette thèse.

PhD Thesis Defense of Sabeur Aridhi - Dec. 2, 2013 - PUBLICATION

Title:Distributed Subgraph Mining in the Cloud Place:ISIMA, Campus des Cézeaux (Clermont-Ferrand), Room E005 Date: Friday November 29th at 9am. Jury members: Reviewers: Pr. Anne LAURENT, LIRMM, University of Montpellier 2, France Pr. Takeaki UNO, National Institute of Informatics, Japan Examiners: Pr. Jérome DARMONT, ERIC, University of Lyon 2, France Pr. Mohamed Mohsen GAMMOUDI, University of Manouba, Tunisia Co-Supervisors: Dr. Laurent D'ORAZIO, LIMOS, University of Clermont Ferrand II, France. Pr. Mondher MADDOURI, LIPAH, Université of Manouba, Tunisia Supervisor: Pr. Engelbert MEPHU NGUIFO, LIMOS, University of Clermont Ferrand II, France. Abstract: Recently, graph mining approaches have become very popular, especially in certain domains such as bioinformatics, chemoinformatics and social networks. One of the most challenging tasks in this setting is frequent subgraph discovery. This task has been highly motivated by the tremendously increasing size of existing graph databases. Due to this fact, there is urgent need of efficient and scaling approaches for frequent subgraph discovery especially with the high availability of cloud computing environments. This thesis deals with distributed frequent subgraph mining in the cloud. First, we provide the required material to understand the basic notions of our two research fields, namely graph mining and cloud computing. Then, we present the contributions of this thesis. In the first axis, we propose a novel approach for large-scale subgraph mining, using the MapReduce framework. The proposed approach provides a data partitioning technique that consider data characteristics. It uses the densities of graphs in order to partition the input data. Such a partitioning technique allows a balanced computational loads over the distributed collection of machines and replace the default arbitrary partitioning technique of MapReduce. We experimentally show that our approach decreases significantly the execution time and scales the subgraph discovery process to large graph databases. In the second axis, we address the multi-criteria optimization problem of tuning thresholds related to distributed frequent subgraph mining in cloud computing environments while optimizing the global monetary cost of storing and querying data in the cloud. We define cost models for managing and mining data with a large scale subgraph mining framework over a cloud architecture. We present an experimental validation of the proposed cost models in the case of distributed subgraph mining in the cloud.


Top Research Conferences in Data Mining, Data Science - Nov. 24, 2013 - PUBLICATION

Here are the top 10 research conferences, based on the last 10 years data. The leading conference is - KDD (www.kdd.org), both by Field rating and by Citations/Publication. http://www.kdnuggets.com/2013/11/top-conferences-data-mining-data-science.html?goback=%2Eanb_160888_*2_*1_*1_*1_*1_*1#%21   Here is a full list of 38 conferences in data mining. Another ranking of conferences is Google Scholar: Top publications - Data Mining & Analysis    


Exposé de Jacqueline: le lundi 14/10/2013 - Oct. 11, 2013 - PUBLICATION
THEME: Conception, développement et test de modèles de fouille de données
 
RESUME:
Plusieurs méthodes permettant de découvrir des corrélations entre les données de grandes bases ont été proposées. Nous avons implémenté une nouvelle approche basée sur la notion de dominance, permettant à l’utilisateur d’obtenir des règles valides inhérentes à la prise de décision, sans spécifier de valeurs limites des mesures et sans favoriser ni exclure aucune mesure. En se basant sur l’opérateur Skyline, il a été possible d’élaborer le SkyRule qui permet de trouver l’ensemble des règles non dominées, mais aussi le RankRule qui permet de classer les règles et de n’en retenir que la quantité désiré.

Program : Summer School MLSS'13 - Sept. 13, 2013 - PUBLICATION

Program : Summer School MLSS'13
program-4.pdf


MLSS'13: Machine Learning Summer School 2013 - Sept. 13, 2013 - PUBLICATION

Machine Learning Summer School 2013 @ Al Hambra Hotel, Hammamet, Tunisia September 16-18, 2013 Program : Summer School MLSS'13   Prof. Engelbert Mephu Nguifo will give a talk @ MLSS'13 on Tuesday the 17th of September. The talk is about " Machine learning: Paradigms and Lessons" and will be held in the plenary session between 8:00 and 9:30 am.    


séminaire Dr. Haïtham Sghaier (HDR) 12 septembre - 15h30 - Amphi Bruno Garcia - Sept. 12, 2013 - PUBLICATION

Jeudi 12 septembre - 15h30 - Amphi Bruno Garcia Title: Top-down computational biology and biochemical methods to predict the evolution of ionizing-radiation-resistant prokaryotes Dr. Haïtham Sghaier, HDR Research Unit UR04CNSTN01 "Medical and Agricultural Applications of Nuclear Techniques", National Center for Nuclear Sciences and Technology (CNSTN), Sidi Thabet Technopark, 2020 Sidi Thabet, Tunisia sghaier.haitham@gmail.comhaitham.sghaier@cnstn.rnrt.tn Abstract Since the beginning of their discovery some 55 years ago, the origin of ionizing-radiation-resistant prokaryotes (IRRP) has been under debate. IRRP were regarded as representing a scattered group from a phylogenetic perspective, urging the notion that these microorganisms emerged through convergent evolution. Despite this provocative hypothesis, the formulation of other theories, and pertinent discoveries, the evolution of IRRP remains either incompletely understood or profoundly misinterpreted. In this presentation, I highlight and elaborate on these issues and discuss top-down computational biology and biochemical methods to decipher the evolution of IRRP and the nature of their ancestor(s).


Smoothing 3D protein structure motifs through graph mining and amino-acids similarities - July 14, 2013 - PUBLICATION

@JOBIM 2013
Jobim13.pdf


@JOBIM 2013 : Smoothing 3D protein structure motifs through graph mining and amino-acids similarities - July 14, 2013 - PUBLICATION

Wajdi Dhifli, Rabie Saidi, Engelbert Mephu Nguifo. Smoothing 3D protein structure motifs through graph mining and amino-acids similarities. Journées Ouvertes en Biologie, Informatique et Mathématiques (JOBIM), Toulouse, France 2013. Abstract: One of the most powerful techniques to study proteins is to look for recurrent fragments (also called substructures), then use them as patterns to characterize the proteins under study. Although protein sequences have been extensively studied in the literature, studying protein three-dimensional (3D) structures can reveal relevant structural and functional information which may not be derived from protein sequences alone. An emergent trend consists in parsing proteins 3D structures into graphs of amino acids. Hence, the search of recurrent substructures is formulated as a process of frequent sub-graph discovery where each subgraph represents a 3D-motif. In this scope, several efficient approaches for frequent 3D-motifsdiscovery have been proposed in the literature. However, the set of discovered 3D-motifs is too large to be efficiently analyzed and explored in any further process. In this paper, we propose a novel pattern selection approach that shrinks the large number of discovered frequent 3D-motifs by selecting the representative ones. Existing pattern selection approaches do not exploit the domain knowledge. Yet, in our approach we incorporate the evolutionary information of amino acids defined in the substitution matrices in order to select the representative 3D-motifs. We show the effectiveness of our approach on a number of real datasets. The results issued from our experiments show that our approach detects relations between patterns that current subgraph selection approaches fail to detect, and that it is able to considerably decrease the number of motifs while enhancing their interestingness.


Call for papers: NIPS 2013 - April 22, 2013 - PUBLICATION

Neural Information Processing Systems Conference and Workshops December 5-10, 2013 Lake Tahoe, Nevada, USA http://nips.cc/Conferences/2013/ Deadline for Paper Submissions: Friday, May 31, 2013, 11 pm Universal Time (4 pm Pacific Daylight Time). Submit at: https://cmt.research.microsoft.com/NIPS2013/ Submissions are solicited for the Twenty-Seventh Annual Conference on Neural Information Processing Systems, an interdisciplinary conference that brings together researchers in all aspects of neural and statistical information processing and computation, and their applications. The conference is a highly selective, single track meeting that includes oral and poster presentations of refereed papers as well as invited talks. The 2013 conference will be held on December 5-8 at Lake Tahoe, Nevada. One day of tutorials (December 5) will precede the main conference, and two days of workshops (December 9-10) will follow it at the same location. Note that differently from previous years, the conference will start on a Thursday. Submission process: Electronic submissions will be accepted until Friday, May 31, 2013, 11 pm Universal Time (4 pm Pacific Daylight Time). As was the case last year, final papers will be due in advance of the conference. However, minor changes such as typos and additional references will still be allowed for a certain period after the conference. Reviewing: As in previous years, reviewing will be double-blind: the reviewers will not know the identities of the authors. However, differently from previous years, anonymous reviews and meta-reviews of accepted papers will be made public after the end of the review process. Evaluation Criteria: Submissions will be refereed on the basis of technical quality, novelty, potential impact, and clarity. Dual Submissions Policy: Submissions that are identical (or substantially similar) to versions that have been previously published, or accepted for publication, or that have been submitted in parallel to other conferences are not appropriate for NIPS and violate our dual submission policy. Exceptions to this rule are the following: 1. Submission is permitted of a short version of a paper that has been submitted to a journal, but has not yet been published in that journal. Authors must declare such dual-submissions either through the CMT submission form, or via email to the program chairs at program-chairs@nips.cc. It is the authors’ responsibility to make sure that the journal in question allows dual concurrent submissions to conferences. 2. Submission is permitted for papers presented or to be presented at conferences or workshops without proceedings, or with only abstracts published. Previously published papers with substantial overlap written by the authors must be cited so as to preserve author anonymity (e.g. “the authors of [1] prove that …”). Differences relative to these earlier papers must be explained in the text of the submission. It is acceptable to submit to NIPS 2013 work that has been made available as a technical report (or similar, e.g. in arXiv) without citing it. While this could compromise the authors' anonymity, reviewers will be asked to refrain from actively searching for the authors’ identity or disclose to the area chairs if their identity is known to them. The dual-submission rules apply during the NIPS review period which begins May 31 and ends September 5, 2013. Submission Instructions: All submissions will be made electronically, in PDF format. Papers are limited to eight pages, including figures and tables, in the NIPS style. An additional ninth page containing only cited references is allowed. Complete submission and formatting instructions, including style files, are available from the NIPS website, http://nips.cc. Supplementary Material: Authors can submit up to 10 MB of material, containing proofs, audio, images, video, data or source code. Note that the reviewers and the program committee reserve the right to judge the paper solely on the basis of the 9 pages of the paper; looking at any extra material is up to the discretion of the reviewers and is not required. Technical Areas: Papers are solicited in all areas of neural information processing and statistical learning, including, but not limited to: * Algorithms and Architectures: statistical learning algorithms, kernel methods, graphical models, Gaussian processes, Bayesian methods, neural networks, deep learning, dimensionality reduction and manifold learning, model selection, combinatorial optimization, relational and structured learning. * Applications: innovative applications that use machine learning, including systems for time series prediction, bioinformatics, systems biology, text/web analysis, multimedia processing, and robotics. * Brain Imaging: neuroimaging, cognitive neuroscience, EEG (electroencephalogram), ERP (event related potentials), MEG (magnetoencephalogram), fMRI (functional magnetic resonance imaging), brain mapping, brain segmentation, brain computer interfaces. * Cognitive Science and Artificial Intelligence: theoretical, computational, or experimental studies of perception, psychophysics, human or animal learning, memory, reasoning, problem solving, natural language processing, and neuropsychology. * Control and Reinforcement Learning: decision and control, exploration, planning, navigation, Markov decision processes, game playing, multi-agent coordination, computational models of classical and operant conditioning. * Hardware Technologies: analog and digital VLSI, neuromorphic engineering, computational sensors and actuators, microrobotics, bioMEMS, neural prostheses, photonics, molecular and quantum computing. * Learning Theory: generalization, regularization and model selection, Bayesian learning, spaces of functions and kernels, statistical physics of learning, online learning and competitive analysis, hardness of learning and approximations, statistical theory, large deviations and asymptotic analysis, information theory. * Neuroscience: theoretical and experimental studies of processing and transmission of information in biological neurons and networks, including spike train generation, synaptic modulation, plasticity and adaptation. * Speech and Signal Processing: recognition, coding, synthesis, denoising, segmentation, source separation, auditory perception, psychoacoustics, dynamical systems, recurrent networks, language models, dynamic and temporal models. * Visual Processing: biological and machine vision, image processing and coding, segmentation, object detection and recognition, motion detection and tracking, visual psychophysics, visual scene analysis and interpretation. Demonstrations and Workshops: There is a separate Demonstration track at NIPS. Authors wishing to submit to the Demonstration track should consult the Call for Demonstrations. The workshops will be held at Lake Tahoe, Nevada, December 9-10. The upcoming call for workshop proposals will provide details. Web URL: https://nips.cc/Conferences/2013/CallForPapers


Réunion le jeudi 21/03 à 10h: présentation de Nader. - March 20, 2013 - PUBLICATION

Réunion le jeudi 21/03 à 10h: présentation de Nader.


Réunion le jeudi 14/02 de 15h à 17h: présentation de Wajdi. La réunion aura lieu à la salle A111. - Feb. 12, 2013 - PUBLICATION

Réunion le jeudi 14/02 de 15h à 17h: présentation de Wajdi. La réunion aura lieu à la salle A111. Titre: "Mining Dynamic Frequent Patterns From Time Evolving Graphs: An Application on Protein Structures"


réunion 30 Janvier à 14h: présentation de Jocelyn. La réunion aura lieu à la salle A102. - Jan. 29, 2013 - PUBLICATION

réunion 30 Janvier à 14h: présentation de Jocelyn. La réunion aura lieu à la salle A102.


réunion 18 octobre à 13h30. La réunion aura lieu à la salle A104 . - Oct. 14, 2012 - PUBLICATION

réunion 18 octobre à 13h30. La réunion aura lieu à la salle A104 .


PhD Defense - Soutenance de Thèse - Oct. 2, 2012 - PUBLICATION

Bonjour, J'ai le plaisir de vous inviter à la soutenance de ma thèse en Informatique intitulée "Motif Extraction from Complex Data: Case of Protein Classification". La soutenance se déroulera à l’ISIMA, Campus des Cézeaux (Clermont-Ferrand), la Salle du Conseil (A102) le mercredi 3 octobre à 15h. La présentation sera donnée en anglais. Vous êtes chaleureusement conviés au traditionnel pot qui suivra. A bientôt, Rabie SAIDI Le jury est composé de: Rapporteurs: Pr. Florence d'Alché-Buc University of Evry, France Dr. Henry Soldano University of Paris-Nord, France Pr. Mohammed Javeed Zaki Rensselaer Polytechnic Institute, USA Examinateurs: Pr. Rumen Andonov University of Rennes 1, France Pr. Abdoulaye Baniré Diallo University of Québec at Montreal, Canada Pr. David Hill University of Clermont-Ferrand II, France Co-directeur: Dr. Mondher Maddouri University of Gafsa, Tunisia Directeur: Pr. Engelbert Mephu Nguifo University of Clermont-Ferrand II, France Titre: Extraction de Motifs des Données Complexes: Cas de la Classification des Protéines Résumé: La classification est l'un des défis important en bioinformatique, aussi bien pour les données protéiques que nucléiques. La présence de ces données en grandes masses, leur ambiguïté et en particulier les coûts élevés de l'analyse in vitro en termes de temps et d'argent, rend l'utilisation de la fouille de données plutôt une nécessité qu'un choix rationnel. Cependant, les techniques de fouille de données, qui traitent souvent des données sous le format relationnel, sont confrontés avec le format inapproprié des données biologiques. Par conséquent, une étape inévitable de prétraitement doit être établie. Cette thèse traite du prétraitement de données protéiques comme une étape de préparation avant leur classification. Nous présentons l'extraction de motifs comme un moyen able pour répondre à cette tâche. Les motifs extraits sont utilisés comme descripteurs, en vue de coder les protéines en vecteurs d'attributs. Cela permet l'utilisation des classifieurs connus. Cependant, la conception d'un espace approprié d'attributs, n'est pas une tâche triviale. Nous traitons deux types de données protéiques à savoir les séquences et les structures 3D. Dans le premier axe, i.e.; celui des séquences, nous proposons un nouveau procédé de codage qui utilise les matrices de substitution d'acides aminés pour définir la similarité entre les motifs lors de l'étape d'extraction. En utilisant certains classifieurs, nous montrons l'efficacité de notre approche en la comparant avec plusieurs autres méthodes de codage. Nous proposons également de nouvelles métriques pour étudier la robustesse de certaines de ces méthodes lors de la perturbation des données d'entrée. Ces métriques permettent de mesurer la capacité d'une méthode de révéler tout changement survenant dans les données d'entrée et également sa capacité à cibler les motifs intéressants. Le second axe est consacré aux structures protéiques 3D, qui ont été récemment considérées comme graphes d'acides aminés selon différentes représentations. Nous faisons un bref survol sur les représentations les plus utilisées et nous proposons une méthode naïve pour aider à la construction de graphes d'acides aminés. Nous montrons que certaines méthodes répandues présentent des faiblesses remarquables et ne reflètent pas vraiment la conformation réelle des protéines. Par ailleurs, nous nous intéressons à la découverte, des sous-structures récurrentes qui pourraient donner des indications fonctionnelles et structurelles. Nous proposons un nouvel algorithme pour trouver des motifs spatiaux dans les protéines. Ces motifs obéissent à un format dé ni sur la base d'une argumentation biologique. Nous comparons avec des motifs séquentiels et spatiaux de certains travaux reliés. Pour toutes nos contributions, les résultats expérimentaux confirment l'efficacité de nos méthodes pour représenter les séquences et les structures protéiques, dans des tâches de classification. Les programmes développés sont disponibles sur ma page web http://fc.isima.fr/~saidi. Mots-clés: Prétraitement, extraction de motif, classification de protéines, structure protéique, motif séquentiel, motif spatial. ______________________________________________________________________ Hello, I am pleased to invite you to my PhD defense in Computer Science, entitled " Motif Extraction from Complex Data: Case of Protein Classification". The defense will take place at the l’ISIMA, Campus des Cézeaux (Clermont-Ferrand), Council Room (A102) on Wednesday october 3th at 3pm. The defense will be in English. You are warmly welcome to the reception that will follow the defense. Looking forward to seeing you, Rabie SAIDI The jury is composed of: Reviewers: Pr. Florence d'Alché-Buc University of Evry, France Dr. Henry Soldano University of Paris-Nord, France Pr. Mohammed Javeed Zaki Rensselaer Polytechnic Institute, USA Examiners: Pr. Rumen Andonov University of Rennes 1, France Pr. Abdoulaye Baniré Diallo University of Québec at Montreal, Canada Pr. David Hill University of Clermont-Ferrand II, France Co-Supervisor: Dr. Mondher Maddouri University of Gafsa, Tunisia Supervisor: Pr. Engelbert Mephu Nguifo University of Clermont-Ferrand II, France Title: Motif Extraction from Complex Data: Case of Protein Classification Abstract: The classification of biological data is one of the significant challenges in bioinformatics, as well for protein as for nucleic data. The presence of these data in huge masses, their ambiguity and especially the high costs of the in vitro analysis in terms of time and money, make the use of data mining rather a necessity than a rational choice. However, the data mining techniques, which often process data under the relational format, are confronted with the inappropriate format of the biological data. Hence, an inevitable step of preprocessing must be established. This thesis deals with the protein data preprocessing as a preparation step before their classification. We present motif extraction as a reliable way to address that task. The extracted motifs are used as descriptors to encode proteins into feature vectors. This enables the use of known data mining classifiers which require this format. However, designing a suitable feature space, for a set of proteins, is not a trivial task. We deal with two kinds of protein data i.e., sequences and tri-dimensional structures. In the first axis i.e., protein sequences, we propose a novel encoding method that uses amino-acid substitution matrices to de ne similarity between motifs during the extraction step. We demonstrate the efficiency of such approach by comparing it with several encoding methods, using some classifiers. We also propose new metrics to study the robustness of some of these methods when perturbing the input data. These metrics allow to measure the ability of the method to reveal any change occurring in the input data and also its ability to target the interesting motifs. The second axis is dedicated to 3D protein structures which are recently seen as graphs of amino acids. We make a brief survey on the most used graph-based representations and we propose a naïve method to help with the protein graph making. We show that some existing and widespread methods present remarkable weaknesses and do not really reflect the real protein conformation. Besides, we are interested in discovering recurrent sub-structures in proteins which can give important functional and structural insights. We propose a novel algorithm to find spatial motifs from proteins. The extracted motifs obey a well-defined shape which is proposed based on a biological basis. We compare with sequential motifs and spatial motifs of recent related works. For all our contributions, the outcomes of the experiments confirm the efficiency of our proposed methods to represent both protein sequences and protein 3D structures in classification tasks. Software programs developed during this research work are available on my home page http://fc.isima.fr/~saidi. Keywords: Preprocessing, motif/feature extraction, protein classification, protein structures, sequential motif, spatial motif.


SIAM international conference on Data Mining (SDM) - Sept. 17, 2012 - PUBLICATION

http://www.siam.org/meetings/sdm13/

October 12, 2012 11:59 PM PST: Paper Submission*
December 20, 2012: Author Notification

réunion Mercredi prochain 12 septembre à 15h30. La réunion aura lieu à la salle A102. - Sept. 11, 2012 - PUBLICATION
réunion Mercredi prochain 12 septembre à 15h30.  La réunion aura lieu à la salle A102. 
Chacun fera un point sur ses avancées (problématique, solutions envisagées, plan de travail). 5 à 10 mn maxi, 3 à 4 slides suffisent.

2013 ACM SIGMOD/PODS @ New York, New York, USA - Aug. 29, 2012 - PUBLICATION

http://www.sigmod.org/2013/

Important Dates

SIGMOD Deadlines

November 13, 2012: Submission deadline for papers February 5, 2013: Notification of acceptance, rejection, revision March 5, 2013: Submission deadline for revised papers April 9, 2013: Notification of acceptance, rejection for revised papers April 16, 2013: Camera-ready deadline

PODS Deadlines

Dec 5, 2012: Submission deadline for papers Feb 25, 2013: Notification of acceptance, rejection


The 17th Pacific-Asia Conference on Knowledge Discovery and Data Mining - Aug. 12, 2012 - PUBLICATION
Call For Papers PAKDD 2013
 
The 17th Pacific-Asia Conference on Knowledge Discovery and Data Mining
Gold Coast, Australia
Conference Website
 
 
Submission System
 
Important Dates
Paper submission due: Oct. 1    (Mon). 2012
Notification to author: Dec. 19  (Wed). 2012
Camera ready due: Jan. 6    (Sun). 2013

FREE ACM Learning Webinar, June 28: "2012 - Big Data: End of the World or End of BI?" - June 6, 2012 - PUBLICATION

Registration link  


expose - May 31, 2012 - PUBLICATION


expose.rar


expose - May 31, 2012 - PUBLICATION


expose1.rar


Extraction de quadri-concepts à partir de d-folksonomies : Application à la détection de tendances - May 31, 2012 - PUBLICATION

Cet exposé présente  une étude théorique sur l'approche quadratique effectuée sur les folksonomies pour l'extraction de quadri-concepts. Ces structures sont des quadruplets d'utilisateurs, tags, ressources et  dates. Un algorithme appelé QuadriCons a été proposé pour permettre une telle extraction. Dans une deuxième partie, nous analysons les folksonomies à travers une détection de tendances sur les bases MovieLens et Last.FM afin de mettre en avant l'utilité des quadri-concepts.


Évolution de la stabilité de la sélection de variables en fonction de la taille d’échantillon et de la dimension - May 30, 2012 - PUBLICATION

This paper appeared in CAP 2012 Résumé : La sélection de variables est une étape importante lors de la construction d’un classificateur sur des données de grande dimension. Lorsque le nombre d’observations est faible, cette sélection a tendance à être instable, au point qu’il est courant d’observer que sur deux jeux de données différents mais traitant d’un problème similaire, les variables sélectionnées ne se recoupent presque pas. Pourtant, ce problème de la stabilité semble encore peu étudié. Dans cet article, nous présentons des méthodes de quantification de la stabilité, puis nous en étudions les variations en fonction de divers paramètres (dimensionalité, nombre d’observations, distribution des variables, seuil de sélection) sur des données artificielles, avant de réaliser ces mesures sur des données réelles d’expression génique (données puces). Mots-clés : Sélection de variables, stabilité, petits échantillons.


How to Write and Publish in Knowledge & Data Engineering - Feb. 20, 2012 - PUBLICATION

How to Write and Publish in Knowledge & Data Engineering
Writing09-Web.pdf


How to Write and Publish in Knowledge & Data Engineering - Feb. 20, 2012 - PUBLICATION

How to Write and Publish in Knowledge & Data Engineering


Events - Feb. 2, 2012 - PUBLICATION

This page is used to view your full list of events and event details.

Manage this page as any other, except:

  • DO NOT delete this page while IZ-Calender is in use.
  • DO NOT change the slug of this page from here, use Admin menu-> IZ-Calender -> Settings -> Set the events page slug
    Go to: http://codex.wordpress.org/Pages#Changing_the_URL_.28or_.22Slug.22.29_of_Your_Pages to read more on page slugs.
  • DO NOT edit this page's status or Visibility
  • To remove this page from your navigation structure go to Admin menu-> IZ-Calender -> Settings -> Display this page in my primary nav -> Select "No"
  • The information you see here will not display in your theme (user-interface)

Frequent subgraph selection by means of substitution matrix - Jan. 31, 2012 - PUBLICATION

Frequent subgraph selection by means of substitution matrix
DDSMG.pdf


Conférences - Jan. 1, 1970 - PUBLICATION

award - Jan. 1, 1970 - PUBLICATION

Ekaterina was awarded the third prize for his Master's thesis (all disciplines) by the  High School of Economics - Russia   in 2015.    


L'intelligence artificiel au cœur de la recherche scientifique Française - Jan. 1, 1970 - PUBLICATION

Mining Triclusters of Similar Values in Triadic Real-Valued Contexts - Jan. 1, 1970 - PUBLICATION

Presentation of IA by Mr. Mehu - Jan. 1, 1970 - PUBLICATION

You will find join the presentation made for the conference on " XXI ième siècle : révolution robotique "



Next meeting speakers

Thursday, 15 Avril 2021, 2:00 pm

Speakers: Helene Tran,

Topics: Classification of prostate cancer tumors in multiparametric MRI with Deep Learning

Thursday. 29 Avril 2021, 2:00 pm

Speaker: Raissa Saleu

Topic: Optimization of urban deliveries with drones and vehicles in parallel

 

Poster from the DAPPEM project

By HOSSAIN Sheikh Imran

 

Miners team during the Covid19