Near infrared hyperspectral imaging for forensic analysis of document forgery.

Hyperspectral images in the near infrared range (HSI-NIR) were evaluated as a nondestructive method to detect fraud in documents. Three different types of typical forgeries were simulated by (a) obliterating text, (b) adding text and (c) approaching the crossing lines problem. The simulated samples were imaged in the range of 928-2524 nm with spectral and spatial resolutions of 6.3 nm and 10 µm, respectively. After data pre-processing, different chemometric techniques were evaluated for each type of forgery. Principal component analysis (PCA) was performed to elucidate the first two types of adulteration, (a) and (b). Moreover, Multivariate Curve Resolution-Alternating Least Squares (MCR-ALS) was used in an attempt to improve the results of the type (a) obliteration and type (b) adding text problems. Finally, MCR-ALS and Partial Least Squares-Discriminant Analysis (PLS-DA), employed as a variable selection tool, were used to study the type (c) forgeries, i.e. crossing lines problem. Type (a) forgeries (obliterating text) were successfully identified in 43% of the samples using both the chemometric methods (PCA and MCR-ALS). Type (b) forgeries (adding text) were successfully identified in 82% of the samples using both the methods (PCA and MCR-ALS). Finally, type (c) forgeries (crossing lines) were successfully identified in 85% of the samples. The results demonstrate the potential of HSI-NIR associated with chemometric tools to support document forgery identification.

Classification of bloodstains deposited at different times on floor tiles using hierarchical modelling and a handheld NIR spectrometer.

Bloodstains are commonly encountered at crime scenes, especially on floor tiles, and can be deposited over different periods and intervals. Therefore, it is crucial to develop techniques that can accurately identify bloodstains deposited at different times. This study builds upon a previous investigation and aims to enhance the performance of three distinct hierarchical models (HMs) designed to differentiate and identify stains of human blood (HB), animal blood (AB), and common false positives (CFPs) on nine different types of floor tiles. Soft Independent Modeling Class Analogies (SIMCA), and Partial Least Squares-Discriminant Analysis (PLS-DA) were employed as decision rules in this process. The originally published model was constructed using a training set that included samples with a known time of deposit of six days. This model was then tested to predict samples with various deposition times, including human blood samples aged for 0, 1, 9, 20, 30, and 162 days, as well as animal blood samples aged for 0, 1, 10, 13, 20, 29, 105, and 176 days. To improve the identification of human blood, the models were modified by adding zero-day and one-day-old bloodstains to the original training set. All models showed improvement when fresher samples were included in the training set. The best results were achieved with the hierarchical model that used partial least squares-discriminant analysis as the second decision rule and incorporated one-day-old samples in the training set. This model yielded sensitivity values above 0.92 and specificity values above 0.7 for samples aged between zero and 30 days.

Hierarchical classification models and Handheld NIR spectrometer to human blood stains identification on different floor tiles.

One of the most important types of evidence in certain criminal investigations is traces of human blood. For a detailed investigation, blood samples must be identified and collected at the crime scene. The present study aimed to evaluate the potential of the identification of human blood in stains deposited on different types of floor tiles (five types of ceramics and four types of porcelain tiles) using a portable NIR instrument. Hierarchical models were developed by combining multivariate analysis techniques capable of identifying traces of human blood (HB), animal blood (AB) and common false positives (CFP). The spectra of the dried stains were obtained using a portable MicroNIR spectrometer (Viavi). The hierarchical models used two decision rules, the first to separate CFP and the second to discriminate HB from AB. The first decision rule, used to separate the CFP, was based on the Q-Residual criterion considering a PCA model. For the second rule, used to discriminate HB and AB, the Q-Residual criterion were tested as obtained from a PCA model, a One-Class SIMCA model, and a PLS-DA model. The best results of sensitivity and specificity, both equal to 100%, were obtained when a PLS-DA model was employed as the second decision rule. The hierarchical classification models built for these same training sets using a PCA or SIMCA model also obtained excellent sensitivity results for HB classification, with values above 94% and 78% of specificity. No CFP samples were misclassified. Hierarchical models represent a significant advance as a methodology for the identification of human blood stains at crime scenes.

Detection and identification of Cannabis sativa L. using near infrared hyperspectral imaging and machine learning methods. A feasibility study.

Remote identification of illegal plantations of Cannabis sativa Linnaeus is an important task for the Brazilian Federal Police. The current analytical methodology is expensive and strongly dependent on the expertise of the forensic investigator. A faster and cheaper methodology based on automatic methods can be useful for the detection and identification of Cannabis sativa L. in a reliable and objective manner. In this work, the high potential of Near Infrared Hyperspectral Imaging (HSI-NIR) combined with machine learning is demonstrated for supervised detection and classification of Cannabis sativa L. This plant, together with other plants commonly found in the surroundings of illegal plantations and soil, were directly collected from an illegal plantation. Due to the high correlation of the NIR spectra, sparse Principal Component Analysis (sPCA) was implemented to select the most important wavelengths for identifying Cannabis sativa L. One class Soft Independent Class Analogy model (SIMCA) was built, considering just the spectral variables selected by sPCA. Sensitivity and specificity values of 89.45% and 97.60% were, respectively, obtained for an external validation set subjected to the s-SIMCA. The results proved the reliability of a methodology based on NIR hyperspectral cameras to detect and identify Cannabis sativa L., with only four spectral bands, showing the potential of this methodology to be implemented in low-cost airborne devices.

Classification of Brazilian and foreign gasolines adulterated with alcohol using infrared spectroscopy.

The smuggling of products across the border regions of many countries is a practice to be fought. Brazilian authorities are increasingly worried about the illicit trade of fuels along the frontiers of the country. In order to confirm this as a crime, the Federal Police must have a means of identifying the origin of the fuel. This work describes the development of a rapid and nondestructive methodology to classify gasoline as to its origin (Brazil, Venezuela and Peru), using infrared spectroscopy and multivariate classification. Partial Least Squares Discriminant Analysis (PLS-DA) and Soft Independent Modeling Class Analogy (SIMCA) models were built. Direct standardization (DS) was employed aiming to standardize the spectra obtained in different laboratories of the border units of the Federal Police. Two approaches were considered in this work: (1) local and (2) global classification models. When using Approach 1, the PLS-DA achieved 100% correct classification, and the deviation of the predicted values for the secondary instrument considerably decreased after performing DS. In this case, SIMCA models were not efficient in the classification, even after standardization. Using a global model (Approach 2), both PLS-DA and SIMCA techniques were effective after performing DS. Considering that real situations may involve questioned samples from other nations (such as Peru), the SIMCA method developed according to Approach 2 is a more adequate, since the sample will be classified neither as Brazil nor Venezuelan. This methodology could be applied to other forensic problems involving the chemical classification of a product, provided that a specific modeling is performed.

Spectrophotometric cocaine determination in a biphasic medium employing flow-batch sequential injection analysis.

Quantifying cocaine in apprehended samples is important to the Brazilian Federal Police because the concentration can indicate the origin of the drug and consequently the traffic route. In addition to the other risks of using this drug is the variability in cocaine concentration, which makes large doses lethal. Gas Chromatography with a Flame Ionization Detector (GC-FID) and a Mass Selective Detector (GC-MS) are the techniques usually employed, but these systems are not available in all police laboratories, due to the relatively high cost. In the present work, a flow-system procedure for the spectrophotometric determination of cocaine using cobalt thiocyanate as a complexing reagent was developed. In this reaction, two phases are formed: the superior (pink) contains an excess of cobalt thiocyanate solution and the lower layer (blue) contains the complex cocaine-cobalt thiocyanate. Samples and reagent are inserted through a sequential-injection valve between two air bubbles inside a reaction chamber. An optic fiber sensor connected to the chamber recorded the absorbance at 630 nm signal. The detection and quantification limits were 29.4 mg L(-1) and 98 mg L(-1), respectively. Relative standard deviation was 4.9% for solutions containing 400 mg L(-1) (n=10), with stable baselines. The analytical throughput was 12 determinations per hour.