Search Results (4,845)

The Western Junggar Orogen (Xinjiang) is featured by widespread granite intrusions and substantial Au-Cu-Mo resources, making it an ideal site to study granitoids and their metallogenic link. Here, we first conducted geological surveys and analyses with ASD spectrometry, polarized light microscopy (PLM), and X-Ray diffraction (XRD) to determine the granitoid lithology. Then, we used spectral and remote sensing data statistics and rock textural features to select band combinations from ASTER and Landsat 8 OLI VNIR-SWIR data. Three band combinations, i.e., spectral absorption bands + T1, SWIR + T1, and VNIR-SWIR + T1, serve as the input layers for convolutional neural networks (AlexNet, VGG16, and GoogLeNet). They are used for remote sensing identification of granitoid lithology and the assessment of its accuracy. The results highlight the AlexNet model’s superior performance, as evidenced by the highest weighted F1 score (91.98%) and kappa coefficient (0.84) with ASTER VNIR-SWIR + T1 as the input layers. We suggest that the AlexNet model can best identify the granitoid subtypes (with ASTER images) in the Western Junggar. In contrast, Landsat 8 OLI images performed poorly, possibly because they have only two SWIR bands. We offer detailed spatial distribution characteristics of granite subtypes and provide remote sensing exploration methods for studying polymetallic ore belts in the Central Asian Orogenic Belt (CAOB). Full article

Leaf area index (LAI) serves as a crucial indicator for characterizing the growth and development process of maize. However, the LAI inversion of maize based on unmanned aerial vehicles (UAVs) is highly susceptible to various factors such as weather conditions, light intensity, and sensor performance. In contrast to satellites, the spectral stability of UAV-based data is relatively inferior, and the phenomenon of “spectral fragmentation” is prone to occur during large-scale monitoring. This study was designed to solve the problem that maize LAI inversion based on UAVs is difficult to achieve both high spatial resolution and spectral consistency. A two-stage remote sensing data fusion method integrating coarse and fine fusion was proposed. The SHapley Additive exPlanations (SHAP) model was introduced to investigate the contributions of 20 features in 7 categories to LAI inversion of maize, and canopy temperature extracted from thermal infrared images was one of them. Additionally, the most suitable feature sampling window was determined through multi-scale sampling experiments. The grid search method was used to optimize the hyperparameters of models such as Gradient Boosting, XGBoost, and Random Forest, and their accuracy was compared. The results showed that, by utilizing a 3 × 3 feature sampling window and 9 features with the highest contributions, the LAI inversion accuracy of the whole growth stage based on Random Forest could reach R² = 0.90 and RMSE = 0.38 m²/m². Compared with the single UAV data source mode, the inversion accuracy was enhanced by nearly 25%. The R² in the jointing, tasseling, and filling stages were 0.87, 0.86, and 0.62, respectively. Moreover, this study verified the significant role of thermal infrared data in LAI inversion, providing a new method for fine LAI inversion of maize. Full article

To achieve large-scale stitching of the hyperspectral remote sensing images obtained by unmanned aerial vehicles (UAVs) equipped with an acousto-optic tunable filter spectrometer, this study proposes a method based on a feature fusion strategy and a seam-finding strategy using hyperspectral image classification. In the feature extraction stage, SuperPoint deep features from images in different spectral segments of the data cube were extracted and fused. The feature depth matcher, LightGlue, was employed for feature matching. During the data cube fusion stage, unsupervised K-means spectral classification was performed separately on the two hyperspectral data cubes. Subsequently, grayscale transformations were applied to the classified images. A dynamic programming method, based on a grayscale loss function, was then used to identify seams in the transformed images. Finally, the identified splicing seam was applied across all bands to produce a unified hyperspectral data cube. The proposed method was applied to hyperspectral data cubes acquired at specific waypoints by UAVs using an acousto-optic tunable filter spectral imager. Experimental results demonstrated that the proposed method outperformed both single-spectral-segment feature extraction methods and stitching methods that rely on seam identification from a single spectral segment. The improvement was evident in both the spatial and spectral dimensions. Full article

Remote sensing (RS) spectral time series provide a substantial source of information for the regular and cost-efficient monitoring of the Earth’s surface. Important monitoring tasks include land use and land cover classification, change detection, forest monitoring and crop type identification, among others. To develop accurate solutions for RS-based applications, often supervised shallow/deep learning algorithms are used. However, such approaches usually require fixed-length inputs and large labeled datasets. Unfortunately, RS images acquired by optical sensors are frequently degraded by aerosol contamination, clouds and cloud shadows, resulting in missing observations and irregular observation patterns. To address these issues, efforts have been made to implement frameworks that generate meaningful representations from the irregularly sampled data streams and alleviate the deficiencies of the data sources and supervised algorithms. Here, we propose a conceptually and computationally simple representation learning (RL) approach based on autoencoders (AEs) to generate discriminative features for crop type classification. The proposed methodology includes a set of single-layer AEs with a very limited number of neurons, each one trained with the mono-temporal spectral features of a small set of samples belonging to a class, resulting in a model capable of processing very large areas in a short computational time. Importantly, the developed approach remains flexible with respect to the availability of clear temporal observations. The signal derived from the ensemble of AEs is the reconstruction difference vector between input samples and their corresponding estimations, which are averaged over all cloud-/shadow-free temporal observations of a pixel location. This averaged reconstruction difference vector is the base for the representations and the subsequent classification. Experimental results show that the proposed extremely light-weight architecture indeed generates separable features for competitive performances in crop type classification, as distance metrics scores achieved with the derived representations significantly outperform those obtained with the initial data. Conventional classification models were trained and tested with representations generated from a widely used Sentinel-2 multi-spectral multi-temporal dataset, BreizhCrops. Our method achieved 77.06% overall accuracy, which is ∼6% higher than that achieved using original Sentinel-2 data within conventional classifiers and even ∼4% better than complex deep models such as OmnisCNN. Compared to extremely complex and time-consuming models such as Transformer and long short-term memory (LSTM), only a 3% reduction in overall accuracy was noted. Our method uses only 6.8k parameters, i.e., ∼400x fewer than OmnicsCNN and ∼27x fewer than Transformer. The results prove that our method is competitive in terms of classification performance compared with state-of-the-art methods while substantially reducing the computational load. Full article

In this work, a highly sensitive, selective, and industrially compatible gas sensor prototype is presented. The sensor utilizes three distributed-feedback quantum cascade lasers (DFB-QCLs), employing wavelength modulation spectroscopy (WMS) for the detection of hydrogen sulfide (H₂S), methane (CH₄), methyl mercaptan (CH₃SH), and carbonyl sulfide (COS) in the spectral regions of 8.0 µm, 7.5 µm, and 4.9 µm, respectively. In addition, field-programmable gate array (FPGA) hardware is used for real-time signal generation, laser driving, signal processing, and handling industrial communication protocols. To comply with on-site safety standards, the QCL sensor prototype is housed in an industrial-grade enclosure and equipped with the necessary safety features to ensure certified operation under ATEX/IECEx regulations for hazardous and explosive environments. The system integrates an automated gas sampling and conditioning module, alongside a purge and pressurization system, with intrinsic safety electronic components, thereby enabling reliable explosion prevention and malfunction protection. Detection limits of approximately 0.3 ppmv for H₂S, 60 ppbv for CH₃SH, and 5 ppbv for COS are demonstrated. Noise-equivalent absorption sensitivity (NEAS) levels for H₂S, CH₃SH, and COS were determined to be 5.93 × 10⁻⁹, 4.65 × 10⁻⁹, and 5.24 × 10⁻¹⁰ cm⁻¹ Hz^−1/2. The suitability of the sensor prototype for simultaneous sulfur species monitoring is demonstrated in process streams of a hydrodesulphurization (HDS) and fluid catalytic cracking (FCC) unit at the project’s industrial partner, OMV AG. Full article

The great interest in the rapid and reliable differentiation of extra virgin olive oil from other olive oil categories is directly related to its unique sensory characteristics and high market prices. The aim of the present study was to investigate the potential of FTIR as a rapid and non-invasive technique to discriminate extra virgin olive oil (EVOO) from other olive oil categories (virgin olive oil, ordinary, and lampante) based on the acquired spectral profile of olive oil. Spectral data were collected, pre-processed, and correlated by Random Forest (RF) analysis with the sensory category (EVOO vs. other) of olive oil samples, as defined by sensory analysis undertaken previously by trained panelists. The results showed that the application of Savitzky–Golay (S-G) smoothing with a second derivative (d = 2), second- and third-order polynomial (p = 2, p = 3), and window size (w) of 12 and 13 points achieved the highest accuracy (0.91) between the two classes of samples. Characteristic spectral bands of triacylglycerols related to the carbonyl groups present in triacylglycerols (C=O) located near 1744 cm⁻¹ (specific features: 1739, 1748, and 1751 cm⁻¹), the fingerprinting area 1250–1000 cm⁻¹ (specific features: 1088, 1094, 1116, 1123, 1124, 1158, 1162, 1236, 1240, and 1247 cm⁻¹), which correspond to CH bending, and 1680 cm⁻¹, which is associated with unsaturated aldehydes were observed to constitute the main basis of the discrimination of EVOO from the “other” class. The ability of the model to achieve high classification accuracy demonstrates the robustness of the FTIR spectral data combined with advanced machine learning techniques. Due to the lower cost and more rapid analysis time afforded by FTIR, this method provides promising perspectives for industrial olive oil classification. Full article

Chlorophyll is crucial for pear tree growth and fruit quality. In order to integrate the unmanned aerial vehicle (UAV) multispectral vegetation indices and textural features to realize the estimation of the SPAD value of pear leaves, this study used the UAV multispectral remote sensing images and ground measurements to extract the vegetation indices and textural features, and analyze their correlation with the SPAD value of leaves during the fruit expansion period of the pear tree. Finally, four machine learning methods, namely XGBoost, random forest (RF), back-propagation neural network (BPNN), and optimized integration algorithm (OIA), were used to construct inversion models of the SPAD value of pear trees, with different feature inputs based on vegetation indices, textural features, and their combinations, respectively. Moreover, the differences among these models were compared. The results showed the following: (1) both vegetation indices and textural features were significantly correlated with SPAD values, which were important indicators for estimating the SPAD values of pear leaves; (2) combining vegetation indices and textural features significantly improved the accuracy of SPAD value estimation compared with a single feature type; (3) the four machine learning algorithms demonstrated good predictive ability, and the OIA model outperformed the single model, with the model based on the OIA inversion model combining vegetation indices and textural features having the best accuracy, with R2 values of 0.931 and 0.877 for the training and validation sets, respectively. This study demonstrated the efficacy of integrating multiple models and features to accurately invert SPAD values, which, in turn, supported the refined management of pear orchards. Full article

A new method to discover open-loop, unstable, longitudinal aerodynamic parameters, using a ‘two-stage optimization approach’ for designing optimal inputs, and with an application on the fighter aircraft platform, has been presented. System identification of supersonic aircraft requires formulating optimal inputs due to the extremely limited maneuver time, high angles of attack, restricted flight conditions, and the demand for an enhanced computational effect. A pre-requisite of the parametric model identification is to have a priori aerodynamic parameter estimates, which were acquired using linear regression and Least Squares (LS) estimation, based upon simulated time histories of outputs from heuristic inputs, using an F-16 Flight Dynamic Model (FDM). In the ‘first stage’, discrete-time pseudo-random binary signal (PRBS) inputs were optimized using a minimization algorithm, in accordance with aircraft spectral features and aerodynamic constraints. In the ‘second stage’, an innovative concept of integrating the Fisher Informative Matrix with cost function based upon D-optimality criteria and Crest Factor has been utilized to further optimize the PRBS parameters, such as its frequency, amplitude, order, and periodicity. This unique optimum design also solves the problem of non-convexity, model over-parameterization, and misspecification; these are usually caused by the use of traditional heuristic (doublets and multistep) optimal inputs. After completing the optimal input framework, parameter estimation was performed using Maximum Likelihood Estimation. A performance comparison of four different PRBS inputs was made as part of our investigations. The model performance was validated by using statistical metrics, namely the following: residual analysis, standard errors, t statistics, fit error, and coefficient of determination (R2). Results have shown promising model predictions, with an accuracy of more than 95%, by using a Single Sequence Band-limited PRBS optimum input. This research concludes that, for the identification of the decoupled longitudinal Linear Time Invariant (LTI) aerodynamic model of supersonic aircraft, optimum PRBS shows better results than the traditional frequency sweeps, such as multi-sine, doublets, square waves, and impulse inputs. This work also provides the ability to corroborate control and stability derivatives obtained from Computational Fluid Dynamics (CFD) and wind tunnel testing. This further refines control law design, dynamic analysis, flying qualities assessments, accident investigations, and the subsequent design of an effective ground-based training simulator. Full article

The accurate classification of broad-absorption line (BAL) quasars and non-broad-absorption line (non-BAL) quasars is key in understanding active galactic nuclei (AGN) and the evolution of the universe. With the rapid accumulation of data from large-scale spectroscopic survey projects (e.g., LAMOST, SDSS, and DESI), traditional manual classification methods face limitations. In this study, we propose a new method based on deep learning techniques to achieve an accurate distinction between BAL quasars and non-BAL quasars. We use a convolutional neural network (CNN) as the core model, in combination with various dimensionality reduction techniques, including principal component analysis (PCA), t-distributed stochastic neighborhood embedding (t-SNE), and isometric mapping (ISOMAP). These dimensionality reduction methods help extract meaningful features from high-dimensional spectral data while reducing model complexity. We employ quasar spectra from the 16th data release (DR16) of the Sloan Digital Sky Survey (SDSS) and obtain classification labels from the DR16Q quasar catalogues to train and evaluate our model. Through extensive experiments and comparisons, the combination of PCA and CNN achieve a test accuracy of 99.11%, demonstrating the effectiveness of deep learning for classifying the spectral data. Additionally, we explore other dimensionality reduction methods and machine learning models, providing valuable insights for future research in this field. Full article

Land use/land cover (LULC) nomenclature is commonly organized as a tree-like hierarchy, contributing to hierarchical LULC mapping. The hierarchical structure is typically defined by considering natural characteristics or human activities, which may not optimally align with the discriminative features and class relationships present in remotely sensed imagery. This paper explores a novel cluster-based class hierarchy modeling framework that generates data-driven hierarchical structures for LULC semantic segmentation. First, we perform spectral clustering on confusion matrices generated by a flat model, and then we introduce a hierarchical cluster validity index to obtain the optimal number of clusters to generate initial class hierarchies. We further employ ensemble clustering techniques to yield a refined final class hierarchy. Finally, we conduct comparative experiments on three benchmark datasets. Results demonstrating that the proposed method outperforms predefined hierarchies in both hierarchical LULC segmentation and classification. Full article

Neural audio reconstruction is an important subtopic of Neural Audio Synthesis (NAS), which is a current emerging topic of modern Artificial Intelligence (AI) applications. The objective of a neural audio reconstruction model is to achieve a viable audio waveform from an audio feature representation that excludes the phase information. Since the data-dependent nature of such systems demands an increased quantity of data, methods of increasing the quantity of data for neural network training arise as a topic of substantial interest. Although the applications of data augmentation methods for classification tasks are well documented, there is still room for development for applications of such methods on signal synthesis tasks. Additionally, the Fractional-Order Calculus (FOC) framework provides possibilities for quality applications for the signal processing domain. Still, it is important to show that the methods based on the FOC framework can be applied to different application domains to show the capabilities of this framework. In this paper, FOC-based methods are applied to a speech dataset for data augmentation purposes to increase the audio reconstruction performance of a neural network, a spectral consistency-based neural audio reconstruction model called Deep Griffin-Lim Iteration (DeGLI), with respect to objective measures PESQ and STOI. An FOC-based method for rescaling linear frequency for augmenting magnitude spectrogram data is proposed. Furthermore, together with an FOC-based phase estimation method, it is shown that an augmentation strategy that has the objective of increased spectral consistency should be considered in data augmentation for audio reconstruction tasks. The test results reveal that this type of strategy increases the performance of a spectral consistency-based neural audio reconstruction model by over 13% for smaller depths. Full article

Noise in 3D photogrammetric point clouds—both close-range and UAV-generated—poses a significant challenge to the accuracy and usability of digital models. This study presents a novel deep learning-based approach to improve the quality of point clouds by addressing this issue. We propose a two-step methodology: first, a variational autoencoder reduces features, followed by clustering models to assess and mitigate noise in the point clouds. This study evaluates four clustering methods—k-means, agglomerative clustering, Spectral clustering, and Gaussian mixture model—based on photogrammetric parameters, reprojection error, projection accuracy, angles of intersection, distance, and the number of cameras used in tie point calculations. The approach is validated using point cloud data from the Temple of Neptune in Paestum, Italy. The results show that the proposed method significantly improves 3D reconstruction quality, with k-means outperforming other clustering techniques based on three evaluation metrics. This method offers superior versatility and performance compared to traditional and machine learning techniques, demonstrating its potential to enhance UAV-based surveying and inspection practices. Full article

Emotion recognition is an advanced technology for understanding human behavior and psychological states, with extensive applications for mental health monitoring, human–computer interaction, and affective computing. Based on electroencephalography (EEG), the biomedical signals naturally generated by the brain, this work proposes a resource-efficient multi-entropy fusion method for classifying emotional states. First, Discrete Wavelet Transform (DWT) is applied to extract five brain rhythms, i.e., delta, theta, alpha, beta, and gamma, from EEG signals, followed by the acquisition of multi-entropy features, including Spectral Entropy (PSDE), Singular Spectrum Entropy (SSE), Sample Entropy (SE), Fuzzy Entropy (FE), Approximation Entropy (AE), and Permutation Entropy (PE). Then, such entropies are fused into a matrix to represent complex and dynamic characteristics of EEG, denoted as the Brain Rhythm Entropy Matrix (BREM). Next, Dynamic Time Warping (DTW), Mutual Information (MI), the Spearman Correlation Coefficient (SCC), and the Jaccard Similarity Coefficient (JSC) are applied to measure the similarity between the unknown testing BREM data and positive/negative emotional samples for classification. Experiments were conducted using the DEAP dataset, aiming to find a suitable scheme regarding similarity measures, time windows, and input numbers of channel data. The results reveal that DTW yields the best performance in similarity measures with a 5 s window. In addition, the single-channel input mode outperforms the single-region mode. The proposed method achieves 84.62% and 82.48% accuracy in arousal and valence classification tasks, respectively, indicating its effectiveness in reducing data dimensionality and computational complexity while maintaining an accuracy of over 80%. Such performances are remarkable when considering limited data resources as a concern, which opens possibilities for an innovative entropy fusion method that can help to design portable EEG-based emotion-aware devices for daily usage. Full article

With the increasing demand for wood in the wood market and the frequent trade of high-value wood, the accurate identification of wood varieties has become essential. This study employs two hyperspectral imaging systems—visible and near-infrared spectroscopy (VNIR) and short-wave infrared spectroscopy (SWIR)—in combination with a deep learning model to propose a method for wood species identification. Spectral data from wood samples were obtained through hyperspectral imaging technology, and classification was performed using a combination of convolutional neural networks (CNNs) and Transformer models. Multiple spectral preprocessing and feature extraction techniques were applied to enhance data quality and model performance. The experimental results show that the full-band modeling is significantly better than the feature-band modeling in terms of classification accuracy and robustness. Among them, the classification accuracy of SWIR reaches 100%, the number of model parameters is 1,286,228, the total size of the model is 4.93 MB, and the Floating Point Operations (FLOPs) is 1.29 M. Additionally, the Shapley Additive Explanation (SHAP) technique was utilized for model interpretability, revealing key spectral bands and feature regions that the model emphasizes during classification. Compared with other models, CNN-Transformer is more effective in capturing the key features. This method provides an efficient and reliable tool for the wood industry, particularly in wood processing and trade, offering broad application potential and significant economic benefits. Full article

Background/Objectives: Diffuse myocardial fibrosis and altered deformation are relevant prognostic factors in aortic stenosis (AS) patients. The aim of this exploratory study was to investigate the relationship between myocardial strain, and myocardial extracellular volume (ECV) in patients with severe AS with a photon-counting detector (PCD)-CT. Methods: We retrospectively included 77 patients with severe AS undergoing PCD-CT imaging for transcatheter aortic valve replacement (TAVR) planning between January 2022 and May 2024 with a protocol including a non-contrast cardiac scan, an ECG-gated helical coronary CT angiography (CCTA), and a cardiac late enhancement scan. Myocardial strain was assessed with feature tracking from CCTA and ECV was calculated from spectral cardiac late enhancement scans. Results: Patients with cardiac amyloidosis (n = 4) exhibited significantly higher median mid-myocardial ECV (48.2% versus 25.5%, p = 0.048) but no significant differences in strain values (p > 0.05). Patients with prior myocardial infarction (n = 6) had reduced median global longitudinal strain values (−9.1% versus −21.7%, p < 0.001) but no significant differences in global mid-myocardial ECV (p > 0.05). Significant correlations were identified between the global longitudinal, circumferential, and radial strains and the CT-derived left ventricular ejection fraction (EF) (all, p < 0.001). Patients with low-flow, low-gradient AS and reduced EF exhibited lower median global longitudinal strain values compared with those with high-gradient AS (−15.2% versus −25.8%, p < 0.001). In these patients, the baso-apical mid-myocardial ECV gradient correlated with GLS values (R = 0.28, p = 0.02). Conclusions: In patients undergoing PCD-CT for TAVR planning, ECV and GLS may enable us to detect patients with cardiac amyloidosis and reduced myocardial contractility Full article