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

Myakalwar, Ashwin Kumar; Spegazzini, Nicolás; Zhang, Chi; Anubham, Siva Kumar; Dasari, Ramachandra R.; Barman, Ishan

doi:10.1038/srep13169

Cited by 61 publications

(33 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Aligned with the propositions of this paper, Myakalwar et al [23] proposed an approach relying on two stages to identify the most relevant wavelengths to classify different types of explosives. In the first stage, partial least squares discriminant analysis (PLS-DA) was used to recognize relevant spectra subsets, and such regions were subjectively assessed in terms of the chemical functions found in each subset based on experts' a priori knowledge.…”

Section: Introductionmentioning

confidence: 94%

A genetic algorithm‐based framework for wavelength selection on sample categorization

Anzanello

Yamashita

Marcelo

et al. 2017

Drug Testing and Analysis

View full text Add to dashboard Cite

In forensic and pharmaceutical scenarios, the application of chemometrics and optimization techniques has unveiled common and peculiar features of seized medicine and drug samples, helping investigative forces to track illegal operations. This paper proposes a novel framework aimed at identifying relevant subsets of attenuated total reflectance Fourier transform infrared (ATR-FTIR) wavelengths for classifying samples into two classes, for example authentic or forged categories in case of medicines, or salt or base form in cocaine analysis. In the first step of the framework, the ATR-FTIR spectra were partitioned into equidistant intervals and the k-nearest neighbour (KNN) classification technique was applied to each interval to insert samples into proper classes. In the next step, selected intervals were refined through the genetic algorithm (GA) by identifying a limited number of wavelengths from the intervals previously selected aimed at maximizing classification accuracy. When applied to Cialis®, Viagra®, and cocaine ATR-FTIR datasets, the proposed method substantially decreased the number of wavelengths needed to categorize, and increased the classification accuracy. From a practical perspective, the proposed method provides investigative forces with valuable information towards monitoring illegal production of drugs and medicines. In addition, focusing on a reduced subset of wavelengths allows the development of portable devices capable of testing the authenticity of samples during police checking events, avoiding the need for later laboratorial analyses and reducing equipment expenses. Theoretically, the proposed GA-based approach yields more refined solutions than the current methods relying on interval approaches, which tend to insert irrelevant wavelengths in the retained intervals. Copyright © 2016 John Wiley & Sons, Ltd.

show abstract

Section: Introductionmentioning

confidence: 94%

A genetic algorithm‐based framework for wavelength selection on sample categorization

Anzanello

Yamashita

Marcelo

et al. 2017

Drug Testing and Analysis

View full text Add to dashboard Cite

show abstract

“…In national security, PLS‐DA coupled with stand‐off LIBS was used to classify thin explosive residue layers on painted surfaces, and good classification results were obtained despite the fact that the painted surface contributes to the LIBS emission signal . Myakalwar et al constructed 2 different PLS‐DA classifiers based on feature selection through prerequisite knowledge of the sample composition and genetic algorithm (GA), respectively. GA‐based PLS‐DA models demonstrate superior classification performance compared with corresponding algorithms that use the full spectral data, thus highlighting the need for removing uninformative or spurious information that may represent as much as 99% of the entire information collected.…”

Section: Qualitative Analysismentioning

confidence: 99%

Chemometrics in laser‐induced breakdown spectroscopy

Zhang

Tang

2018

Journal of Chemometrics

View full text Add to dashboard Cite

Laser-induced breakdown spectroscopy (LIBS) is a new type of elemental analytical technology with the advantages of real-time, online, and noncontact as well as enabling the simultaneous analysis of multiple elements. It has become a frontier analytical technique in spectral analysis. However, the issue of how to improve the accuracy of qualitative and quantitative analyses by extracting useful information from a large amount of complex LIBS data remains the main problem for the LIBS technique. Chemometrics is a chemical subdiscipline of multi-interdisciplinary methods; it offers advantages in data processing, signal analysis, and pattern recognition. It can solve some complicated problems that are difficult for traditional chemical methods. In this paper, we reviewed the research progress of chemometrics methods in LIBS for spectral data preprocessing as well as for qualitative and quantitative analyses in the most recent 5 years (2012-2016). KEYWORDSchemometrics, data preprocessing, laser-induced breakdown spectroscopy, qualitative analysis, quantitative analysis | INTRODUCTIONAs one of the most promising analytical tools in the 21st century, laser-induced breakdown spectroscopy (LIBS) is a novel analytical technique for materials and elements; it is based on atomic emission spectroscopy and a laser as an excitation source. 1-4 In LIBS, a low-energy pulse laser (typically tens to hundreds of millijoules per pulse) generated from a laser device is reflected by a plane mirror and focused by a plano-convex lens onto the sample surface; a laser-induced plasma with high temperature is then generated. The light with different frequencies is radiated during the plasma cooling process, and it is collected by an optical fiber coupled to a spectrometer. The qualitative and quantitative analyses by the LIBS technique can be performed using the wavelength and integrated intensity of the spectral line. A schematic diagram of the LIBS instrument is presented in Figure 1. It consists of Nd:YAG laser, optical part, X-Y-Z manual micrometric stage, optical fiber, spectrometer, Charge coupled device (CCD) camera, and computer.The LIBS technology has benefited from the invention of the ruby crystal laser 5 and was first reported by Brech and Cross. 6 It has become a research focus in the spectral field with the development of laser and optical detection techniques. Compared with conventional analytical tools, LIBS demonstrates some substantial advantages with regards to being rapid, real-time, on-site, and nondestructive while allowing remote detection without complicated sample preparation procedures as well as simultaneous multicomponent analysis. 7-9 Because of these advantages, LIBS technology has been widely used in process analysis and in the control of industrial manufacturing, food supervision, environmental monitoring, historical relic identification, and space exploration. [10][11][12][13] The National Aeronautics and

show abstract

“…The details of the experimental setup can be found in Myakalwar 35 , et al Experiments were performed on a set of five HEMs-HMX, NTO, PETN, RDX, and TNT in ambient conditions to acquire multiple spectra. As KNN requires the same size of dataset of each class, sixty spectra per sample were considered.…”

Section: Methodsmentioning

confidence: 99%

An Approach to Reduce the Sample Consumption for LIBS based Identification of Explosive Materials

2017

View full text Add to dashboard Cite

An experimental design based on spectral construction, which has potential to minimise the sample consumption, the number of laser shots and time required to collect the data from laser induced breakdown spectroscopy for identification of the explosive materials is reported in the study. This approach is an ideal solution in the field of hazardous material detection, where the availability of the sample can be a serious limiting factor. The experimental data recorded on a set of five high energy materials has been considered to test the performance of the proposed methodology. Multiple spectra are constructed by assuming a normal distribution at each wavelength of the spectrum, where random numbers are generated using the mean and standard deviations obtained from arbitrarily chosen five experimental spectra from each class. The newly generated spectra are called as synthetic spectra. The correct classification obtained from -K -nearest neighbour combined with principal component analysis and partial least square -discriminant analysis demonstrated very promising results. The correct classification rates differed by only 4 per cent -7 per cent as compared to conventional approach where experimental spectra alone are considered for the analysis. Further, when RDX is excluded, the obtained results are almost identical with conventional approach.

show abstract

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

Cited by 61 publications

References 40 publications

A genetic algorithm‐based framework for wavelength selection on sample categorization

A genetic algorithm‐based framework for wavelength selection on sample categorization

Chemometrics in laser‐induced breakdown spectroscopy

An Approach to Reduce the Sample Consumption for LIBS based Identification of Explosive Materials

Contact Info

Product

Resources

About