Identification and classification of explosives using semi-supervised learning and laser-induced breakdown spectroscopy.

Public places are often under threat from explosion events, which pose health and safety risks to the public. Therefore, the detection of explosive materials has become an important concern in the fields of antiterrorism and security. Laser-induced breakdown spectroscopy (LIBS) has been demonstrated to be useful in identifying explosives but has limitations. This study focuses on using semi-supervised learning combined with LIBS for explosive identification. Labeled data were utilized for the construction of a semi-supervised model for distinguishing explosive clusters and improving the accuracy of the K-nearest neighbor algorithm. The method requires only minimal prior information, and the time for obtaining a large amount of labeled data can be saved. The results of our investigation demonstrated that semi-supervised learning with LIBS can be used to discriminate explosives from interfering substances (plastics) containing similar components. The algorithm exhibits good robustness and practicability.

[1]  Ali Khumaeni,et al.  Analysis of sodium aerosol using transversely excited atmospheric CO2 laser-induced gas plasma spectroscopy , 2014 .

[2]  Xiaoyun Chen,et al.  Active Semisupervised Clustering Algorithm with Label Propagation for Imbalanced and Multidensity Datasets , 2013 .

[3]  Javier Moros,et al.  New chemometrics in laser-induced breakdown spectroscopy for recognizing explosive residues , 2012 .

[4]  Yongfeng Lu,et al.  Simultaneous determination of La, Ce, Pr, and Nd elements in aqueous solution using surface-enhanced laser-induced breakdown spectroscopy. , 2017, Talanta.

[5]  Edward F. Plinski,et al.  Statistical classification of soft solder alloys by laser-induced breakdown spectroscopy: review of methods , 2016 .

[6]  J. Moros,et al.  A spectral sieve-based strategy for sensing inorganic and organic traces on solid surfaces using laser-induced breakdown spectroscopy , 2015 .

[7]  Hua Zhao,et al.  Multivariate Analysis of Laser-Induced Breakdown Spectroscopy for Discrimination between Explosives and Plastics , 2012 .

[8]  Frank C De Lucia,et al.  Evaluation of femtosecond laser-induced breakdown spectroscopy for explosive residue detection. , 2009, Optics express.

[9]  Hua Zhao,et al.  Detection of explosives with laser-induced breakdown spectroscopy , 2012 .

[10]  Antonio Palucci,et al.  Analysis of explosive and other organic residues by laser induced breakdown spectroscopy , 2009 .

[11]  Shawn D. McGrane,et al.  Advances in explosives analysis—part I: animal, chemical, ion, and mechanical methods , 2015, Analytical and Bioanalytical Chemistry.

[12]  F. J. Gallego,et al.  Recognition of explosives fingerprints on objects for courier services using machine learning methods and laser-induced breakdown spectroscopy. , 2013, Talanta.

[13]  S J Rehse,et al.  Laser-induced breakdown spectroscopy (LIBS): an overview of recent progress and future potential for biomedical applications , 2012, Journal of medical engineering & technology.

[14]  Wang Qianqian,et al.  Study on Cluster Analysis Used with Laser-Induced Breakdown Spectroscopy ⁄ , 2016 .

[15]  Chi Zhang,et al.  Less is more: Avoiding the LIBS dimensionality curse through judicious feature selection for explosive detection , 2015, Scientific Reports.

[16]  Qianqian Wang,et al.  Comparison of 1064 nm and 266 nm excitation of laser-induced plasmas for several types of plastics and one explosive ☆ , 2008 .

[17]  Zhi-Hua Zhou,et al.  Semi-supervised learning by disagreement , 2010, Knowledge and Information Systems.

[18]  Z. Ren,et al.  Accuracy improvement on polymer identification using laser-induced breakdown spectroscopy with adjusting spectral weightings. , 2014, Optics express.

[19]  Qian-Qian Wang,et al.  [Classification of plastics with laser-induced breakdown spectroscopy based on principal component analysis and artificial neural network model]. , 2012, Guang pu xue yu guang pu fen xi = Guang pu.

[20]  Frank C De Lucia,et al.  Laser-induced breakdown spectroscopy analysis of energetic materials. , 2003, Applied optics.

[21]  Zongyu Hou,et al.  Utilization of moderate cylindrical confinement for precision improvement of laser-induced breakdown spectroscopy signal. , 2012, Optics express.

[22]  Anna P. M. Michel,et al.  Review: Applications of single-shot laser-induced breakdown spectroscopy , 2010 .

[23]  Xuming Han,et al.  Polu-nadzirana propagacija afiniteta temeljena na vršnoj gustoći , 2016 .

[24]  Frank C. De Lucia,et al.  Strategies for residue explosives detection using laser-induced breakdown spectroscopy , 2008 .

[25]  Venugopal Rao Soma,et al.  Femtosecond laser induced breakdown spectroscopy based standoff detection of explosives and discrimination using principal component analysis. , 2018, Optics express.

[26]  Germain Forestier,et al.  Semi-supervised learning using multiple clusterings with limited labeled data , 2016, Inf. Sci..

[27]  J. Moros,et al.  Advanced recognition of explosives in traces on polymer surfaces using LIBS and supervised learning classifiers. , 2014, Analytica chimica acta.

[28]  Frank C De Lucia,et al.  Classification of explosive residues on organic substrates using laser induced breakdown spectroscopy. , 2012, Applied optics.

[29]  S. McGrane,et al.  Advances in explosives analysis—part II: photon and neutron methods , 2015, Analytical and Bioanalytical Chemistry.

[30]  Zhong Peng,et al.  Study of cluster analysis used in explosives classification with laser-induced breakdown spectroscopy , 2016 .