Online Classifier of AMICA Model to Evaluate State Anxiety While Standing in Virtual Reality

G Liao, S Wang, Z Wei, 刘博涵 (Bohan Liu), R Okubo, ME Hernandez

IEEE EMBC 2022 PubMed ↗ Scholar ↗

摘要

此摘要由英文原文自动翻译。

焦虑等情绪状态的变化对行为与心理健康有重大影响。然而,检测个体的焦虑需要受过训练的专家施行专业评估,往往耗费大量时间与资源。因此,临床实践亟需客观且实时的焦虑检测方法。Adaptive Mixture Independent Component Analysis(AMICA)的最新进展已展现利用脑电(EEG)数据检测情绪状态变化的能力。然而,由于识别不同模型可能需耗时数小时,未来的脑机接口应用必须寻求替代方法。本研究探讨机器学习分类器的可行性:利用脑电数据的频域特征,将500毫秒的脑电样本分类至多模型AMICA标签所确立的不同皮层状态。使用12个脑电输入特征预测皮层状态的随机森林分类器,在二分类中达到75%的准确率。基于这些发现,本研究可为实时焦虑状态检测与分类奠定基础。

原始摘要(英文)

Changes in emotional state, such as anxiety, have a significant impact on behavior and mental health. However, the detection of anxiety in individuals requires trained specialists to administer specialized assessments, which often take a significant amount of time and resources. Thus, there is a significant need for objective and real-time anxiety detection methods to aid clinical practice. Recent advances in Adaptive Mixture Independent Component Analysis (AMICA) have demonstrated the ability to detect changes in emotional states using electroencephalographic (EEG) data. However, given that several hours may be needed to identify the different models, alternative methods must be sought for future brain-computer-interface applications. This study examines the feasibility of a machine learning classifier using frequency domain features of EEG data to classify individual 500 ms samples of EEG data into different cortical states, as established by multi-model AMICA labels. Using a random forest classifier with 12 input features from EEG data to predict cortical states yielded a 75 percent accuracy in binary classification. Based on these findings, this work may provide a foundation for real-time anxiety state detection and classification.

本文贡献

基于AMICA脑电特征的在线分类器,可在人于虚拟现实中站立时检测状态焦虑——可应用于跌倒预防与VR治疗的实时监测。

BibTeX

@inproceedings{liao2022amica,
  title     = {Online Classifier of AMICA Model to Evaluate State Anxiety While Standing in Virtual Reality},
  author    = {G Liao and S Wang and Z Wei and Bohan Liu and R Okubo and ME Hernandez},
  booktitle = {IEEE Engineering in Medicine and Biology Conference (EMBC)},
  year      = {2022}
}