Improvements in small sized sensors allow the easy detection of the presence of Volatile Organic Compounds (VOCs) in the air using easy-to-deploy Internet of Things (IoT) devices. However, classifying what VOC exists in the environment still remains as a complex task. Knowing what VOCs are in the air can help us remove the main cause that vents VOC materials as a way to maintain clean air quality. In this work, we present VOCkit, an IoT sensor kit for non-chemical experts to easily detect and classify different types of VOCs. VOCkit combines miniature chemically-designed fluorometric sensors for recognizing VOCs with an embedded imaging system for classification. Exposing the fluorometric sensors with various VOCs, result in the photophysical property change of fluorescent compounds, which composes the sensors, and the synergistic combination of the changes create unique individual fluorescent color patterns respectively to the VOC material. The fluorescent color change pattern is captured using an embedded camera and the images are processed with machine learning algorithms on the embedded platform for VOC classification. Using 500 fluorometric sensor images collected for five different commonly contactable VOCs, we show the feasibility of VOC classification on small-sized IoT devices. For the VOC types of our interest, our results show a classification accuracy of 97%, implying the potential applicability of VOCkit for real-world usage.

小型传感器的改进允许使用易于部署的物联网（IoT）设备轻松检测空气中挥发性有机化合物（VOC）的存在。但是，对环境中存在的VOC进行分类仍然是一项复杂的任务。了解空气中的挥发性有机化合物可以帮助我们消除排放挥发性有机化合物材料的主要原因，以此来保持清洁的空气质量。在这项工作中，我们介绍了VOCkit，这是一种物联网传感器套件，适用于非化学专家，可以轻松检测和分类不同类型的VOC。VOCkit结合了用于识别VOC的微型化学设计的荧光传感器和用于分类的嵌入式成像系统。用各种VOC暴露荧光传感器，会导致组成传感器的荧光化合物的光物理特性发生变化，并且这些变化的协同组合分别为VOC材料创建了独特的单个荧光颜色图案。使用嵌入式相机捕获荧光颜色变化图案，并在嵌入式平台上使用机器学习算法对图像进行处理，以进行VOC分类。使用针对五个不同的通常可接触VOC收集的500个荧光传感器图像，我们展示了在小型IoT设备上进行VOC分类的可行性。对于我们感兴趣的VOC类型，我们的结果表明分类精度为97％，用于实际用途的VOCkit。