Pattern recognition of spectral entropy features for detection of alcoholic and control visual ERP’s in multichannel EEGs

Abstract

This paper presents a novel ranking method to select spectral entropy (SE) features that discriminate alcoholic and control visual event-related potentials (ERP'S) in gamma sub-band (30-55 Hz) derived from a 64-channel electroencephalogram (EEG) recording. The ranking is based on a t test statistic that rejects the null hypothesis that the group means of SE values in alcoholics and controls are identical. The SE features with high ranks are indicative of maximal separation between their group means. Various sizes of top ranked feature subsets are evaluated by applying principal component analysis (PCA) and k-nearest neighbor (k-NN) classification. Even though ranking does not influence the performance of classifier significantly with the selection of all 61 active channels, the classification efficiency is directly proportional to the number of principal components (pc). The effect of ranking and PCA on classification is predominantly observed with reduced feature subsets of (N = 25, 15) top ranked features. Results indicate that for N = 25, proposed ranking method improves the k-NN classification accuracy from 91 to 93.87% as the number of pcs increases from 5 to 25. With same number of pcs, the k-NN classifier responds with accuracies of 84.42-91.54% with non-ranked features.Similarly for N = 15 and number of pcs varying from 5 to 15, ranking enhances k-NN detection accuracies from 88.9 to 93.08% as compared to 86.75-91.96% without ranking. This shows that the detection accuracy is increased by 6.5 and 2.8%, respectively, for N = 25, whereas it enhances by 2.2 and 1%, respectively, for N = 15 in comparison with non-ranked features. In the proposed t test ranking method for feature selection, the pcs of only top ranked feature candidates take part in classification process and hence provide better generalization.

Neural correlates of visuoperceptive changes in severe alcohol use disorder: A critical review of neuroimaging and electrophysiological findings

“…Such a proposal is consistent with results from resting‐state EEG documenting lower spectral power in the alpha frequency range (7.5–12 Hz) in bilateral occipital areas of individuals with SAUD, although specifically in men (Ehlers & Phillips, 2007). It also converges with recent findings showing that the spectral entropy features that best discriminate the visual ERPs of individuals with SAUD and healthy controls in a specific gamma sub‐band (30–55 Hz) during a visual object recognition task are located in the frontal, fronto‐parietal, and occipital regions (Padma Shri & Sriraam, 2016, 2017). According to the authors (Padma Shri & Sriraam, 2017), activity in these regions reflects the specificity of individual with SAUD's sensory control, attentional, and visual processes.…”

“…It also converges with recent findings showing that the spectral entropy features that best discriminate the visual ERPs of individuals with SAUD and healthy controls in a specific gamma sub‐band (30–55 Hz) during a visual object recognition task are located in the frontal, fronto‐parietal, and occipital regions (Padma Shri & Sriraam, 2016, 2017). According to the authors (Padma Shri & Sriraam, 2017), activity in these regions reflects the specificity of individual with SAUD's sensory control, attentional, and visual processes. Finally, and while not directly applicable to SAUD, a magnetoencephalographic study focusing on the occipital activity of heavy drinkers during a visual‐spatial processing task requiring to detect the location of black and white checkerboards also revealed reduced activity of the alpha band in lateral visual association cortices (Lew et al, 2020).…”

Process Monitoring in Friction Stir Welding Using Convolutional Neural Networks

“…For the FCNN, the mean values were calculated for each signal in each ROI. For the RNN, the instantaneous frequency [19] and the spectral entropy, which are also often used as a feature in medicine signal processing [20], were determined and employed as input. For the CNN, spectrograms were generated, similar to Hartl et al [15].…”

“…Metals 2021, 11, x FOR PEER REVIEW 5 of 13 [20], were determined and employed as input. For the CNN, spectrograms were generated, similar to Hartl et al [15].…”

Entropy: A Promising EEG Biomarker Dichotomizing Subjects With Opioid Use Disorder and Healthy Controls

“…They obtained an accuracy of 91.7%, sensitivity of 90% and specificity of 93.3%. Padma Shri and Sriraam 35 also distinguish healthy controls and alcoholics with spectral entropy features of visual event-related potentials by applying principal component analysis and k-nearest neighbor classification. There are also a few studies that classify opioid users by entropy features.…”