Biological hazardous substances such as certain fungi and bacteria represent a high risk for the broad public if fallen into wrong hands. Incidents based on bio-agents are commonly considered to have unpredictable and complex consequences for first responders and people. The impact of such an event can be minimized by an early and fast detection of hazards. The presented approach is based on optical standoff detection applying laser-induced fluorescence (LIF) on bacteria. The LIF bio-detector has been designed for outdoor operation at standoff distances from 20 m up to more than 100 m. The detector acquires LIF spectral data for two different excitation wavelengths (280 and 355 nm) which can be used to classify suspicious samples. A correlation analysis and spectral classification by a decision tree is used to discriminate between the measured samples. In order to demonstrate the capabilities of the system, suspensions of the low-risk and non-pathogenic bacteriaBacillus thuringiensis,Bacillus atrophaeus,Bacillus subtilis,Brevibacillus brevis,Micrococcus luteus,Oligella urethralis,Paenibacillus polymyxaandEscherichia coli(K12) have been investigated with the system, resulting in a discrimination accuracy of about 90%.
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%.
Laser-induced fluorescence (LIF) provides the ability to distinguish organic materials by a fast and distant in situ analysis. When detecting the substances directly in the environment, e.g., in an aerosol cloud or on surfaces, additional fluorescence signals of other fluorophores occurring in the surrounding are expected to mix with the desired signal. We approached this problem with a simplified experimental design for an evaluation of classification algorithms. An upcoming question for enhanced identification capabilities is the case of mixed samples providing different signals from different fluorophores. For this work, mixtures of up to four common fluorophores (NADH, FAD, tryptophan and tyrosine) were measured by a dual-wavelength setup and spectrally analyzed. Classification and regression are conducted with neural networks and show an excellent performance in predicting the ratios of the selected ingredients.
Chemical contamination of objects and surfaces, caused by accident or on purpose, is a common security issue. Immediate countermeasures depend on the class of risk and consequently on the characteristics of the substances. Laser‐based standoff detection techniques can help to provide information about the thread without direct contact of humans to the hazardous materials. This article explains a data acquisition and classification procedure for laser‐induced fluorescence spectra of several chemical agents. The substances are excited from a distance of 3.5 m by laser pulses of two UV wavelengths (266 and 355 nm) with less than 0.1 mJ per laser pulse and a repetition rate of 100 Hz. Each pair of simultaneously emitted laser pulses is separated using an optical delay line. Every measurement consists of a dataset of 100 spectra per wavelength containing the signal intensities in the spectral range from 250 to 680 nm, recorded by a 32‐channel photo multiplying tube array. Based on this dataset, three classification algorithms are trained which can distinguish the samples by their single spectra with an accuracy of over 98%. These predictive models, generated with decision trees, support vector machines, and neural networks, can identify all agents (eg, benzaldehyde, isoproturon, and piperine) within the current set of substances.
The classification of CBE hazards is commonly not best performing if based on laser-induced fluorescence. Improving the technology by recording spectral and temporal fluorescence emission a significant gain of information can be achieved. Machine learning algorithms show a major contribution of temporal fluorescence data to the classification of biological agents.