SBIR Phase II: Development of An Accurate Low-Cost Wearable Ultraviolet Dosimeter For The General Population

这项小企业创新研究（SBIR）二期项目的更广泛影响是提供一种促进健康阳光行为的新工具，在过去60年里，黑色素瘤发病率稳步上升，这是美国的一个主要公共卫生问题。这项技术已经用于各种人群（儿童、成人、黑色素瘤幸存者、狼疮患者）的阳光行为临床研究，可以显着改善疾病患者的生活质量，这些疾病需要特别敏感的紫外线探测器来防止暴露在潜在的致癌水平的阳光下。这个拟议中的项目将通过一种可以集成到个人电子可穿戴设备中的设备，对更广泛的健康产生积极影响。建议项目将支持低成本紫外线测量的先进发展。太阳光是一种复杂的电磁源，产生的光谱随着太阳的位置、地球上的位置、从地面到平流层的天气条件以及局部阴影而发生强烈变化。以前的探测器是基于简单的线性、单波长校准，不适合具有不同光谱形状的信号。拟议的项目将扩展新系统的开发，其检测限为0.005紫外线指数（紫外线指数，与健康有关的强度量度），而实际情况为0.1紫外线指数；这通过集成机器学习扩展了传统的检测限制。第二阶段的研究目标是设计一个原型系统，减小封装尺寸，扩展机器学习能力，并在现实环境中优化系统性能。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact of this Small Business Innovation Research (SBIR) Phase II project is to provide a new tool promoting healthy sun behavior, a major public health issue in the US as melanoma incidences have increased steadily over the past 60 years. This technology is already used in clinical studies on sun behavior across a variety of populations (children, adults, melanoma survivors, people suffering from lupus) and can significantly improve the quality of life for patients with disorders requiring particularly sensitive UV detectors to prevent exposure to potentially carcinogenic levels of sun. This proposed project will positively impact broader health with a device that can be incorporated in personal electronic wearable devices. The proposed project will support the advanced development of low-cost UV measurement. Sunlight is a complex electromagnetic source generating spectra that vary strongly with the position of the sun, location on earth, weather conditions from the ground to the stratosphere, and local shadows. Previous detectors were based on simple linear, single wavelength calibrations inappropriate for a signal with a varying spectral shape. The proposed project will extend the development of a new system with a detection limit of 0.005 UVI (UV Index, the health-relevant measure of intensity), compared with the state of practice of 0.1 UVI; this extends traditional detection limits by integrating machine learning. The Phase II research objectives are to engineer a prototype system, reduce the package size, extend the machine learning capabilities, and optimize system performance in real-world environments.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.