Automation of recognition of chemicals using electronic sensor technology based on neural network data processing

The composition of the initial substance was determined using an electronic sensor “electronic nose”, consisting of 8 sensors, to which air was supplied with a syringe with alcohol vapor containing various kinds of impurities. The signal from the sensors was recorded with a sampling frequency of 1 s for 120 s. The output of the device was presented in two different interpretations - in the form of curves obtained from each sensor, or the areas under the curves. The purpose of the work is to build a recognition system for 11 impurities and water in the starting material. The composition of the initial substance was determined using an “electronic nose”, which allows one to obtain 120 values from each of 8 sensors in the form of curves or the values of the areas under the curves. A large number of classes (12), the dynamic presentation of the source data information make it advisable to build a pattern recognition system based on a neural network - a multilayer perceptron trained on the basis of the error back propagation algorithm. When training the network, existing samples are used, indicating which class they belong to. The properties of each analyte are represented as a vector of 120 values of 8 attributes defining one of 12 classes. To reduce the dimensionality of the input data of the neural network, the authors proposed the use of convolution of the available information without significant loss of information capacity of signs by constructing 8 polynomial regressions of the 19th order that describe the curves from each of the 8 sensors of the “electronic nose”. The input matrix obtained as a result of convolution consisted of 20 polynomial regression coefficients of each of 8 curves for 12 classes under consideration. A two-layer neural network with 43 neurons and a sigmoidal activation function in the hidden layer and 12 neurons and a linear activation function in the output layer was constructed. As a result of network training, 2 classification errors were obtained, which allows us to use the approach proposed by the authors to build a recognition system based on preliminary convolution of data dynamically obtained from the “electronic nose”

Psychosocial Development and First Substance Use in Third and Fourth Grade Students: A Short-Term Longitudinal Study

Third and fourth grade students () completed measures of psychosocial development, substance use, and intentions to use in January, and again in May, 1998. A revised Erikson Psychosocial Inventory Scale (EPSI) was employed to assess psychosocial development while estimates of substance use and intentions were obtained from anonymous self-reports. The sample was split on the basis of change in substance use and intentions from January to May. Using this grouping scheme as an independent variable, scores on the EPSI subscales (trust, autonomy, initiative, industry, and identity) were compared over time. Interestingly, no differences in psychosocial development were evident for the initial substance use comparisons, but differences were evident five months later. Respondents who initiated substance use and/or increased intentions during the five-month interval exhibited small gains (averaging less than 2.0%) on measures of trust, autonomy, and initiative and modest declines in industry and identity (−1.2%). Respondents who neither initiated substance use nor increased intentions during the five-month interval experienced significant gains (averaging 6.0%) on all five of the EPSI subscales. These findings suggest that early substance use may impede psychosocial development, thus justifying prevention efforts in the earlier grades as well as efforts to delay onset.

Siv Byqvist: Cannabis, Amphetamine, or Opiates? Addicts' Choices of Drugs from First use to Established Abuse

The progression of narcotics abuse from first use to regular use (> 2 days per week) to established abuse (a year prior to enrollment in a rehabilitation program) was analysed from a sample of 1 268 men and women in Sweden, who were interviewed at the beginning of treatment (BAK/SWEDATE-project). Cannabis was the most common initial substance, but amphetamine (CS), heroin (opiates) and hallucinogens were also cited. There were a number of paths from debut toward regular use and established abuse. However, from first use to regular use, most subjects continued with the initial substance. Between regular use and established abuse, subjects began using other substances as well. After approximately 10 years of abuse, extensive multiple drug abuse could be noted. Four main paths are described. Also cannabis, CS and heroin abuser progression is described. The results show significant gender differences. The progression was quicker for women: first use occurred earlier, the transition to regular use took place quickly and they were younger when they entered treatment. A larger share of women than men used heroin and amphetamine. Alcohol consumption was high and most extensive among cannabis-abusing women. The results are discussed in relation to earlier research on the stepping stone model and the drug career and show the importance of early intervention.

Study of Cyclization of 1-Benzoyl-3-methyl-3-(2-methoxycarbonylphenyl)thiourea to 1-Methyl-2-thioxo-4-quinazolone

The reaction mechanism of the title reaction was proposed on the bases of the kinetic study. The reaction takes place in two stages considerably differing in rates. In the first, faster stage, the anion of initial substance cyclizes to 1-methyl-3-benzoyl-2-thioxo-4-quinazolone. The reaction is reversible, the concentration of 1-methyl-3-benzoyl-2-thioxo-4-quinazolone decreases with increasing concentration of methanolate. In the second stage, the benzoyl group rearrangement in the given substance from nitrogen to sulfur and subsequent methanolysis to 1-methyl-2-thioxo-4-quinazolone take place. The rate-determining step is the methanolysis for [CH3O(-)] < 4 . 10-3 mol l-1 and the benzoyl group rearrangement for higher methanolate concentrations.