Neurobehavioral Associations with NREM and REM Sleep Architecture in Children with Autism Spectrum Disorder

Nguyen, Jennifer; Zhang, Bo; Hanson, Ellen; Mylonas, Dimitrios; Maski, Kiran

doi:10.3390/children9091322

Cited by 2 publications

(1 citation statement)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An electroencephalogram (EEG) [ 1 , 2 ] is a test that detects brain electrical activity using sensors (electrodes) attached to the scalp. EEG can be used to help diagnose conditions including seizures [ 3 , 4 ], sleep disorders [ 5 , 6 ], and head injuries [ 7 ], as well as for emotion recognition. This technology is still in its early stages, but it has the potential to transform how we communicate with each other and with machines, as well as improve our understanding of how the brain processes emotions.…”

Section: Introductionmentioning

confidence: 99%

M1M2: Deep-Learning-Based Real-Time Emotion Recognition from Neural Activity

Akter

Prodhan

Pias

et al. 2022

Sensors

View full text Add to dashboard Cite

Emotion recognition, or the ability of computers to interpret people’s emotional states, is a very active research area with vast applications to improve people’s lives. However, most image-based emotion recognition techniques are flawed, as humans can intentionally hide their emotions by changing facial expressions. Consequently, brain signals are being used to detect human emotions with improved accuracy, but most proposed systems demonstrate poor performance as EEG signals are difficult to classify using standard machine learning and deep learning techniques. This paper proposes two convolutional neural network (CNN) models (M1: heavily parameterized CNN model and M2: lightly parameterized CNN model) coupled with elegant feature extraction methods for effective recognition. In this study, the most popular EEG benchmark dataset, the DEAP, is utilized with two of its labels, valence, and arousal, for binary classification. We use Fast Fourier Transformation to extract the frequency domain features, convolutional layers for deep features, and complementary features to represent the dataset. The M1 and M2 CNN models achieve nearly perfect accuracy of 99.89% and 99.22%, respectively, which outperform every previous state-of-the-art model. We empirically demonstrate that the M2 model requires only 2 seconds of EEG signal for 99.22% accuracy, and it can achieve over 96% accuracy with only 125 milliseconds of EEG data for valence classification. Moreover, the proposed M2 model achieves 96.8% accuracy on valence using only 10% of the training dataset, demonstrating our proposed system’s effectiveness. Documented implementation codes for every experiment are published for reproducibility.

show abstract

Section: Introductionmentioning

confidence: 99%

M1M2: Deep-Learning-Based Real-Time Emotion Recognition from Neural Activity

Akter

Prodhan

Pias

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

Sleep architecture is associated with core symptom severity in autism spectrum disorder

Kawai

Buck

Chick

et al. 2022

Sleep

View full text Add to dashboard Cite

Objective While caregiver-reported sleep disturbances are common in children and adolescents with autism spectrum disorder (ASD), few studies have measured objective sleep in ASD compared to controls, and their findings are mixed. We investigated 1) differences in sleep architecture, specifically slow-wave sleep (SWS) and rapid eye movement sleep (REM), between ASD and typically developing controls (TD); and 2) if any observed differences in sleep were associated with core ASD symptoms. Methods We used ambulatory polysomnography (PSG) in 53 participants with ASD (ages 6 to 18) and 66 age-matched TD in their home sleeping environment. The primary outcome measures were SWS and REM sleep. Core behavioral ASD symptoms were assessed using the Autism Diagnostic Interview-Revised (ADI-R). Spectral power bands during sleep, and additional behavioral measures, were examined in exploratory analyses. Results Compared to TD, participants with ASD exhibited a higher SWS ratio and lower REM ratio. Within the ASD group, higher SWS was associated with more severe symptoms on the Restricted, Repetitive, and Stereotyped Behaviors subscale of the ADI-R. No association was observed between REM ratio and any ASD symptom. Conclusions Increased SWS and reduced REM sleep ratio differentiated ASD from TD. However, only increased SWS was associated with more severe core ASD symptoms. Increased SWS may reflect neuronal immaturity specific to ASD in this age group. These findings may inform the underlying mechanisms of clinical symptoms observed in children and adolescents with ASD.

show abstract

Neurobehavioral Associations with NREM and REM Sleep Architecture in Children with Autism Spectrum Disorder

Cited by 2 publications

References 47 publications

M1M2: Deep-Learning-Based Real-Time Emotion Recognition from Neural Activity

M1M2: Deep-Learning-Based Real-Time Emotion Recognition from Neural Activity

Sleep architecture is associated with core symptom severity in autism spectrum disorder

Contact Info

Product

Resources

About