Rapid on-site identification of pesticide residues in tea by one-dimensional convolutional neural network coupled with surface-enhanced Raman scattering

Rapid identification and quantitative analysis of malachite green in fish via SERS and 1D convolutional neural network

Rapid and quantitative detection of malachite green (MG) in aquaculture products is very important for safety assurance in food supply. Here, we develop a point-of-care testing (POCT) platform that combines a flexible and transparent surface-enhanced Raman scattering (SERS) substrate with deep learning network for achieving rapid and quantitative detection of MG in fish. The flexible and transparent SERS substrate was prepared by depositing silver (Ag) film on the polydimethylsiloxane (PDMS) film using laser molecular beam epitaxy (LMBE) technique. The wrinkled Ag NPs@PDMS film exhibits high SERS activity, excellent reproducibility and good mechanical stability. Additionally, the fast in situ detection of MG residues onfishscales was achieved by using the wrinkled Ag NPs/PDMS film and a portable Raman spectrometer, with a minimum detectable concentration of 10-6 M. Subsequently, a one-dimensional convolutional neural network (1D CNN) model was constructed for rapid quantification of MG concentration. The results demonstrated that the 1D CNN quantitative analysis model possessed superior predictive performance, with a coefficient of determination (R2) of 0.9947 and a mean squared error (MSE) of 0.0104. The proposed POCT platform, integrating a transparent flexible SERS substrate, a portable Raman spectrometer and a 1D CNN model, provides an efficient strategy for rapid identification and quantitative analysis of MG in fish.

Identification of surface-enhanced Raman spectroscopy using hybrid transformer network

Surface-enhanced Raman Spectroscopy (SERS) is extensively implemented in drug detection due to its sensitivity and non-destructive nature. Deep learning methods, which are represented by convolutional neural network (CNN), have been widely applied in identifying the spectra from SERS for powerful learning ability. However, the local receptive field of CNN limits the feature extraction of sequential spectra for suppressing the analysis results. In this study, a hybrid Transformer network, TMNet, was developed to identify SERS spectra by integrating the Transformer encoder and the multi-layer perceptron. The Transformer encoder can obtain precise feature representations of sequential spectra with the aid of self-attention, and the multi-layer perceptron efficiently transforms the representations to the final identification results. TMNet performed excellently, with identification accuracies of 99.07% for the spectra of hair containing drugs and 97.12% for those of urine containing drugs. For the spectra with additive white Gaussian, baseline background, and mixed noises, TMNet still exhibited the best performance among all the methods. Overall, the proposed method can accurately identify SERS spectra with outstanding noise resistance and excellent generalization and holds great potential for the analysis of other spectroscopy data.

Enhanced data preprocessing with novel window function in Raman spectroscopy: Leveraging feature selection and machine learning for raspberry origin identification

In this study, a simple and accurate approach is proposed for enhancing the origin identification of raspberry samples using a combination of innovative Raman spectral preprocessing techniques, feature selection, and machine learning algorithms. Window function was creatively introduced and combined with baseline removal technique to preprocess the Raman spectral data, reducing the dimensionality of the raw data and ensuring the quality of the processed data. An optimization process was conducted to determine the optimal parameter for the window function, resulting in a binning window width of 5 that yielded the highest accuracy. After applying three feature selection techniques, it was found that the information gain model had the best performance in extracting discriminative spectral features. Finally, ten different machine learning algorithms were employed to construct predictive models, and the optimal models were selected. Linear Support Vector Classifier (LinearSVC), Multi-Layer Perceptron Classifier (MLPClassifier), and Linear Discriminant Analysis (LDA) achieve accuracy, precision, recall, and F1 values above 0.96, while the Random Vector Functional Link Network Classifier (RVFLClassifier) surpasses 0.93 for these performance metrics. These results demonstrate the effectiveness of the proposed approach in identifying the origin of raspberry samples with high accuracy and robustness, providing a valuable tool for agricultural product authentication and quality control.

A review on nanomaterial-based SERS substrates for sustainable agriculture

The agricultural sector plays a pivotal role in driving the economy of many developing countries. Any dent in this economical structure may have a severe impact on a country's population. With rising climate change and increasing pollution, the agricultural sector is experiencing significant damage. Over time this cumulative damage will affect the integrity of food crops and create food security issues around the world. Therefore, an early warning system is needed to detect possible stress on food crops. Here we present a review of the recent developments in nanomaterial-based Surface Enhanced Raman Spectroscopy (SERS) substrates which could be utilized to monitor agricultural crop responses to natural and anthropogenic stress. Initially, our review delves into diverse and cost-effective strategies for fabricating SERS substrates, emphasizing their intelligent utilization across various agricultural scenarios. In the second phase of our review, we spotlight the specific application of SERS in addressing critical food security issues. By detecting nutrients, hormones, and effector molecules in plants, SERS provides valuable insights into plant health. Furthermore, our exploration extends to the detection of contaminants, chemicals, and foodborne pathogens within plants, showcasing the versatility of SERS in ensuring food safety. The cumulative knowledge derived from these discussions illustrates the transformative potential of SERS in bolstering the agricultural economy. By enhancing precision in nutrient management, monitoring plant health, and enabling rapid detection of harmful substances, SERS emerges as a pivotal tool in promoting sustainable and secure agricultural practices. Its integration into agricultural processes not only augments productivity but also establishes a robust defence against potential threats to crop yield and food quality. As SERS continues to evolve, its role in shaping the future of agriculture becomes increasingly pronounced, promising a paradigm shift in how we approach and address challenges in food production and safety.

RamanSPy: An Open-Source Python Package for Integrative Raman Spectroscopy Data Analysis

Raman spectroscopy is a nondestructive and label-free chemical analysis technique, which plays a key role in the analysis and discovery cycle of various branches of science. Nonetheless, progress in Raman spectroscopic analysis is still impeded by the lack of software, methodological and data standardization, and the ensuing fragmentation and lack of reproducibility of analysis workflows thereof. To address these issues, we introduce RamanSPy, an open-source Python package for Raman spectroscopic research and analysis. RamanSPy provides a comprehensive library of tools for spectroscopic analysis that supports day-to-day tasks, integrative analyses, the development of methods and protocols, and the integration of advanced data analytics. RamanSPy is modular and open source, not tied to a particular technology or data format, and can be readily interfaced with the burgeoning ecosystem for data science, statistical analysis, and machine learning in Python. RamanSPy is hosted at https://github.com/barahona-research-group/RamanSPy, supplemented with extended online documentation, available at https://ramanspy.readthedocs.io, that includes tutorials, example applications, and details about the real-world research applications presented in this paper.

Detection and Identification of Pesticides in Fruits Coupling to an Au-Au Nanorod Array SERS Substrate and RF-1D-CNN Model Analysis

In this research, a method was developed for fabricating Au-Au nanorod array substrates through the deposition of large-area Au nanostructures on an Au nanorod array using a galvanic cell reaction. The incorporation of a granular structure enhanced both the number and intensity of surface-enhanced Raman scattering (SERS) hot spots on the substrate, thereby elevating the SERS performance beyond that of substrates composed solely of an Au nanorod. Calculations using the finite difference time domain method confirmed the generation of a strong electromagnetic field around the nanoparticles. Motivated by the electromotive force, Au ions in the chloroauric acid solution were reduced to form nanostructures on the nanorod array. The size and distribution density of these granular nanostructures could be modulated by varying the reaction time and the concentration of chloroauric acid. The resulting Au-Au nanorod array substrate exhibited an active, uniform, and reproducible SERS effect. With 1,2-bis(4-pyridyl)ethylene as the probe molecule, the detection sensitivity of the Au-Au nanorod array substrate was enhanced to 10-11 M, improving by five orders of magnitude over the substrate consisting only of an Au nanorod array. For a practical application, this substrate was utilized for the detection of pesticides, including thiram, thiabendazole, carbendazim, and phosmet, within the concentration range of 10-4 to 5 × 10-7 M. An analytical model combining a random forest and a one-dimensional convolutional neural network, referring to the important variable-one-dimensional convolutional neural network model, was developed for the precise identification of thiram. This approach demonstrated significant potential for biochemical sensing and rapid on-site identification.

Qualitative and quantitative studies of phthalates in extra virgin olive oil (EVOO) by surface-enhanced Raman spectroscopy (SERS) combined with long short term memory (LSTM) neural network

Phthalates are commonly used plasticizers in the plastics industry, and have received extensive attention due to their reproductive toxicity. Since phthalates are lipophilic solutions, phthalates can easily migrate from packaging to edible oils. This study synthesized stable and sensitive Gold Nanostars as SERS substrates to conduct qualitative and quantitative analysis of two common phthalates, dibutyl phthalate and di(2-ethylhexyl) phthalate. Two ethanol standard solutions and actual oil solutions of phthalates at different concentrations (10, 5, 1, 0.5, 0.1, 0.02 mg/kg) were prepared. After dimension reduction, LSTM achieved the accuracy of 98% for pure EVOO and EVOO adulterated with different types of phthalates. In terms of quantification, LSTM demonstrates great predictive performance with Rp2 greater than 0.97 and the ratio of performance to deviation greater than 5. These results have certain guiding significance for the analysis of plasticizers in edible oil.

Determination of Trace Organic Contaminant Concentration via Machine Classification of Surface-Enhanced Raman Spectra

Surface-enhanced Raman spectroscopy (SERS) has been well explored as a highly effective characterization technique that is capable of chemical pollutant detection and identification at very low concentrations. Machine learning has been previously used to identify compounds based on SERS spectral data. However, utilization of SERS to quantify concentrations, with or without machine learning, has been difficult due to the spectral intensity being sensitive to confounding factors such as the substrate parameters, orientation of the analyte, and sample preparation technique. Here, we demonstrate an approach for predicting the concentration of sample pollutants from SERS spectra using machine learning. Frequency domain transform methods, including the Fourier and Walsh-Hadamard transforms, are applied to spectral data sets of three analytes (rhodamine 6G, chlorpyrifos, and triclosan), which are then used to train machine learning algorithms. Using standard machine learning models, the concentration of the sample pollutants is predicted with >80% cross-validation accuracy from raw SERS data. A cross-validation accuracy of 85% was achieved using deep learning for a moderately sized data set (∼100 spectra), and 70-80% was achieved for small data sets (∼50 spectra). Performance can be maintained within this range even when combining various sample preparation techniques and environmental media interference. Additionally, as a spectral pretreatment, the Fourier and Hadamard transforms are shown to consistently improve prediction accuracy across multiple data sets. Finally, standard models were shown to accurately identify characteristic peaks of compounds via analysis of their importance scores, further verifying their predictive value.

Surface-Enhanced Raman Spectroscopy-Based Detection of Micro-RNA Biomarkers for Biomedical Diagnosis Using a Comparative Study of Interpretable Machine Learning Algorithms

Surface-enhanced Raman spectroscopy (SERS) has wide diagnostic applications due to narrow spectral features that allow multiplex analysis. We have previously developed a multiplexed, SERS-based nanosensor for micro-RNA (miRNA) detection called the inverse molecular sentinel (iMS). Machine learning (ML) algorithms have been increasingly adopted for spectral analysis due to their ability to discover underlying patterns and relationships within large and complex data sets. However, the high dimensionality of SERS data poses a challenge for traditional ML techniques, which can be prone to overfitting and poor generalization. Non-negative matrix factorization (NMF) reduces the dimensionality of SERS data while preserving information content. In this paper, we compared the performance of ML methods including convolutional neural network (CNN), support vector regression, and extreme gradient boosting combined with and without NMF for spectral unmixing of four-way multiplexed SERS spectra from iMS assays used for miRNA detection. CNN achieved high accuracy in spectral unmixing. Incorporating NMF before CNN drastically decreased memory and training demands without sacrificing model performance on SERS spectral unmixing. Additionally, models were interpreted using gradient class activation maps and partial dependency plots to understand predictions. These models were used to analyze clinical SERS data from single-plexed iMS in RNA extracted from 17 endoscopic tissue biopsies. CNN and CNN-NMF, trained on multiplexed data, performed most accurately with RMSElabel = 0.101 and 9.68 × 10-2, respectively. We demonstrated that CNN-based ML shows great promise in spectral unmixing of multiplexed SERS spectra, and the effect of dimensionality reduction on performance and training speed.

Application and Progress of Machine Learning in Pesticide Hazard and Risk Assessment

Long-term exposure to pesticides is associated with the incidence of cancer. With the exponential increase in the number of new pesticides being synthesized, it becomes more and more important to evaluate the toxicity of pesticides by means of simulated calculations. Based on existing data, machine learning methods can train and model the predictions of the effects of novel pesticides, which have limited available data. Combined with other technologies, this can aid the synthesis of new pesticides with specific active structures, detect pesticide residues, and identify their tolerable exposure levels. This article mainly discusses support vector machines, linear discriminant analysis, decision trees, partial least squares, and algorithms based on feedforward neural networks in machine learning. It is envisaged that this article will provide scientists and users with a better understanding of machine learning and its application prospects in pesticide toxicity assessment.

Artificial Intelligence for Surface-Enhanced Raman Spectroscopy

Surface-enhanced Raman spectroscopy (SERS), well acknowledged as a fingerprinting and sensitive analytical technique, has exerted high applicational value in a broad range of fields including biomedicine, environmental protection, food safety among the others. In the endless pursuit of ever-sensitive, robust, and comprehensive sensing and imaging, advancements keep emerging in the whole pipeline of SERS, from the design of SERS substrates and reporter molecules, synthetic route planning, instrument refinement, to data preprocessing and analysis methods. Artificial intelligence (AI), which is created to imitate and eventually exceed human behaviors, has exhibited its power in learning high-level representations and recognizing complicated patterns with exceptional automaticity. Therefore, facing up with the intertwining influential factors and explosive data size, AI has been increasingly leveraged in all the above-mentioned aspects in SERS, presenting elite efficiency in accelerating systematic optimization and deepening understanding about the fundamental physics and spectral data, which far transcends human labors and conventional computations. In this review, the recent progresses in SERS are summarized through the integration of AI, and new insights of the challenges and perspectives are provided in aim to better gear SERS toward the fast track.

Multiplex SERS detection of polycyclic aromatic hydrocarbon (PAH) pollutants in water samples using gold nanostars and machine learning analysis

Polycyclic aromatic hydrocarbons (PAHs) have attracted a lot of environmental concern because of their carcinogenic and mutagenic properties, and the fact they can easily contaminate natural resources such as drinking water and river water. This study presents a simple and sensitive point-of-care SERS detection of PAHs combined with machine learning algorithms to predict the PAH content more precisely and accurately in real-life samples such as drinking water and river water. We first synthesized multibranched sharp-spiked surfactant-free gold nanostars (GNSs) that can generate strong surface-enhanced Raman scattering (SERS) signals, which were further coated with cetyltrimethylammonium bromide (CTAB) for long-term stability of the GNSs as well as to trap PAHs. We utilized CTAB-capped GNSs for solution-based 'mix and detect' SERS sensing of various PAHs including pyrene (PY), nitro-pyrene (NP), anthracene (ANT), benzo[a]pyrene (BAP), and triphenylene (TP) spiked in drinking water and river water using a portable Raman module. Very low limits of detection (LOD) were achieved in the nanomolar range for the PAHs investigated. More importantly, the detected SERS signal was reproducible for over 90 days after synthesis. Furthermore, we analyzed the SERS data using artificial intelligence (AI) with machine learning algorithms based on the convolutional neural network (CNN) model in order to discriminate the PAHs in samples more precisely and accurately. Using a CNN classification model, we achieved a high prediction accuracy of 90% in the nanomolar detection range and an f1 score (harmonic mean of precision and recall) of 94%, and using a CNN regression model, achieved an RMSEconc = 1.07 × 10-1 μM. Overall, our SERS platform can be effectively and efficiently used for the accurate detection of PAHs in real-life samples, thus opening up a new, sensitive, selective, and practical approach for point-of-need SERS diagnosis of small molecules in complex practical environments.

Au-Ag OHCs-based SERS sensor coupled with deep learning CNN algorithm to quantify thiram and pymetrozine in tea

Pesticide residue detection in food has become increasingly important. Herein, surface-enhanced Raman scattering (SERS) coupled with an intelligent algorithm was developed for the rapid and sensitive detection of pesticide residues in tea. By employing octahedral Cu₂O templates, Au-Ag octahedral hollow cages (Au-Ag OHCs) were developed, which improved the surface plasma effect via rough edges and hollow inner structure, amplifying the Raman signals of pesticide molecules. Afterward, convolutional neural network (CNN), partial least squares (PLS), and extreme learning machine (ELM) algorithms were applied for the quantitative prediction of thiram and pymetrozine. CNN algorithms performed optimally for thiram and pymetrozine, with correlation values of 0.995 and 0.977 and detection limits (LOD) of 0.286 and 29 ppb, respectively. Accordingly, no significant difference (P greater than 0.05) was observed between the developed approach and HPLC in detecting tea samples. Hence, the proposed Au-Ag OHCs-based SERS technique could be utilized for quantifying thiram and pymetrozine in tea.

On-line multi-gas component measurement in the mud logging process based on Raman spectroscopy combined with a CNN-LSTM-AM hybrid model

The qualitative and quantitative analysis of gas components extracted from drilling fluids during mud logging is essential for identifying drilling anomalies, reservoir characteristics, and hydrocarbon properties during oilfield recovery. Gas chromatography (GC) and gas mass spectrometers (GMS) are currently used for the online analysis of gases throughout the mud logging process. Nevertheless, these methods have limitations, including expensive equipment, high maintenance costs, and lengthy detection periods. Raman spectroscopy can be applied to the online quantification of gases at mud logging sites due to its in-situ analysis, high resolution, and rapid detection. However, laser power fluctuations, field vibrations, and the overlapping of characteristic peaks of different gases in the existing online detection system of Raman spectroscopy can affect the quantitative accuracy of the model. For these reasons, a gas Raman spectroscopy system with a high reliability, low detection limits, and increased sensitivity has been designed and applied to the online quantification of gases in the mud logging process. The near-concentric cavity structure is used to improve the signal acquisition module in the gas Raman spectroscopic system, thus enhancing the Raman spectral signal of the gases. One-dimensional convolutional neural networks (1D-CNN) combined with long- and short-term memory networks (LSTM) are applied to construct quantitative models based on the continuous acquisition of Raman spectra of gas mixtures. In addition, the attention mechanism is used to futher improve the quantitative model performance. The results indicated that our proposed method has the capability to continuously on-line detect 10 hydrocarbon and non-hydrocarbon gases in the mud logging process. The limitation of detection (LOD) for different gas components based on the proposed method are in the range of 0.0035%-0.0223%. Based on the proposed CNN-LSTM-AM model, the average detection errors of different gas components range from 0.899% to 3.521%, and their maximum detection errors range from 2.532% to 11.922%. These results demonstrate that our proposed method has a high accuracy, low deviation, and good stability and can be applied to the on-line gas analysis process in the mud logging field.

H-CNN combined with tissue Raman spectroscopy for cervical cancer detection

Cervical cancer is one of the most common cancers with a long latent period and slow onset process. Early and accurate identification of the stage of cervical cancer can significantly improve the cure rate and patient survival time. In this study, we collected 699 Raman spectral data of tissue sections from 233 different patients. We analyzed and compared the characteristics and differences of the mean Raman spectra of the seven tissues and pointed out the main differences in the biochemical composition of the seven tissues. In this study, 1D hierarchical convolutional neural network (H-CNN) is proposed by integrating the prior knowledge of hierarchical classification relations with the research of deep learning in Raman spectroscopy. H-CNN is based on CNN and is added with three network branches. Hierarchical classification is performed from coarse to fine for tissue samples of cervicitis, Low-grade Squamous Cell Carcinoma, High-grade Squamous Cell Carcinoma, Well Differentiated Squamous Cell Carcinoma, Moderately Differentiated Squamous Cell Carcinoma, Poorly Differentiated Squamous Cell Carcinoma and cervical adenocarcinoma. To evaluate the recognition performance of H-CNN, we compared it with traditional methods such as Bayesian classifier (NB), decision tree classifier (DT), support vector machine classifier (SVM) and CNN. The experimental results show that H-CNN can accurately identify different classes of tissue sections and has apparent advantages in several aspects such as recognition accuracy, stability and sensitivity compared with the other four traditional recognition methods. The classification Macro-Accuracy of H-CNN can reach 94.91%, Macro-Recall can reach 95.31%, Macro-F1 can reach 95.23%, and Macro-AUC can reach 97.35%. The hierarchical classification method proposed in this study can diagnose patients more accurately. This could lay the foundation for further research on Raman spectroscopy as a clinical diagnostic method for cervical cancer.

Identification of antibiotic residues in aquatic products with surface-enhanced Raman scattering powered by 1-D convolutional neural networks

Universal and fast antibiotic residues detection technology is imperative for the control of food safety in aquatic products. However, accurate surface-enhanced Raman scattering (SERS) quantitative detection of complicated samples is still a challenge. A recognition method powered by deep learning and took advantage of the unique fingerprint information merits of SERS was proposed. Herein, the spectra were collected by Ag nanofilm SERS substrate prepared by self-assembly of Ag nanoparticles on water/oil interface. A SERS-based database of commonly used antibiotics in aquatic products was set up, which is suitable for employed as input data for learning and training. The results show that the five types of antibiotics are successfully distinguished through principal component analysis (PCA) and each antibiotic in every type was successfully distinguished. Furthermore, one-dimensional convolutional neural networks (1-D CNN) was used to distinguish the antibiotics, and the results show that all the test samples were correctly predicted by 1-D CNN model. The results of this research suggest the great potential of the combination of SERS spectra with deep learning as a method for rapid and highly accurate identification of antibiotic residues in aquatic products.

Unraveling surface-enhanced Raman spectroscopy results through chemometrics and machine learning: principles, progress, and trends

Surface-enhanced Raman spectroscopy (SERS) has gained increasing attention because it provides rich chemical information and high sensitivity, being applicable in many scientific fields including medical diagnosis, forensic analysis, food control, and microbiology. Although SERS is often limited by the lack of selectivity in the analysis of samples with complex matrices, the use of multivariate statistics and mathematical tools has been demonstrated to be an efficient strategy to circumvent this issue. Importantly, since the rapid development of artificial intelligence has been promoting the implementation of a wide variety of advanced multivariate methods in SERS, a discussion about the extent of their synergy and possible standardization becomes necessary. This critical review comprises the principles, advantages, and limitations of coupling SERS with chemometrics and machine learning for both qualitative and quantitative analytical applications. Recent advances and trends in combining SERS with uncommonly used but powerful data analysis tools are also discussed. Finally, a section on benchmarking and tips for selecting the suitable chemometric/machine learning method is included. We believe this will help to move SERS from an alternative detection strategy to a general analytical technique for real-life applications.

Discrimination of Deoxynivalenol Levels of Barley Kernels Using Hyperspectral Imaging in Tandem with Optimized Convolutional Neural Network

Deoxynivalenol (DON) in raw and processed grain poses significant risks to human and animal health. In this study, the feasibility of classifying DON levels in different genetic lines of barley kernels was evaluated using hyperspectral imaging (HSI) (382-1030 nm) in tandem with an optimized convolutional neural network (CNN). Machine learning methods including logistic regression, support vector machine, stochastic gradient descent, K nearest neighbors, random forest, and CNN were respectively used to develop the classification models. Spectral preprocessing methods including wavelet transform and max-min normalization helped to enhance the performance of different models. A simplified CNN model showed better performance than other machine learning models. Competitive adaptive reweighted sampling (CARS) in combination with successive projections algorithm (SPA) was applied to select the best set of characteristic wavelengths. Based on seven wavelengths selected, the optimized CARS-SPA-CNN model distinguished barley grains with low levels of DON (<5 mg/kg) from those with higher levels (5 mg/kg < DON ≤ 14 mg/kg) with an accuracy of 89.41%. The lower levels of DON class I (0.19 mg/kg ≤ DON ≤ 1.25 mg/kg) and class II (1.25 mg/kg < DON ≤ 5 mg/kg) were successfully distinguished based on the optimized CNN model, yielding a precision of 89.81%. The results suggest that HSI in tandem with CNN has great potential for discrimination of DON levels of barley kernels.

Multiplex Surface-Enhanced Raman Scattering: An Emerging Tool for Multicomponent Detection of Food Contaminants

For survival and quality of human life, the search for better ways to ensure food safety is constant. However, food contaminants still threaten human health throughout the food chain. In particular, food systems are often polluted with multiple contaminants simultaneously, which can cause synergistic effects and greatly increase food toxicity. Therefore, the establishment of multiple food contaminant detection methods is significant in food safety control. The surface-enhanced Raman scattering (SERS) technique has emerged as a potent candidate for the detection of multicomponents simultaneously. The current review focuses on the SERS-based strategies in multicomponent detection, including the combination of chromatography methods, chemometrics, and microfluidic engineering with the SERS technique. Furthermore, recent applications of SERS in the detection of multiple foodborne bacteria, pesticides, veterinary drugs, food adulterants, mycotoxins and polycyclic aromatic hydrocarbons are summarized. Finally, challenges and future prospects for the SERS-based detection of multiple food contaminants are discussed to provide research orientation for further.

Automatic detection of pesticide residues on the surface of lettuce leaves using images of feature wavelengths spectrum

The inappropriate application of pesticides to vegetable crops often results in environmental pollution, which seriously impacts the environment and human health. Given that current methods of pesticide residue detection are associated with issues such as low accuracy, high equipment cost, and complex flow, this study puts forward a new method for detecting pesticide residues on lettuce leaves. To establish this method, spectral analysis was used to determine the characteristic wavelength of pesticide residues (709 nm), machine vision equipment was improved, and a bandpass filter and light source of characteristic wavelength were installed to acquire leaf image information. Next, image preprocessing and feature information extraction were automatically implemented through programming. Several links were established for the training model so that the required feature information could be automatically extracted after the batch input of images. The pesticide residue detected using the chemical method was taken as the output and modeled, together with the input image information, using the convolutional neural network (CNN) algorithm. Furthermore, a prediction program was rewritten to generalize the input images during the prediction process and directly obtain the output pesticide residue. The experimental results revealed that when the detection device and method designed in this study were used to detect pesticide residues on lettuce leaves in a key state laboratory, the coefficient of determination of the equation reached 0.883, and the root mean square error (RMSE) was 0.134 mg/L, indicating high accuracy and that the proposed method integrated the advantages of spectrum detection and deep learning. According to comparison testing, the proposed method can meet Chinese national standards in terms of accuracy. Moreover, the improved machine vision equipment was less expensive, thus providing powerful support for the application and popularization of the proposed method.

Machine learning using convolutional neural networks for SERS analysis of biomarkers in medical diagnostics

Surface-enhanced Raman spectroscopy (SERS) has wide diagnostic applications because of narrow spectral features that allow multiplexed analysis. Machine learning (ML) has been used for non-dye-labeled SERS spectra but has not been applied to SERS dye-labeled materials with known spectral shapes. Here, we compare the performances of spectral decomposition, support vector regression, random forest regression, partial least squares regression, and convolutional neural network (CNN) for SERS "spectral unmixing" from a multiplexed mixture of 7 SERS-active "nanorattles" loaded with different dyes for mRNA biomarker detection. We showed that CNN most accurately determined relative contributions of each distinct dye-loaded nanorattle. CNN and comparative models were then used to analyze SERS spectra from a singleplexed, point-of-care assay detecting an mRNA biomarker for head and neck cancer in 20 samples. The CNN, trained on simulated multiplexed data, determined the correct dye contributions from the singleplex assay with RMSE_label = 6.42 × 10^-2. These results demonstrate the potential of CNN-based ML to advance SERS-based diagnostics.

A deep learning model designed for Raman spectroscopy with a novel hyperparameter optimization method

Raman spectroscopy is a spectroscopic technique typically used to determine vibrational modes of molecules and is commonly used in chemistry to provide a structural fingerprint by which molecules can be identified. With the help of deep learning, Raman spectroscopy can be analyzed more efficiently and thus provide more accurate molecular information. However, no general neural network is designed for one-dimensional Raman spectral data so far. Furthermore, different combinations of hyperparameters of neural networks lead to results with significant differences, so the optimization of hyperparameters is a crucial issue in deep learning modeling. In this work, we propose a deep learning model designed for Raman spectral data and a hyperparameter optimization method to achieve its best performance, i.e., a method based on the simulated annealing algorithm to optimize the hyperparameters of the model. The proposed model and optimization method have been fully validated in a glioma Raman spectroscopy dataset. Compared with other published methods including linear regression, support vector regression, long short-term memory, VGG and ResNet, the mean squared error is reduced by 0.1557 while the coefficient determination is increased by 0.1195 on average.

A Novel Method for Carbendazim High-Sensitivity Detection Based on the Combination of Metamaterial Sensor and Machine Learning

Benzimidazole fungicide residue in food products poses a risk to consumer health. Due to its localized electric-field enhancement and high-quality factor value, the metamaterial sensor is appropriate for applications regarding food safety detection. However, the previous detection method based on the metamaterial sensor only considered the resonance dip shift. It neglected other information contained in the spectrum. In this study, we proposed a method for highly sensitive detection of benzimidazole fungicide using a combination of a metamaterial sensor and mean shift machine learning method. The unit cell of the metamaterial sensor contained a cut wire and two split-ring resonances. Mean shift, an unsupervised machine learning method, was employed to analyze the THz spectrum. The experiment results show that our proposed method could detect carbendazim concentrations as low as 0.5 mg/L. The detection sensitivity was enhanced 200 times compared to that achieved using the metamaterial sensor only. Our present work demonstrates a potential application of combining a metamaterial sensor and mean shift in benzimidazole fungicide residue detection.

Detection of Water pH Using Visible Near-Infrared Spectroscopy and One-Dimensional Convolutional Neural Network

pH is an important parameter for water quality detection. This study proposed a novel calibration regression strategy based on a one-dimensional convolutional neural network (1D-CNN) for water pH detection using visible near-infrared (Vis-NIR) spectroscopy. Two groups of Vis-NIR spectral analysis experiments of water pH detection were employed to evaluate the performance of 1D-CNN. Two conventional multivariate regression calibration methods, including partial least squares (PLS) and least squares support vector machine (LS-SVM), were introduced for comparative analysis with 1D-CNN. The successive projections algorithm (SPA) was adopted to select the feature variables. In addition, the learning mechanism of 1D-CNN was interpreted through visual feature maps by convolutional layers. The results showed that the 1D-CNN models obtained the highest prediction accuracy based on full spectra for the two experiments. For the spectrophotometer experiment, the root mean square error of prediction (RMSEP) was 0.7925, and the determination coefficient of prediction (Rp2) was 0.8515. For the grating spectrograph experiment, the RMSEP was 0.5128 and the Rp2 was 0.9273. The convolutional layers could automatically preprocess the spectra and effectively extract the spectra features. Compared with the traditional regression methods, 1D-CNN does not need complex spectra pretreatment and variable selection. Therefore, 1D-CNN is a promising regression approach, with higher prediction accuracy and better modeling convenience for rapid water pH detection using Vis-NIR spectroscopy.

Recent advances in the application of Raman spectroscopy for fish quality and safety analysis

Fish is one of the highly demanded aquatic products, and its quality and safety play a pivotal role in daily diet. However, the possible hazardous substance in perishable fish both in pre- and postharvest periods may decrease their values and pose a threat to public health. Laborious and expensive traditional methods drive the need of developing effective tools for detecting fish quality and safety properties in a rapid, nondestructive, and effective manner. Recent advances in Raman spectroscopy (RS) and surface-enhanced Raman scattering (SERS) have shown enormous potential in various aspects, which largely boost their applications in fish quality and safety evaluation. They have incomparable merits such as providing molecule fingerprint information and allowing for rapid, sensitive, and noninvasive detection with simple sample preparation. This review provides a comprehensive overview focusing on the applications of RS and SERS for fish quality assessment and safety inspection, highlighting the hazardous substance and illegal behavior both in preharvest (veterinary drug residues and environmental pollutants) and postharvest (freshness and illegal behavior) particularly. Moreover, challenges and prospects are also proposed to facilitate the vigorous development of RS and SERS. This review is aimed to emphasize potential opportunities for applying RS and SERS as promising techniques for routine food quality and safety detection. PRACTICAL APPLICATION: With these applications, it can be clearly indicated that RS and SERS are promising and powerful in fish quality and safety surveillance, thereby reducing the occurrence of commercial fraud and food safety issues. More efforts still should be concentrated on exploiting the high-performance Raman instruments, establishing a universal Raman database, developing reproducible SERS substrates and combing RS with other versatile spectral techniques to promote these technologies from laboratory to practice. It is hoped that this review should arouse more research interests in RS and SERS technologies for fish quality and safety surveillance, as well as provide more insights to make a breakthrough.

Rapid and accurate identification of pathogenic bacteria at the single-cell level using laser tweezers Raman spectroscopy and deep learning

We report a new method for the rapid identification of pathogenic bacterial species at the single-cell level that combines laser tweezers Raman spectroscopy (LTRS) with deep learning (DL). LTRS can accurately measure single-cell Raman spectra (scRS) without destroying and labeling cells. Based on the scRS data, DL rapidly and accurately identifies pathogenic bacteria. We measured scRS of 15 species bacteria using homemade LTRS. For each species, approximately, 160 cells from three different patients were measured, one patient's data were used as test set, and the rest after being augmented was used as training set. A residual network (ResNet) model, trained on the augmented training set, achieved an accuracy of 94.53% on the test set. Moreover, we applied gradient-weighted class activation mapping to visualize the proposed model. Finally, we demonstrated the advantages of ResNet over traditional machine-learning algorithms.

Machine learning for rapid quantification of trace analyte molecules using SERS and flexible plasmonic paper substrates

Given the intrinsic nature of low reproducibility and signal blinking in the surface enhanced Raman scattering (SERS) technique, especially while detecting trace/ultra-trace amounts, it remains a major challenge to quantify the analyte under study. Here we present a simple and economically viable, flexible hydrophobic plasmonic filter paper-based SERS substrate for the quantification of two trace analytes [crystal violet (CV) and picric acid (PA)] using machine learning techniques and SERS data. The wettability of the substrate was modified with an easy and low-cost technique of coating it with silicone oil. Gold nanoparticles were synthesized using a femtosecond laser ablation in water technique. The prepared nanoparticles were characterized using UV, TEM, and SEM techniques and subsequently loaded onto filter papers before using them for SERS studies. We have considered the SERS intensities of the analytes at different concentrations with over 900 spectra to train the model. Principal component analysis (PCA) was used to reduce the dimensionality and, hence, the complexity of the model. Furthermore, support vector regression was used to quantify the analyte molecules and we achieved an R² error of 0.9629 for CV and 0.9472 for PA. In conjunction with a portable Raman spectrometer and a computation time of less than <10 s, we believe that this is an affordable and rapid method for quantification of analytes using the SERS technique.

Pushing the Limits of Surface-Enhanced Raman Spectroscopy (SERS) with Deep Learning: Identification of Multiple Species with Closely Related Molecular Structures

Raman spectroscopy is a non-destructive and label-free molecular identification technique capable of producing highly specific spectra with various bands correlated to molecular structure. Moreover, the enhanced detection sensitivity offered by surface-enhanced Raman spectroscopy (SERS) allows analyzing mixtures of related chemical species in a relatively short measurement time. Combining SERS with deep learning algorithms allows in some cases to increase detection and classification capabilities even further. The present study evaluates the potential of applying deep learning algorithms to SERS spectroscopy to differentiate and classify different species of bile acids, a large family of molecules with low Raman cross sections and molecular structures that often differ by a single hydroxyl group. Moreover, the study of these molecules is of interest for the medical community since they have distinct pathological roles and are currently viewed as potential markers of gut microbiome imbalances. A convolutional neural network model was developed and used to classify SERS spectra from five bile acid species. The model succeeded in identifying the five analytes despite very similar molecular structures and was found to be reliable even at low analyte concentrations.

Deep Learning-Based Spectral Extraction for Improving the Performance of Surface-Enhanced Raman Spectroscopy Analysis on Multiplexed Identification and Quantitation

Surface-enhanced Raman spectroscopy (SERS) has been recognized as a promising analytical technique for its capability of providing molecular fingerprint information and avoiding interference of water. Nevertheless, direct SERS detection of complicated samples without pretreatment to achieve the high-efficiency identification and quantitation in a multiplexed way is still a challenge. In this study, a novel spectral extraction neural network (SENN) model was proposed for synchronous SERS detection of each component in mixed solutions using a demonstration sample containing diquat dibromide (DDM), methyl viologen dichloride (MVD), and tetramethylthiuram disulfide (TMTD). A SERS spectra dataset including 3600 spectra of DDM, MVD, TMTD, and their mixtures was first constructed to train the SENN model. After the training step, the cosine similarity of the SENN model can achieve 0.999, 0.997, and 0.994 for DDM, MVD, and TMTD, respectively, which means that the spectra extracted from the mixture are highly consistent with those collected by the SERS experiment of the corresponding pure samples. Furthermore, a convolutional neural network model for quantitative analysis is combined with the SENN, which can simultaneously and rapidly realize the qualitative and quantitative SERS analysis of mixture solutions with lower than 8.8% relative standard deviation. The result demonstrates that the proposed strategy has great potential in improving SERS analysis in environmental monitoring, food safety, and so on.

Structure analysis and non-invasive detection of cadmium-phytochelatin2 complexes in plant by deep learning Raman spectrum

Plants synthesize phytochelatins to chelate in vivo toxic heavy metal ions and produce nontoxic complexes for tolerating the stress. Detection of the complexes would simplify the identification of high phytoremediation cultivars, as well as assessment of plant food for safe consumption. Thus, a confocal Raman spectroscopy combined with density functional theory and deep learning was used for characterizing phytochelatin2 (PC₂), and Cd-PC₂ mixtures. Results showed the PC₂ chelate Cd²⁺ in a 2:1 ratio to produce Cd(PC₂)₂; Cd-S bonds of the Cd(PC₂)₂ have signature Raman vibrations at 305 and 610 cm^-1 which are the most distinctive spectral signatures for varieties of Cd-PCs complexes. The PC₂ was used as a natural probe to stabilize the chemical status of Cd, and to enrich and magnify Raman signature of the trace Cd for deep learning models which enabled condition of the Cd(PC₂)₂ in pak choi leaf to be visualized, quantified, and classified by directly using raw spectra of the leaf. This study provides a general protocol by using Raman information for structure analysis and non-invasive detection of heavy metal-PCs complexes in plants and provides a novel idea for simplifying identification of high phytoremediation cultivars, as well as assessment of heavy metal related food safeties.

Rapid identification of ore minerals using multi-scale dilated convolutional attention network associated with portable Raman spectroscopy

Electron portable Raman spectroscopy tools for ore mineral identification are widely used in raw ore analysis and mineral process engineering. This paper demonstrates an extremely fast and accurate method for identifying unknown ore mineral samples by portable Raman spectroscopy from the RRUFF database. Resampling and background subtraction procedures are used to eliminate the influence of the Raman spectrometer and fluorescence scattering. For the complex mineral spectral classification task, a multi-scale dilated convolutional attention network is designed. In addition, to investigate the identification performance of our method, several machine learning and two basic deep learning models, including k-nearest neighbor (k-NN), support vector machine (SVM), random forest (RF), cosine similarity, extreme gradient boosting machine (XGBoost), Alexnet and ResNet 18, are also developed on the mineral spectra database and applied for mineral identification. Comparative studies show that our CNN network outperforms other models with state-of-the-art results, achieving a top-1 accuracy of 89.51% and a top-3 accuracy of 96.54%. The function of each module and the explanations of the feature extraction in our CNN network were analyzed by ablation experiments and the Grad-CAM algorithm. The identification of ore mineral samples also proves the outstanding performance of our method. In conclusion, the proposed novel approach that exploits the advantages of portable Raman spectroscopy and a deep learning method is promising for rapidly identifying ore mineral samples.

Handheld SERS coupled with QuEChERs for the sensitive analysis of multiple pesticides in basmati rice

Pesticides are a safety issue globally and cause serious concerns for the environment, wildlife and human health. The handheld detection of four pesticide residues widely used in Basmati rice production using surface-enhanced Raman spectroscopy (SERS) is reported. Different SERS substrates were synthesised and their plasmonic and Raman scattering properties evaluated. Using this approach, detection limits for pesticide residues were achieved within the range of 5 ppb-75 ppb, in solvent. Various extraction techniques were assessed to recover pesticide residues from spiked Basmati rice. Quick, Easy, Cheap, Effective, Rugged and Safe (QuEChERs) acetate extraction was applied and characteristic spectral data for each pesticide was obtained from the spiked matrix and analysed using handheld-SERS. This approach allowed detection limits within the matrix conditions to be markedly improved, due to the rapid aggregation of nanogold caused by the extraction medium. Thus, detection limits for three out of four pesticides were detectable below the Maximum Residue Limits (MRLs) of 10 ppb in Basmati rice. Furthermore, the multiplexing performance of handheld-SERS was assessed in solvent and matrix conditions. This study highlights the great potential of handheld-SERS for the rapid on-site detection of pesticide residues in rice and other commodities.

RamanNet: a lightweight convolutional neural network for bacterial identification based on Raman spectra

Raman spectroscopy combined convolutional neural network (CNN) enables rapid and accurate identification of the species of bacteria. However, the existing CNN requires a complex hyperparameters model design. Herein, we propose a new simple network architecture with less hyperparameter design and low computation cost, RamanNet, for rapid and accurate identifying of bacteria at the species level based on its Raman spectra. We verified that compared with the previous CNN methods, the RamanNet reached comparable results on the Bacteria-ID Raman spectral dataset and PKU-bacterial Raman spectral datasets, but using only about 1/45 and 1/297 network parameters, respectively. RamanNet achieved an average isolate-level accuracy of 84.7 ± 0.3%, antibiotic treatment identification accuracy of 97.1 ± 0.3%, and distinguished accuracy of 81.6 ± 0.9% for methicillin-resistant and -susceptible Staphylococcus aureus (MRSA and MSSA) on the Bacteria-ID dataset, respectively. Moreover, it achieved an average accuracy of 96.04% on the PKU-bacterial dataset. The RamanNet model benefited from fewer model parameters that can be quickly trained even using CPU. Therefore, our method has the potential to rapidly and accurately identify bacterial species based on their Raman spectra and can be easily extended to other classification tasks based on Raman spectra.

We propose a novel CNN model named RamanNet for rapid and accurate identification of bacteria at the species-level based on Raman spectra. Compared to previous CNN methods, the RamanNet reached comparable results on the Bacteria-ID Raman spectral dataset.

Application of Convolutional Neural Network-Based Detection Methods in Fresh Fruit Production: A Comprehensive Review

As one of the representative algorithms of deep learning, a convolutional neural network (CNN) with the advantage of local perception and parameter sharing has been rapidly developed. CNN-based detection technology has been widely used in computer vision, natural language processing, and other fields. Fresh fruit production is an important socioeconomic activity, where CNN-based deep learning detection technology has been successfully applied to its important links. To the best of our knowledge, this review is the first on the whole production process of fresh fruit. We first introduced the network architecture and implementation principle of CNN and described the training process of a CNN-based deep learning model in detail. A large number of articles were investigated, which have made breakthroughs in response to challenges using CNN-based deep learning detection technology in important links of fresh fruit production including fruit flower detection, fruit detection, fruit harvesting, and fruit grading. Object detection based on CNN deep learning was elaborated from data acquisition to model training, and different detection methods based on CNN deep learning were compared in each link of the fresh fruit production. The investigation results of this review show that improved CNN deep learning models can give full play to detection potential by combining with the characteristics of each link of fruit production. The investigation results also imply that CNN-based detection may penetrate the challenges created by environmental issues, new area exploration, and multiple task execution of fresh fruit production in the future.

Rapid field trace detection of pesticide residue in food based on surface-enhanced Raman spectroscopy

Surface-enhanced Raman spectroscopy is an alternative detection tool for monitoring food security. However, there is still a lack of a conclusion of SERS detection with respect to pesticides and real sample analysis, and the summary of intelligent algorithms in SERS is also a blank. In this review, a comprehensive report of pesticides detection using SERS technology is given. The SERS detection characteristics of different types of pesticides and the influence of substrate on inspection are discussed and compared by the typical ways of classification. The key points, including the progress in real sample analysis and Raman data processing methods with intelligent algorithm, are highlighted. Lastly, major challenges and future research trends of SERS analysis of pesticide residue are also addressed. SERS has been proven to be a powerful technique for rapid test of residue pesticides in complex food matrices, but there still is a tremendous development space for future research.

Nontarget and high-throughput screening of pesticides and metabolites residues in tea using ultra-high-performance liquid chromatography and quadrupole-orbitrap high-resolution mass spectrometry

A Sin-QuEChERS, coupled to UHPLC Q-Exactive Orbitrap MS, was used for nontargeted high-throughput rapid screening and quantitative analysis of residual pesticides and metabolites in green teas. The sample was extracted with 0.1% formic acid in acetonitrile with shaking, salted out and centrifuged, and purified with Sin-QuEChERS Nano solid phase extraction column; with Full MS/ddMS2 as the data collection mode, the database containing 384 pesticides combined with Trace Finder 3.0 software, In the absence of standard products, rapid screening and confirmation of potential pesticide residues in tea samples with accurate mass, isotope abundance ratio, secondary fragment ions, etc. 20 pesticides were used as quality controls to verify the screening method, and the linearity of these pesticides was between 1 and 200 μg/L, and the correlation coefficients were all greater than 0.9922. Moreover, the LOQ was between 0.002 and 0.01 mg/kg. The average recoveries of spiked tea samples were 74%-111%. Efficiency and reliability of this method were investigated by the analysis of 38 Chinese green tea samples. 18 potential residual pesticides were detected by non-targeted screening. The researchers then conducted a quantitative analysis of the 18 potential residual pesticides.

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.