Differentiation of human blood from animal blood using Raman spectroscopy: A survey of forensically relevant species

Identification of Bloodstains by Species Using Extreme Learning Machine and Hyperspectral Imaging Technology

How to identify bloodstains and obtain some potential evidence is of great significance for solving criminal cases. First, the spectral data of different species of bloodstain samples (human blood and animal blood) were acquired by using a hyperspectral imager. Then, an extreme learning machine (ELM) algorithm was used to build the training models of different species of bloodstain samples. Meanwhile, two traditional support vector machine and random forest classification algorithms were also compared with the ELM algorithm. The prediction results showed that the precision, sensitivity, specificity, and F1 score of the ELM algorithm were the highest. This indicates that hyperspectral technology, together with an ELM algorithm, could identify bloodstain species rapidly, non-destructively, and accurately. It has provided a new technical reference for bloodstain detection and identification.

RamanFormer: A Transformer-Based Quantification Approach for Raman Mixture Components

Raman spectroscopy is a noninvasive technique to identify materials by their unique molecular vibrational fingerprints. However, distinguishing and quantifying components in mixtures present challenges due to overlapping spectra, especially when components share similar features. This study presents "RamanFormer", a transformer-based model designed to enhance the analysis of Raman spectroscopy data. By effectively managing sequential data and integrating self-attention mechanisms, RamanFormer identifies and quantifies components in chemical mixtures with high precision, achieving a mean absolute error of 1.4% and a root mean squared error of 1.6%, significantly outperforming traditional methods such as least squares, MLP, VGG11, and ResNet50. Tested extensively on binary and ternary mixtures under varying conditions, including noise levels with a signal-to-noise ratio of up to 10 dB, RamanFormer proves to be a robust tool, improving the reliability of material identification and broadening the application of Raman spectroscopy in fields, such as material science, forensics, and biomedical diagnostics.

The Evaluation of Artificial Intelligence Technology for the Differentiation of Fresh Human Blood Cells From Other Species' Blood in the Investigation of Crime Scenes

OBJECTIVES

The current study used the deep machine learning approach to differentiate human blood specimens from cow, goat, and chicken blood stains based on cell morphology.

METHODS

A total of 1,955 known Giemsa-stained digitized images were acquired from the blood of humans, cows, goats, and chickens. To train the deep learning models, the well-known VGG16, Resnet18, and Resnet34 algorithms were used. Based on the image analysis, confusion matrices were generated.

RESULTS

Findings showed that the F1 score for the chicken, cow, goat, and human classes were all equal to 1.0 for each of the three algorithms. The Matthews correlation coefficient (MCC) was 1 for chickens, cows, and humans in all three algorithms, while the MCC score was 0.989 for goats by ResNet18, and it was 0.994 for both ResNet34 and VGG16 algorithms. The three algorithms showed 100% sensitivity, specificity, and positive and negative predictive values for the human, cow, and chicken cells. For the goat cells, the data showed 100% sensitivity and negative predictive values with specificity and positive predictive values ranging from 98.5% to 99.6%.

CONCLUSION

These data showed the importance of deep learning as a potential tool for the differentiation of the species of origin of fresh crime scene blood stains.

Near-infrared excitation Raman analysis of Underlying colorants on redyed fabric

Forensic analysis of fabric is often critically important to establish a relationship between a suspect and a crime scene or demonstrate the absence of such connections. Most of commercially available fabric is colored with primarily organic colorants. These dye substances are highly fluorescent, which limits the use to conventional Raman spectroscopy for the analysis of the colorant content of fabric. At the same time, elucidation of the chemical composition of dyes in fabrics can be used to advance the importance of this physical piece of evidence for forensic research. Our recent findings showed that near-infrared excitation Raman spectroscopy (NIeRS) could be used to overcome this limitation. However, it remains unclear to what extent NIeRS could be used to identify the presence of several different colorants on fabric, as well as utilize for the analysis of dyes on fabric contaminated with paints. In this study, we utilized a hand-held NIeRS instrument to ex-amine re-colored cotton fabric and cotton fabric with household paints applied on it. Our results indicate that NIeRS coupled with chemometrics highly accurately identify the presence of several colorants on cotton. We also found that the presence of paint fully obscures the ability of NIeRS to extract the information about the dye content of the fabric. These results expand our understanding of the use of NIeRS in the forensic analysis of colored fabric.

Use of Raman spectroscopy to study rat lung tissues for distinguishing asphyxia from sudden cardiac death

Determining asphyxia as the cause of death is crucial but is based on an exclusive strategy because it lacks sensitive and specific morphological characteristics in forensic practice. In some cases where the deceased has underlying heart disease, differentiation between asphyxia and sudden cardiac death (SCD) as the primary cause of death can be challenging. Herein, Raman spectroscopy was employed to detect pulmonary biochemical differences to discriminate asphyxia from SCD in rat models. Thirty-two rats were used to build asphyxia and SCD models, with lung samples collected immediately or 24 h after death. Twenty Raman spectra were collected for each lung sample, and 640 spectra were obtained for further data preprocessing and analysis. The results showed that different biochemical alterations existed in the lung tissues of the rats that died from asphyxia and SCD and could be used to distinguish between the two causes of death. Moreover, we screened and used 8 of the 11 main differential spectral features that maintained their significant differences at 24 h after death to successfully determine the cause of death, even with decomposition and autolysis. Eventually, seven prevalent machine learning classification algorithms were employed to establish classification models, among which the support vector machine exhibited the best performance, with an area under the curve value of 0.9851 in external validation. This study shows the promise of Raman spectroscopy combined with machine learning algorithms to investigate differential biochemical alterations originating from different deaths to aid determining the cause of death in forensic practice.

Species identification of adult ixodid ticks by Raman spectroscopy of their feces

BACKGROUND

Ticks and tick-borne diseases pose significant challenges to cattle production, thus the species identification of ticks and knowledge on their presence, abundance, and dispersal are necessary for the development of effective control measures. The standard method of inspection for the presence of ticks is the visual and physical examination of restrained animals, but the limitations of human sight and touch can allow larval, nymphal, and unfed adult ticks to remain undetected due to their small size and site of attachment. However, Raman spectroscopy, an analytical tool widely used in agriculture and other sectors, shows promise for the identification of tick species in infested cattle. Raman spectroscopy is a non-invasive and efficient method that employs the interaction between molecules and light for the identification of the molecular constituents of specimens.

METHODS

Raman spectroscopy was employed to analyze the structure and composition of tick feces deposited on host skin and hair during blood-feeding. Feces of 12 species from a total of five genera and one subgenus of ixodid ticks were examined. Spectral data were subjected to partial least squares discriminant analysis, a machine-learning model. We also used Raman spectroscopy and the same analytical procedures to compare and evaluate feces of the horn fly Haematobia irritans after it fed on cattle.

RESULTS

Five genera and one sub-genus at overall true prediction rates ranging from 92.3 to 100% were identified from the Raman spectroscopy data of the tick feces. At the species level, Dermacentor albipictus, Dermacentor andersoni and Dermacentor variabilis at overall true prediction rates of 100, 99.3 and 100%, respectively, were identified. There were distinct differences between horn fly and tick feces with respect to blood and guanine vibrational frequencies. The overall true prediction rate for the separation of tick and horn fly feces was 98%.

CONCLUSIONS

Our findings highlight the utility of Raman spectroscopy for the reliable identification of tick species from their feces, and its potential application for the identification of ticks from infested cattle in the field.

Non-Destructive Identification of Dyes on Fabric Using Near-Infrared Raman Spectroscopy

Fabric is a commonly found piece of physical evidence at most crime scenes. Forensic analysis of fabric is typically performed via microscopic examination. This subjective approach is primarily based on pattern recognition and, therefore, is often inconclusive. Most of the fabric material found at crime scenes is colored. One may expect that a confirmatory identification of dyes can be used to enhance the reliability of the forensic analysis of fabric. In this study, we investigated the potential of near-infrared Raman spectroscopy (NIRS) in the confirmatory, non-invasive, and non-destructive identification of 15 different dyes on cotton. We found that NIRS was able to resolve the vibrational fingerprints of all 15 colorants. Using partial-squared discriminant analysis (PLS-DA), we showed that NIRS enabled ~100% accurate identification of dyes based on their vibrational signatures. These findings open a new avenue for the robust and reliable forensic analysis of dyes on fabric directly at crime scenes. Main conclusion: a hand-held Raman spectrometer and partial least square discriminant analysis (PLS-DA) approaches enable highly accurate identification of dyes on fabric.

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.

Applications of Raman spectroscopy in the analysis of biological evidence

During the past few decades, Raman spectroscopy has progressed and captivated added attention in the field of science. However, the application of Raman spectroscopy is not limited to the field of forensic science and analytical chemistry; it is one of the emerging spectroscopic techniques, utilized in the field of forensic science which in turn could be a supporting tool in the law and justice system. The advantage of Raman spectroscopy over the other conventional techniques is that it is rapid, reliable, and non-destructive in nature with minimal or no sample preparation. The quantitative and qualitative analysis of evidence from biological and non-biological origins could easily be performed by using Raman spectroscopy. The forensic domain is highly complex with multidisciplinary branches, and therefore a plethora of techniques are utilized for the detection, identification, and differentiation of innumerable pieces of evidence for the purpose of law and justice. Herein, a systematic review is carried out on the application of Raman spectroscopy in the realm of forensic biology and serology considering its usefulness in practical perspectives. This review paper highlights the significance of modern techniques, including micro-Raman spectroscopy, confocal Raman spectroscopy, surface-enhanced Raman spectroscopy, and paper-based surface-enhanced Raman spectroscopy, in the field of Raman spectroscopy. These techniques have demonstrated notable advancements in terms of their applications and capabilities. Furthermore, to comprehensively capture the progress in the development of Raman spectroscopy, all the published papers which could be retrieved from the available databases from the year 2007 to 2022 were incorporated.

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.

On the Application of Microfluidic-Based Technologies in Forensics: A Review

Microfluidic technology is a powerful tool to enable the rapid, accurate, and on-site analysis of forensically relevant evidence on a crime scene. This review paper provides a summary on the application of this technology in various forensic investigation fields spanning from forensic serology and human identification to discriminating and analyzing diverse classes of drugs and explosives. Each aspect is further explained by providing a short summary on general forensic workflow and investigations for body fluid identification as well as through the analysis of drugs and explosives. Microfluidic technology, including fabrication methodologies, materials, and working modules, are touched upon. Finally, the current shortcomings on the implementation of the microfluidic technology in the forensic field are discussed along with the future perspectives.

Machine Learning for Prediction, Classification, and Identification of Immobilized Enzymes for Biocatalysis

BACKGROUND

Enzyme immobilization is a beneficial component involved in biocatalytic strategies. Understanding and evaluating the enzyme immobilization system plays an important role in the successful development and implementation of the biocatalysis route. Ensuring the implementation of a successful enzyme immobilization process is vital for realizing a highly functioning and well suited biocatalytic process within pharmaceutical development.

AIM

To develop a method which can accurately and objectively identify and classify differences within enzyme immobilization systems, sample preparation methods, and data collection parameters.

METHODS

Raman hyperspectral imaging was used to obtain a total of eight spectral data sets from enzyme immobilization samples. Partial least squares discriminant analysis (PLS-DA) was used to classify and identify the samples based on their differences.

RESULTS

Several two-class, four-class, and eight-class PLS-DA models were built to classify the different sample data sets. All models reached between 92-100% accuracy after cross-validation and external validation, illustrating great success of the models for identifying differences between the samples.

CONCLUSION

Raman hyperspectral imaging with machine learning can be used to investigate, interpret, and classify different data collection parameters, sample preparation methods, and enzyme immobilization supports, providing crucial insight into enzyme immobilization process development.

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.

A novel Raman spectroscopic method for detecting traces of blood on an interfering substrate

Traces of body fluids discovered at a crime scene are a primary source of DNA evidence. Raman spectroscopy is a promising universal technique for identifying biological stains for forensic purposes. The advantages of this method include the ability to work with trace amounts, high chemical specificity, no need for sample preparation and the nondestructive nature. However, common substrate interference limits the practical application of this novel technology. To overcome this limitation, two approaches called "Reducing a spectrum complexity" (RSC) and "Multivariate curve resolution combined with the additions method" (MCRAD) were investigated for detecting bloodstains on several common substrates. In the latter approach, the experimental spectra were "titrated" numerically with a known spectrum of a targeted component. The advantages and disadvantages of both methods for practical forensics were evaluated. In addition, a hierarchical approach to reduce the possibility of false positives was suggested.

Self-supervised learning for inter-laboratory variation minimization in surface-enhanced Raman scattering spectroscopy

Surface-enhanced Raman scattering (SERS) spectroscopy is still considered poorly reproducible despite its numerous advantages and is not a sufficiently robust analytical technique for routine implementation outside of academia. In this article, we present a self-supervised deep learning-based information fusion technique to minimize the variance in the SERS measurements of multiple laboratories for the same target analyte. In particular, a variation minimization model, coined the minimum-variance network (MVNet), is designed. Moreover, a linear regression model is trained using the output of the proposed MVNet. The proposed model showed improved performance in predicting the concentration of the unseen target analyte. The linear regression model trained on the output of the proposed model was evaluated by several well-known metrics, such as root mean square error of prediction (RMSEP), BIAS, standard error of prediction (SEP), and coefficient of determination (R²). The leave-one-lab-out cross-validation (LOLABO-CV) results indicate that the MVNet also minimizes the variance of completely unseen laboratory datasets while improving the reproducibility and linear fit of the regression model. The Python implementation of MVNet and the code for the analysis can be found on the GitHub page https://github.com/psychemistz/MVNet.

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.

Effects of crime scene contaminants on surface-enhanced Raman analysis of hair

Forensic analysis of hair is important as hair is one of the most commonly examined forms of trace evidence found at crime scenes. A growing body of evidence suggests that surface-enhanced Raman spectroscopy (SERS), a label-free and non-destructive analytical technique, can be used to detect and identify artificial colorants present on hair. However, hair collected at crime scenes is often contaminated by substances of biological and non-biological origin present at such locations. In this study, we investigate the extent to which four contaminants, saliva, blood, dirt, and bleach can alter the accuracy of SERS-based detection and identification of both permanent and semi-permanent colorants present on hair. Our findings show that saliva and dirt reduce the intensity of the colorants' signals but do not obscure their detection and identification. At the same time, an exposure of the colored hair to bleach or the presence of blood eliminates SERS-based analysis of artificial dyes present on such samples. We identified the procedure that can be used to remove blood contamination, which, in turn, enables identification of the hair colorants on such pre-cleaned samples. However, bleach treatment irreversibly eliminates SERS-based detection of artificial colorants on hair. These findings expand our understandings about the potential of SERS in forensic investigation of colorants on trace hair evidence.

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.

Raman-based identification of tick species (Ixodidae) by spectroscopic analysis of their feces

Ticks are blood-feeding parasites that vector a large number of pathogens of medical and veterinary importance. There are strong connections between tick and pathogen species. Timely detection of certain tick species on cattle can cease the spread of numerous devastating diseases such as Bovine babiesiosis and anaplasmosis. Detection of ticks is currently performed by slow and laborious scout-based inspection of cattle. In this study, we investigated the possibility of identification of tick species (Ixodidae) based on spectroscopic signatures of their feces. We collected Raman spectra from individual grains of feces of seven different species of ticks. Our results show that Raman spectroscopy (RS) allows for highly accurate (above 90%) differentiation between tick species. Furthermore, RS can be used to predict the tick developmental stage and differentiate between nymphs, meta-nymphs and adult ticks. We have also demonstrated that diagnostics of tick species present on cattle can be achieved using a hand-held Raman spectrometer. These findings show that RS can be used for non-invasive, non-destructive and confirmatory on-site analysis of tick species present on cattle.

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.

Machine Learning-Based Heavy Metal Ion Detection Using Surface-Enhanced Raman Spectroscopy

Surface-Enhanced Raman Spectroscopy (SERS) is often used for heavy metal ion detection. However, large variations in signal strength, spectral profile, and nonlinearity of measurements often cause problems that produce varying results. It raises concerns about the reproducibility of the results. Consequently, the manual classification of the SERS spectrum requires carefully controlled experimentation that further hinders the large-scale adaptation. Recent advances in machine learning offer decent opportunities to address these issues. However, well-documented procedures for model development and evaluation, as well as benchmark datasets, are missing. Towards this end, we provide the SERS spectral benchmark dataset of lead(II) nitride (Pb(NO3)2) for a heavy metal ion detection task and evaluate the classification performance of several machine learning models. We also perform a comparative study to find the best combination between the preprocessing methods and the machine learning models. The proposed model can successfully identify the Pb(NO3)2 molecule from SERS measurements of independent test experiments. In particular, the proposed model shows an 84.6% balanced accuracy for the cross-batch testing task.

Recent advances of vibrational spectroscopy and chemometrics for forensic biological analysis

Biological materials found at a crime scene are crucially important evidence for forensic investigation because they provide contextual information about a crime and can be linked to the donor-individuals through combination with DNA analysis. Applications of vibrational spectroscopy to forensic biological analysis have been emerging because of its advantageous characteristics such as the non-destructivity, rapid measurement, and quantitative evaluation, compared to most current methods based on histological observation or biochemical techniques. This review presents an overview of recent developments in vibrational spectroscopy for forensic biological analysis. We also emphasize chemometric techniques, which can elicit reliable and advanced analytical outputs from highly complex spectral data from forensic biological materials. The analytical subjects addressed herein include body fluids, hair, soft tissue, bones, and bioagents. Promising applications for various analytical purposes in forensic biology are presented. Simultaneously, future avenues of study requiring further investigation are discussed.

SERSNet: Surface-Enhanced Raman Spectroscopy Based Biomolecule Detection Using Deep Neural Network

Surface-Enhanced Raman Spectroscopy (SERS)-based biomolecule detection has been a challenge due to large variations in signal intensity, spectral profile, and nonlinearity. Recent advances in machine learning offer great opportunities to address these issues. However, well-documented procedures for model development and evaluation, as well as benchmark datasets, are lacking. Towards this end, we provide the SERS spectral benchmark dataset of Rhodamine 6G (R6G) for a molecule detection task and evaluate the classification performance of several machine learning models. We also perform a comparative study to find the best combination between the preprocessing methods and the machine learning models. Our best model, coined as the SERSNet, robustly identifies R6G molecule with excellent independent test performance. In particular, SERSNet shows 95.9% balanced accuracy for the cross-batch testing task.

Recent Advances in Electrochemical Biosensors: Applications, Challenges, and Future Scope

The electrochemical biosensors are a class of biosensors which convert biological information such as analyte concentration that is a biological recognition element (biochemical receptor) into current or voltage. Electrochemical biosensors depict propitious diagnostic technology which can detect biomarkers in body fluids such as sweat, blood, feces, or urine. Combinations of suitable immobilization techniques with effective transducers give rise to an efficient biosensor. They have been employed in the food industry, medical sciences, defense, studying plant biology, etc. While sensing complex structures and entities, a large data is obtained, and it becomes difficult to manually interpret all the data. Machine learning helps in interpreting large sensing data. In the case of biosensors, the presence of impurity affects the performance of the sensor and machine learning helps in removing signals obtained from the contaminants to obtain a high sensitivity. In this review, we discuss different types of biosensors along with their applications and the benefits of machine learning. This is followed by a discussion on the challenges, missing gaps in the knowledge, and solutions in the field of electrochemical biosensors. This review aims to serve as a valuable resource for scientists and engineers entering the interdisciplinary field of electrochemical biosensors. Furthermore, this review provides insight into the type of electrochemical biosensors, their applications, the importance of machine learning (ML) in biosensing, and challenges and future outlook.

Development of Crime Scene Intelligence Using a Hand-Held Raman Spectrometer and Transfer Learning

The classification of ignitable liquids, such as gasoline, is critical crime scene intelligence to assist arson investigations. Rapid field gasoline classification is challenging because the current forensic testing standard requires gas chromatography-mass spectrometry analysis of evidence in an accredited laboratory. In this work, we reported a new intelligent analytical platform for field identification and classification of gasoline evidence. A hand-held Raman spectrometer was utilized to collect Raman spectra of reference gasoline samples with various octane numbers. The Raman spectrum pattern was converted into image presentations by continuous wavelet transformation (CWT) to facilitate artificial intelligence development using the transfer learning technique. GoogLeNet, a pretrained convolutional neural network (CNN), was adapted to train the classification model. Six different classification models were also developed from the same data set using conventional machine learning algorithms to evaluate the performance of our new approach. The experimental results indicated that the pretrained CNN model developed by our new data workflow outperformed other models in several performance benchmarks, such as accuracy, precision, recall, F1, Cohen's Kappa, and Matthews correlation coefficient. When the transfer learning model was challenged with the data collected from weathered gasoline samples, the classifier could still offer 73 and 53% accuracy for 50 and 25% weathered gasoline samples, respectively. In conclusion, wavelet transforms combined with transfer learning successfully processed and classified complex Raman spectral data without feature engineering. We envision that this nondestructive, automated, and accurate platform will accelerate crime scene intelligence development based on evidence's chemical signatures detected by hand-held Raman spectrometers.

Chemometrics in forensic science: approaches and applications

Forensic investigations are often reliant on physical evidence to reconstruct events surrounding a crime. However, there remains a need for more objective approaches to evidential interpretation, along with rigorously validated procedures for handling, storage and analysis. Chemometrics has been recognised as a powerful tool within forensic science for interpretation and optimisation of analytical procedures. However, careful consideration must be given to factors such as sampling, validation and underpinning study design. This tutorial review aims to provide an accessible overview of chemometric methods within the context of forensic science. The review begins with an overview of selected chemometric techniques, followed by a broad review of studies demonstrating the utility of chemometrics across various forensic disciplines. The tutorial review ends with the discussion of the challenges and emerging trends in this rapidly growing field.

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.

Machine Learning-Assisted Raman Spectroscopy for pH and Lactate Sensing in Body Fluids

This study presents the combination of Raman spectroscopy with machine learning algorithms as a prospective diagnostic tool capable of detecting and monitoring relevant variations of pH and lactate as recognized biomarkers of several pathologies. The applicability of the method proposed here is tested both in vitro and ex vivo. In a first step, Raman spectra of aqueous solutions are evaluated for the identification of characteristic patterns resulting from changes in pH or in the concentration of lactate. The method is further validated with blood and plasma samples. Principal component analysis is used to highlight the relevant features that differentiate the Raman spectra regarding their pH and concentration of lactate. Partial least squares regression models are developed to capture and model the spectral variability of the Raman spectra. The performance of these predictive regression models is demonstrated by clinically accurate predictions of pH and lactate from unknown samples in the physiologically relevant range. These results prove the potential of our method to develop a noninvasive technology, based on Raman spectroscopy, for continuous monitoring of pH and lactate in vivo.

Direct differentiation of whole blood for forensic serology analysis by thread spray mass spectrometry

Direct analysis of whole blood on bloodstained textiles is achieved with thread spray mass spectrometry (MS). This capability satisfies investigators' first priority in crime scene investigations, which is determining if a stain is blood. This thread spray method explores the use of evidentiary fabric threads for rapid determination of hemoglobin directly from whole blood within textiles without prior extraction steps. The multiplicity of information that can be derived from the thread spray MS method distinguishes it from the current presumptive Bluestar® method, by enabling the detection of hemoglobin (both α- and β-chains), the heme co-factor and lipids all from a single blood sample. Lipid composition was found to differ for blood samples originating from human, canine, and horse species. The robustness of the thread spray MS method as a forensic analytical platform was evaluated in three ways: (1) its successful applicability to samples previously tested by the Bluestar® presumptive method, offering a confirmatory test without prior sample pre-treatment, (2) successful detection of heme from previously washed fabrics, which demonstrated the unprecedented sensitivity of the thread spray method, and (3) the ability to analyze samples stored under ambient conditions for up to 30 days. These results attest to the potential capabilities of the thread spray MS platform in forensic serology, and its application for direct analysis of evidentiary garments, which confer the advantages of rapid analysis and the reduction of the false positive and negative identification rates for blood on textiles.

Postmortem Diagnosis of Fatal Hypothermia by Fourier Transform Infrared Spectroscopic Analysis of Edema Fluid in Formalin-Fixed, Paraffin-Embedded Lung Tissues

The goal of this study was to investigate whether pulmonary edema could become a specific diagnostic marker for fatal hypothermia using Fourier transform infrared (FTIR) spectroscopy in combination with chemometrics. The spectral profile analysis indicated that hypothermia fatalities associated with pulmonary edema fluid contained more β-sheet protein conformational structures than the control causes of death, which included sudden cardiac death, brain injury, cerebrovascular disease, mechanical asphyxiation, intoxication, and drowning. Subsequently, the results of principal component analysis (PCA) further revealed that the content of β-sheet protein conformational structures in the pulmonary edema fluid was the main discriminatory marker between fatal hypothermia and the other causes of death. Ultimately, a robust postmortem diagnostic model for fatal hypothermia using a partial least-squares discriminant analysis (PLS-DA) algorithm was constructed. Pulmonary edema fluid spectra collected from eight new forensic autopsy cases that did not participate in the construction of the diagnostic model were predicted using the model. The results showed the causes of death of all these eight cases were correctly classified. In conclusion, this preliminary study demonstrates that FTIR spectroscopy in combination with chemometrics could be a promising approach for the postmortem diagnosis of fatal hypothermia.

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.

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.

Error analysis of the spectral shift for partial least squares models in Raman spectroscopy

Raman spectroscopy paired with the partial least squares (PLS) method is commonly used for quantitative or qualitative analysis of complex samples. However, spectral shift induced by different Raman spectroscopy, different environment or different measured time will decrease the accuracy of the PLS model. In this work, the processing algorithms that improve the accuracy by removing the noise, background and varying sources of other spectral interference were first reviewed. The error induced by the spectral shift was analyzed and the formulas of the error were derived. The formulas were then used to calculate the theoretical error in the example of discriminating human and nonhuman blood. A comparison of the actual errors obtained from the mathematical method and experiment with the theoretical value demonstrated the effectiveness of the equation. The compensation for nonhuman blood according to the average error demonstrated the improvement of the accuracy. Finally, the non-uniform sampling of the Raman shift by charge-coupled device (CCD) was considered in the error equation. An accurate error equation was obtained. This work could help improve the stability of PLS models in the case of the spectral shift of the spectrometer in Raman spectroscopy.