Search Results (101)

Background/Objectives: Tinnitus causes significant cognitive and emotional distress; however, its clinical assessment mostly relies on subjective measures without evaluation of objective indices. In this narrative review, we examined the potential of electroencephalography (EEG)-based neurophysiological markers as objective biomarkers in tinnitus assessment. Methods: The Web of Science, PubMed, EMBASE, and MEDLINE databases were searched to identify research articles on EEG-based analysis of individuals with tinnitus. Studies in which treatment and control groups were compared across four analytical domains (spectral power analysis, functional connectivity, microstate analysis, and entropy measures) were included. Qualitative synthesis was conducted to elucidate neurophysiological mechanisms, methodological characteristics, and clinical implications. Results: Analysis of 18 studies (n = 1188 participants) revealed that tinnitus is characterized by distributed neural dysfunction that extends beyond the auditory system. Spectral power analyses revealed sex-dependent, frequency-specific abnormalities across distributed brain regions. Connectivity analyses demonstrated elevated long-range coupling in high-frequency bands concurrent with diminished low-frequency synchronization. Microstate analyses revealed alterations in spatial configuration and transition probabilities. Entropy quantification indicated elevated complexity, particularly in the frontal and auditory cortices. Conclusions: EEG-derived neurophysiological markers demonstrate associations with tinnitus in group analyses and show potential for elucidating pathophysiological mechanisms. However, significant limitations, including low spatial resolution, small sample sizes, methodological heterogeneity, and lack of validation for individual-level diagnosis or treatment prediction, highlight the need for cautious interpretation. Standardized analytical protocols, larger validation studies, multimodal neuroimaging integration, and demonstration of clinical utility in prospective trials are required before EEG markers can be established as biomarkers for tinnitus diagnosis and management. Full article

Background: Artificial intelligence (AI) emerges as a powerful tool to assist breast cancer screening; however, its integration into different mammographic modalities remains insufficiently explored. Digital Mammography (DM) is widely accessible but presents limitations in dense breast tissue, whereas Contrast-Enhanced Spectral Mammography (CESM) provides functional information that enhances lesion visualization. Understanding how deep learning models behave across these modalities, and determining whether their decision-making patterns remain consistent, is essential for equitable clinical adoption. Methods: This study evaluates three convolutional neural network (CNN) architectures, ResNet-18, DenseNet-121, and EfficientNet-B0, for binary classification of breast lesions using DM and CESM images from the public CDD-CESM dataset (2006 images, three diagnostic classes). The models are trained separately on DM and CESM using three classification tasks: Normal vs. Benign, Benign vs. Malignant, and Normal vs. Malignant. A 3-fold cross-validation scheme and an independent test set are employed. Training uses transfer learning with ImageNet weights, weighted binary cross-entropy (BCE) loss, and SHapley Additive exPlanations (SHAP) analysis to visualize pixel-level relevance of model decisions. Results: CESM yields higher performance in the Normal vs. Benign and Benign vs. Malignant tasks, whereas DM achieves the highest discriminative ability in the Normal vs. Malignant comparison (EfficientNet-B0: AUC = 97%, Accuracy = 93.15%), surpassing the corresponding CESM results (AUC = 93%, Accuracy = 85.66%). SHAP attribution maps reveal anatomically coherent decision patterns in both modalities, with CESM producing sharper and more localized relevance regions due to contrast uptake, while DM exhibits broader yet spatially aligned attention. Across architectures, EfficientNet-B0 demonstrates the most stable performance and interpretability. Conclusions: CESM enhances subtle lesion discrimination through functional contrast, whereas DM, despite its simpler acquisition and wider availability, provides highly accurate and explainable outcomes when combined with modern CNNs. The consistent SHAP-based relevance observed across modalities indicates that both preserve clinically meaningful information. To the best of our knowledge, this study is the first to directly compare DM and CESM under identical preprocessing, training, and evaluation conditions using explainable deep learning models. Full article

Low-light image enhancement (LLIE) degradation arises from insufficient illumination, reflectance occlusion, and noise coupling, and it manifests in the frequency domain as suppressed amplitudes with relatively stable phases. To address the fact that pure spatial mappings struggle to balance brightness enhancement and detail fidelity, whereas pure frequency-domain processing lacks semantic modeling, we propose AFMNet—a dual-domain collaborative enhancement network guided by an information-theoretic frequency prior. This prior regularizes global illumination, while spatial branches restore local details. First, a Multi-Scale Amplitude Estimator (MSAE) adaptively generates fine-grained amplitude-modulation maps via multi-scale fusion, encouraging higher output entropy through adaptive spectral-energy redistribution. Next, a Dual-Branch Spectral–Spatial Attention (DBSSA) module—comprising a Frequency-Modulated Attention Block (FMAB) and a Scale-Variable Depth Attention Block (SVDAB)—is employed: FMAB injects the modulation map as a frequency-domain prior into the attention mechanism to conditionally modulate the amplitude of value features while keeping the phase unchanged, thereby helping to preserve structural information in the enhanced output; SVDAB uses multi-scale depthwise-separable convolutions with scale attention to produce adaptively enhanced spatial features. Finally, a Spectral-Gated Feed-Forward Network (SGFFN) applies learnable spectral filters to local features for band-wise selective enhancement. This collaborative design achieves a favorable balance between illumination correction and detail preservation, and AFMNet delivers state-of-the-art performance on multiple low-light enhancement benchmarks. Full article

Reliable decoding of motor imagery (MI) from electroencephalographic signals remains a challenging problem due to their nonlinear, noisy, and non-stationary nature. To address this issue, this work proposes an end-to-end deep learning model, termed TEKTE-Net, that integrates time embeddings with a kernelized Transfer Entropy estimator to infer directed functional connectivity in MI-based brain–computer interface (BCI) systems. The proposed model incorporates a customized convolutional module that performs Takens’ embedding, enabling the decoding of the underlying EEG activity without requiring explicit preprocessing. Further, the architecture estimates nonlinear and time-delayed interactions between cortical regions using Rational Quadratic kernels within a differentiable framework. Evaluation of TEKTE-Net on semi-synthetic causal benchmarks and the BCI Competition IV 2a dataset demonstrates robustness to low signal-to-noise conditions and interpretability through temporal, spatial, and spectral analyses of learned connectivity patterns. In particular, the model automatically highlights contralateral activations during MI and promotes spectral selectivity for the beta and gamma bands. Overall, TEKTE-Net offers a fully trainable estimator of functional brain connectivity for decoding EEG activity, supporting MI-BCI applications, and promoting interpretability of deep learning models. Full article

Public perception of traditional villages’ streetscape is a crucial link for unlocking their benefits in promoting physical and mental health and realizing environmental value transformation. Current studies on the influence mechanisms of rural streetscape characteristics on perception largely rely on subjective ratings and mostly depend on linear models. To address this, this study takes a traditional village in eastern China, which is rich in natural and cultural conditions, as an example and constructs an evaluation framework comprising 29 streetscape feature indicators. Based on multimodal data including electroencephalography (EEG), image segmentation, color, and spatial depth computation, XGBoost-SHAP was employed to reveal the nonlinear influence mechanisms of streetscape features on neurophysiological indicators (alpha-band power spectral density, α PSD) in the traditional rural context, which differs from the blue–green spaces and residential, campus, and urban environments in previous studies. The results indicate that (1) the dominant factors affecting α PSD in traditional villages are tree, color consistency, architectural aesthetics, spatial enclosure index, P_EBG, and road, in descending order. (2) Threshold effects and interaction effects that differ from previous studies on campuses, window views, and other contexts were identified. The positive effect of tree view index on α activity peaks at the threshold of 0.09, beyond which diminishing returns occur. Color complexity, including high color difference from the primary village scheme (i.e., low color consistency, color diversity, and visual entropy), inhibits α activity. The effect of spatial enclosure index (SEI) on α activity exhibits an inverted U-shape, peaking at 0.35. Tree–VE_nats, road–SEI, and building–SEI show antagonistic effects. Road–sky and SEI–P_FG display conditional interaction effects. (3) Based on k-means clustering analysis, the “key factor identification—threshold effect management—multi-factor synergy optimization” design can directionally regulate α PSD, promoting relaxed and calm streetscape schemes. This approach can be applied to urban and rural environment assessment and design, providing theoretical and technical support for scientific decision-making. Full article

With the rapid advancement of hyperspectral remote sensing technology, the security of hyperspectral images (HSIs) has become a critical concern. However, traditional image encryption methods—designed primarily for grayscale or RGB images—fail to address the high dimensionality, large data volume, and spectral-domain characteristics inherent to HSIs. Existing chaotic encryption schemes often suffer from limited chaotic performance, narrow parameter ranges, and inadequate spectral protection, leaving HSIs vulnerable to spectral feature extraction and statistical attacks. To overcome these limitations, this paper proposes a novel hyperspectral image encryption algorithm based on a newly designed two-dimensional cross-coupled hyperchaotic map (2D-CSCM), which synergistically integrates Cubic, Sinusoidal, and Chebyshev maps. The 2D-CSCM exhibits superior hyperchaotic behavior, including a wider hyperchaotic parameter range, enhanced randomness, and higher complexity, as validated by Lyapunov exponents, sample entropy, and NIST tests. Building on this, a layered encryption framework is introduced: spectral-band scrambling to conceal spectral curves while preserving spatial structure, spatial pixel permutation to disrupt correlation, and a bit-level diffusion mechanism based on dynamic DNA encoding, specifically designed to secure high bit-depth digital number (DN) values (typically >8 bits). Experimental results on multiple HSI datasets demonstrate that the proposed algorithm achieves near-ideal information entropy (up to 15.8107 for 16-bit data), negligible adjacent-pixel correlation (below 0.01), and strong resistance to statistical, cropping, and differential attacks (NPCR ≈ 99.998%, UACI ≈ 33.30%). The algorithm not only ensures comprehensive encryption of both spectral and spatial information but also supports lossless decryption, offering a robust and practical solution for secure storage and transmission of hyperspectral remote sensing imagery. Full article

Background: The assessment of emotion recognition holds growing significance in research on the brain–computer interface and human–computer interaction. Among diverse physiological signals, electroencephalography (EEG) occupies a pivotal position in affective computing due to its exceptional temporal resolution and non-invasive acquisition. However, EEG signals are inherently complex, characterized by substantial noise contamination and high variability, posing considerable challenges to accurate assessment. Methods: To tackle these challenges, we propose a Triple Attention Network (TANet), a triple-attention EEG emotion recognition framework that integrates Conformer, Convolutional Block Attention Module (CBAM), and Mutual Cross-Modal Attention (MCA). The Conformer component captures temporal feature dependencies, CBAM refines spatial channel representations, and MCA performs cross-modal fusion of differential entropy and power spectral density features. Results: We evaluated TANet on two benchmark EEG emotion datasets, DEAP and SEED. On SEED, using a subject-specific cross-validation protocol, the model reached an average accuracy of 98.51 ± 1.40%. On DEAP, we deliberately adopted a segment-level splitting paradigm—in line with influential state-of-the-art methods—to ensure a direct and fair comparison of model architecture under an identical evaluation protocol. This approach, designed specifically to assess fine-grained within-trial pattern discrimination rather than cross-subject generalization, yielded accuracies of 99.69 ± 0.15% and 99.67 ± 0.13% for the valence and arousal dimensions, respectively. Compared with existing benchmark approaches under similar evaluation protocols, TANet delivers substantially better results, underscoring the strong complementary effects of its attention mechanisms in improving EEG-based emotion recognition performance. Conclusions: This work provides both theoretical insights into multi-dimensional attention for physiological signal processing and practical guidance for developing high-performance, robust EEG emotion assessment systems. Full article

Psychogenic non-epileptic seizures (PNES) are often misdiagnosed as epileptic seizures (ES), leading to inappropriate treatment and delayed psychological care. To address this challenge, we analysed electroencephalogram (EEG) data from 74 patients (46 PNES, 28 ES) using one-minute preictal and interictal recordings per subject. Nine entropy measures (Sample, Fuzzy, Permutation, Dispersion, Conditional, Phase, Spectral, Rényi, and Wavelet entropy) were evaluated individually to classify PNES from ES using k-nearest neighbours, Naïve Bayes, linear discriminant analysis, logistic regression, support vector machine, random forest, multilayer perceptron, and XGBoost within a leave-one-subject-out cross-validation framework. In addition, a dynamic state, defined as the entropy difference between interictal and preictal periods, was examined. Sample, Fuzzy, Conditional, and Dispersion entropy were higher in PNES than in ES during interictal recordings (not significant), but significantly lower in the preictal (p < 0.05) and dynamic states (p < 0.01). Spatial mapping and permutation-based importance analyses highlighted O1, O2, T5, F7, and Pz as key discriminative channels. Classification performance peaked in the dynamic state, with Fuzzy entropy and support vector machine achieving the best results (balanced accuracy = 72.4%, F1 score = 77.8%, sensitivity = 74.5%, specificity = 70.4%). These results demonstrate the potential of entropy features for differentiating PNES from ES. Full article

Hyperspectral image classification (HSIC) involves analyzing high-dimensional data that contain substantial spectral redundancy and spatial noise, which increases the entropy and uncertainty of feature representations. Reducing such redundancy while retaining informative content in spectral–spatial interactions remains a fundamental challenge for building efficient and accurate HSIC models. Traditional deep learning methods often rely on redundant modules or lack sufficient spectral–spatial coupling, limiting their ability to fully exploit the information content of hyperspectral data. To address these challenges, we propose SGFNet, which is a spectral-guided fusion network designed from an information–theoretic perspective to reduce feature redundancy and uncertainty. First, we designed a Spectral-Aware Filtering Module (SAFM) that suppresses noisy spectral components and reduces redundant entropy, encoding the raw pixel-wise spectrum into a compact spectral representation accessible to all encoder blocks. Second, we introduced a Spectral–Spatial Adaptive Fusion (SSAF) module, which strengthens spectral–spatial interactions and enhances the discriminative information in the fused features. Finally, we developed a Spectral Guidance Gated CNN (SGGC), which is a lightweight gated convolutional module that uses spectral guidance to more effectively extract spatial representations while avoiding unnecessary sequence modeling overhead. We conducted extensive experiments on four widely used hyperspectral benchmarks and compared SGFNet with eight state-of-the-art models. The results demonstrate that SGFNet consistently achieves superior performance across multiple metrics. From an information–theoretic perspective, SGFNet implicitly balances redundancy reduction and information preservation, providing an efficient and effective solution for HSIC. Full article

Grassland classification via remote sensing is essential for ecosystem monitoring and precision management, yet conventional satellite-based approaches are fundamentally constrained by coarse spatial resolution. To overcome this limitation, we harness high-resolution UAV multi-sensor data, integrating multi-scale image fusion with deep learning to achieve fine-scale grassland classification that satellites cannot provide. First, four categories of UAV data, including RGB, multispectral, thermal infrared, and LiDAR point cloud, were collected, and a fused image tensor consisting of 10 channels (NDVI, VCI, CHM, etc.) was constructed through orthorectification and resampling. For feature-level fusion, four deep fusion networks were designed. Among them, the MultiScale Pyramid Fusion Network, utilizing a pyramid pooling module, effectively integrated spectral and structural features, achieving optimal performance in all six image fusion evaluation metrics, including information entropy (6.84), spatial frequency (15.56), and mean gradient (12.54). Subsequently, training and validation datasets were constructed by integrating visual interpretation samples. Four backbone networks, including UNet++, DeepLabV3+, PSPNet, and FPN, were employed, and attention modules (SE, ECA, and CBAM) were introduced separately to form 12 model combinations. Results indicated that the UNet++ network combined with the SE attention module achieved the best segmentation performance on the validation set, with a mean Intersection over Union (mIoU) of 77.68%, overall accuracy (OA) of 86.98%, F1-score of 81.48%, and Kappa coefficient of 0.82. In the categories of Leymus chinensis and Puccinellia distans, producer’s accuracy (PA)/user’s accuracy (UA) reached 86.46%/82.30% and 82.40%/77.68%, respectively. Whole-image prediction validated the model’s coherent identification capability for patch boundaries. In conclusion, this study provides a systematic approach for integrating multi-source UAV remote sensing data and intelligent grassland interpretation, offering technical support for grassland ecological monitoring and resource assessment. Full article

Hyperspectral band selection (BS) is an important technique to reduce data dimensionality for the classification applications of hyperspectral remote sensing images (HSIs). Recently, searching-based BS methods have received increasing attention for their ability to select the best subset of bands while preserving the essential information of the original data. However, existing searching-based BS methods neglect effective exploitation of the spatial and spectral prior information inherent in the data, thus limiting their performance. To address this problem, in this study, a novel unsupervised BS method called Spectral–Spatial Iterative Greedy Algorithm (SSIGA) is proposed. Specifically, to facilitate efficient local search using spectral information, SSIGA conducts clustering on all the bands by employing a K-means clustering method with balanced cluster size constraints and constructs a K-nearest neighbor graph for each cluster. Based on the nearest neighbor graphs, SSIGA can effectively explore the neighborhood solutions in local search. In addition, to efficiently evaluate the discriminability and information redundancy of the solution given by SSIGA using the spatial and spectral information of HSIs, we designed an effective objective function for SSIGA. The value of the objective function is derived by calculating the Fisher score for each band in the solution based on the results of the superpixel segmentation performed on the target HSI, as well as by computing the average information entropy and mutual information of the bands in the solution. Experimental results on three publicly available real HSI datasets demonstrate that the SSIG algorithm achieves superior performance compared to several state-of-the-art methods. Full article

Cotton is a globally strategic crop that plays a crucial role in sustaining national economies and livelihoods. To address the challenges of accurate cotton field extraction in the complex planting environments of Xinjiang’s Alaer reclamation area, a cotton field identification model was developed that integrates multi-source satellite remote sensing data with machine learning methods. Using imagery from Sentinel-2, GF-1, and Landsat 8, we performed feature fusion using principal component, Gram–Schmidt (GS), and neural network techniques. Analyses of spectral, vegetation, and texture features revealed that the GS-fused blue bands of Sentinel-2 and Landsat 8 exhibited optimal performance, with a mean value of 16,725, a standard deviation of 2290, and an information entropy of 8.55. These metrics improved by 10,529, 168, and 0.28, respectively, compared with the original Landsat 8 data. In comparative classification experiments, the endmember-based random forest classifier (RFC) achieved the best traditional classification performance, with a kappa value of 0.963 and an overall accuracy (OA) of 97.22% based on 250 samples, resulting in a cotton-field extraction error of 38.58 km². By enhancing the deep learning model, we proposed a U-Net architecture that incorporated a Convolutional Block Attention Module and Atrous Spatial Pyramid Pooling. Using the GS-fused blue band data, the model achieved significantly improved accuracy, with a kappa coefficient of 0.988 and an OA of 98.56%. This advancement reduced the area estimation error to 25.42 km², representing a 34.1% decrease compared with that of the RFC. Based on the optimal model, we constructed a digital map of continuous cotton cropping from 2021 to 2023, which revealed a consistent decline in cotton acreage within the reclaimed areas. This finding underscores the effectiveness of crop rotation policies in mitigating the adverse effects of large-scale monoculture practices. This study confirms that the synergistic integration of multi-source satellite feature fusion and deep learning significantly improves crop identification accuracy, providing reliable technical support for agricultural policy formulation and sustainable farmland management. Full article

We explore the spontaneous emission dynamics of a giant atom coupled to a photonic Creutz ladder, focusing on how flat-band frustration and synthetic gauge fields shape atom–photon interactions. The Creutz ladder exhibits perfectly flat bands, Aharonov–Bohm caging, and topological features arising from its nontrivial hopping structure. By embedding the giant atom at multiple spatially separated sites, we reveal interference-driven emission control and the formation of nonradiative bound states. Using both spectral and time-domain analyses, we uncover strong non-Markovian dynamics characterized by persistent oscillations, long-lived entanglement, and recoherence cycles. The emergence of bound-state poles in the spectral function is accompanied by spatially localized photonic profiles and directionally asymmetric emission, even in the absence of band dispersion. Calculations of von Neumann entropy and atomic purity confirm the formation of coherence-preserving dressed states in the flat-band regime. Furthermore, the spacetime structure of the emitted field displays robust zig-zag interference patterns and synthetic chirality, underscoring the role of geometry and topology in photon transport. Our results demonstrate how flat-band photonic lattices can be leveraged to engineer tunable atom–photon entanglement, suppress radiative losses, and create structured decoherence-free subspaces for quantum information applications. Full article

Unsupervised hyperspectral image (HSI) clustering is a fundamental yet challenging task due to high dimensionality and complex spectral–spatial characteristics. In this paper, we propose a novel and efficient clustering framework centered on adaptive and diverse anchor graph modeling. First, we introduce a parameter-free construction strategy that employs Entropy Rate Superpixel (ERS) segmentation to generate multiple anchor graphs of varying sizes from a single HSI, overcoming the limitation of fixed anchor quantities and enhancing structural expressiveness. Second, we propose an anchor-to-pixel label propagation mechanism to transfer anchor-level cluster labels back to the pixel level, reinforcing spatial coherence and spectral discriminability. Third, we perform clustering directly at the anchor level, which substantially reduces computational cost while retaining structure-aware accuracy. Extensive experiments on three benchmark datasets (Trento, Salinas, and Pavia Center) demonstrate the effectiveness and efficiency of our approach. Full article

The spatial distribution of ephemeral and perennial dryland plant species is increasingly modified and restricted by ever-changing climates and development expansion. At the interface of biodiversity conservation and developmental planning in desert landscapes is the growing need for adaptable tools in identifying and monitoring these ecologically fragile plant assemblages, habitats, and, often, heritage sites. This study evaluates usage of Sentinel-2 time series composite imagery to discriminate vegetation assemblages in a hyper-arid landscape. Spatial predictor spaces were compared to classify different vegetation communities: spectral components (PCs), vegetation indices (VIs), and their combination. Further, the uncertainty in discriminating field-verified vegetation assemblages is assessed using Shannon entropy and intensity analysis. Lastly, the intensity analysis helped to decipher and quantify class transitions between maps from different spatial predictors. We mapped plant assemblages in 2022 from combined PCs and VIs at an overall accuracy of 82.71% (95% CI: 81.08, 84.28). A high overall accuracy did not directly translate to high class prediction probabilities. Prediction by spectral components, with comparably lower accuracy (80.32, 95% CI: 78.60, 81.96), showed lower class uncertainty. Class disagreement or transition between classification models was mainly contributed by class exchange (a component of spatial allocation) and less so from quantity disagreement. Different artefacts of vegetation classes are associated with the predictor space—spectral components versus vegetation indices. This study contributes insights into using feature extraction (VIs) versus feature selection (PCs) for pixel-based classification of plant assemblages. Emphasising the ecologically sensitive vegetation in desert landscapes, the study contributes uncertainty considerations in translating optical satellite imagery to vegetation maps of arid landscapes. These are perceived to inform and support vegetation map creation and interpretation for operational management and conservation of plant biodiversity and habitats in such landscapes. Full article