Automated ASD detection using hybrid deep lightweight features extracted from EEG signals

Bayğın, Mehmet; Doğan, Şengül; Tuncer, Türker; Barua, Prabal Datta; Faust, Oliver; Arunkumar, N.; Abdulhay, Enas; Palmer, Elizabeth E.; Acharya, U. Rajendra

doi:10.1016/j.compbiomed.2021.104548

Cited by 91 publications

(57 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recurrent neural networks (RNNs) are a group of DL models employed in speech recognition (Ogunfunmi et al, 2019 ), natural language processing (Deng and Liu, 2018 ), and biomedical signal processing (Vicnesh et al, 2020 ; Baygin et al, 2021 ). CNN models are of Feed-Forward types.…”

Section: Methodsmentioning

confidence: 99%

Automatic Diagnosis of Schizophrenia in EEG Signals Using CNN-LSTM Models

Shoeibi

Sadeghi

Moridian

et al. 2021

Front. Neuroinform.

107

View full text Add to dashboard Cite

Schizophrenia (SZ) is a mental disorder whereby due to the secretion of specific chemicals in the brain, the function of some brain regions is out of balance, leading to the lack of coordination between thoughts, actions, and emotions. This study provides various intelligent deep learning (DL)-based methods for automated SZ diagnosis via electroencephalography (EEG) signals. The obtained results are compared with those of conventional intelligent methods. To implement the proposed methods, the dataset of the Institute of Psychiatry and Neurology in Warsaw, Poland, has been used. First, EEG signals were divided into 25 s time frames and then were normalized by z-score or norm L2. In the classification step, two different approaches were considered for SZ diagnosis via EEG signals. In this step, the classification of EEG signals was first carried out by conventional machine learning methods, e.g., support vector machine, k-nearest neighbors, decision tree, naïve Bayes, random forest, extremely randomized trees, and bagging. Various proposed DL models, namely, long short-term memories (LSTMs), one-dimensional convolutional networks (1D-CNNs), and 1D-CNN-LSTMs, were used in the following. In this step, the DL models were implemented and compared with different activation functions. Among the proposed DL models, the CNN-LSTM architecture has had the best performance. In this architecture, the ReLU activation function with the z-score and L2-combined normalization was used. The proposed CNN-LSTM model has achieved an accuracy percentage of 99.25%, better than the results of most former studies in this field. It is worth mentioning that to perform all simulations, the k-fold cross-validation method with k = 5 has been used.

show abstract

Section: Methodsmentioning

confidence: 99%

Automatic Diagnosis of Schizophrenia in EEG Signals Using CNN-LSTM Models

Shoeibi

Sadeghi

Moridian

et al. 2021

Front. Neuroinform.

107

View full text Add to dashboard Cite

show abstract

“…Autism spectrum disorders (ASDs), with a reported prevalence in developed countries of around 2% [26], typically present within the first three years of life. ASDs are characterised by challenges in social interaction [27,28], speech and language delays, avoidance of eye contact, struggles to cope with changes in environment, the display of repetitive behaviours, and differences in learning profiles [26]. Children and adults with an ASD have a high frequency of anxiety and depression.…”

Section: Autism Spectrum Disordersmentioning

confidence: 99%

Artificial Intelligence Enabled Personalised Assistive Tools to Enhance Education of Children with Neurodevelopmental Disorders—A Review

Barua

Vicnesh

Gururajan

et al. 2022

IJERPH

View full text Add to dashboard Cite

Mental disorders (MDs) with onset in childhood or adolescence include neurodevelopmental disorders (NDDs) (intellectual disability and specific learning disabilities, such as dyslexia, attention deficit disorder (ADHD), and autism spectrum disorders (ASD)), as well as a broad range of mental health disorders (MHDs), including anxiety, depressive, stress-related and psychotic disorders. There is a high co-morbidity of NDDs and MHDs. Globally, there have been dramatic increases in the diagnosis of childhood-onset mental disorders, with a 2- to 3-fold rise in prevalence for several MHDs in the US over the past 20 years. Depending on the type of MD, children often grapple with social and communication deficits and difficulties adapting to changes in their environment, which can impact their ability to learn effectively. To improve outcomes for children, it is important to provide timely and effective interventions. This review summarises the range and effectiveness of AI-assisted tools, developed using machine learning models, which have been applied to address learning challenges in students with a range of NDDs. Our review summarises the evidence that AI tools can be successfully used to improve social interaction and supportive education. Based on the limitations of existing AI tools, we provide recommendations for the development of future AI tools with a focus on providing personalised learning for individuals with NDDs.

show abstract

“…As the input attributes in ASD datasets are nonlinearly related, hence the proposed work utilized Landmark Isomap model for dimension reduction which is an advancement of Isomap in terms of speed [18][19][20][21][22][23]. It emphasizes in 1.…”

Section: Dimension Reduction Using Landmark Isomapmentioning

confidence: 99%

“…2. It comprises of one sequence input layer, a Bi Long Short Term Memory (BiLSTM) layer [20], 3 Fully Connected (FC) layers [21], 2 dropout layers [22] and a regression layer [23].…”

Section: Improved Deep Neural Network Prediction With Classification Architecturementioning

confidence: 99%

ASD Classification in Adolescent and Adult Utilizing Deep Neural Network

Mohanty¹,

Parida²,

Patra³

2021

Atlantis Highlights in Computer Sciences

View full text Add to dashboard Cite

Autism Spectrum Disorder (ASD) is one of the neurological illnesses affecting the behaviour and communicative skills of an individual. It hampers the recognition capability of an individual. Hence it is the primary responsibility towards the affected individuals with ASD for early detection to minimize its effect. ASD clinical diagnosis procedure is lengthy and expensive. So, against the procedure, ASD datasets are stored in authenticated sites like Kaggle and UCI Machine Learning (ML) repository to carry out clinical research. The data from all the category of individuals including adult, adolescent, child and toddler got collected by a mobile based ASDTest app with certain screening questions. The proposed method covered the category of adolescent and adult datasets with implementation of Landmark Isomap for dimension reduction and then improved Deep Neural Network prediction with classification (i-DNNPC) architecture for detecting ASD class. The evaluation of performance parameters confirmed the accomplishment of i-DNNPC classifier model.

show abstract

Automated ASD detection using hybrid deep lightweight features extracted from EEG signals

Cited by 91 publications

References 56 publications

Automatic Diagnosis of Schizophrenia in EEG Signals Using CNN-LSTM Models

Automatic Diagnosis of Schizophrenia in EEG Signals Using CNN-LSTM Models

Artificial Intelligence Enabled Personalised Assistive Tools to Enhance Education of Children with Neurodevelopmental Disorders—A Review

ASD Classification in Adolescent and Adult Utilizing Deep Neural Network

Contact Info

Product

Resources

About