Hand hygiene is essential for food safety and food handlers. Maintaining proper hand hygiene can improve food safety and promote public welfare. However, traditional methods of evaluating hygiene during food handling process, such as visual auditing by human experts, can be costly and inefficient compared to a computer vision system. Because of the varying conditions and locations of real-world food processing sites, computer vision systems for recognizing handwashing actions can be susceptible to changes in lighting and environments. Therefore, we design a robust and generalizable video system that is based on ResNet50 that includes a hand extraction method and a 2-stream network for classifying handwashing actions. More specifically, our hand extraction method eliminates the background and helps the classifier focus on hand regions under changing lighting conditions and environments. Our results demonstrate our system with the hand extraction method can improve action recognition accuracy and be more generalizable when evaluated on completely unseen data by achieving over 20% improvement on the overall classification accuracy.
Infectious diseases and environmental pollution caused by toxic chemical agents such as heavy metals are significant concerns in the global world. For example, Mercury (Hg) and Arsenic (As) have been recognized as chemical threats for human health. It is difficult to achieve multiple detections of different types of targets in lateral flow strips because of the multiple reagent requirements, while microfluidic paper-based analytical devices (μ-PADS) can provide independent channels and testing areas for colorimetric analysis. Herein, our group develops a low-cost, multiplexing, instrument-free, and simple paper-based fluidics biosensor to quantitatively determine Hg and As amounts in a linear range of 0 ppm - 30 ppm with a detection limit of 1 ppm and 2 ppm, respectively. We will present an overview of the results obtained with our fabrication process, the design of the preliminary pattern and image analysis of the responses in the test area, and the specificity test and stability test results.