Vacuum Ultraviolet Laser Induced Breakdown Spectroscopy (VUV-LIBS) with machine learning for pharmaceutical analysis

Alli, Muhammad Bilal; Szwarcman, Daniela; Civitarese, Daniel; Hayden, P.

doi:10.1088/1742-6596/1289/1/012031

Cited by 3 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A review on artificial neural networks in LIBS has been recently published by Li et al, 5 which also discusses some applications of CNN to classification of grape seeds from different cultivars and to classification of pharmaceutical, 6 geological samples, 7 and soils. 8 Several automatic feature selection methods are reported in the LIBS recent literature.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Convolutional and Conventional Artificial Neural Networks for Laser-Induced Breakdown Spectroscopy Quantitative Analysis

Poggialini¹,

Campanella²,

Legnaioli³

et al. 2022

Appl Spectrosc

View full text Add to dashboard Cite

The introduction of Deep Learning algorithms for feature identification in digital imaging has paved the way for Artificial Intelligence applications that up to a decade ago were considered technologically impossible to achieve, from the development of driverless vehicles to the fully automated diagnostics of cancer and other diseases from histological images. The success of Deep Learning applications has, in turn, attracted the attention of several researchers for the possible use of these methods in chemometrics, applied to the analysis of complex phenomena as, for example, the optical emission of laser-induced plasmas. In this paper, we will discuss the advantages and disadvantages of Convolutional Neural Networks, one of the most diffused Deep Learning techniques, in Laser-Induced Breakdown Spectroscopy (LIBS) applications (classification and quantitative analysis), to understand the real potential of ‘Deep LIBS’ in practical everyday use. In particular, the comparison with the results obtained using ‘shallow’ Artificial Neural Networks (ANN) will be presented and discussed, taking as a case study the analysis of six bronze samples of known composition.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparison of Convolutional and Conventional Artificial Neural Networks for Laser-Induced Breakdown Spectroscopy Quantitative Analysis

Poggialini¹,

Campanella²,

Legnaioli³

et al. 2022

Appl Spectrosc

View full text Add to dashboard Cite

show abstract

“…Due to its enormous advantages, such as rapidity, minimal sample preparation, ability to perform stand-off optical measurements, and to perform real-time and in situ measurements for laboratory or industrial use [6,7], LIBS is extensively applied in many research areas, including monitoring at production sites, and the elemental analysis of different materials, such as steel, rubber, alloys, ores, and many more [8][9][10][11][12]. Due to the above qualities and capabilities of LIBS, the pharmaceutical sector is taking an interest in this technique and recently its application has been reported by many researchers [1,[13][14][15][16][17][18][19][20]. Detailed descriptions of the LIBS technique are very well reported in the literature [21][22][23].…”

Section: Introductionmentioning

confidence: 99%

Study of Pharmaceutical Samples using Optical Emission Spectroscopy and Microscopy

Dwivedi¹,

Chauhan²,

Maurya³

et al. 2022

Laser Phys.

View full text Add to dashboard Cite

The growth of the pharmaceutical industry to keep pace with the well-being of humans worldwide has posed many challenges related to quality control. This paper reports on the potential application of a modern optical spectroscopic technique popularly known as laser-induced breakdown spectroscopy (LIBS) to address some quality aspects such as the sample constituents, hardness, and classification of five different pharmaceutical samples. The surface analysis of these samples has been carried out using optical microscopy (OM) and atomic force microscopy (AFM). The LIBS spectra of different pharmaceutical samples of different brands have been recorded in air at atmospheric pressure using a high-energy Nd:YAG laser and an echelle spectrometer coupled with an intensified charge-coupled device camera. The LIBS spectrum provides the spectral signatures of lighter elements like carbon (C), hydrogen (H), nitrogen (N), oxygen (O), and the CN violet band, along with inorganic elements like calcium (Ca), magnesium (Mg), etc. Two different multivariate analysis methods, principal component analysis (PCA) and artificial neural network (ANN), have been employed with the LIBS spectral data matrix to obtain the classification of these samples. OM and AFM were used to investigate the surface quality of the tablets, which helps the pharmaceutical industry in increasing the life of pharmaceutical products. The LIBS-based hardness of the sample matrices is estimated, and a correlation has been established with AFM-based RMS roughness. The results illustrate the strength of the LIBS coupled with multivariate analysis like PCA and ANN for a rapid and reliable analysis of pharmaceutical products. Also, LIBS coupled with OM and AFM might be an effective way to address surface quality aspects of pharmaceutical samples.

show abstract

Wind turbine contaminant classification using machine learning techniques

Cummins,

Campbell,

Durkan

et al. 2023

Spectrochimica Acta Part B: Atomic Spectroscopy

View full text Add to dashboard Cite

Vacuum Ultraviolet Laser Induced Breakdown Spectroscopy (VUV-LIBS) with machine learning for pharmaceutical analysis

Cited by 3 publications

References 10 publications

Comparison of Convolutional and Conventional Artificial Neural Networks for Laser-Induced Breakdown Spectroscopy Quantitative Analysis

Comparison of Convolutional and Conventional Artificial Neural Networks for Laser-Induced Breakdown Spectroscopy Quantitative Analysis

Study of Pharmaceutical Samples using Optical Emission Spectroscopy and Microscopy

Wind turbine contaminant classification using machine learning techniques

Contact Info

Product

Resources

About