Mots-Clés

deep learning interpretation explanations animal emotions

Description

Emotion prediction and interpretation in horses using deep learning models

There is emerging research done on how to interpret animal emotions using an autonomous or intelligent system. This work will explore the possibility of creating an intelligent system capable of predicting the emotion of a horse from its facial expression and postures, based on existing research and ethograms. Our goal in this project is to develop a deep learning-based model using the imaging data-set. The student will have direct interaction with animal behavior experts who are producing and annotating the data-set for this project.

The role of the student will be to:

• do a thorough literature review on emotion classification using imaging dataset

• select the appropriate deep learning architecture

• explore the use of transfer learning approach

• perform hyper-parameter optimization

• interpret or explain the deep learning model to identify important features

Required skills:

• Background in computer science

• Programming languages: Python, C++

• Deep learning frameworks: Keras, pyTorch, Caffe, Theano, etc

• OS: Linux

Required documents:

• Motivation letter

• CV

• Recommendation letter

Supervisors: Misbah RAZZAQ, Lea LASAND

Contact: misbah.razzaq@inrae.fr

Starting data: From January 2023

List of relevant publications:

Misbah Razzaq, Frédérique Clément, Romain Yvinec: An overview of deep learning applications in precocious puberty and thyroid dysfunction, Frontiers in Endocrinology, Frontiers, Oct 2022.

https://doi.org/10.3389/fendo.2022.959546

Misbah Razzaq, et al: An artificial neural network approach integrating plasma proteomics and genetic data identifies PLXNA4 as a new susceptibility locus for pulmonary embolism, Scientific Reports, July 2021.

https://doi.org/10.1038/s41598-021-93390-7

Misbah Razzaq, et al: Explainable artificial neural network for recurrent venous thromboembolism based on plasma proteomics, International Conference on Computational Methods in System Biology (CMSB), Published, September 2021.

https://doi.org/10.1007/978-3-030-85633-5_7

Lansade L, Lemarchand J, Reigner F, Arnould C, Bertin A (2022) Automatic brushes induce positive emotions and foster positive social interactions in group-housed horses Appl Anim Behav Sci 246:105538 doi:https://doi.org/10.1016/j.applanim.2021.105538

Lansade L, Nowak R, Lainé A-L, Leterrier C, Bonneau C, Parias C, Bertin A (2018) Facial expression and oxytocin as possible markers of positive emotions in horses Sci Rep 8:14680

doi:10.1038/s41598-018-32993-z