Instance-Adaptive Graph for EEG Emotion Recognition

Song, Tengfei; Liu, Suyuan; Zheng, Wenming; Zong, Yuan; Cui, Zhen

doi:10.1609/aaai.v34i03.5656

Cited by 41 publications

(30 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The financial prices are shaped in logarithmic yields; these yields are transformed into discrete scales contained in a range of 1 to 7. There is strong evidence in using this scale in different fields (Li et al, 2020;Song et al, 2020;Kupekar, 2020;Bribiesca, Marine, and Martinez, 2020); thereby, this discretization 2 is carried out to try to assimilate a Likert scale; this scale is homogenous for all series; thus, asymmetries are turned to offer logical relationships. Logarithmic yields were softened employing a Fisher test to avoid data concentration on extreme values.…”

Section: Methodsmentioning

confidence: 99%

Behavioral Approach on the Mexican Stock Market Modeled Through Plssem

Marine¹,

Bribiesca²,

Arrona-Palacios³

2021

International Conference on Education

View full text Add to dashboard Cite

This paper analyzes the Mexican Stock Market indicators and their relationships to study the ten most representative stocks in The Mexican Stock Market Index between 2011 to 2020, reflecting behavioral effects using the Mexican Volatility Index. A longitudinal research design of 119 observations sample size is modeled monthly; this sample was transformed into categorical variables to reflect emotional stages. The main objective was to analyze the stock market emotions applying a novel approach to create latent behavioral variables using current Mexican behavioral indicators as reflexive constructs. There is a lack of knowledge in using different techniques to model financial behavior in financial and economic modeling. The typical techniques employed to model market time series have been simple and multiple regression, broadly used in this science. Since behavioral science appliances, there is a need for evolution to modeling the complex nature of behavior. Partial Least Squares and Structural Equation Models (PLS-SEM) can manage different scales, complex relations, reflexive or formative models, non-normal data, and small samples. Possible because of the lack of knowledge al flexibility of PLSSEM models, there is an evident lack in the use of this methodology in modern research and financial teaching, so a new methodology for modeling financial data is exposed that can resolve problems in financial researching and teaching. It is relevant to show a way of modeling emotional financial markets; it is recommended the use of this modeling in different kind of data, different countries, characteristics, sectors, industries, or variables, or any possible application in different sciences with the same problems of assumptions like in economics sciences. Keywords: Investor behavior, risk, market efficiency, Structural Equations, and Partial Least Squares methods

show abstract

Section: Methodsmentioning

confidence: 99%

Behavioral Approach on the Mexican Stock Market Modeled Through Plssem

Marine¹,

Bribiesca²,

Arrona-Palacios³

2021

International Conference on Education

View full text Add to dashboard Cite

show abstract

“…Li et al (2020) integrated psychoacoustic knowledge and raw waveform embedding within an augmented feature space. Song et al (2020) employed an additional branch to characterize the intrinsic dynamic relationships between different EEG channels and a type of sparse graphic representation was presented to extract more discriminative features. Besides the feature extraction methods, more attention is paid to study the emotion classification.…”

Section: Related Workmentioning

confidence: 99%

Singular Learning of Deep Multilayer Perceptrons for EEG-Based Emotion Recognition

Guo

et al. 2021

Front. Comput. Sci.

View full text Add to dashboard Cite

Human emotion recognition is an important issue in human–computer interactions, and electroencephalograph (EEG) has been widely applied to emotion recognition due to its high reliability. In recent years, methods based on deep learning technology have reached the state-of-the-art performance in EEG-based emotion recognition. However, there exist singularities in the parameter space of deep neural networks, which may dramatically slow down the training process. It is very worthy to investigate the specific influence of singularities when applying deep neural networks to EEG-based emotion recognition. In this paper, we mainly focus on this problem, and analyze the singular learning dynamics of deep multilayer perceptrons theoretically and numerically. The results can help us to design better algorithms to overcome the serious influence of singularities in deep neural networks for EEG-based emotion recognition.

show abstract

“…The first type of modality includes those approaches based on facial expression [5,6], speech emotion recognition [7] and body language. Unlike this type of modality, the physiological signals provide a reliable way to recognize emotions since these signals are produced by the human body that may not be susceptible to subjective approaches based on behavioral signals [8]. In this sense, Electrocardiogram (ECG) [9], Electromyography (EMG) [10], Electroencephalogram (EEG) [4] or even a combination of them [11,12], have been used for emotion recognition.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, EEG is a non-invasive device, easy to use, and has a low cost [4,13]. Thus, EEG has been widely used in emotion recognition systems in the last years [3,8,[13][14][15][16][17][18].…”

Section: Introductionmentioning

confidence: 99%

“…In this direction, many methods have been proposed via machine learning to leverage the features extracted from EEG signals [17][18][19]. Recently, several methods are gradually moving towards the deep learning-based approaches, becoming dominant in EEG-based emotion recognition [3,8,[13][14][15][16]20,21]. For example, different deep learning methods have been proposed to consider the spatial information, such as convolutional neural networks (CNNs) [3,14,16], capsule networks (CapsNets) [21] and graph neural networks (GNN) [8,13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Class-Incremental Learning Method Based on Preserving the Learned Feature Space for EEG-Based Emotion Recognition

Jiménez-Guarneros

Alejo

2022

Mathematics

View full text Add to dashboard Cite

Deep learning-based models have shown to be one of the main active research topics in emotion recognition systems from Electroencephalogram (EEG) signals. However, a significant challenge is to effectively recognize new emotions that are incorporated sequentially, as current models must perform retraining from scratch. In this paper, we propose a Class-Incremental Learning (CIL) method, named Incremental Learning preserving the Learned Feature Space (IL2FS), in order to enable deep learning models to incorporate new emotions (classes) into the already known. IL2FS performs a weight aligning to correct the bias on new classes, while it incorporates margin ranking loss and triplet loss to preserve the inter-class separation and feature space alignment on known classes. We evaluated IL2FS over two public datasets (DREAMER and DEAP) for emotion recognition and compared it with other recent and popular CIL methods reported in computer vision. Experimental results show that IL2FS outperforms other CIL methods by obtaining an average accuracy of 59.08 ± 08.26% and 79.36 ± 04.68% on DREAMER and DEAP, recognizing data from new emotions that are incorporated sequentially.

show abstract

Instance-Adaptive Graph for EEG Emotion Recognition

Cited by 41 publications

References 17 publications

Behavioral Approach on the Mexican Stock Market Modeled Through Plssem

Behavioral Approach on the Mexican Stock Market Modeled Through Plssem

Singular Learning of Deep Multilayer Perceptrons for EEG-Based Emotion Recognition

A Class-Incremental Learning Method Based on Preserving the Learned Feature Space for EEG-Based Emotion Recognition

Contact Info

Product

Resources

About