EEG Signal Analysis for Diagnosing Neurological Disorders Using Discrete Wavelet Transform and Intelligent Techniques

Alturki, Fahd A.; AlSharabi, Khalil; Abdurraqeeb, Akram M.; Aljalal, Majid

doi:10.3390/s20092505

Cited by 102 publications

(65 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…(4) In the theta and alpha bands, the energy is greater in the Theta-EEG group, specifically in the time window 258-516 ms related to stimulus categorization processing. Thus the current findings emphasize the relevance of a wavelet analysis for diagnosis of neurological disorders, as in recent studies (Faust et al, 2015; Bhattacharyya and Pachori, 2017; Alturki et al, 2020).…”

Section: Overviewsupporting

confidence: 81%

Anomalous brain energy in old age by wavelet analysis of ERP during a Stroop task

Moguel

Baravalle

Gonzalez-Salinas

et al. 2021

Preprint

View full text Add to dashboard Cite

By event-related potentials (ERP) during a counting Stroop task it was shown that the elderly with excess in theta activity in their electroencephalogram (EEG) are at risk of cognitive decline and have a higher neuronal activity during stimulus categorization than the elderly with a normal EEG. It was suggested that this increased neuronal activity could have a compensatory function. However, the quantification of energy associated with the enhanced neuronal activity was not investigated in this group. By wavelet analysis, we measured total and relative energy in ERP during the execution of a counting Stroop task in two groups of elderly: one with excess in theta activity (Theta-EEG, n = 23) and the other with normal EEG (Normal-EEG, n = 23). In delta, theta, and alpha bands, the Theta-EEG group used a higher amount of total energy as compared to the Normal-EEG group for both types of stimuli, interference and no interference. In theta and alpha bands, the total energy was higher in the Theta-EEG group, specifically in the window of 258-516 ms, coinciding with stimulus categorization. Given that no major behavioral differences were observed between EEG groups, we suggest that a higher energy in delta, theta, and alpha bands is one of the neurobiological mechanisms that allows the Theta-EEG group to cope with the cognitive demands of the task. However, this increased energy might not be an effective mechanism in the long term as it could promote a metabolic and cellular dysregulation that would trigger the transition to cognitive impairment.SIGNIFICANCE STATEMENTBy using wavelet transform analysis we report that the elderly with excess in theta activity show a higher energy in delta, theta, and alpha bands during the categorization of stimuli in a counting Stroop task. Our findings imply that this increase neuronal activity might be related to a dysregulated energy metabolism in the elderly with theta excess that could explain the progress to cognitive impairment in this group. The analysis of energy by wavelet transform in data obtained by ERP complements other techniques that evaluate the risk of cognitive impairment.

show abstract

Section: Overviewsupporting

confidence: 81%

Anomalous brain energy in old age by wavelet analysis of ERP during a Stroop task

Moguel

Baravalle

Gonzalez-Salinas

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Using ten‐fold cross‐validation, 60 s long segments with half‐segment overlapping produced very good classification performance. Alturki et al [14 ] also segmented the signal into a 50 s time window and decomposed the signal into subbands using DWT. Logarithmic band power (LBP), standard deviation (SD), variance, kurtosis, and SE were used for feature extraction from the segmented signals.…”

Section: Introductionmentioning

confidence: 99%

Diagnosis of autism spectrum disorder from EEG using a time–frequency spectrogram image‐based approach

2020

View full text Add to dashboard Cite

Autism is a type of neurodevelopment disorder in which individuals often have difficulties in social relationship, communication, expressing and controlling emotions and poor eye contact, among other symptoms. Currently, electroencephalography (EEG) is the most popular tool to investigate the presence of autism biomarkers. Generally, EEG recordings generate huge volume data with dynamic behaviour. In current practice, the massive EEG data are visually analysed by specialist clinicians to identify autism, which is time consuming, costly, subject to human error, and reduces decision‐making reliability. Hence this Letter aims to develop an efficient autism diagnostic system that can automatically identify autism based on time–frequency spectrogram images from EEG signals. Firstly, the raw EEG data is pre‐processed using several techniques, such as re‐referencing, filtering and normalisation. After that, the pre‐processed EEG signals are converted to two‐dimensional images using a short‐time Fourier transform. Then, textural features are extracted, and significant features are selected using principal component analysis, and feed to support vector machine classifier for classification. The proposed system achieved an average of 95.25% accuracy in ten‐fold cross‐validation evaluation. The developed system's simplicity and performance indicates usefulness as a decision support tool for healthcare professionals in autism diagnosis.

show abstract

“…As evident from Table 4 (data 2), classification results of the LDA and CNN algorithms were the highest (91.67%) while that for the KNN algorithm was the lowest (75%), and the other two algorithms scored between them. Compared to the results for EVOO + HO, only the accuracy of the LDA algorithm increased, which showed that LDA could avoid overfitting better while maximizing the inter‐class interval by separating the hyperplane through a one‐dimensional projection line 37 . In terms of precision and recall, both LDA and CNN algorithms could effectively identify pure EVOO while ensuring a high detection rate for adulterated EVOO.…”

Section: Resultsmentioning

confidence: 93%

Rapid screening for hazelnut oil and high‐oleic sunflower oil in extra virgin olive oil using low‐field nuclear magnetic resonance relaxometry and machine learning

Hou

Wang

et al. 2020

J Sci Food Agric

View full text Add to dashboard Cite

BACKGROUND As extra virgin olive oil (EVOO) has high commercial value, it is routinely adulterated with other oils. The present study investigated the feasibility of rapidly identifying adulterated EVOO using low‐field nuclear magnetic resonance (LF‐NMR) relaxometry and machine learning approaches (decision tree, K‐nearest neighbor, linear discriminant analysis, support vector machines and convolutional neural network (CNN)). RESULTS LF‐NMR spectroscopy effectively distinguished pure EVOO from that which was adulterated with hazelnut oil (HO) and high‐oleic sunflower oil (HOSO). The applied CNN algorithm had an accuracy of 89.29%, a precision of 81.25% and a recall of 81.25%, and enabled the rapid (2 min) discrimination of pure EVOO that was adulterated with HO and HOSO in the volumetric ratio range of 10–100%. CONCLUSIONS LF‐NMR coupled with the CNN algorithm is a viable candidate for rapid EVOO authentication. © 2020 Society of Chemical Industry

show abstract

EEG Signal Analysis for Diagnosing Neurological Disorders Using Discrete Wavelet Transform and Intelligent Techniques

Cited by 102 publications

References 33 publications

Anomalous brain energy in old age by wavelet analysis of ERP during a Stroop task

Anomalous brain energy in old age by wavelet analysis of ERP during a Stroop task

Diagnosis of autism spectrum disorder from EEG using a time–frequency spectrogram image‐based approach

Rapid screening for hazelnut oil and high‐oleic sunflower oil in extra virgin olive oil using low‐field nuclear magnetic resonance relaxometry and machine learning

Contact Info

Product

Resources

About