Search Results (174)

Ghost imaging, ghost interference, and ghost diffraction retrieve an object’s spatial distribution and interference–diffraction patterns via intensity correlation. Flexibly synthesizing multi-channel optical information within a single correlation architecture is a key challenge in the evolution of optical correlation from fundamental research to information processing platforms. This study proposes the Extended Operational Ghost Correlation Model (EO-GCM), which introduces the four arithmetic operations (addition, subtraction, multiplication, and division) into optical correlation data processing. Within circular complex Gaussian pseudothermal light fields, the study systematically derives the analytical expressions for the second-order intensity fluctuation correlations with these operations. The theory shows that addition and subtraction obey superposition, whereas for multiplication and division, the average intensity of one object path becomes a weighting factor for the information of the other path. When weakly correlated, multiplication yields a weighted sum, whereas division yields a weighted difference, with the two weights having opposite signs. Experiments on ghost interference or diffraction and ghost imaging verify theoretical predictions and confirm the proportionality between the absolute value of the negative weight in division and the average intensity of the numerator path. The proposed model enables basic operations on multipath object signals, endowing optical correlation systems with reconfigurable, weighted correlation fusion-based information modulation capabilities. Full article

Extreme opinion propagation in social information networks often appears as a low-frequency but high-impact process, in which abnormal activity becomes synchronized across structurally related users or communities during crisis periods. Conventional correlation-based methods mainly describe average co-movement and may therefore miss dependence patterns that emerge only in the tail regime. To address this issue, this paper proposes a community-structured extremal dependence framework for social opinion propagation risk analysis. A tail pairwise dependence matrix (TPDM) is used to construct a weighted extremal dependence network, on which node-level risk scoring, community detection, and community-level intervention analyses are performed. The proposed risk score integrates degree centrality, betweenness centrality, tail exposure, and community embedding strength, while the intervention component is formulated as a minimum cut problem on the induced community graph. The framework is evaluated on a controlled synthetic social discussion network with 100 nodes. The experiment is intended as a methodological proof of concept rather than as a real-platform empirical validation. The results show that the TPDM-based network produces a structured representation with two dominant coupled communities, several peripheral singleton nodes, concentrated high-risk nodes, and one principal source–target interface in the community graph. These findings indicate that extremal dependence can provide a useful representation of candidate risk-coupling structures under the synthetic setting. However, the inferred edges should not be interpreted as causal propagation paths, and the minimum cut result should be understood as a candidate intervention interface rather than as a guarantee of complete diffusion blockage. Future work should validate the framework on real social media traces, incorporate temporal causal information, and examine robustness under multi-channel diffusion and adaptive user behavior. Full article

Ship trajectory prediction from Automatic Identification System (AIS) data has been predominantly approached as a time-series forecasting problem, where sequential models operate on coordinate sequences to predict future positions. This paradigm, while effective, neglects a key observation: the spatial layout of multiple vessel trajectories on a chart-like plane carries rich interaction information that is difficult to capture through sequential processing alone. To address this, Mapex (Map Exploitation) is proposed as a vision-based framework that rasterizes multi-vessel AIS trajectories into chart-like multi-channel images and processes them with a visual encoder, treating trajectory prediction as a map-reading task. Each vessel contributes three image channels encoding its trajectory heatmap, speed field, and heading field, converting raw coordinates into a spatial representation where physical movement patterns become visually apparent. A parallel coordinate branch supplies the course-over-ground information that the raster does not encode explicitly, and a fusion module combines both streams for autoregressive five-channel trajectory generation. Unlike coordinate-domain models that process position sequences numerically, Mapex understands vessel motion through its spatial layout, capturing relative positions, trajectory shapes, and kinematic patterns as visual features rather than abstract number sequences. Experiments on the Piraeus AIS dataset demonstrate that Mapex reduces the average displacement error (ADE) by approximately $68\%$ compared to the best coordinate-domain baseline and the mean squared error (MSE) by over $80\%$ compared to the strongest prior method, while requiring significantly fewer parameters than recent LLM-based approaches. These results suggest that spatial visualization of trajectories provides a fundamentally richer representation than coordinate sequences for multi-vessel trajectory prediction. Full article

The formation and spatial distribution of sedimentary systems in rift-lake basins are jointly controlled by multiple factors, including sediment supply rates from source areas, clastic sediment transport pathways, and basin geometry and intrabasinal structural configuration (e.g., accommodation zones and faults), which strongly influence the architecture of depositional systems and basin filling processes. The Wenliu Formation (Wenliu Member, Late Paleogene) of the Wenchang Group in the Enping 20/21 Depression of the Yangjiang East Sag, Pearl River Mouth Basin, developed a multi-source and multi-channel sand-transport system; however, the matching relationships and coupling mechanisms among different source areas, transport pathways, and depositional systems remain poorly understood. Based on three-dimensional seismic data, drilling, and well-log information, combined with heavy mineral assemblages and detrital zircon U–Pb age spectra, this study comprehensively investigates the source areas, paleochannel clastic sediment transport pathways, and depositional systems of the Wenliu Member, systematically establishing the source-to-sink (S2S) framework. The results indicate that sediments of the Wenliu Member were supplied from four main source areas, including the northwestern Yangchun Uplift, northeastern Enyang low uplift, and southwestern Yangjiang low uplift, with nine major paleochannel clastic sediment transport pathways identified. The different source zones show distinct variations in area, slope characteristics, and sediment supply modes, corresponding to differentiated paleochannel types and paleodrainage configurations. The study area overall exhibits a typical multi-channel convergence depositional pattern, dominated by braid-delta and fan-delta systems. The Enyang low-slope source zone generated the largest braid-delta deposits, whereas fault-transformed source zones produced fan-delta deposits adjacent to active faults and along basin-margin fault systems. Quantitative analysis further indicates that depositional-system scale is significantly correlated with source-area size, paleodrainage development, and paleochannel geometric parameters. Large depositional bodies are more likely to form when the source area exceeds ~60 km², the paleochannel width exceeds ~1.4 km, and the cross-sectional area exceeds ~10 km². Integrating the spatial relationships among source areas, transport pathways, and depositional systems, four source-to-sink subsystems are identified, which can be further classified into two typical depositional patterns: a long-source gentle-slope braid-delta pattern and a proximal-source rapid-accumulation fan-delta pattern. This study elucidates the coupling relationships among source areas, clastic sediment transport pathways, and depositional sinks in a multi-source rift-lake basin, providing a geological basis for predicting sedimentary systems and guiding hydrocarbon exploration in the study area. Full article

Generative AI has advanced rapidly in architectural design; however, existing building footprint generation models tend to emphasize stylistic exploration while insufficiently integrating site context as a fundamental physical constraint that facilitates alignment with the surrounding urban fabric. To address this limitation, this study proposes a context-responsive methodology for generating building footprints using a multi-layered four-channel representation of site conditions—including roads, sidewalks, adjacent buildings, and site boundaries—within a Latent Diffusion Model framework. The proposed approach encodes these physical conditions into a structured tensor and concatenates them directly to the U-Net input, enabling site context to function as an explicit spatial control variable during generation. An ablation study evaluated the effectiveness of the proposed contextual configuration. Compared with a single-channel model, the four-channel model achieved an 18.08% reduction in average pixel-wise information entropy, indicating a measurable decrease in generative uncertainty. Qualitative analyses further demonstrated that the enriched contextual input promotes geometrically coherent footprint configurations, such as context-responsive setbacks and spatial alignment with surrounding built forms. These findings suggest that structured multi-channel site information enhances contextual grounding in generative design processes and may contribute to more environmentally integrated and spatially coherent architectural outcomes. Full article

Thermal accumulation is a critical constraint in robotic grinding of ZGMn13 high-manganese steel, whereas the variables that can be prescribed or monitored reliably online are often limited to the normal load $F_z$, spindle speed $n$, and feed speed ${\nu }_w$. Most existing studies focus on single-pass conditions or scalar thermal indicators, while full-process near-surface transient temperature histories in multi-layer robotic grinding remains insufficiently addressed. This study presents a full-process near-surface transient temperature histories framework for multi-layer robotic grinding under fixed wheel–workpiece conditions and limited online sensing. Multi-channel near-surface thermal measurements were first reorganized into layer-resolved time-series data. A process-driven thermal surrogate was then constructed from the deployable inputs $\left(F_z,n,{\nu }_w\right)$, and a recursive temperature-evolution model was developed by incorporating intra-layer thermal retention and interlayer residual-heat inheritance. The proposed formulation predicts the near-surface transient temperature history over successive grinding layers. Experimental results showed clear layer-wise transience and progressive thermal accumulation during multi-layer grinding. Under representative conditions, the proposed framework reproduced the dominant transient structure of the measured full-process near-surface temperature histories, and grouped validation further showed that the recursive formulation preserved more useful history-level information than the reduced baselines within the tested domain. Within the tested operating domain, the predicted histories were further reduced to derived thermal indicators and planning-oriented peak-temperature maps. Full article

Fully polarimetric SAR provides richer scattering information than single-polarisation imaging, but multichannel sparse image formation can be computationally and memory demanding, especially when channels are processed jointly. In our previous work, we introduced Orthogonal Matching Pursuit 2D Fully Polarimetric (OMP2D-FP), a greedy reconstruction algorithm that enforces a shared spatial support across polarimetric channels while exploiting a separable 2D formulation to avoid vectorisation and reduce computational burden and memory footprint relative to vectorised OMP-based formulations. In this paper, we extend its validation to real measurements and further develop its theoretical foundations by recasting the atom-selection step as a detection–estimation problem, thereby defining a cumulative objective function (COF) design space that enables the incorporation of disturbance statistics and prior knowledge into sparse recovery. Experiments on fully polarimetric SAR data of a T-72 tank over a wide range of aspect angles, SNR levels, and measurement percentages show that joint support selection improves reconstruction fidelity and polarimetric information preservation over independent per-channel processing, with particularly clear gains under challenging conditions. Preliminary applications of the COF framework (a whitening COF incorporating polarimetric clutter statistics and a mask-based COF incorporating spatial prior knowledge) yield encouraging results, motivating further systematic investigation of adaptive COF designs. Full article

Electroencephalography (EEG) has become an increasingly important tool in depression research due to its ability to capture objective neurophysiological abnormalities associated with depressive disorders, offering high temporal resolution, non-invasiveness, and cost-effectiveness.However, existing methods often fail to fully exploit the multi-domain information in EEG signals, resulting in limited model generalization capabilities. This paper proposes an improved bidirectional long short-term memory (BiLSTM) model that segments continuous EEG into non-overlapping 2-s epochs and learns end-to-end from multi-channel temporal sequences. After band-pass filtering and resampling, each epoch is represented as a channel–time matrix $X\in {\mathbb{R}}^{C\times T}$ (with C = 128) and processed by a BiLSTM encoder followed by a dynamic-routing encapsulated-vector classifier. On the MODMA dataset under subject-independent five-fold cross-validation, the proposed method outperforms a set of reproduced representative baselines (SVM, EEGNet, InceptionNet, Self-attention-CNN and CNN–LSTM) and achieves 84.8% accuracy with an AUC of 0.899. We further discuss recent contemporary directions (e.g., attention/Transformer-based and emotion-aware expert models) and clarify the scope of our empirical comparisons. Furthermore, experiments comparing different frequency bands and band combinations indicate that joint multi-frequency input can enhance classification performance. This study provides an effective multi-domain fusion approach for the automatic diagnosis of depression based on EEG. Full article

Multichannel synthetic aperture radar (SAR) achieves high-resolution imaging while significantly enhancing the spatial freedom of the SAR system. As SAR hardware performance continues to improve, observed scenes often transition from simple to complex scenes. The increasingly complex clutter components introduced by complex scenes make clutter suppression increasingly challenging. Traditional multichannel clutter suppression algorithms usually assume that the observed scene, as a whole, satisfies the independent and identical distribution (IID) condition. However, in actual complex scenes, this assumption often proves difficult to uphold. Therefore, how to achieve more effective clutter suppression for complex scenes is a challenge for SAR. In this paper, we propose a knowledge-aided (KA) multichannel SAR clutter suppression algorithm for complex scenes. First, the single-channel image is processed at the superpixel level and a superpixel fusion algorithm is proposed, which adaptively realizes the refined classification of the complex scene. Then, a two-step clutter suppression processing method with multi-strategy clutter suppression preprocessing and sparse Bayesian residual clutter suppression is proposed. This method not only provides effective classification information for complex scenes but also achieves more efficient clutter suppression in complex scenes based on this classification information. Finally, the clutter suppression performance of this algorithm in complex scenes was validated through measured data. Full article

This paper uses visualization techniques to analyze the learning process of six machine learning classifiers for multichannel time series classification (MTSC), including five deep learning models—1D CNN, CNN-LSTM, ResNet, InceptionTime, and Transformer—and one non-deep learning method, ROCKET. Sixteen datasets from the University of East Anglia (UEA) multivariate time series repository were employed to assess and compare classifier performance. To explore how data characteristics influence accuracy, we applied channel selection, feature selection, and similarity analysis between training and testing sets. Visualization techniques were used to examine the temporal and structural patterns of each dataset, offering insight into how feature relevance, channel informativeness, and group separability affect model performance. The experimental results show that ROCKET achieves the most consistent accuracy across datasets, although its performance decreases with a very large number of channels. Conversely, the Transformer model underperforms in datasets with limited training instances per class. Overall, the findings highlight the importance of visual exploration in understanding MTSC behavior and indicate that channel relevance and data separability have a greater impact on classification accuracy than feature-level patterns. Full article

Quaternion Fractional Moment (QFM) descriptors are widely used in geometric pattern recognition due to their ability to encode multi-channel image information and exhibit invariance properties. However, their robustness under real-world acquisition variability, particularly photometric noise, remains insufficiently understood. Based on the Lipschitz stability theorem, which defines a strong, linear form of stability for dynamical systems, applied to one of our previous works, this article improves upon it by introducing a robustness-driven analysis framework that models feature extraction as a stochastic process, where bounded spatio-temporal perturbations generate multiple descriptor realizations for each pattern. Descriptor robustness is directly quantified in feature space using a novel normalized dispersion stability metric. Furthermore, a Lipschitz stability theorem is formally established and proved, providing theoretical guarantees of descriptor robustness under bounded perturbations. Experiments conducted on Moroccan–Andalusian geometric patterns with p4m and p6m symmetry groups demonstrate that the proposed framework achieves high intrinsic stability (${\sigma }_{norm}$ = 0.042 ± 0.010), while preserving state-of-the-art classification performance (Macro-F1 = 0.589 vs. 0.570 under σ = 0.05 noise). These results confirm that robustness is an intrinsic and measurable property of the descriptor, independent of classifier performance. The proposed framework provides both theoretical and methodological support for reliable geometric pattern recognition in cultural heritage imaging under real-world conditions. Full article

Addressing the challenges in predicting carbon–water fluxes in cold, temperate coniferous forests—specifically, the strong heterogeneity of driving factors, the significant non-linearity of processes, and the lack of consistency of ecological mechanisms in data-driven models—this paper constructs a Multi-Channel Fusion Attention BiLSTM (MCF-ABiLSTM) model. This model is designed for the joint prediction of Net Ecosystem Exchange (NEE) and Latent Heat Flux (LE). The model adopts a multi-channel structure to separately characterize meteorological, soil, and historical flux information, combining channel attention and temporal attention mechanisms to enhance the identification of key driving factors and critical temporal scales. On this basis, dynamic Water Use Efficiency (dWUE) and Sensitivity of Carbon–Water (SCW) indices are proposed to characterize the synergistic response features of carbon uptake and evapotranspiration under humidity and temperature gradients. The stable ecological relationships revealed by these indices are explicitly introduced into the model training process as ecological process consistency constraints, thereby guiding the model to adhere to known physiological mechanisms while improving prediction accuracy. Experimental results demonstrate that the MCF-ABiLSTM model outperforms various benchmark models in predicting both NEE and LE. Furthermore, flux contribution decomposition results indicate that the model’s response structure to environmental drivers is highly consistent with the known carbon–water coupling mechanisms of cold, temperate coniferous forests. This study achieves organic integration of high-precision carbon–water flux prediction, ecological process constraints, and mechanism analysis, providing a modeling framework that possesses both predictive capability and ecological interpretability for research on the carbon–water cycle in cold, temperate forest ecosystems. Full article

Accurate and timely classification of skin lesions is critical for early cancer detection, yet current deep learning approaches suffer from high computational costs, limited interpretability, and poor transparency for clinical deployment. This study presents HCHS-Net, a lightweight and interpretable multimodal framework for six-class skin lesion classification on the PAD-UFES-20 dataset. The proposed framework extracts a 116-dimensional visual feature vector through three complementary handcrafted modules: a Color Module employing multi-channel histogram analysis to capture chromatic diagnostic patterns, a Haralick Module deriving texture descriptors from the gray-level co-occurrence matrix (GLCM) that quantify surface characteristics correlated with malignancy, and a Shape Module encoding morphological properties via Hu moment invariants aligned with the clinical ABCD rule. The architectural design of HCHS-Net adopts a biomimetic approach by emulating the hierarchical information processing of the human visual system and the cognitive diagnostic workflows of expert dermatologists. Unlike conventional black-box deep learning models, this framework employs parallel processing branches that simulate the selective attention mechanisms of the human eye by focusing on biologically significant visual cues such as chromatic variance, textural entropy, and morphological asymmetry. These visual features are concatenated with a 12-dimensional clinical metadata vector encompassing patient demographics and lesion characteristics, yielding a compact 128-dimensional multimodal representation. Classification is performed through an ensemble of three gradient boosting algorithms (XGBoost, LightGBM, CatBoost) with majority voting. HCHS-Net achieves 97.76% classification accuracy with only 0.25 M parameters, outperforming deep learning baselines, including VGG-16 (94.60%), ResNet-50 (94.80%), and EfficientNet-B2 (95.16%), which require 60–97× more parameters. The framework delivers an inference time of 0.11 ms per image, enabling real-time classification on standard CPUs without GPU acceleration. Ablation analysis confirms the complementary contribution of each feature module, with metadata integration providing a 2.53% accuracy gain. The model achieves perfect melanoma and nevus recall (100%) with 99.55% specificity, maintaining reliable discrimination at safety-critical diagnostic boundaries. Comprehensive benchmarking against 13 published methods demonstrates that domain-informed handcrafted features combined with clinical metadata can match or exceed deep learning fusion approaches while offering superior interpretability and computational efficiency for point-of-care deployment. Full article

Condition monitoring of railway track surfaces is crucial for ensuring the safety, operational efficiency, and effective maintenance of railway systems. This work presents a data-driven modelling and an experimental methodology for identifying and classifying contaminants on railway tracks using vibration analysis and artificial intelligence techniques. In this study, the railway dynamics were physically simulated using a 1:20 scaled test rig, where the rails were treated with various contaminants (oil, water, and sand), and the resulting vehicle vibrations were recorded by on-board accelerometers and gyroscopes. To construct the predictive model, a hybrid architecture was designed integrating Short-Time Fourier Transform (STFT) for time-frequency feature extraction and a multi-channel Convolutional Neural Network (CNN) for pattern recognition. Initial results indicate that accelerometer data, particularly from longitudinal and lateral vibrations, are more effective than gyroscope data for classifying certain contaminants. To enhance classification robustness, this work introduces a multi-channel CNN that simultaneously processes the most informative signals, leading to a significant improvement in detection accuracy across all tested contaminants. This study validates the effectiveness of the proposed methodology as a robust and reliable solution for contaminant detection, while also confirming the utility of the scaled testbed as a valuable platform for future research in railway dynamics. Full article

A novel real-time home monitoring application was developed that utilises long short-term memory (LSTM) and is integrated in a smartphone. Its personalised LSTM accurately learns to detect abnormal movement patterns. The application locally processes the smartphone’s accelerometery data in the form of a signal magnitude vector (SMV) to analyse and interpret the movement patterns. The LSTM was conceptualised by a univariate time-series regression model. It adaptively updates its training parameters by processing the individual’s last seven days of movement data, thus providing a stable, individualised, and dynamic activity baseline. It then quantifies the normal and abnormal movement patterns by continuously comparing the learnt information against the current accelerometery readings. An abnormal movement pattern, e.g., a fall or an unexpected period of inactivity triggers multi-channel alerts to care givers using SMS and email. The application’s performance was evaluated using the data collected from 25 adult volunteers, aged 40–70 years. By interpreting their movement patterns, the application demonstrated a detection accuracy quantified by the coefficient of determination (R²) = 0.93 and an absolute error of 0.05. This precision highlighted a low false positive rate in a real-world evaluation. The study successfully demonstrated a robust, cost-effective, and privacy-preserving home monitoring technology. Full article