<?xml version="1.0"?>
<metadata xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:dc="http://purl.org/dc/elements/1.1/"><dc:title>Examining the potential of autoencoders for automatic feature extraction in wireless cognitive load inference</dc:title><dc:creator>Kristan,	Anže	(Avtor)
	</dc:creator><dc:creator>Pejović,	Veljko	(Mentor)
	</dc:creator><dc:creator>Pellarini,	Daniel	(Komentor)
	</dc:creator><dc:subject>autoencoder</dc:subject><dc:subject>machine learning</dc:subject><dc:subject>cognitive load</dc:subject><dc:description>Understanding a user's cognitive load could enable a range of applications, from better driving assistance solutions, to educational games.
This thesis analyses data from a wireless cognitive load inference study and examines the potential of autoencoders for extracting features from this data.
These features would then be used for a more accurate inference of the user's cognitive load.
We compare the performance of 7 classifiers using 4 handcrafted features from the original study and 4 new autoencoder based features.
We define three flavours of the cognitive load inference problem and 7 subsets of data and test each combination of problem flavour, subset, classifier and feature.
Our findings show that the handcrafted features perform best in most cases, however in some cases the autoencoder-based features provide a slightly higher classification accuracy.
Although for one problem flavour the highest accuracies reach over 85 %, performance on the other two problems flavours have much more room for improvement, showing that inference of cognitive load from wireless signals is challenging and requires further study.</dc:description><dc:date>2021</dc:date><dc:date>2021-09-06 12:44:28</dc:date><dc:type>Diplomsko delo/naloga</dc:type><dc:identifier>129656</dc:identifier><dc:identifier>VisID: 32687</dc:identifier><dc:identifier>COBISS_ID: 75910403</dc:identifier><dc:language>sl</dc:language></metadata>
