Deep learning approach for laboratory mice grimace scaling

2016
Eral, Mustafa
Show full item record
6
views
0
downloads
Deep learning is extremely attractive research topic in pattern recognition and machine learning areas. Applications in speech recognition, natural language processing, and machine vision fields gained huge acceleration in performance by employing deep learning. In this thesis, deep learning is used for medical purposes in order to scale pain degree of drug stimulated mice by examining facial grimace. For this purpose each frame in the videos in the training set were scaled manually by experts according to Mouse Grimace Scaling(MGS) manual and these frames were used for training a convolutional neural network. For testing the network, another set of videos which was not used for training before, was used. In order to show the classification power of convolutional neural networks, the same classification tasks are performed with some classic kernel based machine learning algorithms and results are compared. For training and testing, a workstation having two powerful graphic card(GPU) is used. 
Neural networks (Computer science)., Visual texture recognition., Artificial intelligence., Machine learning., Face perception.
http://etd.lib.metu.edu.tr/upload/12620517/index.pdf 
https://hdl.handle.net/11511/25948
Graduate School of Natural and Applied Sciences, Thesis
METU IIS - Integrated Information Service open@metu.edu.tr