Search Results (4,337)

Accurate automatic sleep stage classification from single-channel EEG remains challenging due to the need for effective extraction of multiscale neurophysiological features and modeling of long-range temporal dependencies. This study aims to address these limitations by developing an efficient and compact deep learning architecture tailored for wearable and edge device applications. We propose MultiScaleSleepNet, a hybrid convolutional neural network–bidirectional long short-term memory–transformer architecture that extracts multiscale temporal and spectral features through parallel convolutional branches, followed by sequential modeling using a BiLSTM memory network and transformer-based attention mechanisms. The model obtained an accuracy, macro-averaged F1 score, and kappa coefficient of 88.6%, 0.833, and 0.84 on the Sleep-EDF dataset; 85.6%, 0.811, and 0.80 on the Sleep-EDF Expanded dataset; and 84.6%, 0.745, and 0.79 on the SHHS dataset. Ablation studies indicate that attention mechanisms and spectral fusion consistently improve performance, with the most notable gains observed for stages N1, N3, and rapid eye movement. MultiScaleSleepNet demonstrates competitive performance across multiple benchmark datasets while maintaining a compact size of 1.9 million parameters, suggesting robustness to variations in dataset size and class distribution. The study supports the feasibility of real-time, accurate sleep staging from single-channel EEG using parameter-efficient deep models suitable for portable systems. Full article

With global climate change, urbanization, and agricultural resource limitations, precision agriculture and crop monitoring are crucial worldwide. Integrating multi-source remote sensing data with deep learning enables accurate crop mapping, but selecting optimal network architectures remains challenging. To improve remote sensing-based fruit planting classification and support orchard management and rural revitalization, this study explored feature selection and network optimization. We proposed an improved CF-EfficientNet model (incorporating FGMF and CGAR modules) for fruit planting classification. Multi-source remote sensing data (Sentinel-1, Sentinel-2, and SRTM) were used to extract spectral, vegetation, polarization, terrain, and texture features, thereby constructing a high-dimensional feature space. Feature selection identified 13 highly discriminative bands, forming an optimal dataset, namely the preferred bands (PBs). At the same time, two classification datasets—multi-spectral bands (MS) and preferred bands (PBs)—were constructed, and five typical deep learning models were introduced to compare performance: (1) EfficientNetB0, (2) AlexNet, (3) VGG16, (4) ResNet18, (5) RepVGG. The experimental results showed that the EfficientNetB0 model based on the preferred band performed best in terms of overall accuracy (87.1%) and Kappa coefficient (0.677). Furthermore, a Fine-Grained Multi-scale Fusion (FGMF) and a Condition-Guided Attention Refinement (CGAR) were incorporated into EfficientNetB0, and the traditional SGD optimizer was replaced with Adam to construct the CF-EfficientNet architecture. The results indicated that the improved CF-EfficientNet model achieved high performance in crop classification, with an overall accuracy of 92.6% and a Kappa coefficient of 0.830. These represent improvements of 5.5 percentage points and 0.153, compared with the baseline model, demonstrating superiority in both classification accuracy and stability. Full article

With the rapid development of X-ray free-electron lasers (XFELs), time-resolved resonant inelastic X-ray scattering (tr-RIXS) has attracted more attention. The preliminary designs of the tr-RIXS branchline and expected performance characteristics at the Shenzhen Superconducting Soft X-ray Free Electron Laser (${\mathrm{S}}^3\mathrm{FEL}$) are presented. A start-to-end simulation of the tr-RIXS branchline based on the 6-D phase space ray-tracing method of beamline simulation software package FURION was performed. The simulation design satisfies the key requirements of the tr-RIXS branchline, including spatial dispersion in the vertical dimension, temporal resolution, energy resolution, efficient utilization of SASE spectral photons, and spatial uniformity of the beam spot sizes across different wavelengths. Full article

Eye-tracking technology enables communication for individuals with muscle control difficulties, making it a valuable assistive tool. Traditional systems rely on electrooculography (EOG) or infrared devices, which are accurate but costly and invasive. While vision-based systems offer a more accessible alternative, they have not been extensively explored for eye-writing recognition. Additionally, the natural instability of eye movements and variations in writing styles result in inconsistent signal lengths, which reduces recognition accuracy and limits the practical use of eye-writing systems. To address these challenges, we propose a novel vision-based eye-writing recognition approach that utilizes a webcam-captured dataset. A key contribution of our approach is the introduction of a Discrete Fourier Transform (DFT)-based length normalization method that standardizes the length of each eye-writing sample while preserving essential spectral characteristics. This ensures uniformity in input lengths and improves both efficiency and robustness. Moreover, we integrate a hybrid deep learning model that combines 1D Convolutional Neural Networks (CNN) and Temporal Convolutional Networks (TCN) to jointly capture spatial and temporal features of eye-writing. To further improve model robustness, we incorporate data augmentation and initial-point normalization techniques. The proposed system was evaluated using our new webcam-captured Arabic numbers dataset and two existing benchmark datasets, with leave-one-subject-out (LOSO) cross-validation. The model achieved accuracies of 97.68% on the new dataset, 94.48% on the Japanese Katakana dataset, and 98.70% on the EOG-captured Arabic numbers dataset—outperforming existing systems. This work provides an efficient eye-writing recognition system, featuring robust preprocessing techniques, a hybrid deep learning model, and a new webcam-captured dataset. Full article

Satellite remote sensing has emerged as a reliable and cost-effective approach for monitoring inland water quality, offering spatial and temporal advantages over traditional in situ methods. Lake Victoria, the largest tropical lake and a critical freshwater resource for East Africa, faces increasing eutrophication driven by nutrient inflows from agriculture, urbanization, and industrial activities. This study assessed the spatiotemporal dynamics of water quality along Uganda’s Lake Victoria coast by integrating field measurements (2014–2024) with Landsat 8/9 imagery. Chlorophyll-a, a proxy for algal blooms, and Secchi disk depth, an indicator of water clarity, were selected as key parameters. Cloud-free satellite images were processed using the Dark Object Subtraction method, and spectral reflectance values were correlated with field data. Linear regression models from single bands and band ratios showed strong performance, with adjusted R² values of up to 0.88. When tested on unseen data, the models achieved R² values above 0.70, confirming robust predictive ability. Results revealed high algal concentrations for nearshore and clearer offshore waters. These models provide an efficient framework for monitoring eutrophication, guiding restoration priorities, and supporting sustainable water management in Lake Victoria. Full article

Platycodonis radix is a commonly used traditional Chinese medicine (TCM) material. Its bioactive compounds and medicinal value are closely related to its geographical origin. The internal components of Platycodonis radix from different origins are different due to the influence of environmental factors such as soil and climate. These differences can affect the medicinal value. Therefore, accurate identification of Platycodonis radix origin is crucial for drug safety and scientific research. Traditional methods of identification of TCM materials, such as morphological identification and physicochemical analysis, cannot meet the efficiency requirements. Although emerging technologies such as computer vision and spectroscopy can achieve rapid detection, their accuracy in identifying the origin of Platycodonis radix is limited when relying solely on RGB images or spectral features. To solve this problem, we aim to develop a rapid, non-destructive, and accurate method for origin identification of Platycodonis radix using hyperspectral imaging (HSI) combined with deep learning. We captured hyperspectral images of Platycodonis radix slices in 400–1000 nm range, and proposed a deep learning classification model based on these images. Our model uses one-dimensional (1D) convolution kernels to extract spectral features and two-dimensional (2D) convolution kernels to extract spatial features, fully utilizing the hyperspectral data. The average accuracy has reached 96.2%, significantly better than that of 49.0% based on RGB images and 81.8% based on spectral features in 400–1000 nm range. Furthermore, based on hyperspectral images, our model’s accuracy is 14.6%, 8.4%, and 9.6% higher than the variants of VGG, ResNet, and GoogLeNet, respectively. These results not only demonstrate the advantages of HSI in identifying the origin of Platycodonis radix, but also demonstrate the advantages of combining 1D convolution and 2D convolution in hyperspectral image classification. Full article

This article presents an innovative chaotic communication scheme that integrates the multiuser access technique known as Wideband Code Division Multiple Access (W-CDMA) with the chaos-based selective strategy Chaos-Based Selective Symbol (CSS) and the unconventional modulation Chaos Parameter Shift Keying (CPSK). The system is designed to operate in the 2.45 GHz band and provides a robust and efficient alternative to conventional schemes such as Quadrature Amplitude Modulation (QAM). The proposed CPSK modulation enables the encoding of information for multiple users by regulating the 36 parameters of a Reconfigurable Chaotic Oscillator (RCO), theoretically allowing the simultaneous transmission of up to $2^{24}$ independent users over the same channel. The CSS technique encodes each user’s information using a unique chaotic segment configuration generated by the RCO; this serves as a reference for binary symbol encoding. W-CDMA further supports the concurrent transmission of data from multiple users through orthogonal sequences, minimizing inter-user interference. The system was digitally implemented on the Artix-7 AC701 FPGA (XC7A200TFBG676-2) to evaluate logic-resource requirements, while RF validation was carried out using a ZedBoard FPGA equipped with an AD9361 transceiver. Experimental results demonstrate optimal performance in the 2.45 GHz band, confirming the effectiveness of the chaos-based W-CDMA approach as a multiuser access technique for high-spectral-density environments and its potential for use in 5G applications. Full article

Existing multivariate signal decomposition methods insufficiently account for the mechanical characteristics of gear systems, limiting their capability in fault feature extraction. To address this limitation, we propose a novel method, Multivariate Blaschke-based Mode Decomposition (MBMD). In MBMD, multivariate vibration signals are modeled as multi-dimensional responses of the gear system. Using Stochastic Adaptive Fourier Decomposition (SAFD), these signals are represented as a unified combination of Blaschke products, enabling adaptive multi-channel information fusion. To achieve modal alignment, we introduce the concept of Blaschke multi-spectra, reformulating the decomposition problem as a spectrum segmentation task, which is solved via a joint spectral segmentation algorithm. Furthermore, a voting-based filter bank, designed according to gear fault mechanisms, is employed to suppress noise and enhance fault feature extraction. Experimental validation on gear fault signals demonstrates the effectiveness of MBMD, showing that it can efficiently integrate multivariate information and achieve more accurate fault diagnosis than existing methods, providing a new perspective for mechanical fault diagnosis. Full article

Time-domain signal models have been widely applied to single-channel music source separation tasks due to their ability to overcome the limitations of fixed spectral representations and phase information loss. However, the high acoustic similarity and synchronous temporal evolution between vocals and accompaniment make accurate separation challenging for existing time-domain models. These challenges are mainly reflected in two aspects: (1) the lack of a dynamic mechanism to evaluate the contribution of each source during feature fusion, and (2) difficulty in capturing fine-grained temporal details, often resulting in local artifacts in the output. To address these issues, we propose an attention-driven time-domain convolutional network for vocal and accompaniment source separation. Specifically, we design an embedding attention module to perform adaptive source weighting, enabling the network to emphasize components more relevant to the target mask during training. In addition, an efficient convolutional block attention module is developed to enhance local feature extraction. This module integrates an efficient channel attention mechanism based on one-dimensional convolution while preserving spatial attention, thereby improving the ability to learn discriminative features from the target audio. Comprehensive evaluations on public music datasets demonstrate the effectiveness of the proposed model and its significant improvements over existing approaches. Full article

High-mountain microalgae exhibit remarkable adaptability to extreme environments, making them promising candidates for sustainable biorefineries. We evaluated how photoperiod (12:12, 18:6, 24:0 h) and LED spectra (cool white, full spectrum, red–blue 4:1) affect growth and metabolite formation in Chlorella sp. UFPS019 and Scenedesmus sp. UFPS021. Biomass peaked in Chlorella under red–blue 18:6 (≈1.8 g L⁻¹) and in Scenedesmus under red–blue 24:0 (≈1.7 g L⁻¹), revealing species-specific responses. Carbohydrate fractions were maximized under red–blue 12:12 in both species, and continuous light (24:0) depressed carbohydrate content—most notably under full spectrum. Protein content was highest under red–blue 18:6 in Chlorella sp. and under red–blue 12:12–18:6 in Scenedesmus sp. Lipid fractions increased with light duration, peaking under red–blue 18:6–24:0 in Chlorella and under red–blue 18:6–24:0—with Cool White 24:0 also high—in Scenedesmus sp. Although extended illumination favored lipids, intermediate photoperiods (12:12–18:6) provided better productivity-to-energy trade-offs and broader metabolic profiles. These results show that tuning spectral composition and photoperiod to species-specific physiology enables the targeted, energy-aware production of proteins, carbohydrates, or lipids; red–blue at intermediate durations is a robust, energy-efficient regime, whereas longer exposures can be used strategically when lipid enrichment is prioritized. Full article

Remote sensing images, which obtain surface information from aerial or satellite platforms, are of great significance in fields such as environmental monitoring, urban planning, agricultural management, and disaster response. However, due to the complex and diverse types of ground coverage and significant differences in spectral characteristics in remote sensing images, achieving high-quality semantic segmentation still faces many challenges, such as blurred target boundaries and difficulty in recognizing small-scale objects. To address these issues, this study proposes a novel deep learning model, MKF-NET. The fusion of KAN convolution and Vision Transformer (ViT), combined with the multi-scale feature extraction and dense connection mechanism, significantly improves the semantic segmentation performance of remote sensing images. Experiments were conducted on the LoveDA dataset to systematically evaluate the segmentation performance of MKF-NET and several existing traditional deep learning models (U-net, Unet++, Deeplabv3+, Transunet, and U-KAN). Experimental results show that MKF-NET performs best in many indicators: it achieved a pixel precision of 78.53%, a pixel accuracy of 79.19%, an average class accuracy of 76.50%, and an average intersection-over-union ratio of 64.31%; it provides efficient technical support for remote sensing image analysis. Full article

In Northeast Brazil, climatic factors and technology synergistically enhance melon productivity and fruit quality. However, the region requires further research on the efficient use of water resources, particularly in determining the crop coefficient (Kc), which comprises the evaporation coefficient (Ke) and the transpiration coefficient (Kcb). Air temperature affects crop growth and development, altering the spectral response and the Kcb. However, the direct influence of air temperature on Kcb and spectral response remains underemphasized. This study employed unmanned aerial vehicle (UAV) with RGB and Red-Green-NIR sensors imagery to extract biophysical parameters for improved water management in melon cultivation in semiarid northern Bahia. Field experiments were conducted during two distinct periods: warm (October–December 2019) and cool (June–August 2020). The ‘Gladial’ and ‘Cantaloupe’ cultivars exhibited higher Kcb values during the warm season (2.753–3.450 and 3.087–3.856, respectively) and lower during the cool season (0.815–0.993 and 1.118–1.317). NDVI-based estimates of Kcb showed strong correlations with field data (r > 0.80), confirming its predictive potential. The results demonstrate that UAV-derived NDVI enables reliable estimation of melon Kcb across seasons, supporting its application for evapotranspiration modeling and precision irrigation in the Brazilian semiarid context. Full article

In recent years, the availability of automated change detection algorithms in Google Earth Engine has permitted the cloud-based processing of large quantities of satellite imagery. Models such as the Continuous Change Detection and Classification (CCDC), CCDC-Spectral Mixture Analysis (CCDC-SMA), and Landsat-based Detection of Trends in Disturbance and Recovery (LandTrendr) allow users to exploit decades of Earth Observations (EOs), leveraging the Landsat archive and data from other sensors to detect disturbances in forest ecosystems. Despite the wide adoption of these methods, robust documentation, and a growing community of users, little research has systematically detailed their tuning process in mangrove environments. This work aims to identify the best practices for applying these models to monitor changes within mangrove forest cover, which has been declining gradually in Belize the last several decades. Partnering directly with the Belizean Forest Department, our team developed a replicable, efficient methodology to annually update the country’s mangrove extent, employing EO-based change detection. We ran a series of model variations in both CCDC-SMA and LandTrendr to identify the parameterizations best suited to identifying change in Belizean mangroves. Applying the best performing model run to the starting 2017 mangrove extent, we estimated a total loss of 540 hectares in mangrove coverage by 2024. Overall accuracy across thirty variations in model runs of LandTrendr and CCDC-SMA ranged from 0.67 to 0.75. While CCDC-SMA generally detected more disturbances and had higher precision for true changes, LandTrendr runs tended to have higher recall. Our results suggest LandTrendr offered more flexibility in balancing precision and recall for true changes compared to CCDC-SMA, due to its greater variety of adjustable parameters. Full article

This work presents a comparative study of graphene exfoliation technologies from various graphite precursors—spectral graphite and thermally expanded graphite (Graflex)—using ultrasonic treatment and electrochemical methods in the presence of the ionic surfactant Nafion. The influence of exfoliation parameters, the nature of the starting material, and the presence of surfactant additives on the morphology, dispersibility, stability, and structural characteristics of the resulting graphene-containing dispersions was investigated. Particular attention is paid to a two-step technology combining pulsed electrochemical exfoliation with subsequent mild ultrasonic treatment. Comprehensive characterization of the samples was carried out using UV–Vis spectroscopy, X-ray diffraction (XRD), thermogravimetric analysis (TGA), electron microscopy, electron diffraction (ED), dynamic light scattering (DLS), and X-ray photoelectron spectroscopy (XPS). It was found that the use of Nafion significantly enhances exfoliation efficiency and contributes to the stabilization of the dispersions. Graphene sheets obtained from Graflex exhibit significantly larger lateral dimensions (up to 1 μm or more) compared to those exfoliated from spectral graphite (100–300 nm). The approach combining the use of Graflex and pulsed electrochemical exfoliation in the presence of Nafion with subsequent low-power ultrasonic treatment enables the production of few-layer graphene (1–3 layers) with high stability. Full article

Coded-Aperture Snapshot Spectral Imaging (CASSI) systems acquire 3D spatial–spectral information on dynamic targets by converting 3D hyperspectral images (HSIs) into 2D compressed measurements. Various end-to-end networks have been proposed for HSI reconstruction from these measurements. However, these methods have not explored the frequency-domain information of HSIs. This research presents the spatial/spectral-frequency adaptive network (SSFAN) for CASSI image reconstruction. A frequency-division transformation (FDT) decomposes HSIs into distinct Fourier frequency components, enabling multiscale feature extraction in the frequency domain. The proposed dual-branch architecture consists of a spatial–spectral module (SSM) to preserve spatial–spectral consistency and a frequency division module (FDM) to model inter-frequency dependencies. Channel compression/expansion modules are integrated into the FDM to balance computational efficiency and reconstruction quality. Frequency-division loss supervises feature learning across divided frequency channels. Ablation experiments validate the contributions of each network module. Furthermore, comparison experiments on synthetic and real CASSI datasets demonstrate that SSFAN outperforms state-of-the-art end-to-end methods in reconstruction performance. Full article