Attention Measurement of an Autism Spectrum Disorder User Using EEG Signals: A Case Study

Esqueda-Elizondo, José Jaime; Juárez‐Ramírez, Reyes; López-Bonilla, Oscar Roberto; García-Guerrero, E. E.; Galindo-Aldana, Gilberto; Jiménez-Beristáin, Laura; Serrano-Trujillo, Alejandra; Tlelo‐Cuautle, Esteban; Inzunza-González, Everardo

doi:10.3390/mca27020021

Cited by 24 publications

(17 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sensitivity, also known as Recall [84], measures the proportion of positives that are correctly identified as such; it can be calculated by (9). Similarly, Speci f icity measures the proportion of negatives that are correctly identified as such [84]; it can be calculated by (10). Precision is the proportion of true positives among the positive predictions [84]; it can be calculated by (11).…”

Section: Resultsmentioning

confidence: 99%

“…Electroencephalography (EEG) is a non-invasive procedure for measuring the electrical activity generated within the brain as a result of different mental processes [10]. The electrical signals are acquired through electrodes placed on the scalp's surface; thus, waves with different amplitudes and frequencies that refer to a person's mental state are obtained [11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of Machine Learning Algorithms for Classification of EEG Signals

et al. 2022

Self Cite

View full text Add to dashboard Cite

In brain–computer interfaces (BCIs), it is crucial to process brain signals to improve the accuracy of the classification of motor movements. Machine learning (ML) algorithms such as artificial neural networks (ANNs), linear discriminant analysis (LDA), decision tree (D.T.), K-nearest neighbor (KNN), naive Bayes (N.B.), and support vector machine (SVM) have made significant progress in classification issues. This paper aims to present a signal processing analysis of electroencephalographic (EEG) signals among different feature extraction techniques to train selected classification algorithms to classify signals related to motor movements. The motor movements considered are related to the left hand, right hand, both fists, feet, and relaxation, making this a multiclass problem. In this study, nine ML algorithms were trained with a dataset created by the feature extraction of EEG signals.The EEG signals of 30 Physionet subjects were used to create a dataset related to movement. We used electrodes C3, C1, CZ, C2, and C4 according to the standard 10-10 placement. Then, we extracted the epochs of the EEG signals and applied tone, amplitude levels, and statistical techniques to obtain the set of features. LabVIEW™2015 version custom applications were used for reading the EEG signals; for channel selection, noise filtering, band selection, and feature extraction operations; and for creating the dataset. MATLAB 2021a was used for training, testing, and evaluating the performance metrics of the ML algorithms. In this study, the model of Medium-ANN achieved the best performance, with an AUC average of 0.9998, Cohen’s Kappa coefficient of 0.9552, a Matthews correlation coefficient of 0.9819, and a loss of 0.0147. These findings suggest the applicability of our approach to different scenarios, such as implementing robotic prostheses, where the use of superficial features is an acceptable option when resources are limited, as in embedded systems or edge computing devices.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Evaluation of Machine Learning Algorithms for Classification of EEG Signals

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Data is filtered and the output is a 256 Hz clean signal in the 0.2-45 Hz range [10]. A number of studies showed that this EEG headset was effective in acquiring research-grade data for studying attention, auditory event-related potentials, neurofeedback games for enhancing attention and memory, and inter-brain synchrony in teams across different settings, learners, and tasks [11][12][13][14].…”

Section: Eeg Data Acquisition and Processingmentioning

confidence: 99%

A Multimodal Evaluation of Podcast Learning, Retention, and Electroencephalographically Measured Attention in Medical Trainees

Wolpaw¹,

Ozsoy²,

Berenholtz³

et al. 2022

Cureus

View full text Add to dashboard Cite

Introduction: Podcasts have become popular among medical trainees. However, it is unclear how well learners retain information from podcasts compared to traditional educational modalities, and whether multitasking affects the learner's ability to pay attention and learn. This study attempted to examine the effectiveness of podcast learning by using electroencephalography (EEG) to measure learner attention, in addition to test performance, task load, and preferences.Methods: The study used a repeated measures design with three conditions: podcast listening on a treadmill, podcast listening seated, and textbook reading seated. Participants were anesthesiology residents and medical students at a large United States academic medical center. Three topics were chosen: allergic response, liver physiology, and statistics. Each participant studied all three topics that were randomly assigned to one of three learning conditions -in random order. Participants completed a knowledge test at baseline, after each condition, and at four-week follow-up, and reported preferred learning modality and task load under each modality. Activation levels in alerting, orienting, and executive attentional networks were examined using EEG.Results: Sixty-one participants (11 anesthesiology residents and 50 medical students) were included in the study. Of the 61, six were excluded from the EEG analyses due to corrupted recordings. EEG results showed that mean attention network activation scores did not differ between the study conditions. Trainees preferred podcast learning over reading for all three topics. When compared to textbook reading, podcast learning (seated or on a treadmill) produced significantly better learning gain, and equivalent retention for two of the three topics.Conclusions: Our study is the first to use neurocognitive data, self-reported satisfaction, and knowledge test performance to demonstrate that podcasts are at least equivalent to textbooks for maintaining attention, immediate learning, and retention -even while exercising.

show abstract

“…Recent research has focused on examining how human and machine behavior interact, acknowledging that differing social and psychological origins might affect various forms of human-computer interaction [26]. Techniques for extracting EEG features have repeatedly been shown to be clinically reliable in evaluating and diagnosing a range of cognitive and neurological domains in conditions such as ASD [27][28][29][30], learning difficulties [31], and attention-related issues [32][33][34][35]. It is commonly acknowledged that artificial intelligence (AI) tools can be used to automatically diagnose and treat ASD cases.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Identifying autism using EEG: unleashing the power of feature selection and machine learning

Ranaut,

Khandnor,

Chand

2024

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition that is characterized by communication barriers, societal disengagement, and monotonous actions. Currently, the diagnosis of ASD is made by experts through a subjective and time-consuming qualitative behavioural examination using internationally recognized descriptive standards. In this paper, we present an EEG-based three-phase novel approach comprising 29 autistic subjects and 30 neurotypical people. In the first phase, preprocessing of data is performed from which we derived one continuous dataset and four condition-based datasets to determine the role of each dataset in the identification of autism from neurotypical people. In the second phase, time-domain and morphological features were extracted and four different feature selection techniques were applied. In the last phase, five-fold cross-validation is used to evaluate six different machine learning models based on the performance metrics and computational efficiency. The neural network outperformed when trained with maximum relevance and minimum redundancy (MRMR) algorithm on the continuous dataset with 98.10% validation accuracy and 0.9994 area under the curve (AUC) value for model validation, and 98.43% testing accuracy and AUC test value of 0.9998. The decision tree overall performed the second best in terms of computational efficiency and performance accuracy. The results indicate that EEG-based machine learning models have the potential for ASD identification from neurotypical people with a more objective and reliable method.

show abstract

Attention Measurement of an Autism Spectrum Disorder User Using EEG Signals: A Case Study

Cited by 24 publications

References 50 publications

Evaluation of Machine Learning Algorithms for Classification of EEG Signals

Evaluation of Machine Learning Algorithms for Classification of EEG Signals

A Multimodal Evaluation of Podcast Learning, Retention, and Electroencephalographically Measured Attention in Medical Trainees

Identifying autism using EEG: unleashing the power of feature selection and machine learning

Contact Info

Product

Resources

About