EEG channel selection strategy for deep learning in emotion recognition

Abstract Emotions play an important role in everyday life and contribute to physical and mental health. Emotional states can be detected by electroencephalography (EEG signals). Efficient information retrieval from the EEG sensors is a complex and challenging task. Therefore, deep learning methods for EEG signal analysis attract more and more attention. Many researchers emphasize automated feature learning as the motivation for using deep learning approaches. We propose using a limited number of EEG channels as an input for a deep neural network. In the research, we confirm that our electrode selection enhances the learning process of the convolutional neural network. The classification accuracy for the reduced subset of electrodes yields results comparable to the full dataset in a significantly shorter time—the average learning time 58% faster using our proposed strategy.

[1]  J. Russell.  A circumplex model of affect. , 1980 .

[2]  Agnieszka Wosiak,et al.  Reversed Correlation-Based Pairwised EEG Channel Selection in Emotional State Recognition , 2021, ICCS.

[3]  Agnieszka Wosiak,et al.  Integrating Correlation-Based Feature Selection and Clustering for Improved Cardiovascular Disease Diagnosis , 2018, Complex..

[4]  Zhenqi Li,et al.  A Review of Emotion Recognition Using Physiological Signals , 2018, Sensors.

[5]  Enzo Pasquale Scilingo,et al.  Affective computing in virtual reality: emotion recognition from brain and heartbeat dynamics using wearable sensors , 2018, Scientific Reports.

[6]  Krzysztof Pancerz,et al.  Experiments with Consistency-Based Preprocessing of MMPI Data for Classification Tasks , 2018, KES.

[7]  Stanislas Chambon,et al.  A Deep Learning Architecture for Temporal Sleep Stage Classification Using Multivariate and Multimodal Time Series , 2017, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[8]  Krzysztof Pancerz,et al.  Generational Feature Elimination and Some Other Ranking Feature Selection Methods , 2018, Advances in Feature Selection for Data and Pattern Recognition.

[9]  S. H. Richter,et al.  The neuroscience of positive emotions and affect: Implications for cultivating happiness and wellbeing , 2020, Neuroscience & Biobehavioral Reviews.

[10]  Pasin Israsena,et al.  EEG-Based Emotion Recognition Using Deep Learning Network with Principal Component Based Covariate Shift Adaptation , 2014, TheScientificWorldJournal.

[11]  F. Bryant,et al.  Regulating positive emotions: Implications for promoting well-being in individuals with depression. , 2020, Emotion.

[12]  Thierry Pun,et al.  DEAP: A Database for Emotion Analysis ;Using Physiological Signals , 2012, IEEE Transactions on Affective Computing.

[13]  Bao-Liang Lu,et al.  Investigating Critical Frequency Bands and Channels for EEG-Based Emotion Recognition with Deep Neural Networks , 2015, IEEE Transactions on Autonomous Mental Development.

[14]  Agnieszka Wosiak,et al.  Hybrid Method of Automated EEG Signals’ Selection Using Reversed Correlation Algorithm for Improved Classification of Emotions † , 2020, Sensors.

[15]  Luwei Xiao,et al.  Electroencephalogram Access for Emotion Recognition Based on a Deep Hybrid Network , 2020, Frontiers in Human Neuroscience.

[16]  D. Holec,et al.  Ab initio inspired design of ternary boride thin films , 2018, Scientific Reports.

[17]  Yufei Huang,et al.  A hierarchical LSTM model with attention for modeling EEG non-stationarity for human decision prediction , 2018, 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI).

[18]  Sebastian Stober,et al.  Deep Feature Learning for EEG Recordings , 2015, ArXiv.

[19]  Mufti Mahmud,et al.  Deep Learning in Mining Biological Data , 2020, Cognitive Computation.

[20]  Jassim M. Abdul-Jabbar,et al.  Deep learning for motor imagery EEG-based classification: A review , 2021, Biomed. Signal Process. Control..

[21]  Paja Wiesław,et al.  A Constructive Induction of Feature using Random Forest Approach. , 2020 .

[22]  Su Yang,et al.  EEG-Based Emotion Classification Using a Deep Neural Network and Sparse Autoencoder , 2020, Frontiers in Systems Neuroscience.

[23]  Liang Dong,et al.  Emotion Recognition from Multiband EEG Signals Using CapsNet , 2019, Sensors.

[24]  Zhang Weidong,et al.  Deep learning EEG response representation for brain computer interface , 2015, 2015 34th Chinese Control Conference (CCC).

[25]  Tiago H. Falk,et al.  Deep learning-based electroencephalography analysis: a systematic review , 2019, Journal of neural engineering.