Manoj Kumar Gundawar

Incorporation of Support Vector Machines in the LIBS Toolbox for Sensitive and Robust Classification Amidst Unexpected Sample and System Variability

Despite the intrinsic elemental analysis capability and lack of sample preparation requirements, laser-induced breakdown spectroscopy (LIBS) has not been extensively used for real-world applications, e.g., quality assurance and process monitoring. Specifically, variability in sample, system, and experimental parameters in LIBS studies present a substantive hurdle for robust classification, even when standard multivariate chemometric techniques are used for analysis. Considering pharmaceutical sample investigation as an example, we propose the use of support vector machines (SVM) as a nonlinear classification method over conventional linear techniques such as soft independent modeling of class analogy (SIMCA) and partial least-squares discriminant analysis (PLS-DA) for discrimination based on LIBS measurements. Using over-the-counter pharmaceutical samples, we demonstrate that the application of SVM enables statistically significant improvements in prospective classification accuracy (sensitivity), because of its ability to address variability in LIBS sample ablation and plasma self-absorption behavior. Furthermore, our results reveal that SVM provides nearly 10% improvement in correct allocation rate and a concomitant reduction in misclassification rates of 75% (cf. PLS-DA) and 80% (cf. SIMCA)-when measurements from samples not included in the training set are incorporated in the test data-highlighting its robustness. While further studies on a wider matrix of sample types performed using different LIBS systems is needed to fully characterize the capability of SVM to provide superior predictions, we anticipate that the improved sensitivity and robustness observed here will facilitate application of the proposed LIBS-SVM toolbox for screening drugs and detecting counterfeit samples, as well as in related areas of forensic and biological sample analysis.

Less is more: Avoiding the LIBS dimensionality curse through judicious feature selection for explosive detection

Despite its intrinsic advantages, translation of laser induced breakdown spectroscopy for material identification has been often impeded by the lack of robustness of developed classification models, often due to the presence of spurious correlations. While a number of classifiers exhibiting high discriminatory power have been reported, efforts in establishing the subset of relevant spectral features that enable a fundamental interpretation of the segmentation capability and avoid the ‘curse of dimensionality’ have been lacking. Using LIBS data acquired from a set of secondary explosives, we investigate judicious feature selection approaches and architect two different chemometrics classifiers –based on feature selection through prerequisite knowledge of the sample composition and genetic algorithm, respectively. While the full spectral input results in classification rate of ca.92%, selection of only carbon to hydrogen spectral window results in near identical performance. Importantly, the genetic algorithm-derived classifier shows a statistically significant improvement to ca. 94% accuracy for prospective classification, even though the number of features used is an order of magnitude smaller. Our findings demonstrate the impact of rigorous feature selection in LIBS and also hint at the feasibility of using a discrete filter based detector thereby enabling a cheaper and compact system more amenable to field operations.

Stoichiometric Analysis of Inorganic Compounds Using Laser-Induced Breakdown Spectroscopy with Gated and Nongated Spectrometers

We describe our results obtained from stoichiometric ratio studies of three different energetic, inorganic samples (ammonium perchlorate (AP), boron potassium nitrate (BPN), and ammonium nitrate (AN)) using the technique of laser-induced breakdown spectroscopy (LIBS) with nanosecond pulses. Signal collection was independently executed using both gated and nongated spectrometers. The oxygen peak at 777.31 nm (O) and nitrogen peaks at 742.50 nm (N1), 744.34 nm (N2), and 746.91 nm (N3) were used for evaluating the O/N ratios. Temporal analysis of plasma parameters and ratios was carried out for the gated data. O/N1, O/N2, and O/N3 ratios retrieved from the gated AP data were in excellent agreement with the actual stoichiometry. In the case of gated BPN data, O/N2 and O/N3 ratios were in good agreement. The stoichiometry results obtained with nongated spectrometer, although less accurate than that obtained with gated spectrometer, suggest that it can be used in applications where fair accuracy is sufficient. Our results strongly indicate that non-gated LIBS technique is worthwhile in the kind of applications where precision classification is not required.

Non-gated laser induced breakdown spectroscopy provides a powerful segmentation tool on concomitant treatment of characteristic and continuum emission.

We demonstrate the application of non-gated laser induced breakdown spectroscopy (LIBS) for characterization and classification of organic materials with similar chemical composition. While use of such a system introduces substantive continuum background in the spectral dataset, we show that appropriate treatment of the continuum and characteristic emission results in accurate discrimination of pharmaceutical formulations of similar stoichiometry. Specifically, our results suggest that near-perfect classification can be obtained by employing suitable multivariate analysis on the acquired spectra, without prior removal of the continuum background. Indeed, we conjecture that pre-processing in the form of background removal may introduce spurious features in the signal. Our findings in this report significantly advance the prior results in time-integrated LIBS application and suggest the possibility of a portable, non-gated LIBS system as a process analytical tool, given its simple instrumentation needs, real-time capability and lack of sample preparation requirements.

Laser induced breakdown spectroscopy of high energy materials using nanosecond, picosecond, and femtosecond pulses: challenges and opportunities

We present some of our initial experimental results from laser induced breakdown spectroscopy (LIBS) studies of few high energy materials such as a simple match stick (MS) and BKNO3 (BPN), and ammonium perchlorate (AP) using nanosecond (ns), picosecond (ps), and femtosecond (fs) pulses. The characteristic peaks of each sample in different time domains are analyzed. The merits and de-merits of ultrashort pulses in LIBS experiments for discrimination of high energy materials are highlighted.

Study of preprocessing sensitivity on laser induced breakdown spectroscopy (LIBS) spectral classification

Laser induced breakdown spectroscopy (LIBS) is an atomic emission based spectroscopy that uses a laser pulse as the source of excitation. The laser is focused to form hot plasma, which atomizes and excites the sample. In the LIBS spectrum each “feature” is the amplitude or intensity detected at different wavelengths in the range of 200-1000 nm. Pattern recognition techniques were applied on samples with similar elemental composition resulting in almost similar LIBS spectra which are visually very difficult to differentiate. It was observed that the classification results obtained from different classifiers were sensitive to data preprocessing. The outlier detection and removal techniques PCA, Dendrogram using Agglomerative Algorithm, Editing by Nearest Neighbour (NN) and Distance Matrix approaches were used in preprocessing step. After removing outlier(s) the resulting training patterns were used to model the k-Nearest Neighbour (k-NN), Principal Component Analysis (PCA), Dendrogram, Multiclass Support Vector Machine (SVM) and Decision Tree classifiers. In k-NN after removing outlier(s) the average classification accuracy was increased by 2% for high energy materials (HEM), but no improvement in non high energy materials (Non HEM) or in top level classification (decide either HEM or Non HEM). But, for other classifiers the classification accuracy gets reduced. Finally instead of removing outlier(s) dimensionality reduction by thresholding was applied and the classification accuracy increased by 4% in k-NN for HEM and 38% in multiclass SVM for HEM and 4% for Non-HEM.

Femtosecond Time Resolved Laser Induced Breakdown Spectroscopy Studies of Nitroimidazoles

We studied the femtosecond LIBS spectra of nitroimidazoles and measured decay time constants of CN, C2 peaks. The effect of number of nitro groups on the atomic, molecular emission has been evaluated.

Effects of disordered microstructure and heat release on propagation of combustion front

Abstract Numerical experiments for diagnosis of combustion of actual heterogeneous systems are performed on a one-dimensional chain. The internal microstructure of actual heterogeneous systems is apriori unknown, various distributions like uniform, beta, and normal have been considered for distributing neighboring reaction cells. Two cases, for the nature of distribution of heat release of reaction cells are taken into account, one with identical heat release and the other with disordered heat release. Role of different random distributions in describing heterogeneous combustion process is established in present paper. Particularly, the normal distribution of arranging neighboring reaction cells has been found to be powerful methodology in explaining the combustion process of an actual heterogeneous system at higher ignition temperatures for both cases of distributing heat release. Validation of the developed model with the experimental data of combustion of the CMDB propellants, gasless Ti + xSi system, and different thermite mixtures is performed. Our results show that the experimental burning rates at higher ignition temperatures (ε > 0.32) of the heterogeneous system are better reproduced theoretically with the present model. We have also shown that different combustion limits for different thermite systems are the consequences of disordered heat release. Experimental data for thermite systems that have lower inflammability limits are analyzed in the view of disordered heat releases of cells. The model developed in the view of disordered heat releases reproduces the experimental burn rates and experimental combustion limit.