dc.contributor |
Béjar Torres, Ramón |
dc.contributor |
Mateu Piñol, Carles |
dc.contributor |
Universitat de Lleida. Escola Politècnica Superior |
dc.contributor.author |
Ghenghiu, Alex |
dc.date |
2019-12-16T15:05:24Z |
dc.date |
2019-12-16T15:05:24Z |
dc.date |
2019-07 |
dc.identifier |
http://hdl.handle.net/10459.1/67736 |
dc.identifier.uri |
http://hdl.handle.net/10459.1/67736 |
dc.description |
An important factor for farms earnings is
to detect animals illness on its early stages.
The sooner the disease is detected, the less
cost it takes to treat it. One way to determine
if a cow isn’t healthy is that the animal won’t
drink water. So, it would be interesting to
have a system to determine which of the cows
from the farm are not drinking water. Knowing this, we have implemented an object classifier using Convolution Neural Networks
(CNNs) with Keras. The motivation of this
project is understanding clearly about deep
learning, particularly CNNs, and put in on
real life. Therefore, we also tunned the hyper parameter of each models such as learning rate, batch size, and number of epochs.
In addition, we also used techniques to optimize networks, acting as activation function, dropout and max pooling. During this
process, several models have been generated
in order to observe the relationship between
number of layers, input data and accuracy. |
dc.language |
eng |
dc.rights |
cc-by-nc-nd |
dc.rights |
http://creativecommons.org/licenses/by-nc-nd/4.0/ |
dc.rights |
info:eu-repo/semantics/openAccess |
dc.subject |
Inteligencia artificial |
dc.subject |
Visión artificial |
dc.subject |
Aprendizaje automático |
dc.subject |
Intel·ligència artificial |
dc.subject |
Visió artificial |
dc.title |
Monitorització de les activitats d’animals de granja mitjançant intel·ligència artificial |
dc.type |
info:eu-repo/semantics/masterThesis |