Respiro Dynamics: A Multifaceted Dataset for Enhanced Lung Health Assessment Using Deep Learning.

Our paper presents RespiroDynamics: A Comprehensive Multimodal Respiratory Dataset, compiled from 60 participants, recorded in two sessions labelled ’rest’ and ’exercise’. This dataset incorporates a variety of data types, including Red-Green-Blue (RGB) and Thermal videos, Heart Rate (HR), ECG readings and metadata, all synchronized with observed respiratory activities. Additionally, these data are enriched with reference values from the NHANES III (Hankinson- 1999) distribution. To construct a comprehensive and representative dataset, we engaged 60 males due to cultural factors that prevented us from collecting from females, volunteers from the Egyptian population belonging predominantly to the Caucasian race. The volunteers had high diversity in terms of age, weight, height, lifestyle, and other characteristics, thereby contributing to a well-rounded and varied sample for our research

本研究论文提出了一种名为RespiroDynamics的全面多模态呼吸数据集，该数据集由60名参与者提供，分别在标记为‘休息’和‘运动’的两个时段内进行记录。本数据集融合了多种数据类型，包括红绿蓝（RGB）和热成像视频、心率（HR）、心电图（ECG）读数以及元数据，所有这些数据均与观察到的呼吸活动同步。此外，这些数据还融入了来自美国国家健康与营养检查调查III期（Hankinson-1999）分布的参考值。为了构建一个全面且具有代表性的数据集，鉴于文化因素使我们无法从女性群体中收集数据，我们邀请了60名主要属于白种人的埃及志愿者。这些志愿者在年龄、体重、身高、生活方式及其他特征方面具有高度多样性，从而为我们的研究提供了全面且多样化的样本。