Supporting autism spectrum disorder screening and intervention with machine learning and wearables: a systematic literature review

Francese, Rita; Yang, Xiaoyan

doi:10.1007/s40747-021-00447-1

Cited by 18 publications

(7 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They are not included the emotions of ASD children. Francese et al [68] performed a survey on current research on ASD. They considered only 11 papers for analysis and focused on the ML approach and IoT approach for ASD detection.…”

Section: Asd Monitoring and Detection Based On Iot Devicesmentioning

confidence: 99%

See 1 more Smart Citation

A Systematic Survey of Technology Driven Diagnosis for ASD

Singh

Shukla

Gore

2022

Preprint

View full text Add to dashboard Cite

Autism Spectrum Disorder (ASD), according to The Diagnostic and Statistical Manual of Mental Disorders- Fifth Edition (DSM-5), is a neurodevelopmental disorder that includes deficits of social interaction and social communication with the presence of restricted/repetitive behaviors. Due to communication deficits, ASD children have difficulties in joint attention and social reciprocity. Genetic disorders and/or environmental aspects are the leading causes of ASD. In 2021, the Centers for Disease Control and Prevention reported that approximately 1 among 44children in the U.S. is diagnosed with ASD. As per World Health Organization, ASD affects 14 out of every 10,000 children in Asian countries, which is approximately 23 children per 10,000 children in India. The Reported work shows that the early detection and intervention of ASD improve the language and communication deficiency of ASD children. This paper provides a comprehensive survey on various approaches to monitoring and detecting ASD children. Some monitoring and detection approaches covered in the study are clinical-based detection, MachineLearning -based ASD detection, Internet of Things (IoT)-based ASDdetection, Affective state detection, and Self Injurious Behaviour (SIB)detection of autistic children. This review also lists the several unaddressed challenges of early ASD detection. The purpose of this article is to enhance the understanding, provide guidelines for the domain, and provide insight into developing more practical and close-to-market products.

show abstract

Section: Asd Monitoring and Detection Based On Iot Devicesmentioning

confidence: 99%

“…The missing value imputation method is applied to the dataset before model training for improving the model accuracy. Three papers are related to ASD survey [66][67][68] .…”

Section: Q3 Which Technique Is Used To Assess the Provided Technologi...mentioning

confidence: 99%

A Systematic Survey of Technology Driven Diagnosis for ASD

Singh

Shukla

Gore

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Finally, [15,17] indicated few studies related on smart wearables among individuals with ASD. In addition, the use of machine learning (ML) approaches to predict aggressive behaviors have increased [18] using techniques such as Support Vector Machine (SVM), k Nearest Neighbors (kNN), Decision Tree (DT), and deep neural networks.…”

Section: Introductionmentioning

confidence: 99%

Wearable Solutions for Stress Monitoring for Individuals with Autism Spectrum Disorder (ASD): Systematic Literature Review

Cano,

Franco,

Apablaza

et al. 2023

Preprint

View full text Add to dashboard Cite

Research on wearable solutions for individuals with autism spectrum disorder (ASD) has been conducted to detect stress. However, studies on stress detection for an individual with ASD have been limited, especially on how it should design for individuals with ASD. Wearable solutions may be a tool for parents and caregivers for emotional monitoring for individuals with ASD who have a high risk of experiencing very stressful. However, wearable solutions for individuals with ASD may differ from those without ASD. Individuals with ASD have sensory sensitiveness; therefore, they do not tolerate any accessory type or discomfort to use. We used the Scopus, PubMed, WoS, and IEEE-Xplore databases to answer different research questions related to wearable solutions for individuals with ASD, physiological parameters, and algorithms of artificial intelligence used for stress detection studies found from 2013 to 2023. Our review found 34 articles; not all the studies considered individuals with ASD or were out of the scope.

show abstract

“…Some further application fields are, for example, car driving [11], [12], working environment [13], and entertainment [14]. In clinical applications, wearable systems were employed for measuring sleep parameters [15], for detecting epileptic seizures [16] and for screening, intervention and monitoring of autism spectrum disorders [17], [18]. These approaches are made possible by the availability of new wearable solutions.…”

Section: Introductionmentioning

confidence: 99%

A Survey on EEG-Based Solutions for Emotion Recognition With a Low Number of Channels

et al. 2022

View full text Add to dashboard Cite

The market uptake of Brain-Computer Interface technologies for clinical and non-clinical applications is attracting the scientific world towards the development of daily-life wearable systems. Beyond the use of dry electrodes and wireless technology, reducing the number of channels is crucial to enhance the ergonomics of devices. This paper presents a review of the studies exploiting a number of channels less than 16 for electroencephalographic (EEG) based-emotion recognition. The main findings of this review concern: (i) the criteria to select the most promising scalp areas for EEG acquisitions; (ii) the attention to prior neurophysiological knowledge; and (iii) the convergences among different studies with respect to preferable areas of the scalp for signal acquisition. Three main approaches emerge for channel selection: data-driven, prior knowledge-based, and based on commercially-available wearable solutions. The most spread is the data-driven, but the neurophysiology of emotions is rarely taken into account. Furthermore, commercial EEG devices usually do not provide electrodes purposefully chosen to assess emotions. Considerable convergences emerge for some electrodes: Fp1, Fp2, F3 and F4 resulted the most informative channels for the valence dimension, according to both data-driven and neurophysiological prior knowledge approaches. The P3 and P4 resulted in being significant for the arousal dimension.INDEX TERMS Emotion, EEG, channel selection, machine learning, neurophysiology of emotions, wearable devices.

show abstract

Supporting autism spectrum disorder screening and intervention with machine learning and wearables: a systematic literature review

Cited by 18 publications

References 40 publications

A Systematic Survey of Technology Driven Diagnosis for ASD

A Systematic Survey of Technology Driven Diagnosis for ASD

Wearable Solutions for Stress Monitoring for Individuals with Autism Spectrum Disorder (ASD): Systematic Literature Review

A Survey on EEG-Based Solutions for Emotion Recognition With a Low Number of Channels

Contact Info

Product

Resources

About