Reservoir computing for emotion valence discrimination from EEG signals

Bozhkov, Lachezar; Koprinkova–Hristova, Petia; Georgieva, Pétia

doi:10.1016/j.neucom.2016.03.108

Cited by 34 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This initial work was validated with their own data set, and later extended in [7] by using Higher Order Crossings [19] and features from the General Higuchi Fractal Dimension Spectra [20] to understand EEGs as multifractal signals. Recently in [21] first use of recurrent neural networks using reservoir computing techniques have shown promising results in Valence levels estimation.…”

Section: Related Workmentioning

confidence: 99%

Fusing highly dimensional energy and connectivity features to identify affective states from EEG signals

2017

View full text Add to dashboard Cite

In this paper, a novel method for affect detection is presented. The method combines both connectivity-based and channel-based features with a selection method that considerably reduces the dimensionality of the data and allows for an efficient classification. In particular, the Relative Energy (RE) and its logarithm in the spacial domain, and the spectral power (SP) in the frequency domain are computed for the four typical frequency bands (α, β, γ and θ), and complemented with the mutual information measured over all channel pairs. The resulting features are then reduced by using a hybrid method that combines supervised and unsupervised feature selection. First, a Welch's t-test is used to select the features that best separate the classes, and discard the ones that are less useful for classification. To this end, all features where the t-test yields a p-value above a threshold are eliminated. The remaining ones are further reduced by using Principal Component Analysis. Detection results are compared to state-of-the-art methods on DEAP, a database for emotion analysis composed of labeled recordings from 32 subjects while watching 40 music videos. The effect of using different classifiers is also evaluated, and a significant improvement is observed in all cases.

show abstract

Section: Related Workmentioning

confidence: 99%

Fusing highly dimensional energy and connectivity features to identify affective states from EEG signals

2017

View full text Add to dashboard Cite

show abstract

“…This ESN property speeds up the model training however there is a risk to become unstable. An improved ESN adaptation rule was proposed in [7], coined Intrinsic Plasticity (IP) to guarantee the reservoir parameters tend to equilibrium states and observed that these states are concentrated in different regions depending on the inputs. If two input vectors are close in the input space, they will result in close equilibrium points in the reservoir state.…”

Section: Deep Learning In Ancmentioning

confidence: 99%

Deep Learning in Brain Computer Interfaces

Georgieva

2019

Proceedings of the 9th Balkan Conference on Informatics

Self Cite

View full text Add to dashboard Cite

“…Bozhkov et al 31 90 examined cortical connectivity of autistic children while watching KDEF face pictures and compared them with normal children. EEG signals of 18 autistic children and 18 normal children were recorded during stimuli and then analyzed using theta coherence index (cortical connectivity index).…”

Section: Previous Emotion Studies Emotion and Normal Casesmentioning

confidence: 99%