Phd: Continuous Learning Of Kinematic Walking Models With Inertial Signals To Improve The...

Universities and Institutes of France

France

July 9, 2021

Description

  • Organisation/Company: University Gistave Eiffel
  • Research Field: Computer science › Other
  • Researcher Profile: First Stage Researcher (R1) Recognised Researcher (R2)
  • Application Deadline: 09/07/2021 21:00 - Europe/Brussels
  • Location: France › Bouguenais
  • Type Of Contract: Temporary
  • Job Status: Full-time
  • Hours Per Week: 37
  • Offer Starting Date: 01/10/2021
  • Do you have a heart for the contribution of artificial intelligence in the construction of physical models, to address the challenges and needs of new mobility services? The inmob joint laboratory on the Nantes campus of the Gustave Eiffel University of France could be the next step in your career.

    CONTEXT

    Research at the Geoloc Laboratory of the Gustave Eiffel University focuses on the development of dynamic positioning methods and systems for travellers. It owns a wide range of skills in the design and programming of beaconless positioning and navigation algorithms with original testing facilities. The Okeenea Digital company is an innovative company from the Okeenea group, specialised for 26 years in the design and supply of accessibility solutions to improve mobility in situations of disability. These two organisations have joined forces in the joint laboratory inmob (disability mapping with INertial signal to facilitate MOBility) to improve the mobility of people with disabilities.

    Our ambition is to design new approaches based on artificial intelligence to build physical models that describe the individual specificities of movement of people with disabilities and thus individualise the positioning approaches. This research will increase the performance of current geolocation technologies, which are still insufficient to assist a blind or hearing- impaired person throughout his or her route in complete safety without depending on a very dense network of beacons. To strengthen the labcom team and contribute to the work in artificial intelligence for improved mobility services, we are looking for a research engineer or postdoc, ideally with complementary skills in physics/mathematics and artificial intelligence.

    RESEARCH TOPIC

    Geolocation on smartphones is considered functional by mobility service operators, but there is no sufficiently powerful solution to serve the needs of people with disabilities (PWDs). Beacon networks are being deployed and applications marketed to geolocate in buildings. These technologies pose problems of coverage, continuity of service, maintenance and cost. A lot of research has been carried out to avoid the use of beacons.

    They map radio signals' propagation, rely on collaborative approaches or consider biomechanical data fused with inertial signals recorded by our wearable devices to estimate our movements. The performance of these "autonomous" approaches has stagnated in recent years because they do not take into account the specificities of individual human gait to personalise localization algorithms. As a result, they do not consider the nature of the disability in the solutions, whereas connected tools should enable the individualization of these approaches. IThis observation is at the origin of this proposed research. The processing of the singularity of mobility profiles should allow improving the estimation of walking tracks without deploying any beacon.

    RESEARCH OBJECTIVES

    Research aims at continuous learning the walking gait and integrating the disability profiles into the core of learning. Novel processing of inertial data collected by a handheld smartsensor will be studied to improve the self- contained solution localization performance. We will first focus on the dimensions and specificity of the kinematic model using inertial signals, to reach stability over time for the same individual. A second challenge lies in the semi-supervised learning of this model with the data collected daily by a smartphone. The high noise level of the smartphone's sensors and the lack of a precise labels for daily movements are two other challenges. Finally, the research outcomes will have to be transferred to a smartphone for real-time operation in order to guide visually impaired people. Signal degradation and computational capacity limitations will have to be integrated.

    COMPETENCES

    MSc/Eng Degree in signal processing, geomatics, artificial intelligence or computer science

    Knowledge of signal processing, data mining, applied mathematics, machine learning methods and statistics

    Knowledge of multi-sensor fusion positioning and estimation theory

    Strong programming skills in Python, Matlab and TensorFlow (cpp preferred)

    Experience of working with machine learning applied to physics

    Proven ability to integrate large-scale data

    Understanding of connected object technologies and Android programming

    Ability to effectively integrate research results into publications and intellectual property

    Creativity and openness to innovation

    Enthusiasm, responsibility and excellent collaboration skills

    Passion for producing high quality data

    Strong oral and written skills in English

    HOW TO APPLY?

    Contract Type: 3 years full time (37h/week) with a start in October 2021

    Location: GEOLOC Laboratory, Gustave Eiffel University, Nantes, France

    Application: Send all documents (cover letter, CV, diplomas, list of productions / publications, references) in a single pdf document to valerie.renaudin@univ-eiffel.fr

    Offer Requirements
  • REQUIRED EDUCATION LEVEL
  • Computer science: Master Degree or equivalent

    Other: Master Degree or equivalent

  • REQUIRED LANGUAGES
  • FRENCH: Basic

    Skills/Qualifications

    MSc/Eng Degree in signal processing, geomatics, artificial intelligence or computer science

    Knowledge of signal processing, data mining, applied mathematics, machine learning methods and statistics

    Knowledge of multi-sensor fusion positioning and estimation theory

    Strong programming skills in Python, Matlab and TensorFlow (cpp preferred)

    Experience of working with machine learning applied to physics

    Proven ability to integrate large-scale data

    Understanding of connected object technologies and Android programming

    Ability to effectively integrate research results into publications and intellectual property

    Creativity and openness to innovation

    Enthusiasm, responsibility and excellent collaboration skills

    Passion for producing high quality data

    Strong oral and written skills in English

    Contact Information
  • Organisation/Company: University Gistave Eiffel
  • Department: AME - GEOLOC
  • Organisation Type: Higher Education Institute
  • Website: https: // geoloc.univ-gustave-eiffel.fr/en/
  • E-Mail: valerie.renaudin@univ-eiffel.fr
  • Country: France
  • City: Bouguenais
  • Postal Code: 44344
  • Street: Allée des Ponts et Chaussée
  • Similar Jobs

    Add to favorites Read more...

    Phd: Continuous Learning Of Kinematic Walking Models With Inertial Signals To Improve The...

    Location: France › Bouguenais Research at the Geoloc Laboratory of the Gustave Eiffel University focuses on to improve mobility in situations of disability. Our ambition is to design new approaches based on artificial intelligence to...

    Luxembourg Institute of Health

    Luxembourg Jun 5, 2021

    Add to favorites Read more...

    Data Scientist/Biofinformatician - GF0621

    LIH is looking for a highly motivated candidate in Data demonstrate a broad knowledge in statistical, machine- and deep learning LIH's data integration, target identification and precision health activities KEY SKILLS, EXPERIENCE AND QUALIFICATIONS Familiar...

    Inria

    France Jun 4, 2021

    Add to favorites Read more...

    PhD Position F/M Learning Statistical Human Anatomic Models of Shape and Motion

    2021-03783 - PhD Position F/M Learning Statistical Human Anatomic Models of About the research centre or Inria department with labs, research and higher education institutions in Grenoble and Lyon, Position: A full-time doctoral research position...