EEG responses to emotional videos can quantitatively predict big-five personality traits

Temporal aware Mixed Attention-based Convolution and Transformer Network for cross-subject EEG emotion recognition

Emotion recognition is crucial for human-computer interaction, and electroencephalography (EEG) stands out as a valuable tool for capturing and reflecting human emotions. In this study, we propose a hierarchical hybrid model called Mixed Attention-based Convolution and Transformer Network (MACTN). This model is designed to collectively capture both local and global temporal information and is inspired by insights from neuroscientific research on the temporal dynamics of emotions. First, we introduce depth-wise temporal convolution and separable convolution to extract local temporal features. Then, a self-attention-based transformer is used to integrate the sparse global emotional features. Besides, channel attention mechanism is designed to identify the most task-relevant channels, facilitating the capture of relationships between different channels and emotional states. Extensive experiments are conducted on three public datasets under both offline and online evaluation modes. In the multi-class cross-subject online evaluation using the THU-EP dataset, MACTN demonstrates an approximate 8% enhancement in 9-class emotion recognition accuracy in comparison to state-of-the-art methods. In the multi-class cross-subject offline evaluation using the DEAP and SEED datasets, a comparable performance is achieved solely based on the raw EEG signals, without the need for prior knowledge or transfer learning during the feature extraction and learning process. Furthermore, ablation studies have shown that integrating self-attention and channel-attention mechanisms improves classification performance. This method won the Emotional BCI Competition's final championship in the World Robot Contest. The source code is available at https://github.com/ThreePoundUniverse/MACTN.

Resting-state EEG Microstate Features Can Quantitatively Predict Autistic Traits in Typically Developing Individuals

Autism spectrum disorder (ASD) is not a discrete disorder and that symptoms of ASD (i.e., so-called "autistic traits") are found to varying degrees in the general population. Typically developing individuals with sub-clinical yet high-level autistic traits have similar abnormities both in behavioral performances and cortical activation patterns to individuals diagnosed with ASD. Thus it's crucial to develop objective and efficient tools that could be used in the assessment of autistic traits. Here, we proposed a novel machine learning-based assessment of the autistic traits using EEG microstate features derived from a brief resting-state EEG recording. The results showed that: (1) through the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm and correlation analysis, the mean duration of microstate class D, the occurrence rate of microstate class A, the time coverage of microstate class D and the transition rate from microstate class B to D were selected to be crucial microstate features which could be used in autistic traits prediction; (2) in the support vector regression (SVR) model, which was constructed to predict the participants' autistic trait scores using these four microstate features, the out-of-sample predicted autistic trait scores showed a significant and good match with the self-reported scores. These results suggest that the resting-state EEG microstate analysis technique can be used to predict autistic trait to some extent.

Neurophysiological and Autonomic Correlates of Metacognitive Control of and Resistance to Distractors in Ecological Setting: A Pilot Study

In organisational contexts, professionals are required to decide dynamically and prioritise unexpected external inputs deriving from multiple sources. In the present study, we applied a multimethodological neuroscientific approach to investigate the ability to resist and control ecological distractors during decision-making and to explore whether a specific behavioural, neurophysiological (i.e., delta, theta, alpha and beta EEG band), or autonomic (i.e., heart rate-HR, and skin conductance response-SCR) pattern is correlated with specific personality profiles, collected with the 10-item Big Five Inventory. Twenty-four participants performed a novel Resistance to Ecological Distractors (RED) task aimed at exploring the ability to resist and control distractors and the level of coherence and awareness of behaviour (metacognition ability), while neurophysiological and autonomic measures were collected. The behavioural results highlighted that effectiveness in performance did not require self-control and metacognition behaviour and that being proficient in metacognition can have an impact on performance. Moreover, it was shown that the ability to resist ecological distractors is related to a specific autonomic profile (HR and SCR decrease) and that the neurophysiological and autonomic activations during task execution correlate with specific personality profiles. The agreeableness profile was negatively correlated with the EEG theta band and positively with the EEG beta band, the conscientiousness profile was negatively correlated with the EEG alpha band, and the extroversion profile was positively correlated with the EEG beta band. Taken together, these findings describe and disentangle the hidden relationship that lies beneath individuals' decision to inhibit or activate intentionally a specific behaviour, such as responding, or not, to an external stimulus, in ecological conditions.

Design and implementation of an EEG-based recognition mechanism for the openness trait of the Big Five

The differentiation between the openness and other dimensions of the Big Five personality model indicates that it is necessary to design a specific paradigm as a supplement to the Big Five recognition. The present study examined the relationship between one's openness trait of the Big Five model and the task-related power change of upper alpha band (10–12 Hz). We found that individuals from the high openness group displayed a stronger alpha synchronization over a frontal area in symbolic reasoning task, while the reverse applied in the deductive reasoning task. The results indicated that these two kinds of reasoning tasks could be used as supplement of the Big Five recognition. Besides, we divided one's openness score into three levels and proposed a hybrid-SNN (Spiking Neural Networks)-ANN (Analog Neural Networks) architecture based on EEGNet to recognize one's openness level, named Spike-EEGNet. The recognition accuracy of the two tasks was 90.6 and 92.2%. This result was highly significant for the validation of using a model with hybrid-SNN-ANN architecture for EEG-based openness trait recognition.

Deep Personality Trait Recognition: A Survey

Automatic personality trait recognition has attracted increasing interest in psychology, neuropsychology, and computer science, etc. Motivated by the great success of deep learning methods in various tasks, a variety of deep neural networks have increasingly been employed to learn high-level feature representations for automatic personality trait recognition. This paper systematically presents a comprehensive survey on existing personality trait recognition methods from a computational perspective. Initially, we provide available personality trait data sets in the literature. Then, we review the principles and recent advances of typical deep learning techniques, including deep belief networks (DBNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs). Next, we describe the details of state-of-the-art personality trait recognition methods with specific focus on hand-crafted and deep learning-based feature extraction. These methods are analyzed and summarized in both single modality and multiple modalities, such as audio, visual, text, and physiological signals. Finally, we analyze the challenges and opportunities in this field and point out its future directions.

Predictive modeling of contents of potentially toxic elements using morphometric data, proximal sensing, and chemical and physical properties of soils under mining influence

Several anthropic activities, especially mining, have contributed to the exacerbation of contents of potentially toxic elements in soils around the world. Mines can release a large amount of direct sources of contaminants into the environment, and even after the mines are no longer being exploited, the environmental liabilities generated may continue to provide contamination risks. Potentially toxic elements (PTEs), when present in the environment, can enter the food chain, promoting serious risks to human health and the ecosystem. Several methods have been used to determine the contents of PTEs in soils, but most are laborious, costly and generate waste. In this study, we use a methodological framework to optimize the prediction of levels of PTEs in soils. We used a total set of 120 soil samples, collected at a depth of 0-10 cm. The covariate database is composed of variables measured by proximal sensors, physical and chemical soil characteristics, and morphometric data derived from a DEM with a spatial resolution of 30 m. Five machine learning algorithms were tested: Random Forests, Cubist, Linear Model, Support Vector Machine and K Nearest Neighbor. In general, the Cubist algorithm produced better results in predicting the contents of Pb, Zn, Ba and Fe compared to the other tested models. For the Al contents, the Support Vector Machine produced the best prediction. For the Cr contents, all models showed low predictive power. The most important covariates in predicting the contents of PTEs varied according to the studied element. However, x-ray fluorescence measurements, textural and morphometric variables stood out for all elements. The methodology structure reported in this study represents an alternative for fast, low-cost prediction of PTEs in soils, in addition to being efficient and economical for monitoring potentially contaminated areas and obtaining quality reference values for soils.

An Empirical Comparative Study on the Two Methods of Eliciting Singers' Emotions in Singing: Self-Imagination and VR Training

Emotional singing can affect vocal performance and the audience's engagement. Chinese universities use traditional training techniques for teaching theoretical and applied knowledge. Self-imagination is the predominant training method for emotional singing. Recently, virtual reality (VR) technologies have been applied in several fields for training purposes. In this empirical comparative study, a VR training task was implemented to elicit emotions from singers and further assist them with improving their emotional singing performance. The VR training method was compared against the traditional self-imagination method. By conducting a two-stage experiment, the two methods were compared in terms of emotions' elicitation and emotional singing performance. In the first stage, electroencephalographic (EEG) data were collected from the subjects. In the second stage, self-rating reports and third-party teachers' evaluations were collected. The EEG data were analyzed by adopting the max-relevance and min-redundancy algorithm for feature selection and the support vector machine (SVM) for emotion recognition. Based on the results of EEG emotion classification and subjective scale, VR can better elicit the positive, neutral, and negative emotional states from the singers than not using this technology (i.e., self-imagination). Furthermore, due to the improvement of emotional activation, VR brings the improvement of singing performance. The VR hence appears to be an effective approach that may improve and complement the available vocal music teaching methods.