Discrimination of Human and Nonhuman Blood by Raman Spectroscopy and Partial Least Squares Discriminant Analysis

Raman ConvMSANet: A High-Accuracy Neural Network for Raman Spectroscopy Blood and Semen Identification

Animal blood and semen analysis plays a significant role in national biological resource management, wildlife conservation, and customs security quarantine. Traditional blood analysis methods have disadvantages, such as complex sample preparation, time consumption, and false positives. Therefore, proposing a rapid and highly accurate analysis method is highly valuable. Raman spectroscopy has been widely used in blood analysis, and efficient and accurate analysis results can be obtained through the machine learning algorithm feature extraction. Recently, the transformer network structure was applied to Raman spectroscopy recognition. However, the multihead self-attention mechanism does not perform well in extracting local feature peaks, although it obtains global feature relations. This paper proposes a neural network based on the combination of one-dimensional convolution and multihead self-attention mechanism (Raman ConvMSANet) to identify 52 species of blood and semen Raman spectra. The network can achieve reliable identification effects in multiclassification and sample imbalance situations, and the average identification accuracy of blood and semen can reach more than 98.5%. The proposed network model can be applied not only to blood and semen identification but also to other biological fields.

Classification method based on Siamese-like neural network for inter-species blood Raman spectra similarity measure

Analysis of blood species is an extremely important part in customs inspection, forensic investigation, wildlife protection and other fields. In this study, a classification method based on Siamese-like neural network (SNN) for interspecies blood (22 species) was proposed to measure Raman Spectra similarity. The average accuracy was above 99.20% in the test set of spectra (known species) that did not appear in the training set. This model could detect species not represented in the dataset underlying the model. After adding new species to the training set, we can update the training based on the original model without retraining the model from scratch. For species with lower accuracy, SNN model can be trained intensively in the form of enriched training data for that species. A single model can achieve both multiple-classification and binary classification functions. Moreover, SNN showed higher accuracy rates when trained with smaller datasets compared to other methods.

Differentiation of NaCl, NaOH, and β-Phenylethylamine Using Ultraviolet Spectroscopy and Improved Adaptive Artificial Bee Colony Combined with BP-ANN Algorithm

The aim of this study is to enhance the classification performance of the back-propagation-artificial neural network (BP-ANN) algorithm for NaCl, NaOH, β-phenylethylamine (PEA), and their mixture, as well as to avoid the defects of the artificial bee colony (ABC) algorithm such as prematurity and local optimization. In this paper, a method that combined an improved adaptive artificial bee colony (IAABC) algorithm and BP-ANN algorithm was proposed. This method improved the ABC algorithm by adding an adaptive local search factor and mutation factor; meanwhile, it can enhance the abilities of the global optimization and local search of the ABC algorithm and avoid prematurity. The extracted score vectors of the principal component of the ultraviolet (UV) spectrum were used as the input variable of the BP-ANN algorithm. The IAABC algorithm was used to optimize the weight and threshold of the BP-ANN algorithm, and the iterative algorithm was repeated until the output accuracy was reached. The output variable was the classification results of NaCl, NaOH, PEA, and the mixture. Meanwhile, the proposed IAABC-BP-ANN algorithm was compared with discriminant analysis (DA), sigmaid-support vector machine (SVM), radial basis function-SVM (RBF-SVM), BP-ANN, and ABC-BP-ANN. Then, the above algorithms were used to classify NaCl, NaOH, PEA, and the mixture, respectively. In the experiment, four indicators, accuracy, recall, precision, and F-score, were used as the evaluation criteria. In addition, the regression equation parameters of the mixture for the testing set were obtained by BP-ANN, ABC-BP-ANN, and IAABC-BP-ANN models. All of the results showed that IAABC-BP-ANN exhibits better performance than other algorithms. Therefore, IAABC-BP-ANN combined with UV spectroscopy is a potential identification tool for the detection of NaCl, NaOH, PEA, and the mixture.

Identification of blood species based on surface-enhanced Raman scattering spectroscopy and convolutional neural network

The identification of blood species is of great significance in many aspects such as forensic science, wildlife protection, and customs security and quarantine. Conventional Raman spectroscopy combined with chemometrics is an established method for identification of blood species. However, the Raman spectrum of trace amount of blood could hardly be obtained due to the very small cross-section of Raman scattering. In order to overcome this limitation, surface-enhanced Raman scattering (SERS) was adopted to analyze trace amount of blood. The 785 nm laser was selected as the optimal laser to acquire the SERS spectra, and the blood SERS spectra of 19 species were measured. The convolutional neural network (CNN) was used to distinguish the blood of 19 species including human. The recognition accuracy of the blood species was obtained with 98.79%. Our study provides an effective and reliable method for identification and classification of trace amount of blood.

Determination of blood species using echelle Raman spectrometer and surface enhanced Raman spectroscopy

Blood species identification of human and animals has attracted much attention in the areas of customs inspection and forensic science. The combination of vibrational spectroscopy and machine learning has been proven to be feasible and effective for this purpose. However, the popularization of this technology needs instrument which is compact, robust and more suitable for field application. Besides the quantity of the blood sample should be as little as possible. In this study, we proposed a system using echelle Raman spectrometer combined with surface enhanced Raman spectroscopy (SERS), which protocol combines the advantages of broadband and high resolution of echelle Raman spectrometer with the advantages of high SERS spectral sensitivity. The SERS spectra of 26 species including human were collected with echelle Raman spectrometer, and the convolutional neural network was used for species identification, with an accuracy rate of over 94%. The feasibility, validity and reliability of the combination of echelle Raman spectrometer and SERS for blood species identification were realized.

Study on the Raman spectral characteristics of dynamic and static blood and its application in species identification

This paper proposes a method to identify the blood of 4 poultry species (chicken, duck, goose and pigeon) based on Raman spectroscopy and its baseline. Samples were prepared by pretreatment methods of freezing, thawing, and dilution. The Raman spectra of dynamic blood and static blood were measured, respectively, and the spectral differences between the two research schemes were analyzed. The four species of poultry blood were identified based on the Raman spectroscopy and its baseline. The results show that the method can realize the identification of four species of poultry blood. In addition, the potential of Raman spectroscopy as a technique for determining carotenoids in blood has been clearly confirmed, which opens up the possibility to quickly determine whether poultry eats feed containing carotenoids without sample preparation.

Blood identification at the single-cell level based on a combination of laser tweezers Raman spectroscopy and machine learning

Laser tweezers Raman spectroscopy (LTRS) combines optical tweezers technology and Raman spectroscopy to obtain biomolecular compositional information from a single cell without invasion or destruction, so it can be used to "fingerprint" substances to characterize numerous types of biological cell samples. In the current study, LTRS was combined with two machine learning algorithms, principal component analysis (PCA)-linear discriminant analysis (LDA) and random forest, to achieve high-precision multi-species blood classification at the single-cell level. The accuracies of the two classification models were 96.60% and 96.84%, respectively. Meanwhile, compared with PCA-LDA and other classification algorithms, the random forest algorithm is proved to have significant advantages, which can directly explain the importance of spectral features at the molecular level.

Effects of Urbanization on Ecosystem Services in the Shandong Peninsula Urban Agglomeration, in China: The Case of Weifang City

Ecosystem services are the material basis of economic and social development, and play essential roles in the sustainable development of ecosystems. Urbanization can remarkably alter the provision of ecosystem services. Most studies in this area have focused on densely populated metropolises with poor ecological environments, while comparatively few studies have focused on cities with low ecological pressures. Therefore, to avoid continuing to engage in the repetitive pattern of destroying first and rehabilitating later, quantitative analyses of urbanization and ecosystem services should be carried out in representative cities. In this study, based on partial least squares-discriminant analysis, kernel density estimation, and correlation analysis, we quantitatively evaluated the impact of urbanization on ecosystem services in Weifang city. The Data Center for Resources and Environmental Sciences at the Chinese Academy of Sciences and the Institute of Geographic Sciences and Natural Resources Research provided remote sensing data on land use, the gross domestic production (GDP), population data, and ecosystem services. The results were as follows: (1) The variation in population, GDP, and built-up areas consistently increased throughout the study period, whereas the ecosystem service values (ESVs) decreased; (2) food production, raw material production, nutrient cycle maintenance, and soil conservation were decisive ecosystem services that led to vast reductions in ESVs during the process of urbanization; and (3) the negative correlation coefficient between built-up areas and ecosystem services was greater than that between the population or GDP and ecosystem services, which indicated that the impacts of population and economic urbanization on ecosystem services lagged behind the impact of land urbanization. This study provides references for fully recognizing the ecological effects of urbanization, and make suggestions regarding the application of ecosystem services in sustainable development.

Discrimination between human and animal blood by attenuated total reflection Fourier transform-infrared spectroscopy

Forensic chemistry is an important area of analytical chemistry. This field has been rapidly growing over the last several decades. Confirmation of the human origins of bloodstains is important in practical forensics. Current serological blood tests are destructive and often provide false positive results. Here, we report on the development of a nondestructive method that could potentially be applied at the scene for differentiation of human and animal blood using attenuated total reflection Fourier transform-infrared (ATR FT-IR) spectroscopy and statistical analysis. The following species were used to build statistical models for binary human-animal blood differentiation: cat, dog, rabbit, horse, cow, pig, opossum, and raccoon. Three other species (deer, elk, and ferret) were used for external validation. A partial least squares discriminant analysis (PLSDA) was used for classification purposes and showed excellent performance in internal cross-validation (CV). The method was externally validated first using blood samples from new donors of species used in the training data set, and second using donors of new species that were not used to construct the model. Both validations showed excellent results demonstrating potential of the developed approach for nondestructive, rapid, and statistically confident discrimination between human and animal blood for forensic purposes.

Complex Chemical Data Classification and Discrimination Using Locality Preserving Partial Least Squares Discriminant Analysis

Partial least squares discriminant analysis (PLS-DA) is a well-known technique for feature extraction and discriminant analysis in chemometrics. Despite its popularity, it has been observed that PLS-DA does not automatically lead to extraction of relevant features. Feature learning and extraction depends on how well the discriminant subspace is captured. In this paper, discriminant subspace learning of chemical data is discussed from the perspective of PLS-DA and a recent extension of PLS-DA, which is known as the locality preserving partial least squares discriminant analysis (LPPLS-DA). The objective is twofold: (a) to introduce the LPPLS-DA algorithm to the chemometrics community and (b) to demonstrate the superior discrimination capabilities of LPPLS-DA and how it can be a powerful alternative to PLS-DA. Four chemical data sets are used: three spectroscopic data sets and one that contains compositional data. Comparative performances are measured based on discrimination and classification of these data sets. To compare the classification performances, the data samples are projected onto the PLS-DA and LPPLS-DA subspaces, and classification of the projected samples into one of the different groups (classes) is done using the nearest-neighbor classifier. We also compare the two techniques in data visualization (discrimination) task. The ability of LPPLS-DA to group samples from the same class while at the same time maximizing the between-class separation is clearly shown in our results. In comparison with PLS-DA, separation of data in the projected LPPLS-DA subspace is more well defined.

Raman spectroscopic detection of carotenoids in cattle skin

Carotenoids, powerful anti-oxidants, play a significant role in protecting the skin from oxidation and help in balancing the redox status of skin. This study was aimed at investigating cattle skin to identify carotenoids in the lower epidermis (grain) and dermis (corium) layers for classification using Raman spectroscopy which is a powerful technique for the detection of carotenoids in cattle skin due to the strong resonance enhancement with 532 nm laser excitation. The spectral differences identified between these two layers were quantified by the univariate analysis of Raman peak heights and partial least squares (PLS) analysis. We compared the performance of the Raman spectroscopy method with the standard method, high performance liquid chromatography. The univariate analysis results demonstrated that the lower epidermis of the skin has a higher concentration of carotenoid than dermis using the carotenoid Raman peaks at 1151 cm⁻¹ and 1518 cm⁻¹. The carotenoid Raman intensity was linearly correlated with the total carotenoid concentration determined by standard HPLC methods. Partial Least Squares Regression analysis gives excellent results with R² = 0.99. Our results indicate that Raman spectroscopy is a potential tool to determine carotenoids in cattle skin with high precision.

The lower epidermis and dermis of cattle skin was investigated for the detection of carotenoids using Raman spectroscopy.

Blood species identification based on deep learning analysis of Raman spectra

Blood analysis is an indispensable means of detection in criminal investigation, customs security and quarantine, anti-poaching of wildlife, and other incidents. Detecting the species of blood is one of the most important analyses. In order to classify species by analyzing Raman spectra of blood, a recognition method based on deep learning principle is proposed in this paper. This method can realize multi-identification blood species, by constructing a one-dimensional convolution neural network and establishing a Raman spectra database containing 20 kinds of blood. The network model is obtained through training, and then is employed to predict the testing set data. The average accuracy of blind detection is more than 97%. In this paper, we try to increase the diversity of data to improve the robustness of the model, optimize the network and adjust the hyperparameters to improve the recognition ability of the model. The evaluation results show that the deep learning model has high recognition performance to distinguish the species of blood.

Spatiotemporal Variation Characteristics of Ecosystem Service Losses in the Agro-Pastoral Ecotone of Northern China

Being subject to climate change and human intervention, the land-use pattern in the agro-pastoral ecotone of Northern China has undergone complex changes over the past few decades, which may jeopardize the provision of ecosystem services. Thus, for sustainable land management, ecosystem services should be evaluated and monitored. In this study, based on Landsat TM/ETM data, we quantitatively evaluated the losses of ecosystem service values (ESV) in three sections of the agro-pastoral ecotone from 1980-2015. The results were as follows: (1) the main characteristic of the land conversions was that a large area of grassland was converted into cultivated land in the agro-pastoral ecotone; (2) on the spatial scale, the ESV losses of the agro-pastoral ecotone can be called an "inclined surface" in the direction of the northeast to southwest, and the northeastern section of the agro-pastoral ecotone lost more ESV than the middle and northwest sections (p < 0.05), on the temporal scale, the order of losses was 1990-2000 > 1980-1990 > 2000-2015; (3) the agro-pastoral ecotone lost more ESV, which was mainly due to four kinds of land conversion, which were grassland that was transformed into cultivated land, grassland transformed into unused land, grassland transformed into built-up areas, and cultivated land transformed into built-up areas; (4) although these land conversions were curbed after the implementation of protection policies at the end of the 1990s, due to reduced precipitation and increasing temperatures, the agro-pastoral ecotone will face a more severe situation in the future; and, (5) during the period of 1990-2015, the overall dynamic processes of increasing population gradually expanded to the sparsely populated pastoral area. Therefore, we believe that human interventions are the main cause of ecological deterioration in the agro-pastoral ecotone. This study provides references for fully understanding the regional differences in the ecological and environmental effects of land use change and it helps to objectively evaluate ecological civilization construction in the agro-pastoral ecotone of Northern China.

Forensics: evidence examination via Raman spectroscopy

Forensic science can be broadly defined as the application of any of the scientific method to solving a crime. Within forensic science there are many different disciplines, however, for the majority of them, five main concepts shape the nature of forensic examination: transfer, identification, classification/individualization, association, and reconstruction. The concepts of identification, classification/individualization, and association rely greatly on analytical chemistry techniques. It is, therefore, no stretch to see how one of the rising stars of analytical chemistry techniques, Raman spectroscopy, could be of use. Raman spectroscopy is known for needing a small amount of sample, being non-destructive, and very substance specific, all of which make it ideal for analyzing crime scene evidence. The purpose of this chapter is to show the state of new methods development for forensic applications based on Raman spectroscopy published between 2015 and 2017.

Fourier based partial least squares algorithm: new insight into influence of spectral shift in "frequency domain"

Developments in analytical chemistry technology, especially the combination between the partial least squares and spectroscopy, have contributed significantly to predicting the chemical concentrations and discriminating similar chemical analytes. However, spectral shift is an unwanted but inevitable factor for the spectroscopic analyzer, especially in practical application, which decreases the method's accuracy and stability. To remove the term of spectral shift completely and increase the robustness of spectroscopic analysis method, Fourier transform based partial least squares method was proposed. The approach used Fourier transform first to transform the spectral shift in the "time domain" to the phase term in the "frequency domain." The module of the Fourier transformed spectra was then calculated. As a result, the phase term was removed (the module of the phase term is 1), which means the spectral shift term was removed completely. Finally, the spectra modules were used to build the model and validate. The approach's advantages are: (i) that the approach provides a new insight to treat the spectral shift in spectroscopic analyzer; (ii) that the model is insensitive to spectral shift; (iii) that the approach makes partial least squares combined with spectroscopy more suitable for practical application, rather than lab experiment, because spectral shift is permitted, which means the decreased requirements of measure environment. As an example, blood species discrimination, using Raman spectroscopy, was used in order to demonstrate this approach's effectiveness.

Dual-model analysis for improving the discrimination performance of human and nonhuman blood based on Raman spectroscopy

The discrimination accuracy for human and nonhuman blood is important for customs inspection and forensic applications. Recently, Raman spectroscopy has shown effectiveness in analyzing blood droplets and stains with an excitation wavelength of 785 nm. However, the discrimination of liquid whole blood in a vacuum blood tube using Raman spectroscopy, which is a form of noncontact and nondestructive detection, has not been achieved. An excitation wavelength of 532 nm was chosen to avoid the fluorescent background of the blood tube, at the cost of reduced spectroscopic information and discrimination accuracy. To improve the accuracy and true positive rate (TPR) for human blood, a dual-model analysis method is proposed. First, model 1 was used to discriminate human-unlike nonhuman blood. Model 2 was then used to discriminate human-like nonhuman blood from the "human blood" obtained by model 1. A total of 332 Raman spectra from 10 species were used to build and validate the model. A blind test and external validation demonstrated the effectiveness of the model. Compared with the results obtained by the single partial least-squares model, the discrimination performance was improved. The total accuracy and TPR, which are highly important for practical applications, increased to 99.1% and 97.4% from 87.2% and 90.6%, respectively.

Discrimination of human and nonhuman blood using Raman spectroscopy with self-reference algorithm

We report a self-reference algorithm to discriminate human and nonhuman blood by calculating the ratios of identification Raman peaks to reference Raman peaks and choosing appropriate threshold values. The influence of using different reference peaks and identification peaks was analyzed in detail. The Raman peak at 1003  cm-1 was proved to be a stable reference peak to avoid the influencing factors, such as the incident laser intensity and the amount of sample. The Raman peak at 1341  cm-1 was found to be an efficient identification peak, which indicates that the difference between human and nonhuman blood results from the C-H bend in tryptophan. The comparison between self-reference algorithm and partial least square method was made. It was found that the self-reference algorithm not only obtained the discrimination results with the same accuracy, but also provided information on the difference of chemical composition. In addition, the performance of self-reference algorithm whose true positive rate is 100% is significant for customs inspection to avoid genetic disclosure and forensic science.