Structure–activity correlations for illicit amphetamines using ANN and constitutional descriptors

2015 E-Health and Bioengineering Conference (EHB)

Ghinita

Mandru

et al. 2015

We are presenting an Artificial Neural Networks (ANN) application designed to perform detailed (regional) authenticity and traceability assessments in the case of herbal spices. Its capacity to correctly assign the class (regional) identity when the properties of a new sample are compared simultaneously with models built for several regions of origin has been evaluated. A case study performed for dill (Anethum graveolens) indicates that ANN is very fit for the purpose, the system providing efficient and cost-effective simultaneous regional traceability assessments.

Section: Resultsmentioning

confidence: 99%

Simultaneous regional traceability assessments based on Artificial Neural Networks

2015 E-Health and Bioengineering Conference (EHB)

Ghinita

Mandru

et al. 2015

“…ANNs are able to learn from experience throughout the training process and to make classifications or detect patterns. Hence, they are able to solve complex problems in situations where a large volume of data or incomplete information has to be processed [13][14][15][16]. This paper presents a series of ANNs designed to screen for NBOMe hallucinogens based on their molecular properties and charge descriptors.…”

Section: Fig 1 Molecular Structure Of the 25i-nbome Hallucinogenic mentioning

confidence: 99%

Proving the environmental impact of NBOMe clandestine laboratories: a new analytical tool

Ion

Gosav

2020

Ann_UGAL_Math_Phys_Mec

The research performed during the last decades has allowed a better understanding not only of the moral but also of the environmental implications of drug abuse. It has indicated that the traditional approaches for reducing drug abuse are no longer enough. New and more efficient analytical tools are needed for the detection of clandestine laboratories and for bringing to courts of law irrefutable evidence for their environmental impact. NBOMes are a family of synthetic psychotropic drugs that have increasingly been detected in seizures made by law enforcement all around the world. This paper presents a new analytical tool that can be used for detecting not only these substances of abuse but also the main precursors that are used for their manufacture.

“…A w TE Fisher discriminating function was computed based on the spectra included in the spectral database [14]. For this purpose, the positives have been divided into two classes: class I includes the spectra of the T and E drugs of abuse, while class II consists of the remaining spectra (M and N compounds) [15][16][17]. The mean spectra of the original and of the w TE 2 processed spectra included in class I are presented in Fig.…”

Section: Experimental Partmentioning

confidence: 99%

Pattern recognition analysis of the class identity recognition efficiency of a portable laser infrared sensor detecting amphetamines and their main precursors

Ciochina

2019

Ann_UGAL_Math_Phys_Mec

We are presenting a pattern recognition analysis assessing the class identity recognition efficiency of a portable laser infrared sensor detecting controlled phenethylamines, i.e. the stimulant and hallucinogenic amphetamines, as well as ephedrines, which are their main precursors. The training set consists of laser infrared spectra of the later compounds and of negatives, which are randomly selected non-amphetamines. The spectra have been recorded in the spectral domain 1405 -1150 cm -1 , preprocessed with a w TE 2 Fisher discriminating function, and then subjected to Principal Component Analysis (PCA). The PCA scores have been used in order to build several pattern recognition systems designed to recognize the class identity of the targeted compounds, i.e. Cluster Analysis and Naive Bayesian Classifier. The detection efficiency obtained for these two systems is presented and discussed in detail.