Search Results (6)

Graph Neural Networks (GNNs) have emerged as the standard for learning representations from graph-structured data. While traditional architectures relying on message-passing mechanisms excel in homophilic settings, they essentially function as fixed low-pass filters. However, this smoothing operation limits their ability to generalize to heterophilic graphs, where connected nodes often exhibit dissimilar labels and high-frequency signals are crucial for discrimination. Furthermore, existing Mixture-of-Experts (MoE) methods for graphs often suffer from local-view routing, failing to capture global structural context during expert selection. To address these challenges, this paper proposes SS-AdaMoE, a novel Spatio-Spectral Adaptive Mixture of Experts framework designed for robust node classification across diverse graph patterns. Specifically, a Dual-Domain Expert System is constructed, integrating heterogeneous spatial aggregators with learnable spectral filters based on Bernstein polynomials. This allows the model to adaptively capture arbitrary frequency responses—including high-pass and band-pass signals—which are overlooked by standard GNNs. To resolve the locality bias, a Hierarchical Global-Prior Gating Network augmented by a Linear Graph Transformer is introduced, ensuring that expert selection is guided by both local node features and global topological awareness. Extensive experiments are conducted on five benchmark datasets spanning both homophilic and heterophilic networks. The results demonstrate that SS-AdaMoE consistently outperforms baselines, achieving accuracy improvements of up to 2.65% on Chameleon and 1.41% on Roman-empire over the strongest MoE baseline, while surpassing traditional GCN architectures by margins exceeding 28% on heterophilic datasets such as Texas. These findings validate that the synergy of learnable spectral priors and global gating effectively bridges the gap between spatial aggregation and spectral filtering. Full article

A majority of hyperspectral super-resolution methods aim to enhance the spatial resolution of hyperspectral imaging data (HSI) by integrating high-resolution multispectral imaging data (MSI), leveraging rich spectral information for various geospatial applications. Key challenges include spectral distortions from high-frequency spatial data, high computational complexity, and limited training data, particularly for new-generation sensors with unique noise patterns. In this contribution, we propose a novel parallel patch-wise sparse residual learning (P²SR) algorithm for resolution enhancement based on fusion of HSI and MSI. The proposed method uses multi-decomposition techniques (i.e., Independent component analysis, Non-negative matrix factorization, and 3D wavelet transforms) to extract spatial and spectral features to form a sparse dictionary. The spectral and spatial characteristics of the scene encoded in the dictionary enable reconstruction through a first-order optimization algorithm to ensure an efficient sparse representation. The final spatially enhanced HSI is reconstructed by combining the learned features from low-resolution HSI and applying an MSI-regulated guided filter to enhance spatial fidelity while minimizing artifacts. P²SR is deployable on a high-performance computing (HPC) system with parallel processing, ensuring scalability and computational efficiency for large HSI datasets. Extensive evaluations on three diverse study sites demonstrate that P²SR consistently outperforms traditional and state-of-the-art (SOA) methods in both quantitative metrics and qualitative spatial assessments. Specifically, P²SR achieved the best average PSNR (25.2100) and SAM (12.4542) scores, indicating superior spatio-spectral reconstruction contributing to sharper spatial features, reduced mixed pixels, and enhanced geological features. P²SR also achieved the best average ERGAS (8.9295) and Q2n (0.5156), which suggests better overall fidelity across all bands and perceptual accuracy with the least spectral distortions. Importantly, we show that P²SR preserves critical spectral signatures, such as Fe²⁺ absorption, and improves the detection of fine-scale environmental and geological structures. P²SR’s ability to maintain spectral fidelity while enhancing spatial detail makes it a powerful tool for high-precision remote sensing applications, including mineral mapping, land-use analysis, and environmental monitoring. Full article

Modern deep neural networks (DNNs) have shown promising results in brain studies involving multi-channel electroencephalogram (EEG) signals. The representations produced by the layers of a DNN trained on EEG signals remain, however, poorly understood. In this paper, we propose an approach to interpret deep representations of EEG signals. Our approach produces spatio-spectral feature images (SSFIs) that encode the EEG input patterns that activate the neurons in each layer of a DNN. We evaluate our approach using the PhyAAt dataset of multi-channel EEG signals for auditory attention. First, we train the same convolutional neural network (CNN) architecture on 25 separate sets of EEG signals from 25 subjects and conduct individual model analysis and inter-subject dependency analysis. Then we generate the SSFI input patterns that activate the layers of each trained CNN. The generated SSFI patterns can identify the main brain regions involved in a given auditory task. Our results show that low-level CNN features focus on larger regions and high-level features focus on smaller regions. In addition, our approach allows us to discern patterns in different frequency bands. Further SSFI saliency analysis reveals common brain regions associated with a specific activity for each subject. Our approach to investigate deep representations using SSFI can be used to enhance our understanding of the brain activity and effectively realize transfer learning. Full article

Pattern recognition techniques form the heart of most, if not all, incoherent linear shift-invariant systems. When an object is recorded using a camera, the object information is sampled by the point spread function (PSF) of the system, replacing every object point with the PSF in the sensor. The PSF is a sharp Kronecker Delta-like function when the numerical aperture (NA) is large with no aberrations. When the NA is small, and the system has aberrations, the PSF appears blurred. In the case of aberrations, if the PSF is known, then the blurred object image can be deblurred by scanning the PSF over the recorded object intensity pattern and looking for pattern matching conditions through a mathematical process called correlation. Deep learning-based image classification for computer vision applications gained attention in recent years. The classification probability is highly dependent on the quality of images as even a minor blur can significantly alter the image classification results. In this study, a recently developed deblurring method, the Lucy-Richardson-Rosen algorithm (LR²A), was implemented to computationally refocus images recorded in the presence of spatio-spectral aberrations. The performance of LR²A was compared against the parent techniques: Lucy-Richardson algorithm and non-linear reconstruction. LR²A exhibited a superior deblurring capability even in extreme cases of spatio-spectral aberrations. Experimental results of deblurring a picture recorded using high-resolution smartphone cameras are presented. LR²A was implemented to significantly improve the performances of the widely used deep convolutional neural networks for image classification. Full article

Although increasing evidences support the notion that psychiatric disorders are associated with abnormal communication between brain regions, scattered studies have investigated brain electrophysiological disconnectivity of patients with generalized anxiety disorder (GAD). To this end, this study intends to develop an analysis framework for automatic GAD detection through incorporating multidimensional EEG feature extraction and machine learning techniques. Specifically, resting-state EEG signals with a duration of 10 min were obtained from 45 patients with GAD and 36 healthy controls (HC). Then, an analysis framework of multidimensional EEG characteristics (including univariate power spectral density (PSD) and fuzzy entropy (FE), and multivariate functional connectivity (FC), which can decode the EEG information from three different dimensions) were introduced for extracting aberrated multidimensional EEG features via statistical inter-group comparisons. These aberrated features were subsequently fused and fed into three previously validated machine learning methods to evaluate classification performance for automatic patient detection. We showed that patients exhibited a significant increase in beta rhythm and decrease in alpha1 rhythm of PSD, together with the reduced long-range FC between frontal and other brain areas in all frequency bands. Moreover, these aberrated features contributed to a very good classification performance with 97.83 ± 0.40% of accuracy, 97.55 ± 0.31% of sensitivity, 97.78 ± 0.36% of specificity, and 97.95 ± 0.17% of F1. These findings corroborate previous hypothesis of disconnectivity in psychiatric disorders and further shed light on distribution patterns of aberrant spatio-spectral EEG characteristics, which may lead to potential application of automatic diagnosis of GAD. Full article

Electroencephalography (EEG)-based brain computer interfaces (BCIs) translate motor imagery commands into the movements of an external device (e.g., a robotic arm). The automatic design of spectral and spatial filters is a challenging task, as the frequency bands of the spectral filters must be predefined by previously published studies and given that they may be affected during trials by artifacts and improper motor imagery (MI). This study aimed to eliminate the contaminated trials automatically during classifier training, and to simultaneously learn the spectral and spatial patterns without the need for predefined frequency bands. Compared with previous studies that measured the discriminative power of a frequency band based on mutual information, this study determined the difference of the class conditional probability density function between two MI classes. This information was further shared to measure the contamination level of the trial that simplified the computation. A particle-based approximation technique iteratively constructed a filter bank that extracted discriminative features, and simultaneously removed potentially contaminated trials. The particle weight was estimated by an analysis of variance F-test instead of mutual information as commonly used in previous studies. The experimental results of a publicly available dataset revealed that the proposed method outperformed the other BCI in terms of the classification accuracy. Asymmetrical spatial patterns were found on left- versus right-hand MI classifications. The learnt spectral and spatial patterns were consistent with prior neurophysiological knowledge. Full article