PhD thesis proposal: Virtual Communities based on e-Health Data Mining The University of Saint-Etienne (France) invites applications for a *fully funded 3-year PhD position* at the Hubert-Curien Lab. Main points of the studentship: *Data mining on biological parameters and e-health communities *Starting date is about October, 1st 2012. *In cooperation with the University of Tokyo (Living Environment Laboratory) Field of science: Computer Science PhD Director: Pierre Maret (pierre.maret@univ-st-etienne.fr) Co-supervisor: Fabrice Muhlenbach (fabrice.muhlenbach@univ-st-etienne.fr) Where: Hubert Curien Lab., UMR CNRS 5516, Université Jean Monnet de Saint-Étienne (member of the University of Lyon). Research Team: Fouille et recherche d’information dans les documents structurés (Data Mining and Information Retrieval in Structured Documents) Doctoral School: EDSIS (École Doctorale Sciences, Ingénierie et Santé) of Saint-Étienne Funding: Doctoral contract funding by the French Ministry of Education and Research, ranked at the 1st position by the Doctoral School EDSIS. Gross salary: 1650 euros / month Keywords: Data Mining, Sequence Mining, Virtual Communities, e-Health Deadline: Until the 27th of April 2012 Description: The thesis will be done in cooperation between the University of Saint-Etienne (Hubert-Curien Laboratory) and the University of Tokyo (Living Environment Laboratory). The Japanese laboratory is specialized in the detection of biological parameters from miniaturized sensors. The goal of this PhD thesis concerns the design of new data mining algorithms to exploit the symbolic data (e.g., stress or emotion levels) resulting from the transformation of biological signals in order to make discoveries (abnormal evolution signs, regular patterns, etc.). This knowledge will be used in e-health community services to implement scenarios such as user support, group debriefing, emergency processes. During this PhD thesis, the main problems will concern: - Data mining techniques, and especially sequence mining, with the difficulty to handle different attributes at the same time (e.g., stress and emotion); - Detection of outliers [1] in unusual series of parameters; - Clustering [2] of similar profiles to design new groups (for taking care of people, for sharing information); - Handle the information sharing process in virtual communities [4]. The selected candidate will join the Computer Science team of the Hubert-Curien Laboratory composed of about 20 researchers working at the crossroads of data mining, machine learning, information retrieval and social networks. [1] MUHLENBACH F., LALLICH S., ZIGHED D.A., "Identifying and Handling Mislabelled Instances", Journal of Intelligent Information Systems, Vol. 22 (1), pp. 89-109, 2004. [2] MUHLENBACH F., LALLICH S., "A New Clustering Algorithm Based on Regions of Influence with Self-Detection of the Best Number of Clusters", in W. Wang, H. Kargupta, S. Ranka, P. S. Yu, and X. Wu, editors, Proceedings of the 9th International Conference on Data Mining (ICDM’09), Miami, Florida, December 6-9, 2009, pp. 884-888. 2009. [3] ELLOUMI L., GRAVIER C., MARET P., "Ad-hoc virtual communities for rehabilitation exercising", in Prodeedings of the IADIS International Conference e-Health 2010, Freiburg, Germany. 2010. [4] SUBERCAZE J., EL MORR C., MARET P., JOLY A., KOIVISTO M., ANTONIADIS P., IHARA M., "Towards Successful Virtual Communities", in Proceedings of the 11th International Conference on Enterprise Information Systems (ICEIS'09), Milan, Italy. 2009. Candidates must have demonstrable interest and expertise in data mining as well as in knowledge modeling and e-health. A background in psychology is highly desirable but not essential. A good level in English is also essential. Some interest in the Japanese culture is also desirable. Applicants should have or be in the process of getting a *Master's degree in Computer Science*. Application process: Deadline for 27th of April 2012 but candidates are invited to contact us (pierre.maret@univ-st-etienne.fr and fabrice.muhlenbach@univ-st-etienne.fr) as soon as possible. Candidates should send us the following elements : - A letter to express their motivation - A CV - Marks and awards obtained during their Master degree. - A recommendation letter from their teachers.