<b>fNIRS Dataset during Hand-gripping Activity</b>

The dataset comprises <b>functional near-infrared spectroscopy (fNIRS) recordings of hand-gripping motor activity</b>. The data is provided in three forms:<b>Raw Data</b>: Unprocessed optical density values recorded using the <b>nirSpot-2</b> system.<b>Processed Data</b>: Data converted into <b>oxy-hemoglobin (HbO) and deoxy-hemoglobin (HbR) concentration changes</b> using standard preprocessing techniques.<b>Labeled Data</b>: A fully processed and labeled version of the dataset, facilitating classification tasks.Further details regarding the dataset, including acquisition methodology, preprocessing steps, and potential applications, are provided in the manuscript:Akhter, J., Naseer, N., Nazeer, H., Khan, H., &amp; Mirtaheri, P. (2024). Enhancing Classification Accuracy with Integrated Contextual Gate Network: Deep Learning Approach for Functional Near-Infrared Spectroscopy Brain–Computer Interface Application. <i>Sensors</i>, <i>24</i>(10), 3040.**本数据集包含手部抓握运动活动的功能近红外光谱（functional near-infrared spectroscopy, fNIRS）记录**。数据集提供三种形式的数据： **原始数据**：采用nirSpot-2系统采集的未处理光密度值。 **处理后数据**：通过标准预处理技术转换为氧合血红蛋白（oxy-hemoglobin, HbO）与去氧血红蛋白（deoxy-hemoglobin, HbR）浓度变化量的数据。 **标注数据**：经过完整处理并带有标注的数据集版本，可直接用于分类任务。 有关本数据集的更多细节，包括采集方法、预处理步骤及潜在应用场景，均收录于以下论文中： Akhter, J., Naseer, N., Nazeer, H., Khan, H., & Mirtaheri, P. (2024). 集成上下文门控网络提升分类精度：面向功能近红外光谱脑机接口应用的深度学习方法。 *Sensors*, 24(10), 3040.