5th ISSNIP-IEEE Biosignals and Biorobotics Conference (2014): Biosignals and Robotics for Better and Safer Living (BRC) 2014
DOI: 10.1109/brc.2014.6880978
|View full text |Cite
|
Sign up to set email alerts
|

Towards automated EEG-Based Alzheimer's disease diagnosis using relevance vector machines

Abstract: Abstract-Existing electroencephalography (EEG) basedAlzheimer's disease (AD) diagnostic systems typically rely on experts to visually inspect and segment the collected signals into artefact-free epochs and on support vector machine (SVM) based classifiers. The manual selection process, however, introduces biases and errors into the diagnostic procedure, renders it "semiautomated," and makes the procedure costly and labour-intensive. In this paper, we overcome these limitations by proposing the use of an automa… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
5
0

Year Published

2016
2016
2023
2023

Publication Types

Select...
6
2

Relationship

2
6

Authors

Journals

citations
Cited by 10 publications
(5 citation statements)
references
References 34 publications
0
5
0
Order By: Relevance
“…In an attempt to match the dimensionality reported in previous EEG-based AD literature (e.g., Falk et al, 2012 ; Fraga et al, 2013 ; Cassani et al, 2014b ), the top 24 features from each of the feature modalities was selected. Here, we call feature “Group 1” the top-24 features selected for the EEG modality.…”
Section: Methodsmentioning
confidence: 99%
“…In an attempt to match the dimensionality reported in previous EEG-based AD literature (e.g., Falk et al, 2012 ; Fraga et al, 2013 ; Cassani et al, 2014b ), the top 24 features from each of the feature modalities was selected. Here, we call feature “Group 1” the top-24 features selected for the EEG modality.…”
Section: Methodsmentioning
confidence: 99%
“…The literature on EEG or MEG use in assisting AD diagnosis is clearly 30 divided into two main approaches [8,9,10]. The first one deals with EEG or MEG signals registered when participants are awake at rest, with eyes open or closed (resting-state) [11,12,13,14,15,16], while the other is dedicated to the analysis of signals recorded with subjects performing some pre-defined tasks (task-oriented) [17,18,19,20,21]. Both paradigms can be analyzed in time and 35 frequency domains, bringing information about cognitive functions related to the characteristics of brain signals [22,23,10].…”
Section: A C C E P T E D Mmentioning
confidence: 99%
“…Kanda et al ( 2014 ) achieved an accuracy of up to 84.56% in classification. In another work, Cassani et al ( 2014 ) estimated three EEG signal features: spectral, coherence, and amplitude modulation, and then utilized a SVM to obtain an accuracy of 84.7%. Upon comparing the outcomes of our study with those of Cura et al ( 2021 ) study, we observed that our study outperformed theirs.…”
Section: Resultsmentioning
confidence: 99%
“…achieved an accuracy of up to 84.56% in classification. In another work,Cassani et al (2014) estimated three EEG signal features: spectral, coherence, and amplitude modulation, and then utilized a SVM to obtain an accuracy ofTABLE Classification precision, recall, and accuracy for neurotypical vs. mild and moderate AD features based on k-fold cross-validation techniques. The bold values represent the highest classification precision, recall, and accuracy achieved by each classifier.…”
mentioning
confidence: 99%