ATR-FTIR combined with machine learning for the fast non-targeted screening of new psychoactive substances.

Due to the diversity and fast evolution of new psychoactive substances (NPS), both public health and safety are threatened around the world. Attenuated total reflection-Fourier transform infrared spectroscopy (ATR-FTIR), which serves as a simple and rapid technique for targeted NPS screening, is challenging with the rapid structural modifications of NPS. To achieve the fast non-targeted screening of NPS, six machine learning (ML) models were constructed to classify eight categories of NPS, including synthetic cannabinoids, synthetic cathinones, phenethylamines, fentanyl analogues, tryptamines, phencyclidine types, benzodiazepines, and "other substances" based on the 1099 IR spectra data items of 362 types of NPS collected by one desktop ATR-FTIR and two portable FTIR spectrometers. All these six ML classification models, including k-nearest neighbor (KNN), support vector machine (SVM), random forest (RF), extra trees (ET), voting, and artificial neural networks (ANNs) were trained through cross validation, and f1-scores of 0.87-1.00 were achieved. In addition, hierarchical cluster analysis (HCA) was performed on 100 synthetic cannabinoids with the most complex structural variation to investigate the structure-spectral property relationship, which leads to a summary of eight synthetic cannabinoid sub-categories with different "linked groups". ML models were also constructed to classify eight synthetic cannabinoid sub-categories. For the first time, this study developed six ML models, which were suitable for both desktop and portable spectrometers, to classify eight categories of NPS and eight synthetic cannabinoids sub-categories. These models can be applied for the fast, accurate, cost-effective, and on-site non-targeted screening of newly emerging NPS with no reference data available.

Non-destructive detection and classification of textile fibres based on hyperspectral imaging and 1D-CNN.

Textile fibre is very common in daily life, and its classification and identification play an important role in textile recycling, archaeology, public security, and other industries. However, traditional identification methods are time-consuming, laborious, and often destructive to the samples. In order to quickly, accurately, and nondestructively classify and recognize textile fibres, this study established a textile fibre classification and recognition method based on hyperspectral imaging (HSI) and a one-dimensional convolutional neural network (1D-CNN) model. Hyperspectral images of 25 kinds of commercial textile fibres were collected and denoised by pixel fusion. Four traditional machine learning classification models, k-nearest neighbors (KNN), support vector machine (SVM), random forest (RF), and partial least squares-discriminant analysis (PLS-DA), were used to identify the data. The results show that RF has the highest classification accuracy, reaching 91.4%. Then a back propagation neural network (BPNN) model and a one-dimensional convolutional neural network (1D-CNN) model were constructed and compared with the traditional machine learning methods. The results show that the 1D-CNN models have 97.9% and 98.6% accuracy on the training and test sets, respectively. The precision (Pr), sensitivity (Se), specificity (Sp), and F1 score (F1 score) of the models reached 98.7%, 98.6%, 99.9%, and 98.6%, respectively, which were significantly better than the four traditional machine learning models. It seems that 1D-CNN combined with the HSI technique may be a potential method in the detection and classification of textile fibres.

Classification modeling method for hyperspectral stamp-pad ink data based on one-dimensional convolutional neural network.

In the questioned document, the examination of stamp-pad ink is crucial scientific evidence to discern the difference between genuine and forged documents. In this study, a new method for rapid and non-destructive identification of types of stamp-pad inks by combining hyperspectral imaging (HSI) technology and deep learning was developed. Twenty stamp-pad inks of different brands and models were collected and numbered in turn, and then, each of them was sealed six times repeatedly on the A4 printing paper for the test. After that, the hyperspectral imager was used to collect the hyperspectral images and the reflectance spectral data were obtained after pixel fusion. Principal component analysis (PCA) and non-negative matrix factorization (NMF) were used to deal with the dataset, but visual results were not good. Then, back propagation neural network (BPNN) and one-dimensional convolutional neural network (1D-CNN) were constructed and their merits and drawbacks were compared. The final loss function of the BPNN of training set and validation set was stable at 0.27 and 0.42, and the classification accuracy of the training set and validation set reached 90.02% and 83.99%, respectively. Compared with the BPNN, the 1D-CNN had better stability and efficiency for the classification. The loss function of the training set and validation set was as low as 0.068 and 0.075, and the final classification accuracy reached 98.30% and 97.94%, respectively. Therefore, the combination of hyperspectral imaging technology and 1D-CNN represents a potentially simple, non-destructive, and rapid method for stamp-pad inks detection and classification.