Skip to Main content Skip to Navigation
Theses

Détection des modifications de l’organisation circadienne des activités des animaux en relation avec des états pré-pathologiques, un stress, ou un événement de reproduction

Abstract : Precision livestock farming consists of recording parameters on the animals or their environment using various sensors. In this thesis, the aim is to monitor the behaviour of dairy cows via a real-time localisation system. The data are collected in a sequence of values at regular intervals, a so-called time series. The problems associated with the use of sensors are the large amount of data generated and the quality of this data. The Machine Learning (ML) helps to alleviate this problem. The aim of this thesis is to detect abnormal cow behaviour. The working hypothesis, supported by the biological literature, is that the circadian rhythm of a cow's activity changes if it goes from a normal state to a state of disease, stress or a specific physiological stage (oestrus, farrowing) at a very early stage. The detection of a behavioural anomaly would allow decisions to be taken more quickly in breeding. To do this, there are Time Series Classification (TSC) tools. The problem with behavioural data is that the so-called normal behavioural pattern of the cow varies from cow to cow, day to day, farm to farm, season to season, and so on. Finding a common normal pattern to all cows is therefore impossible. However, most TSC tools rely on learning a global model to define whether a given behaviour is close to this model or not. This thesis is structured around two major contributions. The first one is the development of a new TSC method: FBAT. It is based on Fourier transforms to identify a pattern of activity over 24 hours and compare it to another consecutive 24-hour period, in order to overcome the problem of the lack of a common pattern in a normal cow. The second contribution is the use of fuzzy labels. Indeed, around the days considered abnormal, it is possible to define an uncertain area where the cow would be in an intermediate state. We show that fuzzy logic improves results when labels are uncertain and we introduce a fuzzy variant of FBAT: F-FBAT.
Document type :
Theses
Complete list of metadatas

https://tel.archives-ouvertes.fr/tel-03121939
Contributor : Abes Star :  Contact
Submitted on : Tuesday, January 26, 2021 - 4:59:08 PM
Last modification on : Wednesday, February 24, 2021 - 4:24:03 PM

File

2020CLFAC032_WAGNER.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-03121939, version 1

Collections

Citation

Nicolas Wagner. Détection des modifications de l’organisation circadienne des activités des animaux en relation avec des états pré-pathologiques, un stress, ou un événement de reproduction. Technologies Émergeantes [cs.ET]. Université Clermont Auvergne, 2020. Français. ⟨NNT : 2020CLFAC032⟩. ⟨tel-03121939⟩

Share

Metrics

Record views

105

Files downloads

45