Performance Analysis of Deep Learning Models for Detection of Autism Spectrum Disorder from EEG Signals

Autism Spectrum Disorder (ASD) is a neurodevelopmental life condition characterized by problems with social interaction, low verbal and non-verbal communication skills, and repetitive and restricted behavior. People with ASD usually have variable attention levels because they have hypersensitivity and large amounts of environmental information are a problem for them. Attention is a process that occurs at the cognitive level and allows us to orient ourselves towards relevant stimuli, ignoring those that are not, and act accordingly. This paper presents a methodology based on electroencephalographic (EEG) signals for attention measurement in a 13-year-old boy diagnosed with ASD. The EEG signals are acquired with an Epoc+ Brain–Computer Interface (BCI) via the Emotiv Pro platform while developing several learning activities and using Matlab 2019a for signal processing. For this article, we propose to use electrodes F3, F4, P7, and P8. Then, we calculate the band power spectrum density to detect the Theta Relative Power (TRP), Alpha Relative Power (ARP), Beta Relative Power (BRP), Theta–Beta Ratio (TBR), Theta–Alpha Ratio (TAR), and Theta/(Alpha+Beta), which are features related to attention detection and neurofeedback. We train and evaluate several machine learning (ML) models with these features. In this study, the multi-layer perceptron neural network model (MLP-NN) has the best performance, with an AUC of 0.9299, Cohen’s Kappa coefficient of 0.8597, Matthews correlation coefficient of 0.8602, and Hamming loss of 0.0701. These findings make it possible to develop better learning scenarios according to the person’s needs with ASD. Moreover, it makes it possible to obtain quantifiable information on their progress to reinforce the perception of the teacher or therapist.

show abstract

“…Ref. [28] 10 typically developing children (6 Male and 6 Female) and 10 autistic children (6 Male and 4 Female).…”

Section: Institutional Review Board Statementmentioning

confidence: 99%

“…The authors in [27] used EEG and eye-tracking features to identify children with ASD. In [28], the authors used deep convolutional architectures to detect ASD. Other studies [29] reported statistical features for ASD classification.…”

Section: Introductionmentioning

confidence: 99%

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

Esqueda-Elizondo

Juárez‐Ramírez

López-Bonilla

et al. 2022

MCA

View full text Add to dashboard Cite

show abstract

“…Network variability may be seen through time series estimations using methods for analysing complex and intricate networks such as the human brain. As a result, a collection of invariant measures derived from EEG data must represent the neuronal prospects in the brain that generates the signals [2][3][4][5]. EEGs are established as observations of electrical activity in the brain acquired from the surface of the scalp.…”

Section: Introductionmentioning

confidence: 99%

EEG-Based Anamoly Detection for Autistic Kids – A Pilot Study

Radhakrishnan¹,

Boruah²,

Ramamurthy³

2022

Self Cite

View full text Add to dashboard Cite

An electroencephalogram (EEG) test can be utilized to capture the electrical impulses in the human brain. EEG signal analysis is crucial in the detection and treatment of brain diseases. Autism is one of the neurological disorders that needs to be diagnosed in the early stages of life. Autistic behavior is difficult to differentiate and it can even lead to adverse effects in the daily routine of a kid. Recent advances in Artificial Intelligence have proven to be an effective way of diagnosing ASD. This research employs PyCaret framework to analyze the anomalies present in the EEG signal data in the context of differentiating Autistic children from Typically developing children. The different anomaly detection modules have been used to detect anomalies, compute their anomaly scores and visualize it. The goal of this study is to determine if PyCaret's anomaly detection module can aid the detection of ASD.

show abstract

“…Along with different processing techniques, different ML methods are investigated in the last several years for ASD detection (Brihadiswaran et al, 2019) including Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), and Artificial Neural Network (ANN) (Bosl et al, 2018;Grossi et al, 2017;Hadoush et al, 2019;Ibrahim et al, 2018;Kang et al, 2019). Deep learning methods have recently been used to detect ASD from EEG signals (Radhakrishnan et al, 2021;Khodatars et al, 2021;Ali et al, 2020). The performance of existing ML-based methods is promising, which motivates the current investigation, especially the deep learning method, intending to improve efficiency.…”

Section: Introductionmentioning

confidence: 99%

Autism Detection from 2D Transformed EEG Signal using Convolutional Neural Network

Peya¹,

Akhand²,

Srabonee³

et al. 2022

Journal of Computer Science

View full text Add to dashboard Cite

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder relating to speech complications, nonverbal and social communication, and repetitive behaviors. There is no remedy for ASD but early diagnosis, mediation, and supportive care can aid the development of language, conduct, and communication skills. As the cause of ASD is a neurodevelopmental disorder, its diagnosis based on brain function analyzing different brain signals, especially Electroencephalography (EEG), has drawn attention recently. Brain activity is recorded over time as an EEG signal from the scalp of a human and is used to investigate complicated neuropsychiatric disorders in the brain. In this study, the data from the EEG channels are translated into two-Dimensional (2D) form through correlation, and classification is performed using Convolutional Neural Networks (CNN), the well-known deep learning method for image analysis and classification. Two different CNN models are considered for classification purposes: Generic CNN and Residual Network (ResNet), a well-known deep CNN model. The proposed method with Resnet achieved 88% classification accuracy on a five-fold cross-validation mode, whereas it was 100 on 20% of test samples. Experimental evaluations using clinical EEG data revealed the efficacy of the proposed method outperforming other existing methods.

show abstract

Performance Analysis of Deep Learning Models for Detection of Autism Spectrum Disorder from EEG Signals

Cited by 24 publications

References 35 publications

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

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

EEG-Based Anamoly Detection for Autistic Kids – A Pilot Study

Autism Detection from 2D Transformed EEG Signal using Convolutional Neural Network

Contact Info

Product

Resources

About