Search Results (907)

Hyperspectral imaging (HSI) has emerged as a powerful tool for non-destructive phenotyping, yet fruit crop applications remain underexplored. We propose a methodological framework to enhance the spectral characterization of apple fruits by identifying robust vegetation indices (VIs) and interpretable endmembers. We screened 284 Vis, which were evaluated using four feature selection algorithms (Boruta, MI+Lasso, RFE, and ensemble voting), generalizing across red, yellow, green, and purple apple cultivars. An ensemble criterion (≥2 algorithms) yielded 50 selected VIs from the NDSI/DSI/RSI families, preserving > 95% classification accuracy and capturing cultivar-specific variation. Pigment-sensitive wavelength bands were identified via PLS-DA VIP scores and one-vs-rest ANOVA. Using these bands, we formulated a new normalized-difference, ratio, and difference spectral indices tailored to cultivar-specific pigmentation. Several indices achieved >89% classification accuracy and showed patterns consistent with those of anthocyanin, carotenoid, and chlorophyll. A two-stage spectral unmixing pipeline (K-Means → N-FINDR) achieved the lowest reconstruction RMSE (0.043%). This multi-level strategy provides a scalable, interpretable framework for enhancing phenotypic resolution in apple hyperspectral data, contributing to fruit index development and generalized spectral analysis methods for horticultural applications. Full article

Garlic, as an important economic crop, plays a crucial role in the global agricultural production system. Accurate identification of garlic cultivation areas is of great significance for agricultural resource allocation and industrial development. Traditional crop identification methods face challenges of insufficient accuracy and spatial fragmentation in complex agricultural landscapes, limiting their effectiveness in precision agriculture applications. This study, focusing on Kaifeng City, Henan Province, developed an integrated technical framework for garlic identification that combines deep learning edge detection, multi-source feature optimization, and spatial constraint optimization. First, edge detection training samples were constructed using high-resolution Jilin-1 satellite data, and the DexiNed deep learning network was employed to achieve precise extraction of agricultural field boundaries. Second, Sentinel-1 SAR backscatter features, Sentinel-2 multispectral bands, and vegetation indices were integrated to construct a multi-dimensional feature space containing 28 candidate variables, with optimal feature subsets selected through random forest importance analysis combined with recursive feature elimination techniques. Finally, field boundaries were introduced as spatial constraints to optimize pixel-level classification results through majority voting, generating field-scale crop identification products. The results demonstrate that feature optimization improved overall accuracy from 0.91 to 0.93 and the Kappa coefficient from 0.8654 to 0.8857 by selecting 13 optimal features from 28 candidates. The DexiNed network achieved an F1-score of 94.16% for field boundary extraction. Spatial optimization using field constraints effectively eliminated salt-and-pepper noise, with successful validation in Kaifeng’s garlic. Full article

Paddy rice grain variety classification is essential for quality control, as different rice varieties exhibit significant variations in quality attributes, affecting both food security and market value. The integration of hyperspectral imaging with machine learning presents a promising approach for precise classification, though challenges remain in managing the high dimensionality and variability of spectral data, along with the need for model interpretability. To address these challenges, this study employs a CNN-Transformer model that incorporates Standard Normal Variate (SNV) preprocessing, Competitive Adaptive Reweighted Sampling (CARS) for feature wavelength selection, and interpretability analysis to optimize the classification of hybrid indica paddy rice grain varieties. The results show that the CNN-Transformer model outperforms baseline models, achieving an accuracy of 95.33% and an F1-score of 95.40%. Interpretability analysis reveals that the model’s ability to learn from key wavelength features is significantly stronger than that of the comparison models. The key spectral bands identified for hybrid indica paddy rice grain variety classification lie within the 400–440 nm, 580–700 nm, and 880–960 nm ranges. This study demonstrates the potential of hyperspectral imaging combined with machine learning to advance rice variety classification, providing a powerful and interpretable tool for automated rice quality control in agricultural practices. Full article

Entropy-based analyses have emerged as a powerful tool for quantifying the complexity, regularity, and information content of complex biological signals, such as electroencephalography (EEG). In this regard, EEG-based lie detection offers the advantage of directly providing more objective and less susceptible-to-manipulation results compared to traditional polygraph methods. To this end, this study proposes a novel multi-scale entropy approach by fusing fuzzy entropy (FE), time-shifted multi-scale fuzzy entropy (TSMFE), and hierarchical multi-band fuzzy entropy (HMFE), which enables the multidimensional characterization of EEG signals. Subsequently, using machine learning classifiers, the fused feature vector is applied to lie detection, with a focus on channel selection to investigate distinguished neural signatures across brain regions. Experiments utilize a publicly benchmarked LieWaves dataset, and two parts are performed. One is a subject-dependent experiment to identify representative channels for lie detection. Another is a cross-subject experiment to assess the generalizability of the proposed approach. In the subject-dependent experiment, linear discriminant analysis (LDA) achieves impressive accuracies of 82.74% under leave-one-out cross-validation (LOOCV) and 82.00% under 10-fold cross-validation. The cross-subject experiment yields an accuracy of 64.07% using a radial basis function (RBF) kernel support vector machine (SVM) under leave-one-subject-out cross-validation (LOSOCV). Furthermore, regarding the channel selection results, PZ (parietal midline) and T7 (left temporal) are considered the representative channels for lie detection, as they exhibit the most prominent occurrences among subjects. These findings demonstrate that the PZ and T7 play vital roles in the cognitive processes associated with lying, offering a solution for designing portable EEG-based lie detection devices with fewer channels, which also provides insights into neural dynamics by analyzing variations in multi-scale entropy. Full article

Forests, as one of the most vital ecosystems on Earth, play essential roles in climate regulation, water conservation, and resource provision. However, forest health is threatened by pests, among which the larch caterpillar (Dendrolimus superans) is one of the most destructive defoliators of coniferous forests in northern China. Previous studies have mostly relied on single data sources for pest detection, which are limited by insufficient spectral information or inappropriate selection of sensitive bands, making it difficult to achieve high detection accuracy. Therefore, this study integrates hyperspectral imagery from Zhuhai-1 and multispectral imagery from Sentinel-2, leveraging their high spectral resolution and broad spectral range, thus enhancing discrimination capability. Genetic algorithm (GA) was employed to select optimal features from spectral indices, texture features, and fractional-order derivatives (FOD). Random Forest (RF), Support Vector Machine (SVM), and eXtreme Gradient Boosting (XGBoost) were compared, and model interpretability was further analyzed using Shapley additive explanations (SHAP). The results showed that XGBoost achieved the highest performance, with an overall accuracy and Kappa coefficient of 93.47% and 89.81%, demonstrating superior adaptability. Moreover, the integration of hyperspectral and multispectral data significantly improved detection accuracy compared to using either data source alone. Among the GA-selected features, Band 15 of Zhuhai-1 hyperspectral imagery exhibited strong sensitivity to pest infestation. This study provides a novel and practical approach for forest pest monitoring based on the synergistic use of hyperspectral and multispectral remote sensing data. Full article

Groundwater fluoride contamination poses a significant threat to sustainable water resources and public health, yet conventional water quality analysis is both time-consuming and costly, making large-scale, sustainable monitoring challenging. Machine learning methods offer a promising, cost-effective, and sustainable alternative for assessing the spatial distribution of fluoride. This study aimed to develop and compare the performance of Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN) models for predicting groundwater fluoride contamination in the Datong Basin with the help of satellite embeddings from the AlphaEarth Foundation. Data from 391 groundwater sampling points were utilized, with the dataset partitioned into training (80%) and testing (20%) sets. The ANOVA F-value of each feature was calculated for feature selection, identifying surface elevation, pollution, population, evaporation, vertical distance to the rivers, distance to the Sanggan river, and nine extra bands from the satellite embeddings as the most relevant input variables. Model performance was evaluated using the confusion matrix and the area under the receiver operating characteristic curve (ROC-AUC). The results showed that the SVM model demonstrated the highest ROC-AUC (0.82), outperforming the RF (0.80) and MLP (0.77) models. The introduction of satellite embeddings improved the performance of all three models significantly, with the prediction errors decreasing by 13.8% to 23.3%. The SVM model enhanced by satellite embeddings proved to be a robust and reliable tool for predicting groundwater fluoride contamination, highlighting its potential for use in sustainable groundwater management. Full article

This study, leveraging near-infrared spectroscopy technology and integrating vegetation index analysis, aims to develop a hyperspectral imaging-based non-destructive inspection technique for swift monitoring of crop chlorophyll content by rapidly predicting leaf SPAD. To this end, a high-precision spectral prediction model was first established under laboratory conditions using ex situ lyophilized Leaf samples. This model provides a core algorithmic foundation for future non-destructive field applications. A systematic study was conducted to develop prediction models for leaf SPAD values of Korla fragrant pear at different growth stages (fruit-setting period, fruit swelling period and Maturity period). This involved comparing various spectral preprocessing algorithms (AirPLS, Savitzky–Golay, Multiplicative Scatter Correction, FD, etc.) and CARS Feature Selection methods for the screening of optimal spectral feature band. Subsequently, models were constructed using BP Neural Network and Support Vector Regression algorithms. The results showed that leaf samples at different growth stages exhibited significant differences in their spectral features within the 5000–7000 cm⁻¹ (effective features for predicting chlorophyll (SPAD)) and 7000–8000 cm⁻¹ (moisture absorption valley) bands. The Savitzky–Golay+FD (Savitzky–Golay smoothing combined with first-order derivative (FD)) preprocessing algorithm performed optimally in feature extraction. Growth period specificity models significantly outperformed whole growth period models, with the optimal models for the fruit-setting period and fruit swelling period being FD-CARS-BP (Coefficient of determination (R²) > 0.86), and the optimal model for the Maturity period being Savitzky–Golay-FD+Savitzky–Golay-CARS-BP (Coefficient_of_determination (R²) = 0.862). Furthermore, joint modeling of characteristic spectra and vegetation indices further improved prediction performance (Coefficient of determination (R²) > 0.85, Root Mean Square Error (RMSE) 2.5). This study presents a reliable method for non-destructive monitoring of chlorophyll content in Korla fragrant pears, offering significant value for nutrient management and stress early warning in precision agriculture. Full article

Spectrum prediction is essential for cognitive radio, enabling dynamic management and enhanced utilization, particularly in multi-band environments. Yet, its complex spatiotemporal nature and non-stationarity pose significant challenges for achieving high accuracy. Motivated by this, we propose a multi-scale Mamba-based multi-band spectrum prediction method. The core Mamba module combines Bidirectional Selective State Space Models (SSMs) for long-range dependencies and dynamic convolution for local features, efficiently extracting spatiotemporal characteristics. A multi-scale pyramid and adaptive prediction head select appropriate feature levels per prediction step, avoiding full-sequence processing to ensure accuracy while reducing computational cost. Experiments on real-world datasets across multiple frequency bands demonstrate effective handling of spectrum non-stationarity. Compared to baseline models, the method reduces root mean square error (RMSE) by 14.9% (indoor) and 7.9% (outdoor) while cutting GPU memory by 17%. Full article

The inherent high dimensionality of hyperspectral imagery presents both opportunities and challenges for agricultural crop classification. This study offers a rigorous comparative evaluation of three U-Net-based architectures, i.e., U-Net, U-Net++, and Atrous U-Net, applied to EnMAP hyperspectral data over the heterogeneous agricultural region of Lake Vegoritida, Greece. To address the spectral redundancy, we integrated multiple dimensionality-reduction strategies, including Linear Discriminant Analysis, SHAP-based model-driven feature selection, and unsupervised clustering approaches. Results reveal that model performance is contingent on (a) the network’s architecture and (b) the features’ space provided by band selection. While U-Net++ consistently excels when the full spectrum or ACS-derived subsets are employed, standard U-Net achieves great performance under LDA reduction, and Atrous U-Net benefits from SHAP-driven compact representations. Importantly, band selection methods such as ACS and SHAP substantially reduce spectral dimensionality without sacrificing accuracy, with the U-Net++–ACS configuration delivering the highest F1-score (0.77). These findings demonstrate that effective hyperspectral crop classification requires a joint optimization of architecture and spectral representation, underscoring the potential of compact, interpretable pipelines for scalable and operational precision agriculture. Full article

Differentiation of various crops in small-scale crops is important for food security and economic development in many rural communities. Despite being the oldest and simplest classification technique, thresholding continues to gain popularity for classifying complex images. This study aimed to evaluate the effectiveness of a multilevel thresholding technique in differentiating various crop types in small-scale farms. Three (3) types of crops were identified in the study area, and these were cabbage, maize, and sugar bean. Analytical Spectral Devices (ASD) spectral reflectance data were used to detect subtle differences in the spectral reflectance of crops. Analysis of ASD reflectance data revealed reflectance disparities among the surveyed crops in the Green, red, near-infrared (NIR), and shortwave infrared (SWIR) wavelengths. The ASD reflectance data in the Green, red, and NIR were then used to define thresholds for different crop types. The multilevel thresholding technique was used to classify the surveyed crops on the unmanned aerial vehicle (UAV) imagery, using the defined thresholds as input. Three (3) other machine learning classification techniques were also used to offer a baseline for evaluating the performance of the MLT approach, and these were the multilayer perceptron (MLP) neural network, radial basis function neural network (RBFNN), and the Kohonen’s self-organizing maps (SOM). An analysis of crop cover patterns revealed variations in crop area cover as predicted by the MLT and selected machine learning techniques. The classification results of the surveyed crops revealed the area covered by cabbage crops to be 7.46%, 6.01%, 10.33%, 7.05%, 9.48%, and 7.04% as predicted by the MLT on Blue band, MLT on Green band, MLT on NIR, MLP, RBFNN, and SOM, respectively. The area covered by maize crops as predicted by the MLT on Blue band, MLT on Green band, MLT on NIR, MLP, RBFNN, and SOM were noted to be 13.62%, 26.41%, 12.12%, 11.03%, 12.19% and 15.11%, respectively. Sugar bean was noted to occupy 57.51%, 43.72%, 26.77%, 27.44%, 24.15%, and 16.33% as predicted by the MLT on Blue band, MLT on Green band, MLT on NIR, MLP, RBFNN, and SOM, respectively. Accuracy assessment results generally showed poor crop pattern prediction with all tested classifiers in categorizing the surveyed crops, with the kappa index of agreement (KIA) values of 0.372, 0.307, 0.488, 0.531, 0.616, and 0.659 for the MLT on Blue band, MLT on Green band, MLT on NIR, MLP, RBFNN, and Kohonen’s SOM, respectively. Despite recommendations by recent studies, we noted that the MLT was noted to be unsuitable for classifying complex features such as spectrally overlapping crops. Full article

Droughts significantly impact agriculture, water resources, and ecosystems. Their timely detection is essential for implementing effective mitigation strategies. This study explores the use of multispectral Sentinel-2 remote sensing indices and machine learning techniques to detect drought conditions in three distinct regions of India, such as Jodhpur, Amravati, and Thanjavur, during the Rabi season (October–April). Twelve remote sensing indices were studied to assess different aspects of vegetation health, soil moisture, and water stress, and their possible joint use and influence as indicators of regional drought events. Reference data used to define drought conditions in each region were primarily sourced from official government drought declarations and regional and national news publications, which provide seasonal maps of drought conditions across the country. Based on this information, a district vs. year (3 × 10) ground truth is created, indicating the presence or absence of drought (Drought/No Drought) for each region across the ten-year period. Using this ground truth table, we extended the remote sensing dataset by adding a binary drought label for each observation: 1 for “Drought” and 0 for “No Drought”. The dataset is organized by year (2016–2025) in a two-dimensional format, with indices as columns and observations as rows. Each observation represents a single measurement of the remote sensing indices. This enriched dataset serves as the foundation for training and evaluating machine learning models aimed at classifying drought conditions based on spectral information. The resultant remote sensing dataset was used to predict drought events through various machine learning models, including Random Forest, XGBoost, Bagging Classifier, and Gradient Boosting. Among the models, XGBoost achieved the highest accuracy (84.80%), followed closely by the Bagging Classifier (83.98%) and Random Forest (82.98%). In terms of precision, Bagging Classifier and Random Forest performed comparably (82.31% and 81.45%, respectively), while XGBoost achieved a precision of 81.28%. We applied a seasonal majority voting strategy, assigning a final drought label for each region and Rabi season based on the majority of predicted monthly labels. Using this method, XGBoost and Bagging Classifier achieved $96.67\%$ accuracy, precision, and recall, while Random Forest and Gradient Boosting reached $90\%$ and $83.33\%$, respectively, across all metrics. Shapley Additive Explanation (SHAP) analysis revealed that Normalized Multi-band Drought Index (NMDI) and Day of Season (DOS) consistently emerged as the most influential features in determining model predictions. This finding is supported by the Borda Count and Weighted Sum analysis, which ranked NMDI, and DOS as the top feature across all models. Additionally, Red-edge Chlorophyll Index (RECI), Normalized Difference Water Index (NDWI), Normalized Difference Moisture Index (NDMI), and Ratio Drought Index (RDI) were identified as important features contributing to model performance. These features help reveal the underlying spatiotemporal dynamics of drought indicators, offering interpretable insights into model decisions. To evaluate the impact of feature selection, we further conducted a feature ablation study. We trained each model using different combinations of top features: Top 1, Top 2, Top 3, Top 4, and Top 5. The performance of each model was assessed based on accuracy, precision, and recall. XGBoost demonstrated the best overall performance, especially when using the Top 5 features. Full article

Partial discharge (PD) is a critical indicator of insulation degradation in high-voltage DC systems, necessitating accurate diagnosis to ensure long-term reliability. Conventional AC-based diagnostic methods, such as phase-resolved partial discharge analysis (PRPDA), are ineffective under DC conditions, emphasizing the need for waveform-based analysis. This study presents a novel clustering framework for DC PD pulses, leveraging multi-level wavelet decomposition and statistical feature extraction. Each signal is decomposed into multiple frequency bands, and 70 distinctive waveform features are extracted from each pulse. To mitigate feature redundancy and enhance clustering performance, principal component analysis (PCA) is employed for dimensionality reduction. Experimental data were obtained from multiple defect types and measurement distances using a 22.9 kV cross-linked polyethylene (XLPE) cable system. The proposed method significantly outperformed conventional time-frequency (T-F) mapping techniques, particularly in scenarios involving signal attenuation and mixed noise. Propagation-induced distortion was effectively addressed through multi-resolution analysis. In addition, field noise sources such as HVDC converter switching transients and fluorescent lamp emissions were included to assess robustness. The results confirmed the framework’s capability to distinguish between multiple PD types and noise sources, even in challenging environments. Furthermore, optimal mother wavelet selection and correlation-based feature analysis contributed to improved clustering resolution. This framework supports robust PD classification in practical HVDC diagnostics. The framework can contribute to the development of real-time autonomous monitoring systems for HVDC infrastructure. Future research will explore incorporating temporal deep learning architectures for automated PD-type recognition based on clustered data. Full article

Accurate prediction of transformer top-oil temperature is crucial for insulation ageing assessment and fault warning. This paper proposes a novel prediction method based on Variational Mode Decomposition (VMD), kernel principal component analysis (Kernel PCA), a Time-aware Shapley Additive Explanations–Multilayer Perceptron (TSHAP-MLP) feature selection method, enhanced Bayesian optimization, and a Self-organized Time Series Forecasting System (SOFTS). First, the top-oil temperature signal is decomposed using VMD to extract components of different frequency bands. Then, Kernel PCA is employed to perform non-linear dimensionality reduction on the resulting intrinsic mode functions (IMFs). Subsequently, a TSHAP-MLP approach—incorporating temporal weighting and a sliding window mechanism—is used to evaluate the dynamic contributions of historical monitoring data and IMF features over time. Features with SHAP values greater than 1 are selected to reduce input dimensionality. Finally, an enhanced hierarchical Bayesian optimization algorithm is used to fine-tune the SOFTS model parameters, thereby improving prediction accuracy. Experimental results demonstrate that the proposed model outperforms transformer, TimesNet, LSTM, and BP in terms of error metrics, confirming its effectiveness for accurate transformer top-oil temperature prediction. Full article

Time-Weighted Dynamic Time Warping (TWDTW), adapted from speech recognition, is used in agricultural remote sensing to model crop growth, particularly under limited ground sample conditions. However, most related studies rely on full-season or empirically selected features, overlooking the systematic optimization of features at each observation time to improve TWDTW’s performance. This often introduces a large amount of redundant information that is irrelevant to crop discrimination and increases computational complexity. Therefore, this study focused on maize as the target crop and systematically conducted mapping experiments using Sentinel-1/2 images to evaluate the potential of integrating TWDTW with optimally selected multi-source time series features. The optimal multi-source time series features for distinguishing maize from non-maize were determined using a two-step Jeffries Matusita (JM) distance-based global search strategy (i.e., twelve spectral bands, Normalized Difference Vegetation Index, Enhanced Vegetation Index, and the two microwave backscatter coefficients collected during the maize jointing to tasseling stages). Then, based on the full-season and optimal multi-source time series features, we compared TWDTW with two widely used temporal machine learning models in agricultural remote sensing community. The results showed that TWDTW outperformed traditional supervised temporal machine learning models. In particular, compared with TWDTW driven by the full-season optimal multi-source features, TWDTW using the optimal multi-source time series features improved user accuracy by 0.43% and 2.30%, and producer accuracy by 7.51% and 2.99% for the years 2020 and 2021, respectively. Additionally, it reduced computational costs to only 25% of those driven by the full-season scheme. Finally, maize maps of Yangling District from 2020 to 2023 were produced by optimal multi-source time series features-based TWDTW. Their overall accuracies remained consistently above 90% across the four years, and the average relative error between the maize area extracted from remote sensing images and that reported in the statistical yearbook was only 6.61%. This study provided guidance for improving the performance of TWDTW in large-scale crop mapping tasks, which is particularly important under conditions of limited sample availability. Full article

The aim of this study is to analyze the signal generated in the brain for a specific motor task and to identify the region where it occurs. For this purpose, electroencephalography (EEG) signals were divided into delta, theta, alpha, and beta frequency sub-bands, and feature extraction was performed by looking at the time-frequency characteristics of the signals belonging to the obtained sub-bands. The epoch corresponding to motor imagery or action and the signal source in the brain were determined by power spectral density features. This study focused on a hand open–close motor task as an example. A machine learning structure was used for signal recognition and classification. The highest accuracy of 92.9% was obtained with the neural network in relation to signal recognition and action realization. In addition to the classification framework, this study also incorporated advanced preprocessing and energy analysis techniques. Eye blink artifacts were automatically detected and removed using independent component analysis (ICA), enabling more reliable spectral estimation. Furthermore, a detailed channel-based and sub-band energy analysis was performed using fast Fourier transform (FFT) and power spectral density (PSD) estimation. The results revealed that frontal electrodes, particularly Fp1 and AF7, exhibited dominant energy patterns during both real and imagined motor tasks. Delta band activity was found to be most pronounced during rest with T1 and T2, while higher-frequency bands, especially beta, showed increased activity during motor imagery, indicating cognitive and motor planning processes. Although 30 s epochs were initially used, event-based selection was applied within each epoch to mark short task-related intervals, ensuring methodological consistency with the 2–4 s windows commonly emphasized in the literature. After artifact removal, motor activity typically associated with the C3 region was also observed with greater intensity over the frontal electrode sites Fp1, Fp2, AF7, and AF8, demonstrating hemispheric symmetry. The delta band power was found to be higher than that of other frequency bands across T0, T1, and T2 conditions. However, a marked decrease in delta power was observed from T0 to T1 and T2. In contrast, beta band power increased by approximately 20% from T0 to T2, with a similar pattern also evident in gamma band activity. These changes indicate cognitive and motor planning processes. The novelty of this study lies in identifying the electrode that exhibits the strongest signal characteristics for a specific motor activity among 64-channel EEG recordings and subsequently achieving high-performance classification of the corresponding motor activity. Full article