Evaluation of Interpretability for Deep Learning algorithms in EEG Emotion Recognition: A case study in Autism

Published in

(2021)

External Links:

Generate Graph

TL;DR

This study is the first to bridge previous neuroscience and ASD research findings to feature-relevance calculation for EEG-based emotion recognition with CNN in typically-development (TD) and in ASD individuals.

Authors

J. M. M. Torres

1 papers

Sara E. Medina-DeVilliers

1 papers

T. Clarkson

1 papers

M. Lerner

1 papers

G. Riccardi

1 papers

References81 items

Interpretable SincNet-based Deep Learning for Emotion Recognition from EEG brain activity

Facial emotions are accurately encoded in the neural signal of those with Autism Spectrum Disorder: A deep learning approach.

Integration of Facial Thermography in EEG-based Classification of ASD

Toward Interpretable Machine Learning: Transparent Deep Neural Networks and Beyond

Explainable Artificial Intelligence for Neuroscience: Behavioral Neurostimulation

Evaluation of Interpretability for Deep Learning algorithms in EEG Emotion Recognition: A case study in Autism

Published in

(2021)

External Links:

Generate Graph

TL;DR

Authors

J. M. M. Torres

1 papers

Sara E. Medina-DeVilliers

1 papers

T. Clarkson

1 papers

M. Lerner

1 papers

G. Riccardi

1 papers

References81 items

Interpretable SincNet-based Deep Learning for Emotion Recognition from EEG brain activity

Facial emotions are accurately encoded in the neural signal of those with Autism Spectrum Disorder: A deep learning approach.

Integration of Facial Thermography in EEG-based Classification of ASD

Toward Interpretable Machine Learning: Transparent Deep Neural Networks and Beyond

Explainable Artificial Intelligence for Neuroscience: Behavioral Neurostimulation

An EEG based Channel Optimized Classification Approach for Autism Spectrum Disorder

Estimating Uncertainty in Deep Learning for Reporting Confidence to Clinicians when Segmenting Nuclei Image Data

Evaluation of Source-wise Missing Data Techniques for the Prediction of Parkinson’s Disease Using Smartphones

Why are Saliency Maps Noisy? Cause of and Solution to Noisy Saliency Maps

Cross-Subject Emotion Recognition Using Deep Adaptation Networks

Toward Efficient Automation of Interpretable Machine Learning

Sanity Checks for Saliency Maps

Finding the Optimal Cross-Subject EEG Data Alignment Method for Analysis and BCI

iNNvestigate neural networks!

Multichannel Sleep Stage Classification and Transfer Learning using Convolutional Neural Networks

Enhanced Error Decoding from Error-Related Potentials using Convolutional Neural Networks

Evaluating Feature Importance Estimates

Adversarially Occluded Samples for Person Re-identification

EEG-Based Single Trial Classification Emotion Recognition: A Comparative Analysis in Individuals with and without Autism Spectrum Disorder

Stimulus dependent neural oscillatory patterns show reliable statistical identification of autism spectrum disorder in a face perceptual decision task

EEG Analytics for Early Detection of Autism Spectrum Disorder: A data-driven approach

Kolmogorov–Smirnov test for life test data with hybrid censoring

The Effectiveness of Technology-Based Intervention in Improving Emotion Recognition Through Facial Expression in People with Autism Spectrum Disorder: a Systematic Review

The (Un)reliability of saliency methods

Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks

EEG analysis of facial affect recognition process of individuals with ASD performance prediction leveraging social context

Mechanisms of facial emotion recognition in autism spectrum disorders: Insights from eye tracking and electroencephalography

Classification of respiratory disturbances in Rett Syndrome patients using Restricted Boltzmann Machine

Methods for interpreting and understanding deep neural networks

SmoothGrad: removing noise by adding noise

Learning how to explain neural networks: PatternNet and PatternAttribution

PatternNet and PatternLRP - Improving the interpretability of neural networks

Face Perception and Learning in Autism Spectrum Disorders

Where Does EEG Come From and What Does It Mean?

Emotion Recognition Using Multimodal Deep Learning

Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

A novel feature extraction method based on late positive potential for emotion recognition in human brain signal patterns

On the influence of high-pass filtering on ICA-based artifact reduction in EEG-ERP

On the use of convolutional neural networks and augmented CSP features for multi-class motor imagery of EEG signals classification

A Step towards EEG-based brain computer interface for autism intervention

An Effective Neurofeedback Intervention to Improve Social Interactions in Children with Autism Spectrum Disorder

On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation

The PREP pipeline: standardized preprocessing for large-scale EEG analysis

Guidelines and Best Practices for Electrophysiological Data Collection, Analysis and Reporting in Autism

Adam: A Method for Stochastic Optimization

Sequence to Sequence Learning with Neural Networks

Feature Extraction and Selection for Emotion Recognition from EEG

Classifying Different Emotional States by Means of EEG-Based Functional Connectivity Patterns

ImageNet classification with deep convolutional neural networks

Neural Networks: Tricks of the Trade

Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation

Developmental change in the ERP responses to familiar faces in toddlers with autism spectrum disorders versus typical development.

Automatic Classification of Artifactual ICA-Components for Artifact Removal in EEG Signals

Deep Sparse Rectifier Neural Networks

Single-trial analysis and classification of ERP components — A tutorial

EEG complexity as a biomarker for autism spectrum disorder risk

ADJUST: An automatic EEG artifact detector based on the joint use of spatial and temporal features.

Filter Bank Common Spatial Pattern (FBCSP) in Brain-Computer Interface

Neurocognitive and electrophysiological evidence of altered face processing in parents of children with autism: Implications for a model of abnormal development of social brain circuitry in autism

Understanding the Nature of Face Processing Impairment in Autism: Insights From Behavioral and Electrophysiological Studies

The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials

EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis

Neural correlates of face and object recognition in young children with autism spectrum disorder, developmental delay, and typical development.

Independent component analysis: algorithms and applications

What is clinical psychology?

Towards Explaining Deep Learning Networks to Distinguish Facial Expressions of Pain and Emotions

EEG-Based Affect and Workload Recognition in a Virtual Driving Environment for ASD Intervention

Supplementary for: Deep learning with convolutional neural networks for EEG decoding and visualization

Multimodal hand stereotypies detection in rett syndrome treatment using deep belief neural networks

Layer-Wise Relevance Propagation for Deep Neural Network Architectures

EEG signals classification using linear and non-linear discriminant methods

DEAP: A Database for Emotion Analysis ;Using Physiological Signals

Learning Feature Representations with K-Means

Holm's Sequential Bonferroni Procedure

Autism Spectrum Disorders

Manual for the receptive tests of the diagnostic analysis of nonverbal accuracy 2

(MSEE) degree in Electrical Engineering and Master in Information Technology, from the University of Padua and Polytechnic of Milan (Italy), respectively

An existence result for scalar conservation laws using measure valued solutions.

interested in how these mechanisms relate to the development and maintenance of psychopathology

. Giuseppe Riccardi (M96-SM04-F10) is founder and director of the Signals and Interactive Systems Lab at University of Trento, Italy. He received his Laurea

Field of Study

EngineeringComputer ScienceMedicine

Journal Information

Name

Artificial intelligence in medicine

Page

101822

Volume

104

TL;DR

Authors

References81 items

Interpretable SincNet-based Deep Learning for Emotion Recognition from EEG brain activity

Facial emotions are accurately encoded in the neural signal of those with Autism Spectrum Disorder: A deep learning approach.

Integration of Facial Thermography in EEG-based Classification of ASD

Toward Interpretable Machine Learning: Transparent Deep Neural Networks and Beyond

Explainable Artificial Intelligence for Neuroscience: Behavioral Neurostimulation

TL;DR

Authors

References81 items

Interpretable SincNet-based Deep Learning for Emotion Recognition from EEG brain activity

Facial emotions are accurately encoded in the neural signal of those with Autism Spectrum Disorder: A deep learning approach.

Integration of Facial Thermography in EEG-based Classification of ASD

Toward Interpretable Machine Learning: Transparent Deep Neural Networks and Beyond

Explainable Artificial Intelligence for Neuroscience: Behavioral Neurostimulation

An EEG based Channel Optimized Classification Approach for Autism Spectrum Disorder

Estimating Uncertainty in Deep Learning for Reporting Confidence to Clinicians when Segmenting Nuclei Image Data

Evaluation of Source-wise Missing Data Techniques for the Prediction of Parkinson’s Disease Using Smartphones

Why are Saliency Maps Noisy? Cause of and Solution to Noisy Saliency Maps

Cross-Subject Emotion Recognition Using Deep Adaptation Networks

Toward Efficient Automation of Interpretable Machine Learning

Sanity Checks for Saliency Maps

Finding the Optimal Cross-Subject EEG Data Alignment Method for Analysis and BCI

iNNvestigate neural networks!

Multichannel Sleep Stage Classification and Transfer Learning using Convolutional Neural Networks

Enhanced Error Decoding from Error-Related Potentials using Convolutional Neural Networks

Evaluating Feature Importance Estimates

Adversarially Occluded Samples for Person Re-identification

EEG-Based Single Trial Classification Emotion Recognition: A Comparative Analysis in Individuals with and without Autism Spectrum Disorder

Stimulus dependent neural oscillatory patterns show reliable statistical identification of autism spectrum disorder in a face perceptual decision task

EEG Analytics for Early Detection of Autism Spectrum Disorder: A data-driven approach

Kolmogorov–Smirnov test for life test data with hybrid censoring

The Effectiveness of Technology-Based Intervention in Improving Emotion Recognition Through Facial Expression in People with Autism Spectrum Disorder: a Systematic Review

The (Un)reliability of saliency methods

Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks

EEG analysis of facial affect recognition process of individuals with ASD performance prediction leveraging social context

Mechanisms of facial emotion recognition in autism spectrum disorders: Insights from eye tracking and electroencephalography

Classification of respiratory disturbances in Rett Syndrome patients using Restricted Boltzmann Machine

Methods for interpreting and understanding deep neural networks

SmoothGrad: removing noise by adding noise

Learning how to explain neural networks: PatternNet and PatternAttribution

PatternNet and PatternLRP - Improving the interpretability of neural networks

Face Perception and Learning in Autism Spectrum Disorders

Where Does EEG Come From and What Does It Mean?

Mask R-CNN

Emotion Recognition Using Multimodal Deep Learning

Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

A novel feature extraction method based on late positive potential for emotion recognition in human brain signal patterns

On the influence of high-pass filtering on ICA-based artifact reduction in EEG-ERP

On the use of convolutional neural networks and augmented CSP features for multi-class motor imagery of EEG signals classification

A Step towards EEG-based brain computer interface for autism intervention

An Effective Neurofeedback Intervention to Improve Social Interactions in Children with Autism Spectrum Disorder

On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation

The PREP pipeline: standardized preprocessing for large-scale EEG analysis

Guidelines and Best Practices for Electrophysiological Data Collection, Analysis and Reporting in Autism

Adam: A Method for Stochastic Optimization

Sequence to Sequence Learning with Neural Networks

Feature Extraction and Selection for Emotion Recognition from EEG

Classifying Different Emotional States by Means of EEG-Based Functional Connectivity Patterns

ImageNet classification with deep convolutional neural networks

Neural Networks: Tricks of the Trade

Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation

Developmental change in the ERP responses to familiar faces in toddlers with autism spectrum disorders versus typical development.

Automatic Classification of Artifactual ICA-Components for Artifact Removal in EEG Signals

Deep Sparse Rectifier Neural Networks

Single-trial analysis and classification of ERP components — A tutorial

EEG complexity as a biomarker for autism spectrum disorder risk

ADJUST: An automatic EEG artifact detector based on the joint use of spatial and temporal features.

Filter Bank Common Spatial Pattern (FBCSP) in Brain-Computer Interface

Neurocognitive and electrophysiological evidence of altered face processing in parents of children with autism: Implications for a model of abnormal development of social brain circuitry in autism

Understanding the Nature of Face Processing Impairment in Autism: Insights From Behavioral and Electrophysiological Studies

The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials

EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis

Neural correlates of face and object recognition in young children with autism spectrum disorder, developmental delay, and typical development.

Independent component analysis: algorithms and applications

What is clinical psychology?

Towards Explaining Deep Learning Networks to Distinguish Facial Expressions of Pain and Emotions

EEG-Based Affect and Workload Recognition in a Virtual Driving Environment for ASD Intervention

Supplementary for: Deep learning with convolutional neural networks for EEG decoding and visualization