Spectral Feature Extraction Research Articles

TRMD: a transformer-based reverse design model for quad-band metasurface absorbers

Abstract Metasurfaces have the ability to manipulate electromagnetic waves, which allows for the creation of functions such as perfect absorbers. The goal of a perfect absorber is to achieve high absorption peaks within a specific frequency band. This paper introduces an improved metasurface absorber structure that can achieve efficient absorption in four different frequency bands within the range of 2-9 GHz. In the field of metasurface design, deep learning methods have been recently applied due to their powerful data processing capabilities. However, these methods have primarily used fully connected neural networks and Long Short-Term Memory (LSTM). Despite their capabilities, fully connected networks and LSTM struggle to capture the global information in absorption spectrum data, leading to less accurate predictions. In this study, it was observed that the Transformer model can effectively capture global information using Multi-Head Self-Attention (MHSA) and is not affected by the length of the data. Based on this observation, this paper presents a lightweight model consisting solely of an encoder, achieving a Mean Squared Error (MSE) that is one-twentieth of the State-of-the-Art (SOTA). This model predicts metasurface structure based on target absorption spectra, enabling users to rapidly obtain metasurface absorber structures directly from input absorption spectra. The model consists of two parts: embedding and encoder. The embedding processes input absorption spectra data and adds positional encoding, while the encoder extracts spectral data features. MHSA effectively captures contextual information of absorption spectra, emphasizing key feature information. The final model achieved a MSE convergence of 2 × 10−4 and a coefficient of determination (R 2)value of 0.998, successfully optimizing the design of multi-band metasurface absorbers. Moreover, the predicted results from the model exhibit an absorption spectrum that is highly consistent with the target spectrum.

Deep feature synthesis approach using selective graph attention for replay attack voice spoofing detection

<span lang="EN-US">As voice-based authentication becomes increasingly integrated into security frameworks, establishing effective defenses against voice spoofing, particularly replay attacks, is more crucial than ever. This paper presents a novel comprehensive framework for replay attack detection that leverages the integration of advanced spectral-temporal feature extraction and graph-based feature processing mechanisms. The proposed system presents the design of a waveform encoder and a novel temporal residual unit for spectral and temporal feature extraction in synchronous. Further, an approach of selective attention graph followed by multi-scale feature synthesis is employed to retain precise and spoof indicative feature vectors at the classification layer. The proposed method addresses the significant challenge of distinguishing genuine speech from replayed recordings. The validation of the proposed model is done on the ASVSpoof2019 dataset to demonstrate the efficacy of the proposed approach. The proposed system outperforms existing methods, achieving a lower equal error rate (EER) of 0.015 and a reduced tandem detection cost function (t-DCF) of 0.503. The comparative outcome exhibits the robustness of the method in identifying replay attacks.</span>

Breaking dimensional barriers in hyperspectral target detection: Atrous convolution with Gramian Angular field representations

Hyperspectral images contain extensive spectral bands with rich spectral information that reflects object properties. Leveraging state-of-the-art deep learning techniques has proven to be effective in hyperspectral target detection. However, compared to two-dimensional matrix data, the one-dimensional nature of spectral sequence limits the information that can be extracted, posing a challenge for deep learning-based hyperspectral target detection methodologies. To address this issue, a novel hyperspectral target detection method employing atrous convolution with gramian angular field representations is proposed in this paper. This approach breaks the barrier between one-dimensional vector and two-dimensional matrix by gramian angular field, transforming the spectral sequences from one-dimensional vectors into two-dimensional matrices, enabling the exploration of multidimensional relationships within spectral band relations through an atrous convolution-based spectral feature extraction network. The proposed model transcends the traditional one-dimensional spectral target detection limitations, offering a new perspective for spectral-based hyperspectral target detection. Experimental results on four real-world hyperspectral datasets demonstrate that the proposed method significantly outperforms existing state-of-the-art methods in detection performance, showcasing its potential for advancing hyperspectral target detection.

Enhancing Leaf Area Index Estimation in Southern Xinjiang Fruit Trees: A Competitive Adaptive Reweighted Sampling-Successive Projections Algorithm and Three-Band Index Approach with Fractional-Order Differentiation

The Leaf Area Index (LAI) is a key indicator for assessing fruit tree growth and productivity, and accurate estimation using hyperspectral technology is essential for monitoring plant health. This study aimed to improve LAI estimation accuracy in apricot, jujube, and walnut trees in Xinjiang, China. Canopy hyperspectral data were processed using fractional-order differentiation (FOD) from 0 to 2.0 orders to extract spectral features. Three feature selection methods—Competitive Adaptive Reweighted Sampling (CARS), Successive Projections Algorithm (SPA), and their combination (CARS-SPA)—were applied to identify sensitive spectral bands. Various band combinations were used to construct three-band indices (TBIs) for optimal LAI estimation. Random forest (RF) models were developed and validated for LAI prediction. The results showed that (1) the reflectance spectra of jujube and walnut trees were similar, while apricot spectra differed. (2) The correlation between fractional-order differential spectra and LAI was highest at orders 1.4 and 1.7, outperforming integer-order spectra. (3) The CARS-SPA selected a smaller set of feature bands in the 1100~2500 nm, reducing collinearity and improving spectral index construction. (4) The RF model using TBI4 demonstrated high R², low RMSE, and an RPD value > 2, indicating optimal prediction accuracy. This approach holds promise for hyperspectral LAI monitoring in fruit trees.

Hyperspectral Imaging Combined with Deep Learning for the Early Detection of Strawberry Leaf Gray Mold Disease

The presence of gray mold can seriously affect the yield and quality of strawberries. Due to their susceptibility and the rapid spread of this disease, it is important to develop early, accurate, rapid, and non-destructive disease identification strategies. In this study, the early detection of strawberry leaf diseases was performed using hyperspectral imaging combining multi-dimensional features like spectral fingerprints and vegetation indices. Firstly, hyperspectral images of healthy and early affected leaves (24 h) were acquired using a hyperspectral imaging system. Then, spectral reflectance (616) and vegetation index (40) were extracted. Next, the CARS algorithm was used to extract spectral fingerprint features (17). Pearson correlation analysis combined with the SPA method was used to select five significant vegetation indices. Finally, we used five deep learning methods (LSTMs, CNNs, BPFs, and KNNs) to build disease detection models for strawberries based on individual and fusion characteristics. The results showed that the accuracy of the recognition model based on fused features ranged from 88.9% to 96.6%. The CNN recognition model based on fused features performed best, with a recognition accuracy of 96.6%. Overall, the fused feature-based model can reduce the dimensionality of the classification data and effectively improve the predicting accuracy and precision of the classification algorithm.

SSFAN: A Compact and Efficient Spectral-Spatial Feature Extraction and Attention-Based Neural Network for Hyperspectral Image Classification

Hyperspectral image (HSI) classification is a crucial technique that assigns each pixel in an image to a specific land cover category by leveraging both spectral and spatial information. In recent years, HSI classification methods based on convolutional neural networks (CNNs) and Transformers have significantly improved performance due to their strong feature extraction capabilities. However, these improvements often come with increased model complexity, leading to higher computational costs. To address this, we propose a compact and efficient spectral-spatial feature extraction and attention-based neural network (SSFAN) for HSI classification. The SSFAN model consists of three core modules: the Parallel Spectral-Spatial Feature Extraction Block (PSSB), the Scan Block, and the Squeeze-and-Excitation MLP Block (SEMB). After preprocessing the HSI data, it is fed into the PSSB module, which contains two parallel streams, each comprising a 3D convolutional layer and a 2D convolutional layer. The 3D convolutional layer extracts spectral and spatial features from the input hyperspectral data, while the 2D convolutional layer further enhances the spatial feature representation. Next, the Scan Block module employs a layered scanning strategy to extract spatial information at different scales from the central pixel outward, enabling the model to capture both local and global spatial relationships. The SEMB module combines the Spectral-Spatial Recurrent Block (SSRB) and the MLP Block. The SSRB, with its adaptive weight assignment mechanism in the SToken Module, flexibly handles time steps and feature dimensions, performing deep spectral and spatial feature extraction through multiple state updates. Finally, the MLP Block processes the input features through a series of linear transformations, GELU activation functions, and Dropout layers, capturing complex patterns and relationships within the data, and concludes with an argmax layer for classification. Experimental results show that the proposed SSFAN model delivers superior classification performance, outperforming the second-best method by 1.72%, 5.19%, and 1.94% in OA, AA, and Kappa coefficient, respectively, on the Indian Pines dataset. Additionally, it requires less training and testing time compared to other state-of-the-art deep learning methods.

A Convolution Auto-Encoders Network for Aero-Engine Hot Jet FT-IR Spectrum Feature Extraction and Classification

Aiming at classification and recognition of aero-engines, two telemetry Fourier transform infrared (FT-IR) spectrometers are utilized to measure the infrared spectrum of the areo-engine hot jet, meanwhile a spectrum dataset of six types of areo-engines is established. In this paper, a convolutional autoencoder (CAE) is designed for spectral feature extraction and classification, which is composed of coding network, decoding network, and classification network. The encoder network consists of convolutional layers and maximum pooling layers, the decoder network consists of up-sampling layers and deconvolution layers, and the classification network consists of a flattened layer and a dense layer. In the experiment, data for the spectral dataset were randomly sampled at a ratio of 8:1:1 to produce the training set, validation set, and prediction set, and the performance measures were accuracy, precision, recall, confusion matrix, F1 score, ROC curve, and AUC value. The experimental result of CAE reached 96% accuracy and the prediction running time was 1.57 s. Compared with the classical PCA feature extraction and SVM, XGBoost, AdaBoost, and Random Forest classifier algorithms, as well as AE, CSAE, and CVAE deep learning classification methods, the CAE network can achieve higher accuracy and efficiency and can complete the spectral classification task.

Spectral-Spatial Transformer for Hyperspectral Image Sharpening.

Convolutional neural networks (CNNs) have recently achieved outstanding performance for hyperspectral (HS) and multispectral (MS) image fusion. However, CNNs cannot explore the long-range dependence for HS and MS image fusion because of their local receptive fields. To overcome this limitation, a transformer is proposed to leverage the long-range dependence from the network inputs. Because of the ability of long-range modeling, the transformer overcomes the sole CNN on many tasks, whereas its use for HS and MS image fusion is still unexplored. In this article, we propose a spectral-spatial transformer (SST) to show the potentiality of transformers for HS and MS image fusion. We devise first two branches to extract spectral and spatial features in the HS and MS images by SST blocks, which can explore the spectral and spatial long-range dependence, respectively. Afterward, spectral and spatial features are fused feeding the result back to spectral and spatial branches for information interaction. Finally, the high-resolution (HR) HS image is reconstructed by dense links from all the fused features to make full use of them. The experimental analysis demonstrates the high performance of the proposed approach compared with some state-of-the-art (SOTA) methods.

HTD-TS3: Weakly Supervised Hyperspectral Target Detection Based on Transformer via Spectral-Spatial Similarity.

As an advanced technique in remote sensing, hyperspectral target detection (HTD) is widely concerned in civilian and military applications. However, the limitation of prior and heterogeneous backgrounds makes HTD models sensitive to data corruption under various interference from the environment. In this article, a novel united HTD framework based on the concept of transformer is proposed to extract [HTD based on transformer via spectral-spatial similarity (HTD-TS3)] under weak supervision, which opens up more flexible ways to study HTD. For the first time, the transformer mechanism is introduced into the HTD task to extract spectral and spatial features in a unified optimization procedure. By modeling long-range dependence among spectra, it realizes spectral-spatial joint inference based on long-range context, which addresses the issues of insufficient utilization of spatial information. To provide samples for weakly supervised learning (WSL), the coarse sample selection and spectral sequence construction in an efficient way are proposed, which makes full use of limited prior information. Finally, an exponential constrained nonlinear function is adopted to acquire pixel-level prediction via combining discriminative spectral-spatial features and coarse spatial information. Experiments on real hyperspectral images (HSIs) captured by different sensors at various scenes verify the effectiveness and efficiency of HTD-TS3.

FCSwinU: Fourier Convolutions and Swin Transformer UNet for Hyperspectral and Multispectral Image Fusion.

The fusion of low-resolution hyperspectral images (LR-HSI) with high-resolution multispectral images (HR-MSI) provides a cost-effective approach to obtaining high-resolution hyperspectral images (HR-HSI). Existing methods primarily based on convolutional neural networks (CNNs) struggle to capture global features and do not adequately address the significant scale and spectral resolution differences between LR-HSI and HR-MSI. To tackle these challenges, our novel FCSwinU network leverages the spectral fast Fourier convolution (SFFC) module for spectral feature extraction and utilizes the Swin Transformer's self-attention mechanism for multi-scale global feature fusion. FCSwinU employs a UNet-like encoder-decoder framework to effectively merge spatiospectral features. The encoder integrates the Swin Transformer feature abstraction module (SwinTFAM) to encode pixel correlations and perform multi-scale transformations, facilitating the adaptive fusion of hyperspectral and multispectral data. The decoder then employs the Swin Transformer feature reconstruction module (SwinTFRM) to reconstruct the fused features, restoring the original image dimensions and ensuring the precise recovery of spatial and spectral details. Experimental results from three benchmark datasets and a real-world dataset robustly validate the superior performance of our method in both visual representation and quantitative assessment compared to existing fusion methods.

DAB-LSTMNN: A novel respiratory disease diagnosis deep CNN framework based on attention scheme and BLSTM neural networks

Respiratory diseases have a significant impact on modern society, posing considerable public health risks. With the emergence of the COVID-19 pandemic, addressing respiratory issues has become increasingly urgent and important. Recently, artificial intelligence-based methods utilizing the acoustic recordings of suspected patients have shown promise in the diagnosis of various respiratory diseases, enabling localized treatment and containment of their spread. As the existing methods cannot efficiently extract subtle differences between the sound samples, thereby limiting their generalization ability. To improve the diagnosis accuracy, this paper proposes a novel multi-channel, multi-modal deep learning architecture based on the attention mechanism. The proposed framework combines a deep convolutional neural network (DCNN) with a bidirectional long short-term memory (BLSTM) network, and also utilizes the attention scheme to extract temporal and spectral features from different modalities of speech data (e.g. coughs, counting sounds and sustained vowel articulation). The proposed method effectively classifies COVID-19 patients, asthma patients and healthy individuals, with a test accuracy of 89.27 ± 0.1%, and an F1 score of 85.42 ± 0.2%. The experimental results validate the feasibility of our method, and also indicate that it is competitive with the existing deep networks.

Bidirectional Mamba with Dual-Branch Feature Extraction for Hyperspectral Image Classification.

The hyperspectral image (HSI) classification task is widely used in remote sensing image analysis. The HSI classification methods based on convolutional neural networks (CNNs) have greatly improved the classification performance. However, they cannot well utilize the sequential properties of spectral features and face the challenge of increasing computational cost with the increase in network depth. To address these shortcomings, this paper proposes a novel network with a CNN-Mamba architecture, called DBMamba, which uses a bidirectional Mamba to process spectral feature sequences at a linear computational cost. In the DBMamba, principal component analysis (PCA) is first used to extract the main features of the data. Then, a dual-branch CNN structure, with the fused features from spectral-spatial features by 3D-CNN and spatial features by 2D-CNN, is used to extract shallow spectral-spatial features. Finally, a bidirectional Mamba is used to effectively capture global contextual information in features and significantly enhance the extraction of spectral features. Experimental results on the Indian Pines, Salinas, and Pavia University datasets demonstrate that the classification performance surpasses that of many cutting-edge methods, improving by 1.04%, 0.15%, and 0.09%, respectively, over the competing SSFTT method. The research in this paper enhances the existing knowledge on HSI classification and provides valuable insights for future research in this field.

Possibility of determining high quantitative fecal occult blood on stool surface using hyperspectral imaging.

Fecal immunochemical tests are commonly performed for colorectal cancer screening. Instant fecal occult blood measurement in toilet bowel movements would improve convenience. Hyperspectral imaging (HSI) enables the nondestructive evaluation of materials that are difficult to assess visually. This study aimed to determine whether HSI could be used to identify fecal occult blood on stool surfaces. The study included 100 patients who underwent colonoscopy, divided into groups A and B (50 patients, each) for creating a discriminant algorithm and validating the accuracy of the algorithm, respectively. In group A, 100 areas were randomly selected from the stool surface, and the fecal occult blood quantitative values were measured and photographed using a hyperspectral camera (cutoff: > 400ng/mL). A discriminant algorithm image was created to extract spectral feature differences obtained from HSI via machine learning. In group B, 250 random areas were evaluated and compared to fecal occult blood quantitative values, measuring sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV). Groups A and B comprised 28 and 26 patients with cancer, respectively. Cancer detection sensitivity at the 400ng/mL cutoff was 67.9% and 42.3% in groups A and B, respectively. The discriminant algorithm image exhibited high accuracy in group A (sensitivity; 77.1%, specificity; 96.9%, accuracy; 90.0%, PPV; 93.1%, NPV; 88.7%). In group B, the sensitivity, specificity, accuracy, PPV, and NPV were 83.3, 92.9, 90.8, 76.3, and 95.3%, respectively. HSI can effectively discriminate high quantitative fecal occult blood, highlighting its potential for improved colorectal cancer screening.

DMCCT: Dual-Branch Multi-Granularity Convolutional Cross-Substitution Transformer for Hyperspectral Image Classification

In the field of hyperspectral image classification, deep learning technology, especially convolutional neural networks, has achieved remarkable progress. However, convolutional neural network models encounter challenges in hyperspectral image classification due to limitations in their receptive fields. Conversely, the global modeling capability of Transformers has garnered attention in hyperspectral image classification. Nevertheless, the high computational cost and inadequate local feature extraction hinder its widespread application. In this study, we propose a novel fusion model of convolutional neural networks and Transformers to enhance performance in hyperspectral image classification, namely the dual-branch multi-granularity convolutional cross-substitution Transformer (DMCCT). The proposed model adopts a dual-branch structure to separately extract spatial and spectral features, thereby mitigating mutual interference and information loss between spectral and spatial data during feature extraction. Moreover, a multi-granularity embedding module is introduced to facilitate multi-scale and multi-level local feature extraction for spatial and spectral information. In particular, the improved convolutional cross-substitution Transformer module effectively integrates convolution and Transformer, reducing the complexity of attention operations and enhancing the accuracy of hyperspectral image classification tasks. Subsequently, the proposed method is evaluated against existing approaches using three classical datasets, namely Pavia University, Kennedy Space Center, and Indian Pines. Experimental results demonstrate the efficacy of the proposed method, achieving significant classification results on these datasets with overall classification accuracies of 98.57%, 97.96%, and 96.59%, respectively. These results establish the superiority of the proposed method in the context of hyperspectral image classification under similar experimental conditions.

Dual-layer broadband encoding spectrometer: enhanced encoder basis orthogonality and spectral detection accuracy.

Spectrometer miniaturization has become a significant trend driven by the demand for distributed and continuous spectral sensing. Broadband encoding spectrometers, which utilize broadband encoder arrays to extract spectral features and algorithms to reconstruct spectra, are among the most competitive candidates for high-performance miniaturized spectrometers. Enhancing the spectral feature extraction capability of these broadband encoders is essential for improving spectrometer performance. However, the strategies and approaches for optimizing these encoders are not yet well-defined. This study analyzes the effectiveness of improving the basis orthogonality of the encoders for their optimization and proposes a dual-layer broadband encoder structure to implement this optimization strategy. The designed dual-layer broadband encoders consist of vertically stacked quantum dot encoders and TiO2/SiO2 encoders, with the corresponding basis being mixed Gaussian. Simulation experiments demonstrate that the proposed dual-layer broadband encoder structure significantly improves the encoders' basis orthogonality, leading to enhanced spectral detection accuracy of the spectrometer constructed with these dual-layer encoders. Experimental fabrication of the dual-layer encoders confirms their physical feasibility and basis orthogonality enhancement.

A black tea quality testing method for scale production using CV and NIRS with TCN for spectral feature extraction

To rigorously assess black tea quality in large-scale production, this study introduces a multi-modal fusion approach integrating computer vision (CV) with Near-Infrared Spectroscopy (NIRS). CV technology is first applied to evaluate the tea's appearance quality, while NIRS quantifies key chemical components, including tea polyphenols (TP), free amino acids (FAA), and caffeine (CAF). Additionally, different methods are employed to extract potential quality features from NIR spectra. The information are then fused, and a classifier is utilized to accurately identify tea quality. Results show that the Temporal Convolutional Network (TCN) fused model achieves a 98.2 % accuracy rate, surpassing both the Convolutional Neural Network (CNN) fused model and traditional methods. This study demonstrates that TCNs effectively extract spectral features and that data fusion significantly enhances tea quality testing, offering valuable insights for production optimization.

Contrastive Learning based Speech Spoofing Detection for Multimedia Security in Edge Intelligence

Artificial intelligence (AI) empowered edge computing has given rise to a new paradigm and effectively facilitated the promotion and development of multimedia applications. The speech assistant is one of the significant services provided by multimedia applications, which aims to offer intelligent interactive experiences between humans and machines. However, malicious attackers may exploit spoofed speeches to deceive speech assistants, posing great challenges to the security of multimedia applications. The limited resources of multimedia terminal devices hinder their ability to effectively load speech spoofing detection models. Furthermore, processing and analyzing speech in the cloud can result in poor real-time performance and potential privacy risks. Existing speech spoofing detection methods rely heavily on annotated data and exhibit poor generalization capabilities for unseen spoofed speeches. To address these challenges, this paper first proposes the Coordinate Attention Network (CA2Net) that consists of coordinate attention blocks and Res2Net blocks. CA2Net can simultaneously extract temporal and spectral speech feature information and represent multi-scale speech features at a granularity level. Besides, a contrastive learning-based speech spoofing detection framework named GEMINI is proposed. GEMINI can be effectively deployed on edge nodes and autonomously learn speech features with strong generalization capabilities. GEMINI first performs data augmentation on speech signals and extracts conventional acoustic features to enhance the feature robustness. Subsequently, GEMINI utilizes the proposed CA2Net to further explore the discriminative speech features. Then, a tensor-based multi-attention comparison model is employed to maximize the consistency between speech contexts. GEMINI continuously updates CA2Net with contrastive learning, which enables CA2Net to effectively represent speech signals and accurately detect spoofed speeches. Extensive experiments on the ASVspoof2019 dataset show that GEMINI reduces the Equal Error Rate and tandem Detection Cost Function by up to 96.75% and 96.35% in the physical access scenario, and by up to 86.62% and 87.71% in the logical access scenario compared to peer methods.

E2TNet: Efficient enhancement Transformer network for hyperspectral image classification

Recently, Convolutional Transformer-based models have become popular in hyperspectral image (HSI) classification tasks and gained competitive classification performance. However, some Convolutional Transformer-based models fail to effectively mine the global correlations of coarse-grained and fine-grained features, which is adverse to recognizing the refined scale variation information of land-cover. The combination of convolution operations and multihead self-attention mechanisms also increases the computational cost, leading to low classification efficiency. In addition, shallow spectral–spatial features are directly input into the encoder, which inevitably incurs redundant spectral information. Therefore, this paper proposes an efficient enhancement Transformer network (E2TNet) for HSI classification. Specifically, this paper first designs a spectral–spatial feature fusion module to extract spectral and spatial features from HSI cubes and fuse them. Second, considering that redundant spectral information has a negative impact on classification performance, this paper designs a spectral–spatial feature weighted module to improve the feature representation of critical spectral information. Finally, to explore the global correlations of coarse-grained and fine-grained features and improve classification efficiency, an efficient multigranularity information fusion module is embedded in the encoder of E2TNet. The experiment is conducted on four benchmark hyperspectral datasets, and the experimental results demonstrate that the proposed E2TNet is better than several Convolutional Transformer-based classification models in terms of classification accuracy and classification efficiency.

Enhanced Blue Band Vegetation Index (The Re-Modified Anthocyanin Reflectance Index (RMARI)) for Accurate Farmland Shelterbelt Extraction

Farmland shelterbelts are aimed at farmland protection and productivity improvement, environmental protection and ecological balance, as well as land use planning and management. Farmland shelterbelts play a vital role in determining the structural integrity and overall effectiveness of farmland, and assessing the dynamic changes within these protective forests accurately and swiftly is essential to maintaining their protective functions as well as for policy formulation and effectiveness evaluation in relevant departments. Traditional methods for extracting farmland shelterbelt information have faced significant challenges due to the large workload required and the inconsistencies in the accuracy of existing methods. For example, the existing vegetation index extraction methods often have significant errors, which remain unresolved. Therefore, developing a more efficient extraction method with greater accuracy is imperative. This study focused on Youyi Farm in Heilongjiang Province, China, utilizing satellite data with spatial resolutions ranging from 0.8 m (GF-7) to 30 m (Landsat). By taking into account the growth cycles of farmland shelterbelts and variations in crop types, the optimal temporal window for extraction is identified based on phenological analysis. The study introduced a new index—the Re-Modified Anthocyanin Reflectance Index (RMARI)—which is an improvement on existing vegetation indexes, such as the NDVI and the improved original ARI. Both the accuracy and extraction results showed significant improvements, and the feasibility of the RMARI was confirmed. The study proposed four extraction schemes for farmland shelterbelts: (1) spectral feature extraction, (2) extraction using vegetation indexes, (3) random forest extraction, and (4) RF combined with characteristic index bands. The extraction process was implemented on the GEE platform, and results from different spatial resolutions were compared. Results showed that (1) the bare soil period in May is the optimal time period for extracting farmland shelterbelts; (2) the RF method combined with characteristic index bands produces the best extraction results, effectively distinguishing shelterbelts from other land features; (3) the RMARI reduces background noise more effectively than the NDVI and ARI, resulting in more comprehensive extraction outcomes; and (4) among the satellite images analyzed—GF-7, Planet, Sentinel-2, and Landsat OLI 8—GF-7 achieves the highest extraction accuracy (with a Kappa coefficient of 0.95 and an OA of 0.97), providing the most detailed textural information. However, comprehensive analysis suggests that Sentinel-2 is more suitable for large-scale farmland shelterbelt information extraction. This study provides new approaches and technical support for periodic dynamic forestry surveys, providing valuable reference points for agricultural ecological research.

Study on detection of pesticide residues in tobacco based on hyperspectral imaging technology.

Tobacco is a critical economic crop, yet its cultivation heavily relies on chemical pesticides, posing health risks to consumers, therefore, monitoring pesticide residues in tobacco is conducive to ensuring food safety. However, most current research on pesticide residue detection in tobacco relies on traditional chemical methods, which cannot meet the requirements for real-time and rapid detection. This study introduces an advanced method that combines hyperspectral imaging (HSI) technology with machine learning algorithms. Firstly, a hyperspectral imager was used to obtain spectral data of tobacco samples, and a variety of spectral pre-processing technologies such as mean centralization (MC), trend correction (TC), and wavelet transform (WT), as well as feature extraction methods such as competitive adaptive reweighted sampling (CARS) and least angle regression (LAR) were used to process the spectral data, and then, grid search algorithm (GSA) is used to optimize the support sector machine (SVM). The optimized MC-LAR-SVM model achieved a pesticide classification accuracy of 84.1%, which was 9.5% higher than the original data model. The accuracy of the WT-TC-CARS-GSA-SVM model in the fenvalerate concentration classification experiment was as high as 91.8 %, and it also had excellent performance in other metrics. Compared with the model based on the original data, the accuracy, precision, recall, and F1-score are improved by 8.3 %, 8.2 %, 7.5 %, and 0.08, respectively. The results show that combining spectral preprocessing and feature extraction algorithms with machine learning models can significantly enhance the performance of pesticide residue detection models and provide robust, efficient, and accurate solutions for food safety monitoring. This study provides a new technical means for the detection of pesticide residues in tobacco, which is of great significance for improving the efficiency and accuracy of food safety detection.