Laser-induced fluorescence (LIF) is a well-established technique for monitoring chemical processes and for the standoff detection of biological substances because of its simple technical implementation and high sensitivity. Frequently, standoff LIF spectra from large molecules and bio-agents are only slightly structured and a gain of deeper information, such as classification, let alone identification, might become challenging. Improving the LIF technology by recording spectral and additionally time-resolved fluorescence emission, a significant gain of information can be achieved. This work presents results from a LIF based detection system and an analysis of the influence of time-resolved data on the classification accuracy. A multi-wavelength sub-nanosecond laser source is used to acquire spectral and time-resolved data from a standoff distance of 3.5 m. The data set contains data from seven different bacterial species and six types of oil. Classification is performed with a decision tree algorithm separately for spectral data, time-resolved data and the combination of both. The first findings show a valuable contribution of time-resolved fluorescence data to the classification of the investigated chemical and biological agents to their species level. Temporal and spectral data have been proven as partly complementary. The classification accuracy is increased from 86% for spectral data only to more than 92%.

中文翻译：

---

基于多光谱LIF的对峙检测系统，用于通过光谱和时间特征对CBE危险进行分类。

激光诱导荧光（LIF）是一种行之有效的技术，可用于监控化学过程和生物物质的隔离检测，因为它的技术实施简单且灵敏度高。通常，来自大分子和生物制剂的对立LIF光谱仅是略微结构化的，获得更深层次的信息（例如分类，更不用说识别）可能会变得充满挑战。通过记录光谱和时间分辨的荧光发射来改进LIF技术，可以实现显着的信息增益。这项工作介绍了基于LIF的检测系统的结果，以及对时间分辨数据对分类准确性的影响的分析。多波长亚纳秒激光源用于从3.5 m的隔离距离获取光谱和时间分辨数据。数据集包含来自七个不同细菌物种和六种类型的油的数据。使用决策树算法分别对光谱数据，时间分辨数据以及两者的组合进行分类。最初的发现表明，时间分辨的荧光数据对所研究的化学和生物制剂的物种水平分类具有重要的贡献。时间和频谱数据已被证明是部分互补的。分类准确性从光谱数据的86％提高到了92％以上。使用决策树算法分别对光谱数据，时间分辨数据以及两者的组合进行分类。最初的发现表明，时间分辨的荧光数据对所研究的化学和生物制剂按其物种水平的分类做出了宝贵的贡献。时间和频谱数据已被证明是部分互补的。分类准确性从光谱数据的86％提高到了92％以上。使用决策树算法分别对光谱数据，时间分辨数据以及两者的组合进行分类。最初的发现表明，时间分辨的荧光数据对所研究的化学和生物制剂的物种水平分类具有重要的贡献。时间和频谱数据已被证明是部分互补的。分类准确性从光谱数据的86％提高到了92％以上。