Quantitative identification of illicit drugs by using SOM neural networks

He, Ting; Shen, Jingling; Liang, Meiyan

doi:10.1016/j.measurement.2010.10.014

Cited by 7 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another demonstration of the PLS method coupled to THz spectroscopy was reported in the case of nutrition through the analysis of pesticides in rice . Finally, artificial neural networks (ANN) were also applied to the THz data since this chemometric method allows one to take into account possible nonlinear behaviors in the detected signals to identify illicit drugs . In this case, ANN was not utilized directly as a quantitative method.…”

mentioning

confidence: 99%

“…24 Finally, artificial neural networks (ANN) were also applied to the THz data since this chemometric method allows one to take into account possible nonlinear behaviors in the detected signals to identify illicit drugs. 25 In this case, ANN was not utilized directly as a quantitative method. In previous studies, our group has already applied ANN to quantitative analysis of LIBS spectra 26,27 and has demonstrated the advantages of this technique.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Chemometrics Applied to Quantitative Analysis of Ternary Mixtures by Terahertz Spectroscopy

et al. 2014

View full text Add to dashboard Cite

Chemometrics was applied to qualitative and quantitative analyses of terahertz spectra obtained in transmission mode. A series of mixtures of three pure analytes, namely, citric acid, D-(-)fructose, and α-lactose monohydrate under various concentrations, was prepared as pressed pellets with polyethylene as binder. Then, terahertz absorbance spectra were recorded by terahertz time domain spectroscopy and analyzed. First, principal component analysis allowed one to correctly locate the samples into a ternary diagram. Second, quantitative analysis was achieved by partial least-squares (PLS) regression and artificial neural networks (ANN). The concentrations were predicted with values of relative mean square error lower than 0.9% for the three constituents. As a conclusion, chemometrics was demonstrated to be very efficient for the analysis of the ternary mixtures prepared for this study.

show abstract

mentioning

confidence: 99%

mentioning

confidence: 99%

Chemometrics Applied to Quantitative Analysis of Ternary Mixtures by Terahertz Spectroscopy

et al. 2014

View full text Add to dashboard Cite

show abstract

“…Some researchers also explore the usage of principal component analysis (PCA) for screening drugs of abuse [9], neural network for structures to quantitative analysis [10,11], neural network and knearest neighbor for quantitative analysis of Raman spectroscopy data [12], and the most recent, PCA and neural network to classify molecular data [13]. Literature has shown that this field is still not being extensively explored in the context of soft computing and computational intelligence, as evidenced by some of the most recent studies on drug identification and similarity searching [5,6].…”

Section: Ats Drug Identificationmentioning

confidence: 99%

“…Now 3D Zernike moments of f(x) are defined as the coefficients of the expansion in this orthonormal basis by the formula in (10).…”

Section: D Zernikementioning

confidence: 99%

A Comparative Study of 2D UMI and 3D Zernike Shape Descriptor for ATS Drugs Identification

Pratama

Muda

Choo

et al. 2015

Pattern Analysis, Intelligent Security and the Internet of Things

View full text Add to dashboard Cite

Drug abuse is a threat to national development. Generally, drugs can be identified based on the structure of its molecular components. This procedure is becoming more unreliable with the introduction of new amphetamine-type stimulants (ATS) molecular structures which are increasingly complex and sophisticated. An in-depth study is crucial to accurately identify the unique characteristics of molecular structure in ATS drug. Therefore, this chapter is meant for exploring the usage of shape descriptors (SD) to represent the drug molecular structure. Twodimensional (2D) united moment invariant (UMI) and three-dimensional (3D) Zernike are selected and their performances are analyzed using drug chemical structures obtained from United Nations Office of Drugs and Crime (UNODC) and various sources. The evaluation identifies the most interesting method to be further explored and adapted in the future work to fully compatible with ATS drug identification domain.

show abstract

Qualitative and quantitative identification of nitrofen in terahertz region

Wang

2013

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

Quantitative identification of illicit drugs by using SOM neural networks

Cited by 7 publications

References 9 publications

Chemometrics Applied to Quantitative Analysis of Ternary Mixtures by Terahertz Spectroscopy

Chemometrics Applied to Quantitative Analysis of Ternary Mixtures by Terahertz Spectroscopy

A Comparative Study of 2D UMI and 3D Zernike Shape Descriptor for ATS Drugs Identification

Qualitative and quantitative identification of nitrofen in terahertz region

Contact Info

Product

Resources

About