Phosgene is a highly toxic gas that is widely used in various industries, making its rapid detection essential for safety. To address this need, we developed a smartphone-based technique using convolutional neural networks (CNNs) for real-time, portable phosgene detection. Unlike traditional fluorescence spectroscopy, which requires specialized equipment and expertise, this CNN-based approach is accessible and affordable and offers quick analysis, making it ideal for on-the-spot detection. We employed this method to identify phosgene toxicity in solutions ranging from 0 to 10 ppm by analyzing images of the solutions. Specifically, we used intramolecular charge transfer (ICT)-based TPAOD and SAHY probes to detect phosgene through turn-off and turn-on fluorescence, with detection limits of 19.44 nM (0.00759 ppm) and 34.89 nM (0.00817 ppm), respectively. A lifetime study of TPAOD confirmed that the quenching mechanism operates through static quenching. The SAHY probe was utilized for the CNN model and was also tested for cell imaging studies in HeLa cells.

中文翻译：

---

下一代光气检测：使用三苯胺和 N-水杨醛探针的卷积神经网络，用于增强灵敏度和生物成像


光气是一种剧毒气体，广泛用于各个行业，因此其快速检测对于安全至关重要。为了满足这一需求，我们开发了一种基于智能手机的技术，使用卷积神经网络 （CNN） 进行实时、便携式光气检测。与需要专业设备和专业知识的传统荧光光谱法不同，这种基于 CNN 的方法易于使用且经济实惠，并提供快速分析，使其成为现场检测的理想选择。我们采用这种方法通过分析溶液图像来识别 0 至 10 ppm 溶液中的光气毒性。具体来说，我们使用基于分子内电荷转移 （ICT） 的 TPAOD 和 SAHY 探针通过关断和开启荧光检测光气，检测限分别为 19.44 nM （0.00759 ppm） 和 34.89 nM （0.00817 ppm）。TPAOD 的寿命研究证实，淬火机制通过静态淬火运行。SAHY 探针用于 CNN 模型，还用于 HeLa 细胞的细胞成像研究。