A novel EEG-based approach to classify emotions through phase space dynamics

Soroush, Morteza Zangeneh; Maghooli, Keivan; Setarehdan, Seyed Kamaledin; Nasrabadi, Ali Motie

doi:10.1007/s11760-019-01455-y

Cited by 20 publications

(16 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both approaches might pose serious problems especially in real BCI applications with large number of channels. This fact is also mentioned in several studies [10,53,54]. In this study, we are able to detect artifactual sources and eliminate artifacts using SWT.…”

Section: Discussionsupporting

confidence: 62%

“…It is worth mentioning that all components regardless to their datasets are put in two classes and then classification procedure is performed. Taking a closer look at the recent results in tables 5, 6 and 8, it is evident that classification performance while using the mixture model is quite high and higher than several previous studies such as [52,53]. Referring to table 5, we can even determine the type of the artifact with the accuracy more than 75% in all cases and datasets.…”

Section: Resultsmentioning

confidence: 61%

“…That is why we go for SWT-based artifact removal. In contrast to several studies such as [50,53,54], the proposed method in this study is completely automated and more precise. Since previous studies use different performance criterion and measures, it is impossible to compare their results with that of the current study.…”

Section: Discussionmentioning

confidence: 98%

“…This motivates us to introduce a new automated artifact recognition system in the current study. Additionally, in some studies like [53], some features such as signal amplitude or slope are considered to recognize artifacts which is not appropriate and practical in most real cases. Due to the presence of noise and also different EEG recording systems and procedures, these measures require to be set for every single recording.…”

Section: Discussionmentioning

confidence: 99%

“…Fig 9 illustrates one example of generated artifacts and CSEEGs. Since artifacts including ECG, eye blinking, EMG, EOG and white noise are very important and prominent in most BCI applications, our focus in this study is on these common artifacts and other artifacts like head movement, power-line noise and electrical shift are ignored [10,53]. Expert clinicians including three neurophysiologists are informed to control the experiments and label extracted source based on the mentioned artifacts.…”

Section: = + (8)mentioning

confidence: 99%

See 4 more Smart Citations

EEG Source Identification through Phase Space Reconstruction and Complex Networks

Soroush¹

2020

Preprint

View full text Add to dashboard Cite

Artifact elimination has become an inseparable part while processing electroencephalogram (EEG) in most brain computer interface (BCI) applications. Scientists have tried to introduce effective and efficient methods which can remove artifacts and also reserve desire information pertaining to brain activity. Blind source separation (BSS) methods have been receiving a great deal of attention in recent decades since they are considered routine and standard signal processing tools and are commonly used to eliminate artifacts and noise. Most studies, mainly EEG-related ones, apply BSS methods in preprocessing sections to achieve better results. On the other hand, BSS methods should be followed by a classifier in order to identify artifactual sources and remove them in next steps. Therefore, artifact identification is always a challenging problem while employing BSS methods. Additionally, removing all detected artifactual components leads to loss of information since some desire information related to neural activity leaks to these sources. So, an approach should be employed to suppress the artifacts and reserve neural activity. In this study, a new hybrid method is proposed to automatically separate and identify electroencephalogram (EEG) sources with the aim of classifying and removing artifacts. Automated source identification is still a challenge. Researchers have always made efforts to propose precise, fast and automated source verification methods. Reliable source identification has always been of great importance. This paper addresses blind source separation based on second order blind identification (SOBI) as it is reportedly one of the most effective methods in EEG source separation problems. Then a new method for source verification is introduced which takes advantage of components phase spaces and their dynamics. A new state space called angle space (AS) is introduced and features are extracted based on the angle plot (AP) and Poincare planes. Identified artifactual sources are eliminated using stationary wavelet transform (SWT). Simulated, semi-simulated and real EEG signals are employed to evaluate the proposed method. Different simulations are performed and performance indices are reported. Results show that the proposed method outperforms most recent studies in this subject.

show abstract

Section: Discussionsupporting

confidence: 62%

Section: Resultsmentioning

confidence: 61%