Scholarlink

<p>When humans are exposed to external stimuli, they exhibit a stress response. This response can be categorized into three types based on coping mechanisms: active coping styles, passive coping styles, and no coping. These coping styles can be differentiated by characteristic variation patterns in hemodynamic indices, such as mean blood pressure (MBP), cardiac output (CO), and total peripheral resistance (TPR). Current hemodynamic measurement methods are contact-based and time-consuming, highlighting the need for a non-contact technique to quickly assess stress-coping styles. In this study, we focused on facial blood flow information captured in the near-infrared spectrum and aimed to estimate stress coping styles by applying dimensionality reduction and sparse modeling to near-infrared facial image (NIFI). As an initial step, dimensionality reduction was applied to NIFI to visualize divergence according to stress-coping styles in a two-dimensional space. Subsequently, k-nearest neighbor (k-NN) labeling and sparse modeling were employed to classify stress-coping styles. The proposed model achieved a classification accuracy of 70.5<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\%\)</EquationSource> <EquationSource Format="MATHML"><math> <mo>%</mo> </math></EquationSource> </InlineEquation>. However, in some cases, insufficient separation between coping styles in the two-dimensional space contributed to limited generalization performance. Future work will focus on improving generalization by refining the dimensionality reduction and evaluation methods, and by addressing physiological delays inherent in blood flow responses. This study employs NIFI, which is distinct from Near-Infrared Spectroscopy (NIRS). NIFI assesses autonomic responses through facial skin blood flow and is not intended as a measure of brain activity.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Estimation of stress-responsive hemodynamics from near-infrared facial image using t-SNE

  • 期刊论文

  • 发表日期：

    2025年10月20日

查看全文
  • Shonosuke Ohyama,
  • Kent Nagumo,
  • Akio Nozawa

摘要

When humans are exposed to external stimuli, they exhibit a stress response. This response can be categorized into three types based on coping mechanisms: active coping styles, passive coping styles, and no coping. These coping styles can be differentiated by characteristic variation patterns in hemodynamic indices, such as mean blood pressure (MBP), cardiac output (CO), and total peripheral resistance (TPR). Current hemodynamic measurement methods are contact-based and time-consuming, highlighting the need for a non-contact technique to quickly assess stress-coping styles. In this study, we focused on facial blood flow information captured in the near-infrared spectrum and aimed to estimate stress coping styles by applying dimensionality reduction and sparse modeling to near-infrared facial image (NIFI). As an initial step, dimensionality reduction was applied to NIFI to visualize divergence according to stress-coping styles in a two-dimensional space. Subsequently, k-nearest neighbor (k-NN) labeling and sparse modeling were employed to classify stress-coping styles. The proposed model achieved a classification accuracy of 70.5 \(\%\) % . However, in some cases, insufficient separation between coping styles in the two-dimensional space contributed to limited generalization performance. Future work will focus on improving generalization by refining the dimensionality reduction and evaluation methods, and by addressing physiological delays inherent in blood flow responses. This study employs NIFI, which is distinct from Near-Infrared Spectroscopy (NIRS). NIFI assesses autonomic responses through facial skin blood flow and is not intended as a measure of brain activity.