Context: In recent years, the issue of resource efficiency has also become increasingly important in con- struction engineering, as soil and rock account for more than 50% of mineral construction waste.
Tunnel projects play a special role in this regard, as large quantities are generated at specific times and places. Due to the high degree of mechanisation and the associated advantages in terms of construction performance and safety at work, almost the half of tunnels is built with Tunnel Boring Machines (TBM).
For documentation and control of the construction process, these are equipped with various sensor systems that provide comprehensive data sets. But in this area, modern data- driven processes have not yet found a wide application.
This 24-month research engineer position is funded by the French-German ANR project REMATCH. The overall objective of this project is to use the data sets from TBMs, with the help of AI methods, to enhance the recycling of the large quantities of tunnel excavation material.
In this regard, an innovative real-time measurement system for material characterisation is to be developed which gives decision support on the question if soil is “usable” or “not usable” for other purposes and thus has to be disposed of in a landfill.
This system will base on several approaches using AI methods: firstly, on image recognition of excavated material, secondly, on intelligent data processing of TBM data, and, thirdly, on a knowledge database.
The objectives of this position are to develop a computer vision system that analyses the videos captured from one or several cameras installed at the TBM and filming the excavated material on the conveyor belt.
In order to decide on the possible reuse of the material, different geophysical properties need to be estimated from visual features extracted in real-time from the video stream(s) coming from RGB cameras. This is challenging due to the mediocre acquisition conditions under low lighting and fast motion inducing some motion blur.
In order to make the acquired data ready for machine learning models, different normalisation and image/video enhancement techniques have to be applied as a pre-processing step, and some relevant features may be extracted by conventional image processing methods.
Then, a first step is to develop a machine learning solution based on appropriate CNN models that are trained for either classification and/or regression tasks in a supervised manner. Different models should be designed, implemented and evaluated in terms of robustness and precision.
After evalating these models, they should be appropriately integrated with other AI models that are not based on images but on TBM sensor data, and finally, a system should be developed that operates in real-time on a stream of images and acts in a control loop with the TBM.
The position is in the IMAGINE team of the LIRIS laboratory in Lyon (Campus La Doua) under the supervision of Catherine Pothier and Stefan Duffner, and collaborating with other engineers and/or post-docs on the project as well as the other members of the French-German project consortium. Thus the candidate should participate in the project meetings in Lyon/Paris and Germany (Cologne, Schwanau) and maybe do regular visits of the construction site (Paris) or experimental setup (Cologne or Schwanau, Germany).
The funding is for 24 months. Additional teaching activities may be conducted at INSA Lyon if the candidate desires to. Contact: Stefan Duffner [email protected] and Catherine Pothier [email protected]
Context: In recent years, the issue of resource efficiency has also become increasingly important in con- struction engineering, as soil and rock account for more than 50% of mineral construction waste.
Tunnel projects play a special role in this regard, as large quantities are generated at specific times and places. Due to the high degree of mechanisation and the associated advantages in terms of construction performance and safety at work, almost the half of tunnels is built with Tunnel Boring Machines (TBM).
For documentation and control of the construction process, these are equipped with various sensor systems that provide comprehensive data sets. But in this area, modern data-driven processes have not yet found a wide application.
This 24-month post-doc position is funded by the French-German ANR project REMATCH.
The overall objective of this project is to use the data sets from TBMs, with the help of AI methods, to enhance the recycling of the large quantities of tunnel excavation material.
In this regard, an innovative real-time measurement system for material characterisation is to be developed which gives decision support on the question if soil is “usable” or “not usable” for other purposes and thus has to be disposed of in a landfill.
This system will base on several approaches using AI methods: firstly, on image recognition of excavated material, secondly, on intelligent data processing of TBM data, and, thirdly, on a knowledge database.
The objectives of this post-doc position are to develop a computer vision system that analyses the videos captured from one or several cameras installed at the TBM and filming the excavated material on the conveyor belt. In order to decide on the possible reuse of the material, different geophysical properties needs to be estimated from visual features extracted in real-time from the video stream(s) coming from RGB cameras.
This is challenging due to the mediocre acquisition conditions under low lighting and fast motion inducing some motion blur. More specifically, after some preprocessing, a first step is to develop a machine learning solution based on appropriate CNN models that are trained for either classification and/or regression tasks in a supervised manner. Different models should be designed, implemented and evaluated in terms of robustness and precision.
To go further, novel innovative neural network-based architectures and weakly supervised learning schemes should be proposed to learn a latent representation that reflects the meaningful similarities of relevant soil characteristics.
Then, potentially other physical properties should be incorporated more explicitely into this semantic latent representation (either via a specific CNN or autoencoder- type model) to make the learnt features and models more explainable. After evalating these models, they should be appropriately integrated with other AI models that are not based on images but on TBM sensor data.
The position is in the IMAGINE team of the LIRIS laboratory in Lyon (Campus La Doua) under the supervision of Catherine Pothier and Stefan Duffner. The funding is for 24 months.
Additional teaching activities may be conducted at INSA Lyon if the candidate desires to. Contact: Stefan Duffner [email protected] Catherine Pothier [email protected]
We are hiring a postdoc within our research team at Orange Rennes. Full details about the position and the application procedure are available here https://orange.jobs/jobs/v3/offers/116910?lang=EN.
Duration : 15 months (potentially extensible to 18 months) - Expected starting date January 2023
Team : SyCoSMA at LIRIS-CNRS (UMR 5205), University Claude Bernard-Lyon 1
Project : PepperMint funded by ASLAN Labex
Partners: LIRIS (SyCoSMA, SAARA Teams), ICAR (InSitu Team), University of Oulu-Finland (GenZ),
Supervision: Pr. Salima Hassas , Dr. Mathieu Lefort
Context PepperMint (Interacting with Pepper: mutual learning of turn-taking practices in HRI) is funded by the ASLAN Labex.
It proposes an exploratory study of embodied turn-taking practices in task-related Human-Robot Interaction (HRI) to improve the social abilities of robots and make HRI more natural to humans.
The project initiates a cooperation between researchers in AI (Artificial Intelligence) (LIRIS) and CA (Conversation Analysis) (ICAR and GenZ Oulu - Finland). It investigates if and how CA findings on natural occurring interaction can be used to develop innovative and effective AI models for HRI.
The project is grounded in a detailed multimodal analysis of turn-taking in naturally occurring HRI, putting forward the emergence of turn allocation as complex sequential and multimodal practices.
The project is built upon existing works on AI/ML (Machine Learning) algorithms of the state of the art to program an application for reception and orientation of people in an university library. Previously, we recorded human-robot interactions based on a first ad-hoc version of the robot with state of the art algorithms and ad-hoc turn-taking practices. These data are used in CA studies to identify successful interactions.
The goal of this post doc is to use this annotated dataset for machine learning methods to propose a new AI model for HRI, coupling developmental learning and CA findings. The detailed missions of the Post Doc will be:
– To review the state of the art algorithms for Turn-Taking.
– To collaborate with another Post-Doc in the field of Conversation Analysis, to clean and prepare the annotated data that will be produced by the CA researchers, and create new algorithms for ML according to CA findings.
– To develop a new version of the HRI application with new ML (oriented towards Developmental Learning) algorithms to improve turn-taking practices in HRI. – To contribute to the (scientific) communication activities of the PepperMint Project.
We are looking for a Post Doc to join our project team composed of researchers, engineers and practitioners in the field of AI / Social Robotics and CA.
The ideal candidate will have the following skills and background: – Strong Expertise/Experience/Background in AI and Machine Learning – Good development/programming skills in Object Oriented Programming (e.g. Java, C++, Python)
– Fluent or good level in written English
– Open mindness, teamwork, autonomy and capacity to interact with other disciplines like social sciences.
– Interest in interdisciplinary research – Knowledge in Social Robotics (Human Robot Interaction) would be a plus
Applications should include a detailed curriculum vitae, a statement of interests and two reference contacts.
Applications and letters should be sent via electronic mail to: [email protected]; [email protected] and [email protected]
Deadline for application: October 20th, 2022 (Please note that 2 to 3 months will be taken by the administration for the hiring procedure)
The recruited candidate will be employed by: CNRS, Université Claude Bernard-Lyon 1, at LIRIS-CNRS Laboratory, located at Nautibus building, Lyon.
Context: Collaboration between Scienomics/Paris and IRIT/Toulouse
In product development materials are selected and designed based on several criteria including performance, cost of production, availability, recyclability, and others. It is commonly accepted that the chemical space covers at least 1063 molecules making therefore the discovery of new materials with optimal design an impossible task to be performed following exhaustive screening and testing. Learning from known chemicals, translating the design requirements of the products and the constraints of the related processes into requirements for the materials to be discovered and testing then using virtual experiments is a viable route to follow.
SCIENOMICS is developing SIMAGORA, an online marketplace offering virtual experiments for the eco-conception and development of products, and the materials needed. It implements no-code concepts and allows interoperability between simulation engines from diverse domains. The aim is to democratize simulation technology and will provide to the international scientific community the capability to offer cutting-edge virtual experimentation technology to all companies worldwide.
In SIMAGORA semantics will play an important role since it will allow to gather experience and expertise available and implemented in technology that will be used to assist SIMAGORA users to take decisions. Ontologies are one of the critical technologies since they provide a formal ground for a self-guided online AI agent employing decision algorithms and provides automated virtual experimentation strategies for materials discovery and product development.
This post-doc will have the main task of performing research and development activities for enabling semantics-aware data access, integration of heterogeneous sources and interpretation in terms of product design objectives in SIMAGORA. It involves the generation of simulation scenarios (structured graphs in the simulation space) based on ontologies rather than building them ad hoc. Therefore, the project consists of three main activities:
(a) research and development in ontologies that will allow to capture product design and materials knowledge; (b) conceive methodologies to develop and evaluate knowledge graphs and (c) contribute to the conception of an AI agent, “robo-advisor”, capable to assist in materials discovery and product development through virtual experimentation execution.
Applicants are required to have a PhD in Computer Science, a strong background in semantic web technologies, ontology engineering, ontology construction and reasoning. Fluency in written / spoken English is required too. A good publication record and strong programming skills will be a plus.Capability to integrate a diverse group of people and supervise research and development work of PhD candidates.
Localization : Scienomics, 16 rue de l’Arcade, 75008 Paris, FRANCE with short visits at IRIT, Institut de Recherche en informatique de Toulouse (IRIT) - UPS, 118 Route de Narbonne F-31062 Toulouse Cedex, FRANCE. Duration : 12 months, starting ASAP – 3 months of trying. Salary between 2 131 and 3 338 euros (depending on experience)
Applications will be accepted until the position is closed. Applicants should send a full Curriculum including a complete list of publications, a cover letter indicating their research interests, achievements to date and vision for the future, as well as either support letters or the name of 2 persons that have worked with them. Contact: Cassia Trojahn [email protected] and Scienomics [email protected]
We are looking for a Python/C++ developer, who knows structural biology (basics in ML/DL would be a plus) for a CNRS contract in connection with an award-winning project by a large pharmaceutical group.
This project aims to develop health-targeted protein design methods, combining AI and methods inspired by robotics.
For more information about the position, see
https://docs.google.com/document/d/1wsn-YBQQkvwJgRSzW1vnP_8O0-aOt4xX/export?format=pdf
Application : Please submit your application via the CNRS Jobs Portal: https://emploi.cnrs.fr/Offres/CDD/UPR8001-JUACOR-008/Default.aspx?lang=EN
For additional information, please contact Sophie Barbe [email protected] , Juan Cortés [email protected] ; and Thomas Schiex [email protected] .
You will find below a thesis offer which will start in November 2022 to be discussed (CIFRE):
Topic: Learning for Intent Recognition and conversation management
Reception: SyCoSMA team, LIRIS laboratory / Reecall company, Lyon, CIFRE context Keywords: deep learning, conversational agents, AI, natural language processing (NLP), intent recognition (NLU), few shot learning, active learning, goal-oriented dialog systems
Detailed subject: https://perso.liris.cnrs.fr/frederic.armetta/sujetTheseNLP-2022.pdf
As part of a collaboration contract between the LCIS laboratory and the Healabs company, we are recruiting for 1 year a post-doctoral researcher in the healthcare decision support.
The project aims to integrate, within a tele-monitoring solution, an MAS whose function is to identify risk situations in patients with lymphedema.
Postdoc and Ph.D. in the area of Computer Vision and Deep Learning applied Deepfake Generation and Detection at INRIA Sophia Antipolis, France We are looking for following positions.
Ph.D. deepfake generation https://jobs.inria.fr/public/classic/fr/offres/2022-05263
Postdoc deepfake detection https://jobs.inria.fr/public/classic/fr/offres/2022-05361
Inria is situated in the South of France, in the heart of Europe :)
To apply, please email a full application to Antitza Dantcheva ([email protected]), indicating [DEEPFAKE JOB] in the e-mail subject line.
Location: Clermont-Ferrand, France Host institutions: Institut Pascal and the city hospitals of Clermont-Ferrand and Saint-Etienne
Starting Date: when student found Funding Duration: 3 years Supervisors: Dr. Erol Ozgur, Dr. Mohammad Alkhatib, Prof. Adrien Bartoli, Prof. Youcef Mezouar.
Application Deadline: Open until filled
Project: This position will be funded by IMMORTALLS, an ANR-JCJC project.
Context: Liver cancer is a leading cause of cancer death worldwide. An estimated 830,000 people around the world died from the disease in 2020. Liver resection is considered as one of the most effective treatments.
In this respect, laparoscopic liver resection (LLR) comes up by reducing substantially patient trauma compared to open liver resection. The patient recovers faster which in return reduces healthcare costs.
However the use of LLR remains limited. This is because of three challenges. First, controlling intraoperative bleeding using laparoscopic instruments requires advanced technical skills. Second, the surgeon cannot manually palpate the liver and thus cannot locate the tumours and their resection margins easily. Consequently this raises a risk of inadequate resection on the patient’s liver such as the removal of too much healthy tissue and the leaving of some cancerogenous tissue behind.
Third, laparoscopic ultrasonography (LUS), the only tool for intraoperative subsurface imaging which allows real-time tumour localisation, has a long learning curve. This is because its design consists of a small transducer with a small field of view attached to the end of a long shaft with a pivoting mechanism.
In order to ease LLR, augmented reality (AR) based methods relying on preoperative data were proposed [1,2].
These AR-based methods predict the location of the tumours by overlaying the preoperative data onto the laparoscopy image.
These methods require the whole liver to be visible as much as possible in the laparoscopy image to make a reliable prediction.
However, the liver is usually very partially visible (i.e., about 30% or less).
Although these methods are useful to guide surgeons at the very beginning of surgery, they are neither real-time nor automatic.
[1] “Combining Visual Cues with Interactions for 3D-2D Registration in Liver Laparoscopy”, Annals of Biomedical Engineering, 2020. [2] “Augmented Reality Guidance in Laparoscopic Hepatectomy with Deformable Semi-automatic Computed Tomography Alignment”, Journal of Visceral Surgery, 2019.
Links: http://igt.ip.uca.fr/~ab/ https://erol-papers.github.io
Research: We are looking for one highly motivated PhD student to study on multimodal liver tumour registrations and augmentations to be able to guide the surgeons during LLR. The PhD student will focus on two open problems.
1/ Automatic and real-time deformable registration of a preoperative CT volume to an intraoperative LUS image without any additional tracker sensor.
2/ Augmentation of the subsurface liver tumours and veins in the laparoscopy images (i.e., occluded object visualisation) on a flat screen with the relevant depth cues such that their depth can be conveyed to the surgeon accurately.
The successful outcome of the PhD will simplify mini-invasive liver surgery.
It will shorten hospital stays, improve surgical safety and accuracy, and contribute to an overall better quality of patient life and reduction of healthcare costs.
Requirements: 1/ undergraduate and graduate degrees on Computer Science or closely related fields;
2/ excellent programming skills in C++ and python;
3/ strong theoretical and applied background in computer vision and machine learning;
4/ experience in augmented reality;
5/ proficiency in written and spoken English language.
Application: Applicants must submit 1/ a one-page cover letter, 2/ curriculum vitae with publications list and contacts of 2 references, 3/ a copy of academic transcripts (bachelor/master grades), 4/ availability (the earliest possible starting date).
Applicants must be prepared to provide two reference letters upon request.
Once we receive your application and it fits well to the position, you will be contacted within two weeks.
Applications should be sent, *in a single PDF document*, with the email subject [IMMORTALLS PhD application] to: [email protected]; [email protected]; [email protected]; [email protected]
Dear colleagues, We are looking for a post-doc to work on an exciting interdisciplinary project funded by Cancer Research UK, within the team Translational Healthcare Technologies (www.tht.ac.uk), based in the Centre for Inflammation Research at the University of Edinburgh.
The role is to investigate data-driven technologies for lung cancer characterisation and detection using fluorescence lifetime imaging microscopy (FLIM), centred on one of the two areas: (1) data-driven identification of autofluorescence lifetime signatures for lung cancer, and (2) deep learning-based synthesis of histology images from FLIM images.
The job advert: https://edin.ac/3BBKGkW
Post: 12 months, Grade 7
Closing date: 4th October
Dear fellow roboticists, As part of our Advanced Technology division, our talented robotic engineering teams are working to automate physical processes that require sensing and judgement through the use of robotics and machine vision.
Currently, our focus is on picking and packing groceries using robotic arms. The Adaptive Robotic Manipulation (ARM) team, within Advanced Technology, develops advanced grocery picking capabilities for our robotic pick solutions.
The ARM team is an application-oriented research team which develops and implements intelligent strategies to achieve robust and reliable sensor-driven grocery picking behaviours and validates them in a laboratory environment prior to adoption in production. This is a very challenging endeavour due to the vast range of different objects that need to be picked, the many different configurations of those objects and the variability in the way that the robot will encounter them. In order to deal with this highly unpredictable, complex, contact-rich environment we investigate the exploitation of all nature of sensory inputs (camera, tactile, force-torque, sound, etc.) for adapting the robot’s movements in real-time based on perceptual experience. The unstructured nature of the domain requires an imaginative and innovative approach to problem solving that employs a deep understanding of the potential capabilities of the various technologies and techniques available (hardware, software and algorithmic) coupled with a determinism to see a solution through to the point that it can be trusted to perform.
What would I be doing? Your role as a robotics research engineer within the ARM team will be to suggest and research possible solutions to our grocery picking problems, and implement solutions that can improve the current performance of our existing robotic picking systems. We also work alongside the teams that are closer to production to ensure that our solutions fit their problems in practice with testing and validation of our system in both laboratory and realistic production settings.
Your responsibilities include: Research and design novel computer vision/machine learning methods for problems such as: object tracking and pose estimation, semantic segmentation, real-time image registration, point cloud fusion, and sensor fusion.
Develop prototypes of these algorithms and demonstrate them in a laboratory environment.
Formulate and propose novel directions for research in perception for robotic manipulation that would improve our manipulation capabilities.
Collaborate with other research and production teams in robotic perception and manipulation.
Follow research developments in computer vision and perception for robotic manipulation which can be applied to our problems.
What are we looking for? This role suits an enthusiastic robotics researcher who has proven knowledge and experience in robot vision. We would like to hear from you if you have a PhD/MSc degree in robotics/computer vision, have efficiently worked in a team and have experience in:
C++ and/or Python programming
Developing and integrating robotics software
Applying computer vision techniques in robot control including visual servoing
Camera calibration techniques
Geometric computer vision, linear algebra and non-linear optimisation
Prototyping with any of the following: state estimation, object detection and pose estimation, scene understanding, 3D reconstruction, camera calibration, sensor fusion.
Bonus if you have experience in:
Working with robot manipulators
Training and evaluating Deep Learning models
If interested, please apply through the following link: https://careers.ocadogroup.com/job-description/software/robotics-research-engineer/JR-1911?utm_updated=1662711670789&utm_persistence_period=60
context Vocabularies and ontologies are key elements to ensure data interoperability. As part of the European FAIR-IMPACT project, the DATA TERRA research infrastructure will develop a portal of reference semantic artefacts for the Earth System and the Environment (EarthPortal). To set up this platform, we will use the OntoPortal technology, developed at Stanford for the NCBO BioPortal project, and we will collaborate with INRAE and the University of Montpellier who have developed and maintain the AgroPortal.
The semantic artifacts referenced on the platform must then be aligned with each other, and with the standards used in the European context (eg GeoDcat-AP). A tool for evaluating the FAIRness of semantic artefacts will be proposed in order to comply with European and French directives. This tool will be based on the O'FAIRe tool developed by the AgroPortal team.
Finally, the platform will be connected to the "Data Terra Data Warehouse" service in order to validate the use of this platform to improve the indexing and searching of data.
Assignment The person will be recruited within the framework of the Horizon Europe FAIR-IMPACT project. Its activities will mainly take place in the “Metadata and Ontologies” work-package. In this context, he/she will have to set up the EarthPortal platform, develop functionalities for management, alignment of ontologies and evaluation of FAIRness and connect the platform with the Data Terra data warehouse.
We will reuse technology developed by the National Center for Biomedical Ontologies at Stanford University: the OntoPortal web application made available through its virtual machine ( https://ontoportal.org ).
Also relying on the experience and technology developed by our partners, we will make EarthPortal a reference platform for alignment extraction, generation, validation, evaluation, storage and retrieval. between ontologies, by adopting a Semantic Web and open and linked data approach, and by engaging the community.
Your role will consist of both setting up the platform and analyzing the technical decisions needed to develop new features. You will be responsible for:
- Set up, manage and administer the EarthPortal platform and the FAIRness assessment tool for semantic artefacts, in collaboration with the AgroPortal and OntoPortal teams.
- Work on the integration of semantic artefacts from the different data centers of Data Terra and more broadly from the Earth System and Environment communities
- Facilitate the interoperability of different semantic artefacts (vocabularies, thesaurus, ontologies, metadata schemas, ...) in the EarthPortal.
- Work with the DATA-TERRA data warehouse development team to connect the EarthPortal to the data warehouse.
- Supervise technical courses in this context.
Technology
Web and full stack development, Java/JEE, TypeScript, Ruby/Rails, RESTful web services, XML/JSON, Web technologies (HTML5, Bootstrap, JavaScript), Semantic Web technologies (OWL, RDF, SPARQL, triplestore, Linked data) , OntoPortal technology.
GitHub repositories for more details: - https://github.com/OntoPortal/ - https://github.com/ncbo - https://github.com/agroportal
Profile We are looking for a motivated, curious and interested engineer and/or full stack developer with experience in web application development to develop and manage the platform. The candidate will hold an engineering degree or a master's degree in computer science. The candidate will demonstrate skills or matches with most of the following aspects:
- Web developer with development experience and knowledgeable in REST/JSON web services, JEE technologies, Ruby/Ruby On rails, Bootstrap, TypeScript. Some DevOps knowledge.
- Motivation for exploratory work in relation with scientists within the framework of a European project.
- Experience with Semantic Web technologies, including JSON-LD / RDF / OWL / SKOS / SPARQL
- Knowledge and/or experience in the field of the Earth System and the Environment is preferable
- Excellent remote working capabilities (emails, trackers, collaboration tools, etc.)
- Excellent ability to work with others and engage external users - Very good command of French and English both orally and in writing - Autonomy and initiative, technical decision-making within the framework of the project and justification of choices
- Open-source developer - Friendly person to join a small research team in Montpellier
Employer : CNRS
Context: FAIR-IMPACT project ( www.fair-impact.eu )
Duration: 20 months (with possible extensions)
Where: IR Data Terra- UAR CPST, Montpellier, France
Collaboration: MISTEA (INRAE), LIRMM (UMontpellier), BMIR (Stanford, USA)
Contact : [email protected]
To apply: https://emploi.cnrs.fr/Offres/CDD/UAR2013-KARLEJ-012/Default.aspx
The Lattice is recruiting a researcher on the subject "Impact of Artificial Intelligence on society" (M/F).
The position is to be filled on November 1, 2022, and is based in Montrouge (and more generally at the Ecole Normale Supérieure, in Paris).
He is also part of the 3IA Prairie Institute.
Full details of the offer and how to apply are on the CNRS job portal:
https://emploi.cnrs.fr/Offres/CDD/UMR8094-THIPOI0-007/Default.aspx
A Senior Researcher position is available at the Institute of Electronics and Computer Science (EDI), https://www.edi.lv/en, Riga, Latvia.
I would appreciate it if you could inform potential candidates (to whom you do not want to offer a position in your own group, of course) about this vacancy.
The position is open in the scope of the Horizon Europe project PRAESIIDIUM. The researcher is expected to take a leading role in the development of a next-generation wearable device.
Requirements include Ph.D. by start of the appointment, as well as enthusiasm and capabilities for applied research related to embedded systems, wearable computing, and signal processing.
This position is full time, with funding guaranteed for 3 years. Expected start date: January 1, 2023.
Application via email. Further details and contact information can be found at: https://euraxess.ec.europa.eu/jobs/841037
We are looking for a candidate for a PhD thesis in the field of emotion recognition from electroencephalographic (EEG) signals. The objective of the thesis is to perform statistical analysis of EEG signals and to find correlations between quantities extracted from the raw signals and the emotions associated with the signals during their recording. The candidate will first acquire EEG signals from several users to build a study database. The thesis will then have two stages:
1. As a comparison method, a ‘classical’ analysis of the data will be performed. That is to perform any necessary pre-processing (filtering, elimination of bad signals, estimation of the quality of the signals and decomposition into brain waves, i.e. alpha, beta, theta, gamma waves...), make a statistical study on the data (extraction of quantities from the processed signals, i.e. Hjorth parameters, spectral entropy, moments...), and to find correlations between these different quantities and the emotions associated with the signals.
2. This will lead to the development of machine learning ( particularly deep learning) algorithms to associate EEG signals with their corresponding emotions based on state-of-the-art models (transformers, convolutional neural networks, etc).
The thesis will be carried out in partnership between the company CEPHALGO (specialised in the development of hardware for the recording of EEG signals and their statistical study) under the supervision of Dr Jonathan Chardin and the ICube research laboratory under the supervision of Dr Thomas Lampert HDR, Chair of Data Science and AI (specialised in the development of machine learning and deep learning models). The candidate will share his/her time between the CEPHALGO company and the ICube research laboratory.
Keywords: Deep learning, Affective computing, Valence arousal model, Fourier transform, classifiers, machine learning, PCA, wavelets, statistical analysis.
Skills required: Master’s degree (M2) in Computer Science or similar with a strong mathematical component
Experience in machine learning projects, preferably in addition to Deep Learning
A solid knowledge of the python programming language and associated libraries (numpy, scipy, matplotlib)
Project management skills when collaborating with other research partners
Good interpersonal skills to interact with medical professionals and patients
Adventurous towards the dynamic startup environment and scientific challenges
Desirable skills: Good knowledge of signal processing (Fourier transform, wavelet decomposition, spectrograms, etc.)
Experience in working with EEG data or time-series would be a plus but not necessary
Care for patients suffering from mental disorders
About the company CEPHALGO: Created in 2020, CEPHALGO focuses on introducing technological innovations to assist medical professionals to provide better mental health care. Located in Strasbourg, extended beyond Europe, CEPHALGO’s patient monitoring technique using EEG and AI has been applied in psychiatry across Netherlands, Italy, Spain, Norway, Turkey, and Columbia. Further information can be found at https://cephalgo.com.
About the ICube laboratory: Created in 2013 (from the previous LSIIT laboratory), ICube brings together researchers of the University of Strasbourg, CNRS (French National Center for Scientific Research), ENGEES and INSA of Strasbourg in the fields of engineering and computer science, with imaging as the unifying theme. Further information can be found at https://icube.unistra.fr/en/.
Salary: Negotiable depending on the candidate’s profile. The offer of a thesis contract will be financed via the Cifre programme (Convention industrielle de formation par la recherche: https://www.anrt.asso.fr/fr/le-dispositif-cifre-7844).
Location: The candidate will have to carry out his/her thesis in France between the company's sites and the ICube laboratory, both based in Strasbourg.
How to Apply: Please send an email including your CV, motivation letter, and Master’s grades to Jonathan Chardin at the following e-mail address: [email protected]
28 months postdoctoral fellowship on EU HORIZON project OMEGA-X and ENERSHARE https://institutminestelecom.recruitee.com/o/postdoctoral-fellowship-on-european-energy-data-space-projects-with-edf-rd-28-months
18 months postdoctoral fellowship on the development of the ETSI SAREF ontology https://institutminestelecom.recruitee.com/o/postdoctoral-fellowship-development-of-the-etsi-saref-ontology-18-months
18 months research and development position on the development of our building's Digital Twin https://institutminestelecom.recruitee.com/o/postdoctoral-research-and-development-position-on-a-buildings-digital-twin-18-months-saintetienne
Title: A system for contextualizing security incident response ALEKSO company in partnership with the CEDRIC laboratory
The CEDRIC laboratory (Center for Studies and Research in Computing and Communications) brings together research activities in digital sciences carried out at the National Conservatory of Arts and Crafts ( https://cedric.cnam.fr )
ALEKSO is a young company born in September 2018, but already totaling more than 200 years of cumulative experience in cybersecurity.
ALEKSO responds to business challenges with a single cybersecurity solution that encompasses all system security needs of information.
Its field of intervention ranges from end-point security to security incident remediation, including perimeter security, access management, messaging protection, telecommunications security, security incident detection.
This “know-how” has enabled it to set up an operational security center and to equip itself with complete cybersecurity tools.
The objective of the thesis is to propose a decision support system to support the activity of a security expert responsible for responding to a proven incident.
In order to ensure its scalability and portability, the design of the projected system should be model-driven.
Places of practice: ALEKSO in Le Plessis-Robinson and CEDRIC Laboratory in Paris
Funding: 3-year fixed-term contract with ALEKSO under the terms of CIFRE-type funding
Estimated start of the thesis contract: November 2022. Possibility of having an internship before official recruitment.
Candidate profile: The candidate for this thesis must have: - a Master 2 research in computer science (or equivalent)
- skills in knowledge representation, semantic web and/or conceptual modeling of information systems.
- programming skills
He must also have a good command of French (oral and written) and English (oral and written) Cybersecurity knowledge and R&D expertise in cybersecurity will be a plus.
Recruitment procedure : The candidate must send by email to Ms. Lammari ( [email protected] ) a file consisting of:
- a detailed CV
- a copy of the Master's degree or any document attesting to the Master's level
- a copy of the Master's transcripts
- a copy of the identity card or passport
- a cover letter
I am recruting a new postdoc for the ARIAC project supported by Digital Wallonia.AI and the SPW Recherche that gathers tens of researchers accross Wallonia in artificial intelligence.
She/he will do research in the "trust mechanisms for AI" workpackage and help me to lead this workpackage.
She/he will be integrated in the Human Centered Machine Learning (HuMaLearn - https://humalearn.info.unamur.be) team at UNamur with around 10 other PhD and postdoc researchers and she/he will have collaboration opportunities thanks to the interdisplinary approach of ARIAC and of HuMaLearn.
Please spread the work and do not hesitate to contact me for further details. https://jobs.unamur.be/emploi.2022-09-13.7042797172/view