Classification of spatio-temporal series. Application to the analysis of water quality within of a dynamic network.
Keywords: dynamic network, spatio-temporal data, classification of temporal series, unsupervised learning, water quality
The evaluation of water quality within distribution networks remains a crucial subject for health and environmental protection issues. With this in mind, managers are brought continuously carry out measurements relating to the quality and flow of water using sensors specific data distributed throughout the network, which generates large amounts of spatiotemporal data.
AT these data are added to those from the hydraulic simulation, which can also be used for characterize the dynamics of water within its distribution network.
The objective of this postdoc is the advanced analysis of this data distributed in time and space (network) using statistical learning techniques, in order to extract a synthetic view of the dynamics of changes in water quality.
The case study will be that of a water network in Ile de France, which is equipped with sensors making it possible to acquire masses of physicochemical data such as temperature, electrical conductivity, chlorine concentration, or flow rate.
Particular attention will be paid to unsupervised methods of classification and segmentation time series, in particular those based on latent stochastic processes which provide a flexible framework for summarizing the dynamics of the evolution of temporal data.
Variants of these methods could be developed in order to classify the points of the network according to the temporal and spatial dynamics of water quality, and taking into account the complex nature (time lags and distortions, incompleteness) of the associated time series.
The missions entrusted to the post-doctoral fellow will relate to the development and practical implementation such methods. The tasks to be carried out will be:
(1) familiarization with and elementary exploration of data from water distribution networks,
(2) development of classification algorithms automatic of complex time series based on models with dynamic latent variables, (3) the development of IT tools to perform this data processing.
Profile: candidates must hold a doctoral thesis in the disciplinary fields of machine learning, statistics or series modeling temporal with an interest in real applications; they may also hold a thesis in the field of hydraulics and with a strong experience in big data analysis.
A current use of R, Python or Matlab software / languages is essential for this position.
To apply, send a CV and a cover letter to the following addresses:
Allou Samé: [email protected]
Latifa Oukhellou: [email protected]
Pierre Mandel: [email protected]
Main place of work: Gustave Eiffel University, GRETTIA Laboratory, Champs-sur-Marne,
Secondary workplace: Veolia Eau d´Ile-de-France, DACE - Studies, Research and Development, Nanterre
Department of Computer Science and Engineering, Lehigh University
The Department of Computer Science and Engineering (CSE) in the P.C. Rossin College of Engineering and Applied Science at Lehigh University invites applications for tenure-track faculty at the ranks of assistant professor, associate professor, or full professor.
Tenure on appointment is possible for senior candidates. Outstanding candidates in all areas of computer science will be considered. Applicants must hold a Ph.D. in Computer Science or a closely related field prior to the official start of employment.
Founded in 1865, Lehigh University has combined outstanding academic and learning opportunities with leadership in fostering innovative research. Recognized among the nation's highly ranked research universities, Lehigh offers a rigorous academic community for over 7,000 students and about 550 full-time faculty members. Lehigh University is located in Bethlehem, PA, a vibrant and historic area.
For full consideration, application materials should be received by December 15, 2021. Candidates requesting tenure must submit application materials online at https://academicjobsonline. org/ajo/jobs/20238. Candidates requesting a position without tenure must submit application materials at https://academicjobsonline. org/ajo/jobs/20237.
Applications should include a cover letter, curriculum vitae, teaching statement, research statement, diversity statement, and contact information for at least three references. Questions concerning this search may be sent to [email protected]. edu.
Lehigh University is an equal opportunity, affirmative action, and non-discrimination employer that provides competitive salaries and comprehensive benefits and has a well-developed infrastructure to address dual career and work-life balance matters. As demonstrated by our Core Values and the Principles of Our Equitable Community, Lehigh University is committed to the values of Integrity and Honesty, Equitable Community, Academic Freedom, Intellectual Curiosity, Collaboration, Commitment to Excellence, and Leadership.
Brian D. Davison (he/him/his) Associate Director, Institute for Data, Intelligent Systems, and Computation Professor, Computer Science and Engineering, Lehigh University http://www.cse.lehigh.edu/~brian/
Dear Colleague, We will be looking to recrute a new research colleague in 2022 in order to strengthen our team. We are seeking for someone who has published in high impact journals on computer vision/machine learning/geometry.
If you have anyone in mind, please ask him/her to contact me ASAP. Most information about our lab is on our sight: https://www.cristal. univ-lille.fr
The CNRS position is a research permanent position https://www.dgdr. cnrs.fr/drhchercheurs/concoursch/default-fr.htm. There is no teaching duties and as such, knowledge of the French language is not essential. The deadline is 17th January, we need to prepare the project with the potential candidate so the sooner, the better.
Host laboratory: Toulouse Computer Science Research Institute (IRIT), teams SMAC and SEPIA
Location: Toulouse 1 Capitole University
Salary: 2400 euros net per month
Duration: 8 months
Expected hire date: January 2022
Keywords: crisis management, GAMA, agent-based simulation, routing algorithms vehicles
Required profile : • Engineering degree or master's degree in computer science.
• Solid knowledge in object programming and in particular in Java; Python
• Knowledge of Multi-Agent Systems and / or information systems geographic areas would be appreciated.
• Good level of English (especially reading and writing)
Application procedures: submit, before December 20, a CV, a letter of motivation and possibly letters of reference to [email protected] and [email protected]
Context: The beginning of the 21st century is clearly marked by a succession of crises - environmental, civil, sanitary, etc. - which affect the entire globe.
The consequences directly and indirectly induced by these crises are very often dramatic, in terms of casualties (injured and dead) and environmental impacts.
The costs associates frequently reach several billion, with economic repercussions undeniable on our society.
In this context, it becomes necessary to limit as much as possible consequences of this type of crisis, and therefore anticipate their appearances and manage effectively when they arise.
Crisis managers must therefore have the best tools at their disposal to be able to understand a crisis situation, identify the possibilities for action and their possibilities consequences, and choose those to implement.
However, the current crisis management tools used appear very often undersized to be really effective, and above all disconnected from the digital transition underway in our society.
Based on this observation, the Criz’Innov1 project , in which this offer fits, proposes to equip the crisis unit of tomorrow, to allow it to have a synthetic view of the situation, a vision of its evolution over time and to obtain recommendations on actions and decisions to be taken associated with the identified risks and effects.
Missions: The recruited engineer will have to connect a module to a micro-services architecture optimization to calculate the routes of emergency vehicles (ie. emergency evacuation sequences).
It will also have to develop, with the platform GAMA, a spatialized multi-agent simulation module allowing to visualize the dynamics and the impact of the crisis phenomenon of one of the Criz’Innov project case studies.
This last simulation module must then be connected to the microservices architecture.
Technologies: The technology to be used for the simulation module is essentially GAMA.
The technologies / tools of the route optimization module are: Python, Json, the knowledge of Gurobi would be a plus.
The technologies / tools used in the convergence space are: PostGIS, MongoDB, OrientDB; REST WebServices; EDA architecture based on Apache Kafka
Laurent Prévot [email protected]
Postdoc on "Discourse Segmentation and Parsing of Spoken Conversations"
Laboratoire Parole et Langage (Aix-En-Provence) / LINAGORA Labs (Toulouse) / IRIT (Toulouse Computer Science Institute)
Applications are invited for a 24 month postdoctoral position on discourse modelling for spontaneous, spoken conversation within the context of the ANR project SUMM-RE (ANR-20-CE23-0017, https://anr.fr/Projet-ANR-20-CE23-0017).
The long-term goal of SUMM-RE is to improve algorithms for automatic meeting summarization and meeting minutes. The central hypothesis of the project is that such systems will benefit greatly from exploiting rich information carried by discourse relations (Explanations, Questions/Answers, Corrections…) and discourse structure (in the form of graphs). One of the major objectives of the project is therefore to develop an incremental discourse parser for spontaneous conversation, building on extant work by SUMM-RE members using weak supervision (Badene et al. 2019).
Discourse parsing will be done on English (the AMI corpus) and French data, but the principal focus will be on a 100h corpus of meetings in French whose creation will be completed by the time the postdoc starts.
The postdoc recruited for this position will be in charge of (i) adapting models of discourse segmentation (e.g. Muller et al. 2019) to meeting-style conversation by building on recent advances with weak supervision (Gravellier et al. 2021) and integrating both speech and acoustic parameters in the segmentation model; (ii) applying insights from discourse segmentation, which provides the foundation for discourse parsing, to improve the incremental discourse parser;
(iii) considering and developing mitigation strategies for working directly on ASR output (rather than on gold human transcribed data) for both discourse segmentation and parsing. (The French corpus is transcribed automatically with LINAGORA’s state-of-the-art speech-to-text system, LinSTT.)
Given these tasks we are looking for a candidates with as many of the following skills as possible:
- Experience with speech and ASR, and conversational speech in particular
- Dialogue/conversation/interaction analysis and modeling
- Machine Learning, in particular Weakly Supervised and Unsupervised approaches
- Multimodal (speech + text) Deep Representations for Natural Language Processing
- Multilingual model transfer
We aim for a starting date around April 2022. The salary will be determined according to French university standards (ranging from 2000 to 2300 euros / month depending on experience, after tax and health insurance coverage).
Funding for presenting relevant research results at conferences will be covered by the SUMM-RE project.
A minimal command of French is desirable as the postdoc will be required to handle a large French corpus; mastery of French is, however, not required.
The postdoc will ideally be hosted by the Laboratoire Parole et Langage (LPL), though exceptions will be considered for candidates who wish to be based at IRIT.
LPL is located in the center of Aix-en-Provence (http://www.aixenprovencetourism.com/), a sunny, medium-sized city of South East France, nestled in the Provence countryside, 30 minutes from the Mediterranean and 1h30 from the Alps. It is an active lab currently involved in several large scale projects (Institue for Language Communication and the Brain, https://www.ilcb.fr/ ; Conversational Brains, https://www.cobra-network.eu/), offering a stimulating research environment and a large and diverse opportunities of collaborations.
IRIT is located in the southwestern city of Toulouse, the fourth-largest city in France, only an hour from the Pyrénees and two hours from the Mediterranean. IRIT, and in particular the MELODI team, brings internationally recognized expertise in natural language processing, especially in the subdomains of discourse segmentation (Muller et al. 2019); machine learning for discourse parsing, including approaches using weak supervision (Badene et al. 2019); theories of discourse structure (SDRT; Asher & Lascarides 2003); and exploitation of corpora for studying discourse structure, both monologue and multilogue (Asher et al. 2020).
A curriculum vitae and a list of publications should be sent to Laurent Prévot ([email protected]) no later than January 31st, but we strongly encourage potential candidates to submit their applications as soon as possible, as we might fill the position earlier.
For more information, please visit the following web pages:
SUMM-RE: anr.fr/Projet-ANR-20-CE23-0017, https://labs.linagora.com/summ-re/
Laboratoire Parole et Langage: https://www.lpl-aix.fr/en/welcome-to-lpl/
LINAGORA Labs: labs.linagora.com
MELODI @ IRIT : https://www.irit.fr/departement/intelligence-artificielle/equipe-melodi/
Christophe Zimmer [email protected]
*NLP and deep learning against pandemics* (2 year postdoc) Collaborative project "ComCorText"
*Keywords:* NLP, AI, deep learning, epidemiology, risk factors, outbreak detection.
*Host lab**:* Imaging and Modeling Unit (https://research.pasteur.fr/en/team/imaging-and-modeling/), Institut Pasteur (https://www.pasteur.fr/en), Paris, France
Collaboration with the Epidemiology of Emerging Diseases Unit https://research.pasteur.fr/en/team/epidemiology-of-emerging-diseases/ (Institut Pasteur) and Sanofi
The COVID-19 pandemic has abundantly illustrated the importance of quickly identifying the factors that increase or decrease pathogen transmission. An early understanding of the airborne nature of SARS-CoV-2 transmission, for example, could have helped slow down the pandemic and reduce its human burden. In this project, we will explore the potential of natural language processing (NLP) methods to automatically identify risk factors and protective factors by analyzing large corpora of unstructured text.
This project takes advantage of the unique resource provided by the ComCor study, which contains free text descriptions of suspected circumstances of contamination from >50,000 individuals tested positive for COVID-19, totaling well over 500,000 words. The proposed project will mobilize state-of-the-art NLP techniques based on deep learning, such as contextualized word embeddings learned by transformer models (e.g. BERT).
Methods developed in this project will be tested and validated primarily (but not exclusively) on the ComCor data set in collaboration with the Epidemiology of Emerging Disease Unit of A. Fontanet.
Once validated, we will also explore applications of these methods to other text data sets, including social media and data obtained in the framework of the AIOLOS project. AIOLOS is a French-German research program, that aims at supporting decision-making by integrating information from various to detect early signs of a new outbreak, monitor its spread and derive appropriate response measures. A total of 17 partners (5 main partners, including Sanofi and Fraunhofer and 12 associated partners, including Institut Pasteur) are involved in this project.
*We are looking for a highly motivated and autonomous candidate with a solid background in NLP or related fields to lead this project.* Please send applications (motivation letter + CV with names of 2-3 references) to Ch. Zimmer ([email protected]) and Tiffany Charmet ([email protected])
Hello A position of lecturer in the field of image / artificial intelligence for health will be opened at the University of Reims Champagne-Ardenne as part of the 2022 synchronized competition campaign.
The integration will be done within the CReSTIC(https://crestic.univ-reims.fr)for research, and the IUT of Reims (Computer Science Department) for teaching.
Keywords: image analysis; machine learning; data analysis; 3D imaging; biological data.
The CReSTIC develops research activities in computer science related to medical issues. In particular, CReSTIC collaborates with several departments within hospital structures (nuclear medicine, radiology, neonatology, endocrinology, etc.) as well as major players in the industrial world (construction of imagers, development of free software, etc.), and strives to develop digital methods and tools dedicated to the extraction of information from medical data (3D imaging, electrophysiological signals, biological data, patient journey...).
The recruited candidate will reinforce the teams and researchers working on these activities. He/she will interact with medical actors, as well as researchers and teacher-researchers in computer science but also from disciplines related to these fields (mathematics, biology ...).
He/she will be required to quickly take charge of thesis / internship supervision, and to develop new collaborative activities through academic and/or industrial structuring projects (ANR, Cifre, etc.). The skills expected of the candidate relate to image (analysis, processing), artificial intelligence (machine learning, data analysis, etc.) and the application of these fields in a medical context.
If you would like further information please contact:
- for the research component: Nicolas Passat (Deputy Director of the CReSTIC): [email protected]
- for the teaching component: Jean-Michel Nourrit (Head of the Computer Science Department of the IUT of Reims): [email protected]
Nicolas Passat Professeur en Informatique Université de Reims Champagne-Ardenne [email protected]
Main subject: Image Processing (Tracking, Pattern Recognition, Mapping) & Eye Tracking
Place: GREYC (https://www.greyc.fr ) University of Caen Normandy
Starting: 15/01/2022. Length: 8 months.
Salary: 2264 €/month net of charge (indice 600).
Criteria of eligibility: to have a PhD or a certificate of school of engineer
Context of the project The DynACEV – Eye Tracking project is co-funded by the French National Agency of Research (ANR) and the Regional Council of Normandy. It combines knowledge and methodologies in the human movement sciences, computer sciences and applied mathematics. The primary aim is to investigate visual-motor skill acquisition in climbing task during a learning protocol where various performance contexts are tested: constant practice, variable practice where the rate of novelty is imposed by the experimenter and variable practice where the rate of novelty is chosen by the participant. During this protocol, we particularly focus on studying how vision guides action by tracking and mapping the visual fixation, the hip trajectory and the hands and feet location into the climbing wall plan.
Description of the work The objective of the present work is to track the spatiotemporal coordinates of the point of gaze of a climber and to analyse the scan path of his/her visual intake during ascension on an artificial climbing wall. The task is composed by the following sub-tasks:
- We focus on spatiotemporal analysis of climber and we extract measures related to route of climbing. Then, we study some range of variables related to climbing behaviors.
- We update an existing interface allowing from the eye tracking system to recognize the colored markers, to calculate the visual fixations and then to place these fixations on the plane of the wall. This updated version would be done by considering a time-serie of colored markers.
- For event-detection, we synchronize the eye tracking signal, the signal from the video fixations and the signal from the camera (tracking the hip) using an automated strategy in order to achieve a smooth pursuit and a efficient discrimination of fixations.
PS: a previous work has been completed and will be provided to the applicant to facilitate the understanding of the project.
The data are already collected and correspond to:
- Eye tracking information from Tobii eye tracker system; it provided video of the local scene and visual fixation, saccade, pursuit, etc. We also record additional colored markers that we put on the wall to enrich the number of areas of interest in order to better recognize the local scene.
- Location and time of contact of the hands and feet (through instrumented holds)
- External video of the climbing wall from a calibrated monoscopic camera
- 2D external video (from GoPro5) of the climber (especially the hip trajectory, projected on the wall plan)
No real-time needed, processing can be done offline.
Key words: Eye Tracker, Point of gaze spatiotemporal tracking, Mapping, Pattern Recognition
The candidate is requested to have a PhD in Image and/or Signal processing. An important knowledge of programming langauages f programming Python or C or Matlab is primordial. The work will be done in Caen and supervised by Youssef Chahir from the university of Caen Normandy and Ludovic Seifert from the University of Rouen Normandy.
To apply or for further information please contact:
Youssef Chahir, GREYC, Univ. of Caen Normandy, France: [email protected]
Ludovic Seifert , CETAPS, Univ. of Rouen Normandy, France: [email protected]
Hello everyone, (english announcement follows) as part of the future Interdisciplinary Center for Defense and Security Studies (CIEDS) of the Polytechnic Institute of Paris, we are launching a project dedicated to the evaluation of the cybersecurity of complex systems in realistic environments.
The project, named CERES, is funded by the Defence Innovation Agency of the Ministry of the Armed Forces, and as such, European applications are privileged.
We offer several Master's internship (pre-thesis) and postdoctoral fellowships (descriptions available on http://www-public.telecom-sudp aris.eu/~blanc_gr/jobs.html): - an 18-month postdoctoral stay on the topic "Simulation/co-simulation/emul ation to model systems and threats" - an M2 internship on the topic "Security modelling and evaluation"
- an M2 course on the subject "Digital twin
to secure the technical management of building" We kindly ask interested persons to follow the instructions indicated at the link above.
Otherwise, we would be grateful if you could circulate these offers to the people concerned.
Offers are to be filled as soon as possible.
Happy holidays, Gregory Blanc *** we are launching a project dedicated to the evaluation of complex systems cybersecurity in realistic environments.
The CERES project is funded by the Defence Innovation Agency (French Armies Ministry), and thus, applications from European citizens are favoured.
We are offering several grants for Master thesis internships (pre-doctoral) and postdoctoral studies (more details at http://www-public.telecom-sudp aris.eu/~blanc_gr/jobs.html ) : - one postdoctoral grant (18 months) on the topic of "Simulation/co-simulation/emul ation to model systems and threats" - one Master thesis internship on the topic of "Security Modelling and Assessment" - one Master thesis internship on the topic of "Digital Twin for Securing Building Management Systems"
Prospective candidates are invited to follow the instructions detailed at the above link.
At least, we would be grateful if you could circulate the offers to potential candidates.
These offers are to be filled as soon as possible.
Best wishes, Gregory Blanc
Hello Topic: "Topological multi-co-clustering of multi-view data" proposed by LIPN (UMR CNRS 7030) and funded by AMIES and Start-up HephIA.
Details of the subject are available here: https://bit.ly/3s1fB6X
How to apply: https://bit.ly/3s1fB6X
From February 2022, 18 months
Best regards Mustapha Lebbah
Sorbonne Paris NordUniversity, Laboratoire d'Informatique de Paris-Nord (LIPN), CNRS(UMR 7030), 99, BC Clément F-93430,
Villetaneuse, France. Tel: +331 49 40 38 94 Fax: +331 48 26 07 12
http://www-lipn.univ-paris13. en/~lebbah