A Novel Recurrent Neural Network to Classify EEG Signals for Customers' Decision-Making Behavior Prediction in Brand Extension Scenario

Multi-modal EEG NEO-FFI with Trained Attention Layer (MENTAL) for mental disorder prediction

Early detection and accurate diagnosis of mental disorders is difficult due to the complexity of the diagnostic process, resulting in conditions being left undiagnosed or misdiagnosed. Previous studies have demonstrated that features of Electroencephalogram (EEG) data, such as Power Spectral Density (PSD), are useful biomarkers for indicating the onset of various mental disorders. Existing models using EEG data are typically trained to distinguish between healthy and afflicted individuals, and they are unable to distinguish between individuals with different disorders. We propose MENTAL (Multi-modal EEG NEO-FFI with Trained Attention Layer) to predict an individual's mental state using both EEG and Neo-Five Factor Inventory (NEO-FFI) personality data. We include an attention layer that captures the interactions between personality traits and PSD features, and emphasizes the important PSD features. MENTAL features a Recurrent Neural Network (RNN) to model the temporal nature of EEG data. We train our model with the Two Decades Brainclinics Research Archive for Insights in Neuroscience (TDBRAIN) dataset, which consists of 1274 healthy and psychiatric individuals including over 30 different diagnoses. MENTAL is able to achieve 93.3% accuracy when trained to classify between healthy individuals and those with ADHD. When trained to identify individuals with ADHD from among 33 disorder classes, MENTAL improves accuracy from 70.5 to 81.7%. MENTAL also demonstrates over 20% improvement in predictive accuracy when trained for MDD prediction. For the multi-class classification task of three classes, MENTAL improves accuracy by 4%, and for five classes, by nearly 8%. MENTAL is the first multi-modal model that utilizes both EEG and NEO-FFI data for the task of mental disorder prediction. We are one of the first groups to utilize TDBRAIN for automated disorder classification. MENTAL is accessible and cost-effective, as EEG is more affordable than other neuroimaging methods such as MRI, and the NEO-FFI is a self- reported survey. Our model can lead to acceptance and support for individuals living with mental health challenges and improve quality of life in our society.

Exploring Convolutional Neural Network Architectures for EEG Feature Extraction

The main purpose of this paper is to provide information on how to create a convolutional neural network (CNN) for extracting features from EEG signals. Our task was to understand the primary aspects of creating and fine-tuning CNNs for various application scenarios. We considered the characteristics of EEG signals, coupled with an exploration of various signal processing and data preparation techniques. These techniques include noise reduction, filtering, encoding, decoding, and dimension reduction, among others. In addition, we conduct an in-depth analysis of well-known CNN architectures, categorizing them into four distinct groups: standard implementation, recurrent convolutional, decoder architecture, and combined architecture. This paper further offers a comprehensive evaluation of these architectures, covering accuracy metrics, hyperparameters, and an appendix that contains a table outlining the parameters of commonly used CNN architectures for feature extraction from EEG signals.

Get a New Perspective on EEG: Convolutional Neural Network Encoders for Parametric t-SNE

t-distributed stochastic neighbor embedding (t-SNE) is a method for reducing high-dimensional data to a low-dimensional representation, and is mostly used for visualizing data. In parametric t-SNE, a neural network learns to reproduce this mapping. When used for EEG analysis, the data are usually first transformed into a set of features, but it is not known which features are optimal. The principle of t-SNE was used to train convolutional neural network (CNN) encoders to learn to produce both a high- and a low-dimensional representation, eliminating the need for feature engineering. To evaluate the method, the Temple University EEG Corpus was used to create three datasets with distinct EEG characters: (1) wakefulness and sleep; (2) interictal epileptiform discharges; and (3) seizure activity. The CNN encoders produced low-dimensional representations of the datasets with a structure that conformed well to the EEG characters and generalized to new data. Compared to parametric t-SNE for either a short-time Fourier transform or wavelet representation of the datasets, the developed CNN encoders performed equally well in separating categories, as assessed by support vector machines. The CNN encoders generally produced a higher degree of clustering, both visually and in the number of clusters detected by k-means clustering. The developed principle is promising and could be further developed to create general tools for exploring relations in EEG data.

A systematic review of the prediction of consumer preference using EEG measures and machine-learning in neuromarketing research

Introduction

The present paper discusses the findings of a systematic review of EEG measures in neuromarketing, identifying which EEG measures are the most robust predictor of customer preference in neuromarketing. The review investigated which TF effect (e.g., theta-band power), and ERP component (e.g., N400) was most consistently reflective of self-reported preference. Machine-learning prediction also investigated, along with the use of EEG when combined with physiological measures such as eye-tracking.

Methods

Search terms ‘neuromarketing’ and ‘consumer neuroscience’ identified papers that used EEG measures. Publications were excluded if they were primarily written in a language other than English or were not published as journal articles (e.g., book chapters). 174 papers were included in the present review.

Results

Frontal alpha asymmetry (FAA) was the most reliable TF signal of preference and was able to differentiate positive from negative consumer responses. Similarly, the late positive potential (LPP) was the most reliable ERP component, reflecting conscious emotional evaluation of products and advertising. However, there was limited consistency across papers, with each measure showing mixed results when related to preference and purchase behaviour.

Conclusions and implications

FAA and the LPP were the most consistent markers of emotional responses to marketing stimuli, consumer preference and purchase intention. Predictive accuracy of FAA and the LPP was greatly improved through the use of machine-learning prediction, especially when combined with eye-tracking or facial expression analyses.

Black hole algorithm with convolutional neural networks for the creation of brain-computer interface based in visual perception and visual imagery

Non-invasive brain-computer interfaces can be implemented through different paradigms, the most used one being motor imagery and evoked potentials, although recently there has been an interest in paradigms based on perception and visual imagery. Following this approach, this work demonstrates the classification of visual imagery, visual perception and also the possibility of knowledge transfer between these two domains from EEG signals using convolutional neural networks. Also, we propose an adequate framework for such classification, which uses convolutional neural networks and the black hole heuristic algorithm for the search for optimal neural network structures.

Is Distant Extension Always Upset? Neural Evidence of Empathy and Brand Association Affect Distant Extension Evaluation

Distant brand extension as an essential strategy of obtaining benefits was highly focused on the normal marketing practice and academic research. In the current study, we aim to recognize that how individuals with different levels of empathy respond to distant extensions under corporate social responsibility (CSR) and corporate competence (CC) associations to explore the corresponding neural mechanisms using event-related potentials (ERPs). We divided subjects into two groups involving a high empathy (HE) group and a low empathy (LE) group according to an empathy measure questionnaire. The subjects first faced a brand name following the CSR or CC association descriptions, and then, they were asked to evaluate the new product of brand by a five-point scale. Current results revealed that the participants of the HE group were more apt to accept the distant extension products than those of the LE group. Additionally, in the HE group, products from a brand with CSR associations were more acceptable than CC associations. Moreover, a larger N2 amplitude was elicited in the LE group than in the HE group. For the LE group, an augment N2 was found under CSR than CC associations, reflecting that LE consumers might perceive conflict when evaluating distant extensions and allocate more cognitive resources to deal with CSR information. At the later stage, the HE group showed a greater P3 than the LE group. For the HE group, an increased P3 was elicited under CSR than CC associations, suggesting that empathic individuals might show motivational salience and helping willingness toward distant extension products, especially under the CSR scenario. These results provide potential electrophysiological evidence for the positive impact of brand associations on the evaluation of distant brand extension in the case of subdividing different empathic individuals.

Functional Brain Network Analysis of Knowledge Transfer While Engineering Problem-Solving

As a complex cognitive activity, knowledge transfer is mostly correlated to cognitive processes such as working memory, behavior control, and decision-making in the human brain while engineering problem-solving. It is crucial to explain how the alteration of the functional brain network occurs and how to express it, which causes the alteration of the cognitive structure of knowledge transfer. However, the neurophysiological mechanisms of knowledge transfer are rarely considered in existing studies. Thus, this study proposed functional connectivity (FC) to describe and evaluate the dynamic brain network of knowledge transfer while engineering problem-solving. In this study, we adopted the modified Wisconsin Card-Sorting Test (M-WCST) reported in the literature. The neural activation of the prefrontal cortex was continuously recorded for 31 participants using functional near-infrared spectroscopy (fNIRS). Concretely, we discussed the prior cognitive level, knowledge transfer distance, and transfer performance impacting the wavelet amplitude and wavelet phase coherence. The paired t-test results showed that the prior cognitive level and transfer distance significantly impact FC. The Pearson correlation coefficient showed that both wavelet amplitude and phase coherence are significantly correlated to the cognitive function of the prefrontal cortex. Therefore, brain FC is an available method to evaluate cognitive structure alteration in knowledge transfer. We also discussed why the dorsolateral prefrontal cortex (DLPFC) and occipital face area (OFA) distinguish themselves from the other brain areas in the M-WCST experiment. As an exploratory study in NeuroManagement, these findings may provide neurophysiological evidence about the functional brain network of knowledge transfer while engineering problem-solving.