Using data mining techniques for improving dairy management

• Starting date: October 2017
• University: Bretagne Loire
• PhD school: MathSTIC  Rennes
• Scientific field:  Automatic learning
• Thesis management: Alexandre Termier (Université de Rennes – Inria), Philippe Faverdin (Inrae)
• Thesis supervisors: Véronique Masson  (Inria)
• Funding: #DigitAg – Inria
• #DigitAg : Cofunded PhD – Axe 5 – Challenge 4 

Keywords: Machine Learning, Explicability of Artificial Intelligence, Collective Reach, Multivariate Time Series

Abstract: The use and analysis of data acquired in dairy farming is a challenge both for data science and for animal science. Its goal is to improve farming conditions (health, welfare and environment) as well as farmers’ income. Nowadays, animals are monitored by multiple sensors giving a wealth of heterogeneous data (ex. temperature, weight, milk composition). Current techniques used by animal scientists focus mostly on mono-sensor approaches. The dynamic combination of several sensors could provide new services and information useful for dairy farming. In order to study such combination of several sensors, this PhD will be based on machine learning and pattern mining algorithms. The challenge is to design new algorithms taking into account such data heterogeneity, both from their nature and time scales, and to produce patterns that are actually useful for dairy management. This thesis will be an original and important contribution to the new challenge of the IoT and will interest domain actors to find new added value to a global data analysis. The PhD will take place in an interdisciplinary setting between computer scientists of INRIA and animal scientists of INRA, both located in Rennes.

Contact : alexandre.termier [AT] irisa.fr

Social network: LinkedIn

Communications & Papers

Thesis manuscript: Enhancing Performance and Explainability of Multivariate Time Series Machine Learning Methods: Applications for Social Impact in Dairy Resource Monitoring and Earthquake Early Warning

– K. Fauvel, D. Balouek-Thomert, D. Melgar, P. Silva, A. Simonet, G. Antoniu, A. Costan, V. Masson, M. Parashar, I. Rodero, and A. Termier. 2020. A Distributed Multi-Sensor Machine Learning Approach to Earthquake Early Warning. In Proceedings of the 34th AAAI Conference on Artificial Intelligence – AAAI’20 – https://dx.doi.org/10.1609/aaai.v34i01.5376
– K. Fauvel, V. Masson, and E. Fromont. 2020. A Performance-Explainability Framework to Benchmark Machine Learning Methods: Application to Multivariate Time Series Classifiers. In Proceedings of the IJCAI-PRICAI 2020 Workshop on Explainable Artificial Intelligence – IJCAI-PRICAI’20 – https://arxiv.org/abs/2005.14501
– K. Fauvel, T. Lin, V. Masson, E. Fromont, and A. Termier. 2020. XCM: An Explainable Convolutional Neural Network for Multivariate Time Series Classification. ArXiv (https://arxiv.org/abs/2009.04796)
– K. Fauvel, E. Fromont, V. Masson, P. Faverdin, and A. Termier. 2020. XEM: An Explainable Ensemble Method for Multivariate Time Series Classification. ArXiv (https://arxiv.org/abs/2005.03645)
– K. Fauvel, V. Masson, E. Fromont, P. Faverdin, and A. Termier. 2019. Towards Sustainable Dairy Management – A Machine Learning Enhanced Method for Estrus Detection. In Proceedings of the 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining – KDD’19 (https://hal.inria.fr/hal-02190790/)
– K. Fauvel, V. Masson, P. Faverdin, and A. Termier. 2018. Data Science Techniques for Sustainable Dairy Management. ERCIM News (https://ercim-news.ercim.eu/en113/special/data-science-techniques-for-sustainable-dairy-management)