Evaluation of interpretability for deep learning algorithms in EEG emotion recognition: A case study in autism

Mayor-Torres, Juan Manuel; Medina-DeVilliers, Sara; Clarkson, Tessa; Lerner, Matthew D.; Riccardi, Giuseppe

doi:10.1016/j.artmed.2023.102545

Cited by 13 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Explainable AI (XAI) in EEG emotion recognition will be a critical area of future research. Not only will it help researchers validate existing medical knowledge or discover new ones, as Mayor Torres et al (2023) using the explainable deep learning algorithm SincNet to identify high-alpha and beta suppression in EEG signals of individuals with autism spectrum disorders, but it will also increase physicians’ confidence in using deep learning for diagnosis ( Jafari et al, 2023 ).…”

Section: Introductionmentioning

confidence: 99%

ERTNet: an interpretable transformer-based framework for EEG emotion recognition

Liu,

Chao,

et al. 2024

Front. Neurosci.

View full text Add to dashboard Cite

BackgroundEmotion recognition using EEG signals enables clinicians to assess patients’ emotional states with precision and immediacy. However, the complexity of EEG signal data poses challenges for traditional recognition methods. Deep learning techniques effectively capture the nuanced emotional cues within these signals by leveraging extensive data. Nonetheless, most deep learning techniques lack interpretability while maintaining accuracy.MethodsWe developed an interpretable end-to-end EEG emotion recognition framework rooted in the hybrid CNN and transformer architecture. Specifically, temporal convolution isolates salient information from EEG signals while filtering out potential high-frequency noise. Spatial convolution discerns the topological connections between channels. Subsequently, the transformer module processes the feature maps to integrate high-level spatiotemporal features, enabling the identification of the prevailing emotional state.ResultsExperiments’ results demonstrated that our model excels in diverse emotion classification, achieving an accuracy of 74.23% ± 2.59% on the dimensional model (DEAP) and 67.17% ± 1.70% on the discrete model (SEED-V). These results surpass the performances of both CNN and LSTM-based counterparts. Through interpretive analysis, we ascertained that the beta and gamma bands in the EEG signals exert the most significant impact on emotion recognition performance. Notably, our model can independently tailor a Gaussian-like convolution kernel, effectively filtering high-frequency noise from the input EEG data.DiscussionGiven its robust performance and interpretative capabilities, our proposed framework is a promising tool for EEG-driven emotion brain-computer interface.

show abstract

Section: Introductionmentioning

confidence: 99%

ERTNet: an interpretable transformer-based framework for EEG emotion recognition

Liu,

Chao,

et al. 2024

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Nevertheless, despite the promising results mentioned above, such studies and other related research often lack interpretability and transparency in their findings [35,36]. It can be problematic to explain how the modern DL models arrived at their conclusions, which raises concerns around potential biases and ethical considerations raised by a novel concept of FACTS (Fairness, Accountability, Confidentiality, Transparency, and Safety) [37] in AI.…”

Section: Introductionmentioning

confidence: 99%

Facial Emotion Recognition for Photo and Video Surveillance Based on Machine Learning and Visual Analytics

Kalyta,

Barmak,

Radiuk

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Modern video surveillance systems mainly rely on human operators to monitor and interpret the behavior of individuals in real time, which may lead to severe delays in responding to an emergency. Therefore, there is a need for continued research into the designing of interpretable and more transparent emotion recognition models that can effectively detect emotions in safety video surveillance systems. This study proposes a novel technique incorporating a straightforward model for detecting sudden changes in a person’s emotional state using low-resolution photos and video frames from surveillance cameras. The proposed technique includes a method of the geometric interpretation of facial areas to extract features of facial expression, the method of hyperplane classification for identifying emotional states in the feature vector space, and the principles of visual analytics and “human in the loop” to obtain transparent and interpretable classifiers. The experimental testing using the developed software prototype validates the scientific claims of the proposed technique. Its implementation improves the reliability of abnormal behavior detection via facial expressions by 0.91–2.20%, depending on different emotions and environmental conditions. Moreover, it decreases the error probability in identifying sudden emotional shifts by 0.23–2.21% compared to existing counterparts. Future research will aim to improve the approach quantitatively and address the limitations discussed in this paper.

show abstract

Unlocking the black box: an in-depth review on interpretability, explainability, and reliability in deep learning

ŞAHiN,

Arslan,

Özdemir

2024

Neural Comput & Applic

View full text Add to dashboard Cite

Evaluation of interpretability for deep learning algorithms in EEG emotion recognition: A case study in autism

Cited by 13 publications

References 35 publications

ERTNet: an interpretable transformer-based framework for EEG emotion recognition

ERTNet: an interpretable transformer-based framework for EEG emotion recognition

Facial Emotion Recognition for Photo and Video Surveillance Based on Machine Learning and Visual Analytics

Unlocking the black box: an in-depth review on interpretability, explainability, and reliability in deep learning

Contact Info

Product

Resources

About