Correction to: Classification of Normal, Ictal and Inter-ictal EEG via Direct Quadrature and Random Forest Tree

Abdulhay, Enas; Alafeef, Maha; Abdelhay, Arwa; Al-Bashir, Areen K.

doi:10.1007/s40846-017-0363-9

Cited by 2 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the comparison between DQ and other instantaneous frequency estimation approaches—including generalized zero crossing and energy separation—has been examined in literature, where the outperformance of DQ has been highlighted as a powerful technique for revealing the frequency contents and their time variability of non‐stationary signals, and thereby understanding the detailed generating mechanisms and the true physical nature reflected by signals (Feng et al, 2017). Furthermore, the authors of the present work have illustrated—in previous works—the adequacy of DQ in applications to complex EEG (Abdulhay, Alafeef, Abdelhay, & Al‐Bashir, 2020), to amplitude‐modulated EEG (Oweis & Abdulhay, 2011), and specifically to ASD EEG (Abdulhay et al, 2017).…”

Section: Resultsmentioning

confidence: 68%

“…Linear methods cannot be sufficiently adapted to the nonlinear nature of EEG (Abdulhay et al, 2017; Abdulhay, Alafeef, Alzghoul, et al, 2020; Abdulhay, Elamaran, Chandrasekar, et al, 2020); linear processing assumes the strict superposition principle that fully skips the important requirement of data driven analysis or exploration based on inherent physiological processes not on pre‐assumed models. Furthermore, although a number of approaches were directed toward nonlinearity, accuracy level was influenced by the incapability of complete dissociation between the modulations of energy—in the time and frequency domains—with the purpose of extracting spectral information without the effect of amplitude modulation (Abdulhay, Alafeef, Abdelhay, & Al‐Bashir, 2020). This limitation yields usually incorrect results about the exact pace or rhythm of EEG activity.…”

Section: Resultsmentioning

confidence: 99%

“…f n ( k ) is the frequency modulated component. e n ( k ) is the envelope passing through the maxima of absolute values of f n−1 ( k ) and conducted by the same approach used to calculate the envelope in EMD (Abdulhay, Alafeef, Abdelhay, & Al‐Bashir, 2020).…”

Section: Methodsmentioning

confidence: 99%

“…The works (Abdulhay et al, 2009; Abdulhay, Alafeef, Alzghoul, et al, 2020; Abdulhay, Alafeef, Abdelhay, & Al‐Bashir, 2020; Abdulhay, Alafeef, Hadoush, & Arunkumar, 2020, Abdulhay et al, 2017; Hadoush et al, 2019b; Oweis & Abdulhay, 2011)—previously led by the first author—have illustrated that EEG examination through methods—based on Fourier transform (Duffy & Als, 2012; Wu et al, 2018), wavelet computations (Ahmadlou et al, 2010; Djemal et al, 2017), fractal analysis methods (Ahmadlou et al, 2010), and some time‐scale based feature extractors (Bosl et al, 2011)—are too sensitive to mother wavelet or apriori knowledge/assumptions. Based on those findings, there is a real need to use a different technique: nonlinear, data driven with no apriori assumptions.…”

Section: Introductionmentioning

confidence: 99%

“…This necessity has been solved by the adaptive approach of empirical mode decomposition (EMD) (Abdulhay, Alafeef, Alzghoul, et al, 2020). However, since EMD leads to the decomposition into amplitude modulated‐frequency modulated (AM‐FM) components, any spectral information—extracted from those components—will suffer from the effect of amplitude modulation, which induces inaccurate outcomes (Abdulhay, Alafeef, Abdelhay, & Al‐Bashir, 2020). Hence, the method applied to ASD EEG should not only be data driven but also be able to dissociate the information of amplitude modulation and of frequency modulation.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Autism diagnosis via correlation between vectors of direct quadrature instantaneous frequency of EEG analytic normalized intrinsic mode functions

et al. 2021

Self Cite

View full text Add to dashboard Cite

Autism spectrum disorder (ASD) is a neurological and developmental disorder that commences usually in the early years of age. It impacts the social interaction, communication and learning. It is believed that it is mainly caused by an abnormal connectivity between brain zones. The presented work applies an EEG‐based nonlinear method for the classification of ASD and neuro‐typical groups. The suggested procedure does not require pre‐assumptions and is completely data‐driven. Also, the main advantage is the accurate tracking of the pace of EEG activity without the effect of amplitude modulation on the spectral information. In addition, the tracking is conducted point‐by‐point to avoid shortcomings of inexact global features. First, for every (ASD or neuro‐typical) volunteer, the recorded EEG channels (64 channels) are decomposed by empirical mode decomposition (EMD) in order to get the underlying components (intrinsic mode functions—IMFs). Second, the direct quadrature (DQ) method is used to normalize the IMFs, and to dissociate between amplitude and frequency contents of the resulted components, as well as to help extract then the point‐by‐point spectral information from the analytic normalized IMFs by Hilbert transform. Third, the correlation coefficients between the instantaneous frequency vectors of the counterpart components will be computed over all channels (i.e., between components number ‘i’ of channels ‘x’ and ‘y’, 1 < i < number of components, 1 < x < 64, 1 < y < 64). Fourth, correlation coefficients array is constructed. Fifth, the dimension of the feature array is reduced without loss of significant information. Sixth, classification of reduced features is achieved via neural network. Finally, the statistical assessment of the classification outcome is conducted. The proposed method yields a test accuracy of 94.1%–100%.

show abstract