16/06/2021

PhD position: Automatic detection of circadian anomalies of dairy cows using wavelets and fuzzy logic


  • ORGANISATION/COMPANY
    Université Clermont Auvergne
  • RESEARCH FIELD
    Computer science
    Engineering
    Mathematics
    Physics
  • RESEARCHER PROFILE
    First Stage Researcher (R1)
  • APPLICATION DEADLINE
    02/08/2021 12:00 - Europe/Brussels
  • LOCATION
    France › Saint-Genès-Champanelle
  • TYPE OF CONTRACT
    Temporary
  • JOB STATUS
    Full-time
  • HOURS PER WEEK
    40

OFFER DESCRIPTION

Location

The PhD student will be based in the Universite Clermont Auvergne in France, in the following laboratories:

* This is a partnership between INRAE & the Université Clermont Auvergne, France, and the Complex Systems Institute at Ghent University, Belgium

Supervisors

The PhD student will be supervised by a team of inter-disciplinary supervisors.

Research work

The PhD thesis is part of a project which aims to develop methods for the early detection of health problems or stress through the behavior of an animal recorded by sensors. Ultimately, these methods could be implemented in precision livestock farming tools. A first machine learning method, to detect anomalies in activity rhythm, was designed using a Fourier transform (Wagner et al., 2020b). The candidate will have to continue this work to improve the reliability and accuracy of detection. He / she may explore the following approaches:

  • Refine the registration of time series in order to better compare them.
  • Relate the magnitude and direction of changes in the Fourier harmonics causing the anomaly (eg, overactivity in case of mastitis, less marked circadian rhythm in case of lameness)
  • Using higher order harmonics (so far only 0 and 1 orders have been used)
  • Using wavelet transform, more able to capture ultradians (peaks of activity during the day)
  • Use fuzzy logic to take into account the progressive onset and disappearance of disorders (promising results have been obtained (Wagner et al., 2020a)).

These developments will be tested on data sets already available (dairy cow activity level).

Training and skills

  • Master degree in Computer Science, Physics, Engineering, Applied Math, or any other relevant quantitative discipline
  • Strong background in Data Science or/and in Applied Mathematics
  • Knowledge of some programming languages (C/C++, MATLAB, Python)

Remuneration : 1500€/month

Application

Deadline June 30, 2021. Application must include a CV, an application letter, copies of Master diploma or grades.

Send your application package to Isabelle Veissier via email: Isabelle.Veissier@inrae.fr

References

Wagner, N., V. Antoine, J. Koko, and R. Lardy. 2020a. Fuzzy k-NN Based Classifiers for Time Series with Soft Labels. Pages 578-589. Springer International Publishing, Cham.

Wagner, N., Antoine, J. Koko, M. Mialon, R. Lardy, and I. Veissier. 2020b. Comparison of Machine Learning methods to detect anomalies in the activity of dairy cows. Pages 342-351 in Proc. IFoundations of Intelligent Systems. ISMIS 2020. Springer, Cham.

More Information

Benefits

Remuneration : 1500€/month

Offer Requirements

  • REQUIRED LANGUAGES
    ENGLISH: Excellent

Skills/Qualifications

  • Master degree in Computer Sciences, Engineering, Physics, Mathematics or other relevant quantitative discipline
  • Strong backgrounds in Data Science or/and in Applied Mathematics
  • Knowledge of some programming languages (C/C++, MATLAB, Python)

Map Information

Job Work Location Personal Assistance locations
Work location(s)
1 position(s) available at
Université Clermont Auvergne
France
Saint-Genès-Champanelle

EURAXESS offer ID: 652817

Disclaimer:

The responsibility for the jobs published on this website, including the job description, lies entirely with the publishing institutions. The application is handled uniquely by the employer, who is also fully responsible for the recruitment and selection processes.

 

Please contact support@euraxess.org if you wish to download all jobs in XML.