Using convolutional neural networks to decode EEG-based functional brain network with different severity of acrophobia

Abstract

Objective. The prevalence of acrophobia is high, especially with the rise of many high-rise buildings. In the recent few years, researchers have begun to analyze acrophobia from the neuroscience perspective, especially to improve the virtual reality exposure therapy (VRET). Electroencephalographic (EEG) is an informative neuroimaging technique, but it is rarely used for acrophobia. The purpose of this study is to evaluate the effectiveness of using EEGs to identify the degree of acrophobia objectively. Approach. EEG data were collected by virtual reality (VR) exposure experiments. We classified all subjects’ degrees of acrophobia into three categories, where their questionnaire scores and behavior data showed significant differences. Using synchronization likelihood, we computed the functional connectivity between each pair of channels and then obtained complex networks named functional brain networks (FBNs). Basic topological features and community structure features were extracted from the FBNs. Statistical results demonstrated that FBN features can be used to distinguish different groups of subjects. We trained machine learning (ML) algorithms with FBN features as inputs and trained convolutional neural networks (CNNs) with FBNs directly as inputs. Main results. It turns out that using FBN to identify the severity of acrophobia is feasible. For ML algorithms, the community structure features of some cerebral cortex regions outperform typical topological features of the whole brain, in terms of classification accuracy. The performances of CNN algorithms are better than ML algorithms. The CNN with ResNet performs the best (accuracy reached 98.46 ± 0.42%). Significance. These observations indicate that community structures of certain cerebral cortex regions could be used to identify the degree of acrophobia. The proposed CNN framework can provide objective feedback, which could help build closed-loop VRET portable systems.

Electroencephalography correlates of fear of heights in a virtual reality environment

“…In [27], the authors aimed to distinguish three groups of subjects affected by different severity of acrophobia by means of the EEG signal. The psychometric tools employed were the Acrophobia Questionnaire (AQ) and the Subjective Unit of Distress (SUD) scores.…”

Multi-Input CNN-LSTM deep learning model for fear level classification based on EEG and peripheral physiological signals

“…Validated by 31-fold cross-validation, the result was an accuracy of 88.77%. Wang et al (2020) used the EEG-based Functional Brain Networks, a complex network based on EEGs, to identify the severity of acrophobia. EEGs were collected from 76 subjects walking on a board hanging from a tree in a virtual environment.…”

“…Therefore, EEG-based emotion classification is required not to blink or move to avoid artifact generation or to detect and remove artifacts. Bălan et al (2020) removed the artifact in real-time by replacing it with the average value of the data recorded during the previous 5 s when detecting a value negative or exceeding one and one-half than the average value for 5 s. Wang et al (2020) recorded electrooculograms to remove eye artifacts. Ghosh et al (2023) proposed a method that can automatically detect and remove artifacts using KNN and LSTM.…”

MuscleNET: mapping electromyography to kinematic and dynamic biomechanical variables by machine learning

“…On the other hand, the deep-learning solution uses a hierarchy representation, which learns complex features by configuring and extracting stacks of features [25]. Deep learning architectures, like recurrent neural networks (RNNs), convolutional neural networks (CNNs), and recurrent CNNs (RCNNs), are primarily used in image analysis or processing [26], speech recognition [27], and recently, bioinformatics [28].…”