法国斯特拉斯堡大学2023年招聘博士后（用于水生态系统恢复决策支持的异构信息的表征、查询和调整）

法国斯特拉斯堡大学2023年招聘博士后（用于水生态系统恢复决策支持的异构信息的表征、查询和调整）

斯特拉斯堡大学（法: Université de Strasbourg；德：Universität Straßburg；英：University of Strasbourg），简称UDS或Unistra，位于法国阿尔萨斯大区下莱茵省斯特拉斯堡市，是一所综合性大学，法国卓越大学计划高校。

学校成立于1538年，1971年因法国五月风暴影响拆分为三个独立的大学，于2009年1月1日重新整合为现在的斯特拉斯堡大学。斯特拉斯堡大学在很多领域都享有盛名，拥有18名诺贝尔奖得主，1名菲尔兹数学奖得主。

Post Doctoral Position - Representation, Interrogation And Adaptation Of Heterogeneous Information For Decision Support In Hydro-Ecosystem Restoration

Universities and Institutes of France

France

October 12, 2023

Contact:N/A

Offerd Salary:Negotiation

Location:N/A

Working address:N/A

Contract Type:Other

Working Time:Full time

Working type:N/A

Ref info:N/A

17 Aug 2023

Job Information

Organisation/Company

Université de Strasbourg

Department

Direction de la Recherche

Research Field

Computer science

Researcher Profile

Recognised Researcher (R2)

Country

France

Application Deadline

12 Oct 2023 - 23:59 (Europe/Paris)

Type of Contract

Temporary

Job Status

Full-time

Offer Starting Date

15 Nov 2023

Is the job funded through the EU Research Framework Programme?

Not funded by an EU programme

Is the Job related to staff position within a Research Infrastructure?

No

Offer Description

1. Position identification

Contract/project period: 20 months Expected date of employment: 15/11/23

Proportion of work: 100 %

Workplace: Strasbourg, France (ICube lab)

Desired level of education: PhD in computer science

Experience required:

Contact(s) for information on the position (identity, position, e-mail address, telephone):

Florence Le Ber, Dr. HDR, ICube, florence.leber@engees.unistra.fr

Date of publication: 17/08/23

Closing date for the receipt of applications: 12/10/23

2. Research project or operation

The German-French project TETRA focuses on the development of an AI based toolbox and methodology for the water domain. This project will begin in June 2023 until June 2026 (3 years). Four partners are involved, two German et two French partners, two private compagnies (SEBA, Thalès) and two public research centers (Fraunhofer IOSB, ICube). The project is organized into several work packages. This postdoctoral position is concerned by one of the work packages (WP6): its aim is to develop a decision support system exploiting feedbacks from hydro-ecosystem restoration operations.

The restoration or renaturation of hydro-ecosystems is a major challenge for the coming years in order to protect and preserve the quality and quantity of river water. In addition, dam or power plant managers are obliged by European and national rules to renaturalize parts of their operating area. Unfortunately, restoration experiences are few and far between. A synthesis of feedbacks has been undertaken for restoration operations along the Rhine (https: // obs-rhin.engees.eu/). Operation reports and interview sheets have also been collected but not used. However, this information, including feedback on errors or unexpected results, would be essential to guide or help implement new projects.

3.Activities

・ Description of the research activities:

To exploit this information, we propose to develop AI methods relying on case- based reasoning (CBR). CBR consists of solving new problems by reusing the solution of similar problems that have already been solved. A case corresponds to a problem-solving episode usually represented by a problem-solution pair. Cases are recorded in a case base. A source case is an element of the case base. The CBR process consists of solving a new problem, the target problem, using the case base. A common way of doing this is to select a source case similar to the target problem (case retrieval step) and to modify the retrieved case so that it provides a solution that hypothetically solves the target problem (case adaptation step). After these inference steps, some learning steps are sometimes implemented. CBR has been used on many applications e.g., agriculture or cooking. The following steps are to be developed:

Step 1: Structuration of a case base: information extracted from existing websites and texts will be formalized within cases (a renaturation operation, context, documents and results, etc.). Text mining will be performed by partner Thalès to extract information from textual documents. A graph representation will be researched to represent the information for each operation (knowledge graphs / conceptual graphs). Different levels of representation will be studied and organized in a hierarchical way, with regards to domain knowledge. Expert rules can also be used to complete the cases. Cases will be provided to to populate the ontology developed in another work package (WP4).

Step 2: Problem description and definition of the case retrieval step: this step will rely on graph matching, including approximative graph matching based on ontological reasoning, in relation with WP4. Various similarity measures and graph mining approaches will also be experimented.

Step 3: Solution adaptation: an adaptation approach based on the semantical and numerical information describing both source and target cases will be studied. Besides, A query interface will be developed with the help of an engineer (6 moths) or the decision support system: the user describes a site or an operation and the system retrieves and displays similar sites/operations with their results., and suggests adaptions.

Références

O. Bruneau, E. Gaillard, N. Lasolle, J. Lieber, E. Nauer, J. Reynaud, A SPARQL Query Transformation Rule Language ― Application to Retrieval and Adaptation in Case-Based Reasoning. In: ICCBR 2017. pp 7691. Trondheim, Norway, 2017.

V. Dufour-Lussier, F. Le Ber, J. Lieber, L. Martin, Case Adaptation with Qualitative Algebras, in Twenty-Third IJCAI, Beijing, China, 2013.

A. Inokuchi, T. Washio, H. Motoda, An Apriori-Based Algorithm for Mining Frequent Sub-structures from Graph Data, in 4th European Conference, PKDD, pp. 1323. Lyon, France, 2000.

F. Le Ber, A. Milles, L. Martin, X. Dolques, M. Benoît, A Reasoning Model based on Perennial Crop Allocation Cases and Rules, in ICCBR 2017, pp 6175. Trondheim, Norway, 2017.

F. Le Ber, A. Napoli, J.-L. Metzger, S. Lardon, Modeling and Comparing Farm Maps using Graphs and Case-based Reasoning, Journal of Universal Computer Science, 2003, 9 (9), pp.1073-1095

G. Li, L. Yan, Z. Ma. An approach for approximate subgraph matching in fuzzy RDF graph, Fuzzy Sets and Systems, 2019, 36, pp. 106-126.

F. Liu, Y. Wang, Z. Li, R. Ren, H. Guan, X. Yu et al. MicroCBR: Case-Based Reasoning on Spatio-temporal Fault Knowledge Graph for Microservices Troubleshooting. In ICCBR 2022, pp. 224239. Nancy, France, 2022.

C. K. Riesbeck und R. C. Schank, Inside Case-Based Reasoning, Hillsdale, New Jersey: Lawrence Erlbaum Associates, 1989.

・ Related activities :

Meetings and collaboration with other partners of the projet (especially Thalès), collaboration with domain experts (hydroecology)

4. Skills

・ Qualifications/knowledge:

PhD in computer science

・ Operational skills/expertise:

Knowledge modeling, ontology-based reasoning, knowledge graphs, graph algorithms.

Languages: Python, java, owl/sparql.

Knowledge in qualitative spatial modeling, and GIS would be appreciated.

・ Personal qualities:

Interest in the application domain, ability to work with experts who are not computer scientists. Ability to work collaboratively.

5. Environment and context of work

・ Presentation of the laboratory/unity:

Created in 2013, ICube laboratory brings together researchers of the University of Strasbourg, the CNRS (French National Center for Scientific Research), the ENGEES and the INSA of Strasbourg in the fields of engineering science and computer science, with imaging as the unifying theme. With around 650 members, ICube is a major driving force for research in Strasbourg whose main areas of application are biomedical engineering and the sustainable development.

The "Data Science and Knowledge" team covers a large spectrum of research in computer science, more precisely in artificial intelligence. Our research activities focus on two theoretical research themes: Machine learning; Data and knowledge. We are specialist of some data types and we have a few privileged application domains, among which is the environmental (water, geography, agriculture) domain.

See https: // sdc.icube.unistra.fr/en/index.php/Home

・ Hierarchical relationship:

The recruited person will work under the responsibility of Florence Le Ber who is the responsible for ICube partner in the TETRA project.

・ Special conditions of practice (notice attached):

Place: UMR ICube, Strasbourg and Illkirch, France Project meetings will take place mainly in Karlsruhe (Germany) and Saclay (Paris region).

Salary: 2100-2700欧元 net/month (according to the experience)

To apply, please send your CV, cover letter and diploma to:florence.leber@engees.unistra.fr

Requirements

Research Field

Computer science

Education Level

PhD or equivalent

Internal Application form(s) needed

RecrutementPostDoctorantsTetraG.pdf

English

(74.04 KB - PDF)

Download

Additional InformationWork Location(s)

Number of offers available

1

Company/Institute

Laboratoire des sciences de l'ingénieur, de l'informatique et de l'imagerie ICUBE, UMR 7357

Country

France

City

Illkirch-Graffenstaden

Geofield

Where to apply

E-mail

florence.leber@engees.unistra.fr

Contact

City

Strasbourg

Website

https:// www. unistra.fr

Street

4 rue Blaise Pascal

Postal Code

67000

STATUS: EXPIRED