Cargando…

Mood State Detection in Handwritten Tasks Using PCA–mFCBF and Automated Machine Learning

In this research, we analyse data obtained from sensors when a user handwrites or draws on a tablet to detect whether the user is in a specific mood state. First, we calculated the features based on the temporal, kinematic, statistical, spectral and cepstral domains for the tablet pressure, the hori...

Descripción completa

Detalles Bibliográficos
Autores principales: Nolazco-Flores, Juan Arturo, Faundez-Zanuy, Marcos, Velázquez-Flores, Oliver Alejandro, Del-Valle-Soto, Carolina, Cordasco, Gennaro, Esposito, Anna
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8875261/
https://www.ncbi.nlm.nih.gov/pubmed/35214585
http://dx.doi.org/10.3390/s22041686
_version_ 1784657876063617024
author Nolazco-Flores, Juan Arturo
Faundez-Zanuy, Marcos
Velázquez-Flores, Oliver Alejandro
Del-Valle-Soto, Carolina
Cordasco, Gennaro
Esposito, Anna
author_facet Nolazco-Flores, Juan Arturo
Faundez-Zanuy, Marcos
Velázquez-Flores, Oliver Alejandro
Del-Valle-Soto, Carolina
Cordasco, Gennaro
Esposito, Anna
author_sort Nolazco-Flores, Juan Arturo
collection PubMed
description In this research, we analyse data obtained from sensors when a user handwrites or draws on a tablet to detect whether the user is in a specific mood state. First, we calculated the features based on the temporal, kinematic, statistical, spectral and cepstral domains for the tablet pressure, the horizontal and vertical pen displacements and the azimuth of the pen’s position. Next, we selected features using a principal component analysis (PCA) pipeline, followed by modified fast correlation–based filtering (mFCBF). PCA was used to calculate the orthogonal transformation of the features, and mFCBF was used to select the best PCA features. The EMOTHAW database was used for depression, anxiety and stress scale (DASS) assessment. The process involved the augmentation of the training data by first augmenting the mood states such that all the data were the same size. Then, 80% of the training data was randomly selected, and a small random Gaussian noise was added to the extracted features. Automated machine learning was employed to train and test more than ten plain and ensembled classifiers. For all three moods, we obtained 100% accuracy results when detecting two possible grades of mood severities using this architecture. The results obtained were superior to the results obtained by using state-of-the-art methods, which enabled us to define the three mood states and provide precise information to the clinical psychologist. The accuracy results obtained when detecting these three possible mood states using this architecture were 82.5%, 72.8% and 74.56% for depression, anxiety and stress, respectively.
format Online
Article
Text
id pubmed-8875261
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-88752612022-02-26 Mood State Detection in Handwritten Tasks Using PCA–mFCBF and Automated Machine Learning Nolazco-Flores, Juan Arturo Faundez-Zanuy, Marcos Velázquez-Flores, Oliver Alejandro Del-Valle-Soto, Carolina Cordasco, Gennaro Esposito, Anna Sensors (Basel) Article In this research, we analyse data obtained from sensors when a user handwrites or draws on a tablet to detect whether the user is in a specific mood state. First, we calculated the features based on the temporal, kinematic, statistical, spectral and cepstral domains for the tablet pressure, the horizontal and vertical pen displacements and the azimuth of the pen’s position. Next, we selected features using a principal component analysis (PCA) pipeline, followed by modified fast correlation–based filtering (mFCBF). PCA was used to calculate the orthogonal transformation of the features, and mFCBF was used to select the best PCA features. The EMOTHAW database was used for depression, anxiety and stress scale (DASS) assessment. The process involved the augmentation of the training data by first augmenting the mood states such that all the data were the same size. Then, 80% of the training data was randomly selected, and a small random Gaussian noise was added to the extracted features. Automated machine learning was employed to train and test more than ten plain and ensembled classifiers. For all three moods, we obtained 100% accuracy results when detecting two possible grades of mood severities using this architecture. The results obtained were superior to the results obtained by using state-of-the-art methods, which enabled us to define the three mood states and provide precise information to the clinical psychologist. The accuracy results obtained when detecting these three possible mood states using this architecture were 82.5%, 72.8% and 74.56% for depression, anxiety and stress, respectively. MDPI 2022-02-21 /pmc/articles/PMC8875261/ /pubmed/35214585 http://dx.doi.org/10.3390/s22041686 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Nolazco-Flores, Juan Arturo
Faundez-Zanuy, Marcos
Velázquez-Flores, Oliver Alejandro
Del-Valle-Soto, Carolina
Cordasco, Gennaro
Esposito, Anna
Mood State Detection in Handwritten Tasks Using PCA–mFCBF and Automated Machine Learning
title Mood State Detection in Handwritten Tasks Using PCA–mFCBF and Automated Machine Learning
title_full Mood State Detection in Handwritten Tasks Using PCA–mFCBF and Automated Machine Learning
title_fullStr Mood State Detection in Handwritten Tasks Using PCA–mFCBF and Automated Machine Learning
title_full_unstemmed Mood State Detection in Handwritten Tasks Using PCA–mFCBF and Automated Machine Learning
title_short Mood State Detection in Handwritten Tasks Using PCA–mFCBF and Automated Machine Learning
title_sort mood state detection in handwritten tasks using pca–mfcbf and automated machine learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8875261/
https://www.ncbi.nlm.nih.gov/pubmed/35214585
http://dx.doi.org/10.3390/s22041686
work_keys_str_mv AT nolazcofloresjuanarturo moodstatedetectioninhandwrittentasksusingpcamfcbfandautomatedmachinelearning
AT faundezzanuymarcos moodstatedetectioninhandwrittentasksusingpcamfcbfandautomatedmachinelearning
AT velazquezfloresoliveralejandro moodstatedetectioninhandwrittentasksusingpcamfcbfandautomatedmachinelearning
AT delvallesotocarolina moodstatedetectioninhandwrittentasksusingpcamfcbfandautomatedmachinelearning
AT cordascogennaro moodstatedetectioninhandwrittentasksusingpcamfcbfandautomatedmachinelearning
AT espositoanna moodstatedetectioninhandwrittentasksusingpcamfcbfandautomatedmachinelearning