Multichannel Optimization With Hybrid Spectral- Entropy Markers for Gender Identification Enhancement of Emotional-Based EEGs

Al-Qazzaz, Noor Kamal; Sabir, Mohannad K.; Ali, Sawal Hamid Bin Mohd; Ahmad, Siti Anom; Grammer, Karl

doi:10.1109/access.2021.3096430

Cited by 20 publications

(4 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the first stage of processing each channel of recorded EEG datasets, the sampling frequency was set at fs = 500Hz; conventional filters, including a notch filter at 50Hz, were used to get rid of interference noise; and a band pass filter with a 0.5˘64 Hz frequency range was used to limit the band of the recorded EEG signals [16]. After that, the EEGs were downsampled to a sampling frequency of fs = 256Hz and segmented into non-overlapping epochs of 5 sec length.…”

Section: B Pre-processingmentioning

confidence: 99%

See 1 more Smart Citation

Transfer Learning and Hybrid Deep Convolutional Neural Networks Models for Autism Spectrum Disorder Classification From EEG Signals

Al-Qazzaz,

Aldoori,

Buniya

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

Autism spectrum disorder (ASD) is a developmental disease characterised by restricted and repetitive behaviours, as well as difficulty in social communication and interaction, in children. The clinical diagnosis of ASD is reached by behavioural screening, which delays early intervention. Electroencephalography (EEG) is a method for analysing the brain's electrical activity that has proven useful in the diagnosis of several neurological illnesses. Pre-trained deep Convolutional Neural Networks (CNNs) were used to extract features from the spectral profiles of the EEG dataset and classify patients into mild, moderate, and severe patients, as well as age-matched control subjects. Accordingly, the primary goal of this study is to use the pre-trained CNNs as classifiers in order to reap the benefits of transfer learning, and the secondary goal is to propose a hybrid model by employing decision tree (DT), K nearest neighbour (KNN), and a Support Vector Machine (SVM) machine learning classification techniques to categorise the features of the pre-trained CNN networks into mild, moderate, severe, and normal categories. The results show that using SqueezeNet for transfer learning improves classification accuracy to 85.5%, and that using SqueezeNet for hybrid models improves classification accuracy to 87.8% using SVM. Therefore, a hybrid model based on the combination of SqueezeNet and SVM might be utilised to automatically diagnose ASD based on the individual's EEG data. INDEX TERMS Autism, EEG, deep learning, transfer learning, convolutional neural networks, machine learningI. INTRODUCTION A UTISM spectrum disorders (ASD) are neurodevelopmental illnesses characterized by markedly aberrant social interaction, impaired communication and language skills, and narrow interests [1]. Symptoms occur throughout childhood or infancy and are usually followed by a continuous course with no recovery from an illness [2]. Symptoms appear after the age of six months, become established by the age of two or three years old, and remain into adulthood, but with less severity [3], [4]. The 'spectrum' in ASD is for indicating that autistic individuals can have a multitude of symptoms, such as difficulties in motor movement abilities, limited attention spans, and sleep and gastrointestinal disturbances [2]. These are some prevalent characteristics of children with autism in which frequently, autistic children have communication difficulties, like refusing to engage in conversation, being unable to use appropriate language, repeating what they hear, and having a low linguistic understanding [5], [6]. However, some experience sensory disturbances, as well. These disturbances might be auditory, visual, tactile, gustatory, vestibular, or proprioceptive. Additionally, they avoid social interaction, as they prefer to be alone, the majority

show abstract

Section: B Pre-processingmentioning

confidence: 99%

“…This illustrates that autism diagnosis requires scientific improvements and support, therefore, early autism diagnosis requires clinical signs or biomarkers as clinical assessments alone cannot diagnose early [14]- [16]. One of the most essential indications for diagnosing ASD is the electroencephalogram (EEG).…”

mentioning

confidence: 99%

Transfer Learning and Hybrid Deep Convolutional Neural Networks Models for Autism Spectrum Disorder Classification From EEG Signals

Al-Qazzaz,

Aldoori,

Buniya

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recognizing the most pronounced marks from EEG signals is essential to detecting and identifying brain features as well as assessing the EEG signal variable under evaluation [3]. From a clinical standpoint, the neurologist interprets the post-stroke patient's EEG signal by looking at wave rhythms, amplitudes, asymmetries, changes in magnitudes, the presence of waves, and the ratio between waves [24,25].…”

Section: Related Workmentioning

confidence: 99%

EEG Signal Complexity Measurements to Enhance BCI-Based Stroke Patients’ Rehabilitation

Al-Qazzaz

Aldoori

Ali

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

The second leading cause of death and one of the most common causes of disability in the world is stroke. Researchers have found that brain–computer interface (BCI) techniques can result in better stroke patient rehabilitation. This study used the proposed motor imagery (MI) framework to analyze the electroencephalogram (EEG) dataset from eight subjects in order to enhance the MI-based BCI systems for stroke patients. The preprocessing portion of the framework comprises the use of conventional filters and the independent component analysis (ICA) denoising approach. Fractal dimension (FD) and Hurst exponent (Hur) were then calculated as complexity features, and Tsallis entropy (TsEn) and dispersion entropy (DispEn) were assessed as irregularity parameters. The MI-based BCI features were then statistically retrieved from each participant using two-way analysis of variance (ANOVA) to demonstrate the individuals’ performances from four classes (left hand, right hand, foot, and tongue). The dimensionality reduction algorithm, Laplacian Eigenmap (LE), was used to enhance the MI-based BCI classification performance. Utilizing k-nearest neighbors (KNN), support vector machine (SVM), and random forest (RF) classifiers, the groups of post-stroke patients were ultimately determined. The findings show that LE with RF and KNN obtained 74.48% and 73.20% accuracy, respectively; therefore, the integrated set of the proposed features along with ICA denoising technique can exactly describe the proposed MI framework, which may be used to explore the four classes of MI-based BCI rehabilitation. This study will help clinicians, doctors, and technicians make a good rehabilitation program for people who have had a stroke.

show abstract

“…Bao et al extract frequency-domain entropy features from original acceleration data, which are used as the inputs with mean, energy, and correlation of the original data to build the model, and obtained ideal results [33]. Al-Qazzaz et al extracted linear spectral mean frequency (meanF) and nonlinear multi-scale fuzzy entropy (MFE) features from original electroencephalogram (EEG) and effectively improved the process of automatic gender recognition from emotional-based EEG signals [34].…”

Section: R Wmentioning

confidence: 99%

Information Theory Inspired Pattern Analysis for Time-series Data

Zhao¹,

Capstick²,

Palermo³

et al. 2023

Preprint

View full text Add to dashboard Cite

Current methods for pattern analysis in time series mainly rely on statistical features or probabilistic learning and inference methods to identify patterns and trends in the data. Such methods do not generalize well when applied to multivariate, multi-source, state-varying, and noisy time-series data. To address these issues, we propose a highly generalizable method that uses information theory-based features to identify and learn from patterns in multivariate time-series data. To demonstrate the proposed approach, we analyze pattern changes in human activity data. For applications with stochastic state transitions, features are developed based on Shannon's entropy of Markov chains, entropy rates of Markov chains, entropy production of Markov chains, and von Neumann entropy of Markov chains. For applications where state modeling is not applicable, we utilize five entropy variants, including approximate entropy, increment entropy, dispersion entropy, phase entropy, and slope entropy. The results show the proposed information theory-based features improve the recall rate, F1 score, and accuracy on average by up to 23.01% compared with the baseline models and a simpler model structure, with an average reduction of 18.75 times in the number of model parameters.

show abstract

Multichannel Optimization With Hybrid Spectral- Entropy Markers for Gender Identification Enhancement of Emotional-Based EEGs

Cited by 20 publications

References 76 publications

Transfer Learning and Hybrid Deep Convolutional Neural Networks Models for Autism Spectrum Disorder Classification From EEG Signals

Transfer Learning and Hybrid Deep Convolutional Neural Networks Models for Autism Spectrum Disorder Classification From EEG Signals

EEG Signal Complexity Measurements to Enhance BCI-Based Stroke Patients’ Rehabilitation

Information Theory Inspired Pattern Analysis for Time-series Data

Contact Info

Product

Resources

About