Search Results (1,695)

Unmanned aerial vehicle (UAV)-captured RGB imagery, with high spatial resolution and ease of acquisition, is increasingly applied to individual tree crown detection (ITCD). However, ITCD in dense subtropical forests remains challenging due to overlapping crowns, variable crown size, and similar spectral responses between neighbouring crowns. This paper investigates to what extent the ITCD accuracy can be improved by using dual-seasonal UAV-captured RGB imagery in different subtropical forest types: urban broadleaved, planted coniferous, and mixed coniferous–broadleaved forests. A modified YOLOv8 model was employed to fuse the features extracted from dual-seasonal images and perform the ITCD task. Results show that dual-seasonal imagery consistently outperformed single-seasonal datasets, with the greatest improvement in mixed forests, where the F1 score range increased from 56.3%–60.7% (single-seasonal datasets) to 69.1%–74.5% (dual-seasonal datasets) and the AP value range increased from 57.2%–61.5% to 70.1%–72.8%. Furthermore, performance fluctuations were smaller for dual-seasonal datasets than for single-seasonal datasets. Finally, our experiments demonstrate that the modified YOLOv8 model, which fuses features extracted from dual-seasonal images within a dual-branch module, outperformed both the original YOLOv8 model with channel-wise stacked dual-seasonal inputs and the Faster R-CNN model with a dual-branch module. The experimental results confirm the advantages of using dual-seasonal imagery for ITCD, as well as the critical role of model feature extraction and fusion strategies in enhancing ITCD accuracy. Full article

Substantial improvements in the performance of optical interconnects based on multi-mode fibers are required to support emerging single-channel data transmission rates of 200 Gb/s and 400 Gb/s. Future optical components must combine very high modulation bandwidths—supporting signaling at 100 Gbaud and 200 Gbaud—with reduced spectral width to mitigate chromatic-dispersion-induced pulse broadening and increased brightness to further restrict flux-confining area in multi-mode fibers and thereby increase the effective modal bandwidth (EMB). A particularly promising route to improved performance within standard oxide-confined VCSEL technology is the introduction of multiple isolated or optically coupled oxide-confined apertures, which we refer to collectively as multi-aperture (MA) VCSEL arrays. We show that properly designed MA VCSELs exhibit narrow emission spectra, narrow far-field profiles and extended intrinsic modulation bandwidths, enabling longer-reach data transmission over both multi-mode (MMF) and single-mode fibers (SMF). One approach uses optically isolated apertures with lateral dimensions of approximately 2–3 µm arranged with a pitch of 10–12 µm or less. Such devices demonstrate relaxation oscillation frequencies of around 30 GHz in continuous-wave operation and intrinsic modulation bandwidths approaching 50 GHz. Compared with a conventional single-aperture VCSELs of equivalent oxide-confined area, MA designs can reduce the spectral width (root mean square values < 0.15 nm), lower series resistance (≈50 Ω) and limit junction overheating through more efficient multi-spot heat dissipation at the same total current. As each aperture lases in a single transverse mode, these devices exhibit narrow far-field patterns. In combination with well-defined spacing between emitting spots, they permit tailored restricted launch conditions in MMFs, enhancing effective modal bandwidth. In another MA approach, the apertures are optically coupled such that self-injection locking (SIL) leads to lasing in a single supermode. One may regard one of the supermodes as acting as a master mode controlling the other one. Streak-camera studies reveal post-pulse oscillations in the SIL regime at frequencies up to 100 GHz. MA VCSELs enable a favorable combination of wavelength chirp and chromatic dispersion, extending transmission distances over MMFs beyond those expected for zero-chirp sources and supporting transfer bandwidths up to 60 GHz over kilometer-length SMF links. Full article

To increase target acquisition probability and the signal-to-noise ratio (SNR) of hyperspectral images, this paper presents a wide-field, dual-slit, low-distortion, and high-sensitivity Offner hyperspectral imager, with a wavelength range of 0.4 μm to 0.9 μm, a numerical aperture of 0.15, and a slit length of 73 mm. To avoid signal aliasing, the space between the dual slits is 2.4 mm, increasing the SNR by 1.4 times after dual-slit image fusion. Furthermore, to achieve the required registration accuracy of dual-slit images, the spectral performance of the hyperspectral imager is critical. Thus, we compensate and correct the spectral performance and dispersion nonlinearity of the hyperspectral imager by taking advantages of the material properties and tilt eccentricity of a low-dispersion internal reflection curved prism and high-dispersion double-pass curved prisms. To meet the final operation requirements, the tilt of the internal reflection curved prism is used as a compensator. Using the modulation transfer function (MTF) as the evaluation criterion, an inverse sensitivity analysis confirmed that the compensator is a highly sensitive component. Additionally, the root mean square standard deviation (RSS) discrete calculation method was adopted to assess the influence of actual assembly tolerance on spectral performance. The test results demonstrate that the hyperspectral imager meets the registration accuracy requirements of dual-slit images, with an MTF better than 0.4. Furthermore, the spectral smile and spectral keystone of the dual-slit images are both less than or equal to 0.3 pixels. Full article

We present a compact hybrid imaging system operating in the 3–5 μm spectral band that combines refractive optics with a dispersion-engineered metasurface to overcome the longstanding trade-off between wide field of view (FOV), system size, and thermal stability. The system achieves an ultra-wide 178° FOV within a total track length of only 28.25 mm, employing just three refractive lenses and one metasurface. Through co-optimization of material selection and system architecture, it maintains the modulation transfer function (MTF) exceeding 0.54 at 33 lp/mm and the geometric (GEO) radius below 15 μm across an extended operational temperature range from –40 °C to 60 °C. The metasurface is designed using a propagation phase approach with cylindrical unit cells to ensure polarization-insensitive behavior, and its broadband dispersion-free phase profile is optimized via a particle swarm algorithm. The results indicate that phase-matching errors remain small at all wavelengths, with a mean value of 0.11068. This design provides an environmentally resilient solution for lightweight applications, including automotive infrared night vision and unmanned aerial vehicle remote sensing. Full article

Pipeline leak detection through acoustic signal measurement faces critical challenges, including insufficient utilization of time-frequency domain features, poor adaptability to noisy environments, and inadequate exploitation of frequency-domain prior knowledge in existing deep learning approaches. This paper proposes a Multi-Scale Frequency-Aware Transformer (MSFAT) architecture that integrates measurement-based acoustic signal analysis with artificial intelligence techniques. The MSFAT framework consists of four core components: a frequency-aware embedding layer that achieves joint representation learning of time-frequency dual-domain features through parallel temporal convolution and frequency transformation, a multi-head frequency attention mechanism that dynamically adjusts attention weights based on spectral distribution using frequency features as modulation signals, an adaptive noise filtering module that integrates noise detection, signal enhancement, and adaptive fusion functions through end-to-end joint optimization, and a multi-scale feature aggregation mechanism that extracts discriminative global representations through complementary pooling strategies. The proposed method addresses the fundamental limitations of traditional measurement-based detection systems by incorporating domain-specific prior knowledge into neural network architecture design. Experimental validation demonstrates that MSFAT achieves 97.2% accuracy and an F1-score, representing improvements of 10.5% and 10.9%, respectively, compared to standard Transformer approaches. The model maintains robust detection performance across signal-to-noise ratio conditions ranging from 5 to 30 dB, demonstrating superior adaptability to complex industrial measurement environments. Ablation studies confirm the effectiveness of each innovative module, with frequency-aware mechanisms contributing most significantly to the enhanced measurement precision and reliability in pipeline leak detection applications. Full article

A novel airborne pathogen detection method, based on Flashing Ratchet Potential (FRP) and Electric Current Spectroscopy (ECS), is presented. The system employs a precisely engineered asymmetric electrode array to generate controlled directional transport of oxygen ions (O₂⁻•), produced via thermionic emission and three-body electron attachment. As these ions interact with airborne particles in the detection zone, measurable perturbations in the ECS profile emerge, yielding distinct spectral signatures that indicate particle presence. Proof-of-concept experiments, using standardized talcum powder aerosols as surrogates for viral-scale particles, established optimal operating parameters of 6 V potential and 600 kHz modulation frequency, with reproducible detection signals showing a relative shift of 4.5–13.4% compared to filtered-air controls. The system’s design concept incorporates humidity-resilient features, intended to maintain stability under varying environmental conditions. Together with the proposed size selectivity (50–150 nm), this highlights its potential robustness for real-world applications. To the best of our knowledge, this is the first demonstration of an open-air electro-ratchet transport system coupled with electric current spectroscopy for bioaerosol monitoring, distinct from prior optical or electrochemical airborne biosensors, highlighting its promise as a tool for continuous environmental surveillance in high-risk settings such as hospitals, airports, and public transit systems. Full article

Observational studies in several regions and our dataset indicate changes in global solar radiation (R_S); here, we analyze how atmospheric conditions modulate its spectral composition. This study investigates the effects of atmospheric conditions on the spectral composition of global solar radiation (R_S) across different wavelength ranges: ultraviolet A (UVA), photosynthetically active radiation (PAR), and near-infrared radiation (NIR), using the ratios UVA/R_S, PAR/R_S, and NIR/R_S. A high-quality spectral irradiance dataset (300–1025 nm) covering eight years of observations from a representative rural site in Central Europe (Meteorological Observatory Lindenberg, Tauche, in North-East Germany) was used. The average values obtained for the ratios were 0.049 ± 0.010 for UVA/R_S, 0.433 ± 0.044 for PAR/R_S, and 0.259 ± 0.030 for NIR/R_S. Thus, the UVA range contributed approximately 5% to global radiation, PAR 43%, and NIR 26%. Strong correlations were found between each spectral component and R_S, with determination coefficients exceeding 0.90 in all cases, particularly for PAR. This suggests that, in the absence of direct spectral measurements, these components can be reliably estimated from R_S. A seasonal pattern was also identified, with maximum values in warmer months and minimum values in colder ones, most notably for PAR/R_S. In contrast, NIR/R_S exhibited an inverse pattern, likely influenced by atmospheric water vapor. A long-term decreasing trend in these ratios was also identified, being most pronounced in the UVA/R_S ratio. Additionally, atmospheric conditions significantly affected the spectral distribution of R_S, with UVA and PAR proportions increasing under specific conditions, while NIR remained more stable. Under overcast conditions, the ratios for shorter wavelengths (UVA and PAR) increased, indicating higher scattering effects, while NIR was less affected. Full article

In advanced spectroscopy, the classical symmetric optical frequency comb is limited in temporal flexibility and selection freedom, which constrains the efficiency and stability of quantum manipulation. To overcome this limitation, we propose a method to realize precise energy-level manipulation using a femtosecond non-temporally symmetric optical frequency comb in the semiclassical three-level system. Numerical calculations show that the fall time of the pulse is the key parameter to realize the precise manipulation, and a shorter fall time contributes to the efficient accumulation of population. By optimizing the pulse parameters, 99.15% accumulation of population in the target state can be successfully achieved and stably maintained using an asymmetric slowly turned-on and rapidly turned-off (STRT) pulse train. Our demonstration of the non-temporally symmetric optical frequency comb provides a promising approach to efficient quantum-state preparation using spectral modulation. 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 proliferation of unmanned aerial vehicles (UAVs) and the associated rise in security concerns, there is a growing demand for robust detection and identification systems capable of operating reliably in complex electromagnetic environments. To address this challenge, this paper proposes a deep learning-based passive UAV detection and identification system leveraging radio frequency (RF) spectrograms. The system employs a high-resolution RF front-end comprising a multi-beam directional antenna and a wideband spectrum analyzer to scan the target airspace and capture UAV signals with enhanced spatial and spectral granularity. A YOLO-based detection module is then used to extract frequency hopping signal (FHS) regions from the spectrogram, which are subsequently classified by a convolutional neural network (CNN) to identify specific UAV models. Extensive measurements are carried out in both line-of-sight (LoS) and non-line-of-sight (NLoS) urban environments. The proposed system achieves over 96% accuracy in both detection and identification under LoS conditions. In NLoS conditions, it improves the identification accuracy by more than 15% compared with conventional full-spectrum CNN-based methods. These results validate the system’s robustness, real-time responsiveness, and strong practical applicability. 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

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

Accurate segmentation of medical images is essential for clinical diagnosis and treatment planning. Hyperspectral imaging (HSI), with its rich spectral information, enables improved tissue characterization and structural localization compared with traditional grayscale or RGB imaging. However, the effective modeling of both spatial and spectral dependencies remains a significant challenge, particularly in small-scale medical datasets. In this study, we propose GSA-Net, a 3D segmentation framework that integrates Gated Spectral-Axial Attention (GSA) to capture long-range interband dependencies and enhance spectral feature discrimination. The GSA module incorporates multilayer perceptrons (MLPs) and adaptive LayerScale mechanisms to enable the fine-grained modulation of spectral attention across feature channels. We evaluated GSA-Net on a hyperspectral cholangiocarcinoma (CCA) dataset, achieving an average Intersection over Union (IoU) of 60.64 ± 14.48%, Dice coefficient of 74.44 ± 11.83%, and Hausdorff Distance of 76.82 ± 42.77 px. It outperformed state-of-the-art baselines. Further spectral analysis revealed that informative spectral bands are widely distributed rather than concentrated, and full-spectrum input consistently outperforms aggressive band selection, underscoring the importance of adaptive spectral attention for robust hyperspectral medical image segmentation. Full article

Mid-infrared molecular sensing faces challenges in simultaneously achieving high-resolution qualitative identification and quantitative analysis of multiple biomolecules. To address this, we present a tunable mid-infrared sensing platform, integrating the simulation of a single-layer graphene square-aperture array sensor with a machine learning algorithm called principal component analysis for advanced spectral processing. The graphene square-aperture structure excites dynamically tunable localized surface plasmon resonances by modulating the graphene’s Fermi level, enabling precise alignment with the vibrational fingerprints of target molecules. This plasmon–molecule coupling amplifies absorption signals and serves as discernible “molecular barcodes” for precise identification without change in the structural parameters. We demonstrate the platform’s capability to detect and differentiate carbazole-based biphenyl molecules and protein molecules, even in complex mixtures, by systematically tuning the Fermi level to match their unique vibrational bands. More importantly, for mixtures with unknown total amounts and different concentration ratios, the principal component analysis algorithm effectively processes complex transmission spectra and presents the relevant information in a simpler form. This integration of tunable graphene plasmons with machine learning algorithms establishes a label-free, multiplexed mid-infrared sensing strategy with broad applicability in biomedical diagnostics, environmental monitoring, and chemical analysis. Full article

Accurate assessment of sleep architecture is critical for diagnosing and managing sleep disorders, which significantly impact global health and well-being. While polysomnography (PSG) remains the clinical gold standard, its inherent intrusiveness, high cost, and logistical complexity limit its utility for routine or home-based monitoring. Recent advances highlight that subtle variations in respiratory dynamics, such as respiratory rate and cycle regularity, exhibit meaningful correlations with distinct sleep stages and could serve as valuable non-invasive biomarkers. In this work, we propose a framework for estimating sleep stage distribution—specifically Wake, Light (N1+N2), Deep (N3), and REM—based on respiratory audio captured over a single sleep episode. The framework comprises three principal components: (1) a segmentation module that identifies distinct respiratory cycles in respiratory sounds using a fine-tuned Transformer-based architecture; (2) a feature extraction module that derives a suite of statistical, spectral, and distributional descriptors from these segmented respiratory patterns; and (3) stage-specific regression models that predict the proportion of time spent in each sleep stage. Experiments on the public PSG-Audio dataset (287 subjects; mean 5.3 h per subject), using subject-wise cross-validation, demonstrate the efficacy of the proposed approach. The segmentation model achieved lower RMSE and MAE in predicting respiratory rate and cycle duration, outperforming classical signal-processing baselines. For sleep stage proportion prediction, the proposed method yielded favorable RMSE and MAE across all stages, with the TabPFN model consistently delivering the best results. By quantifying interpretable respiratory features and intentionally avoiding black-box end-to-end modeling, our system may support transparent, contact-free sleep monitoring using passive audio. Full article