Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/132289
Title: Exploración de técnicas de semi-supervised learning para la clasificación de células de sangre periférica
Author: León Ortiz, Isaac
Tutor: Alférez, Santiago  
Others: Calvet Liñán, Laura  
Abstract: Through digital image processing, machine learning and deep learning tools, a database of cell images of peripheral blood smear samples from a period of 9 years. With this and other such large data sets and with so much information, it can be difficult to find the machine learning algorithm capable of analysing and classifying the information with the least consumption of resources and obtaining the best results. This final master's thesis uses semi-supervised learning techniques to minimize problems and improve the classification of these samples with respect to other techniques such as Convolutional Neural Networks. As a result of the study, two models of neural networks have been generated, a Convolutional Neural Network that allows the classification of images with a precision of 95%, and a deep neural network that uses autoencoders and a dense layer to identify each cell with a 96% accuracy. These results show the usefulness of semi-supervised learning techniques in the classification and analysis of unlabelled data, and may lead to a better understanding of the functioning and applicability of neural networks in any field of Bioinformatics.
Keywords: artificial intelligence
machine learning
convolutional neural network
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 8-Jun-2021
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Trabajos finales de carrera, trabajos de investigación, etc.

Files in This Item:
File Description SizeFormat 
isaacleorTFM0621memoria.pdfMemoria del TFM2,61 MBAdobe PDFThumbnail
View/Open