Search Results (148)

Virtual reality (VR) has emerged as a powerful tool in neuroscience and psychiatry, providing immersive and ecologically valid environments to investigate human cognition. Stress is known to disrupt core cognitive functions, particularly learning and memory, which are critical for mental health. While classical paradigms such as the radial arm maze have yielded fundamental insights into animal research, their application in humans has been limited. The aim of this study was to develop NeuroHM, a VR-based radial arm maze, to evaluate spatial learning and memory in adults under experimentally induced stress. A total of 100 participants were recruited and randomly assigned to either a control group (n = 50) or a stress group (n = 50). Participants navigated the virtual radial arm maze from a first-person perspective, relying on distal planetary landmarks to maintain spatial orientation and recall spatial locations. The primary dependent variables were working memory errors, reference memory errors, and latency. Salivary cortisol levels were collected to validate the stress induction protocol and to examine the relationship between stress and cognitive performance. Participants in the stress group showed increased latency and higher reference memory errors compared to controls, with working memory exhibiting the most pronounced impairment. Our findings show that acute stress significantly disrupts cognition and highlight NeuroHM as a promising tool for cognitive assessment in mental health research. Full article

The Kuramoto–Sivashinsky (KS) equation and its fractional generalizations (FKSs) arise as canonical models for a wide class of nonlinear dissipative–dispersive systems, including thin-film flows, combustion fronts, drift–wave turbulence in plasmas, and chemically reacting media, where shock-like and strongly localized structures play a central role in the dynamics. Despite their apparent simplicity, KS-type models become analytically intractable once higher-order dissipation, geometric effects, and memory (fractional) operators are incorporated, and standard perturbative or transform-based schemes often lead to cumbersome recursive structures, slow convergence, or severe restrictions on the initial data. In this work, a novel direct approximation procedure, referred to as the Tantawy Technique (TT), is developed and implemented to solve and analyze planar fractional KS-type equations and their Burgers-type reductions in a systematic manner. The central difficulty is to construct, for a given physically motivated initial profile, a rapidly convergent series in fractional time that remains stable for a broad range of the fractional order and transport coefficients, while still retaining a clear link to the underlying shock-wave physics. To overcome this, the TT combines (i) a Tanh-based exact shock solution of the planar integer-order KS equation, obtained first as a reference via the standard Tanh method, with (ii) a carefully designed fractional-time ansatz in powers of $t^{\rho }$, where the spatial coefficients are determined recursively from the governing equation in the Caputo sense. This construction yields closed-form expressions for the first few terms in the approximation hierarchy and allows one to monitor convergence through residual and absolute error measures. Full article

The unique geographical isolation and climate sensitivity of island ecosystems make them valuable for ecological research. The Normalized Difference Vegetation Index (NDVI) is an important indicator when monitoring and evaluating these systems, and its prediction has become a key research focus. However, island NDVI prediction remains uncertain due to a limited understanding of vegetation growth and insufficient high-quality data. Deterministic models fail to capture or quantify such uncertainty, often leading to overfitting. To address this issue, this study proposes an uncertainty prediction model for the island NDVI within a coding–prediction–decoding framework, referred to as a Convolutional Autoencoder–Regularized Bayesian Neural Network (CAE-RBNN). The model integrates a convolutional autoencoder with feature regularization to extract latent NDVI features, aiming to reconcile spatial scale disparities with environmental data, while a Bayesian Neural Network (BNN) quantifies uncertainty arising from limited samples and an incomplete understanding of the process. Finally, Monte Carlo sampling and SHAP analysis evaluate model performance, quantify predictive uncertainty, and enhance interpretability. Experiments on six islands in the Xisha archipelago demonstrate that CAE-RBNN outperforms the Convolutional Neural Network–Recurrent Neural Network (CNN-RNN), the Convolutional Recurrent Neural Network (ConvRNN), Convolutional Long Short-Term Memory (ConvLSTM), and Random Forest (RF). Among them, CAE-RBNN reduces the MAE and MSE of the single-time-step prediction task by 8.40% and 10.69%, respectively, compared with the suboptimal model and decreases them by 16.31% and 22.57%, respectively, in the continuous prediction task. More importantly, it effectively quantifies the uncertainty of different driving forces, thereby improving the reliability of island NDVI predictions influenced by the environment. Full article

Jixin fruit (Malus domestica ‘Jixin’) is a high-value specialty fruit of significant economic importance in northeastern and northwestern China. Automatic recognition of fruit maturity is a critical prerequisite for intelligent harvesting. However, challenges inherent to field environments—including heterogeneous ripeness levels among fruits on the same plant, gradual color transitions during maturation that result in ambiguous boundaries, and occlusion by branches and foliage—render traditional image recognition methods inadequate for simultaneously achieving high recognition accuracy and computational efficiency. Although existing deep learning models can improve recognition accuracy, their substantial computational demands and high hardware requirements preclude deployment on resource-constrained embedded devices such as harvesting robots. To achieve the rapid and accurate identification of Jixin fruit maturity, this study proposes Multi-Attention DeepLabV3+ (MA-DeepLabV3+), a streamlined semantic segmentation framework derived from an enhanced DeepLabV3+ model. First, a lightweight backbone network is adopted to replace the original complex structure, substantially reducing computational burden. Second, a Multi-Scale Self-Attention Module (MSAM) is proposed to replace the traditional Atrous Spatial Pyramid Pooling (ASPP) structure, reducing network computational cost while enhancing the model’s perception capability for fruits of different scales. Finally, an Attention and Convolution Fusion Module (ACFM) is introduced in the decoding stage to significantly improve boundary segmentation accuracy and small target recognition ability. Experimental results on a self-constructed Jixin fruit dataset demonstrated that the proposed MA-DeepLabV3+ model achieves an mIoU of 86.13%, mPA of 91.29%, and F1 score of 90.05%, while reducing the number of parameters by 89.8% and computational cost by 55.3% compared to the original model. The inference speed increased from 41 frames per second (FPS) to 81 FPS, representing an approximately two-fold improvement. The model memory footprint is only 21 MB, demonstrating potential for deployment on embedded devices such as harvesting robots. Experimental results demonstrate that the proposed model achieves significant reductions in computational complexity while maintaining high segmentation accuracy, exhibiting robust performance particularly in complex scenarios involving color gradients, ambiguous boundaries, and occlusion. This study provides technical support for the development of intelligent Jixin fruit harvesting equipment and offers a valuable reference for the application of lightweight deep learning models in smart agriculture. Full article

The industrial heritage of the Third Front construction (hereafter referred to as Third Front industrial heritage) serves as a significant physical manifestation of China’s urban society, economy, and culture during a unique historical period. Its widespread abandonment not only constitutes a waste of social resources but also accelerates the erosion of collective memory surrounding the Third Front initiative. As one of Sichuan Province’s (including present-day Chongqing) key Third Front construction regions during that era, Guangyuan City possesses a substantial legacy of Third Front industrial heritage sites. These sites are predominantly idle and face ongoing risks of deterioration, necessitating comprehensive and systematic research into their classification, protection, and regeneration. This paper focuses on 39 Third Front industrial heritage sites in Guangyuan City, employing architectural typology to construct a ‘type-medium-value’ research framework integrating field research with strategic distribution analysis at the urban level, spatial form analysis at the settlement level, and spatial combination analysis at the building level to quantitatively identify and qualitatively deconstruct the spatial logic of these sites. This enables the analysis of the functional characteristics, structural logic, and spatial intent embodied by different types, thereby exploring the multidimensional value implications of Third Front industrial heritage through this value medium. Ultimately, this research proposes targeted adaptive mechanisms and revitalisation pathways for Third Front industrial heritage. It aims to promote the cultural legacy of this heritage and perpetuate the Third Front spirit within the context of strengthening the Chinese national community consciousness in the new era, while aligning with the Party and state’s development strategies. This approach aims to provide a reference for revitalising and utilising Third Front industrial heritage in other underdeveloped regions. Full article

Independent vector analysis (IVA) has emerged as a powerful tool for fusing and analyzing functional magnetic resonance imaging (fMRI) data. Applying IVA to multi-task fMRI data enhances analytical power by capturing the relationships across different tasks in order to discover their underlying multivariate relationship to one another. Incorporation of prior information into IVA enhances the separability and interpretability of estimated components. In this paper, we demonstrate successful fusion of multi-task fMRI feature data under two settings: constrained IVA and constrained transposed IVA (tIVA). We show that using these methods for fusing multi-task fMRI feature data offers novel ways to improve the quality and interpretability of the analysis. While constrained IVA extracts components linked to distinct brain networks, tIVA reverses the roles of spatial components and subject profiles, enabling flexible analysis of behavioral effects. We apply both methods to a multi-task fMRI dataset of 247 subjects. We demonstrate that for task-based fMRI, structural MRI (sMRI) references provide a better match for task data than resting-state fMRI (rs-fMRI) references, and using sMRI priors improves identification of group differences in task-related networks, such as the sensory-motor network during the Auditory Oddball (AOD) task. Additionally, constrained tIVA allows for targeted investigation of the effects of behavioral variables by applying them individually during the analysis. For instance, by using the letter number sequence subtest, a measure of working memory, as a behavioral constraint in tIVA, we observed significant group differences in the auditory and sensory-motor networks during the AOD task. Results show that the use of two constrained approaches, guided by well-aligned structural and behavioral references, enables a more comprehensive analysis of underlying brain function as modulated by task. Full article

To address the high incidence of work-related musculoskeletal disorders (WMSDs) at manual edge-banding workstations in furniture factories, and in an effort to tackle the existing research challenges of poor cumulative risk quantification and inconsistent evaluations, this paper proposes a three-stage system for continuous, automated, non-invasive WMSD risk monitoring. First, MediaPipe 0.10.11 is used to extract 33 key joint coordinates, compute seven types of joint angles, and resolve missing joint data, ensuring biomechanical data integrity for subsequent analysis. Second, joint angles are converted into graded parameters via RULA, REBA, and OWAS criteria, enabling automatic calculation of posture risk scores and grades. Third, an Adaptive Pooling Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM) dual-branch hybrid model based on the Efficient Channel Attention (ECA) mechanism is built, which takes nine-dimensional features as the input to predict expert-rated fatigue states. For validation, 32 experienced female workers performed manual edge-banding tasks, with smartphones capturing videos of the eight work steps to ensure authentic and representative data. The results show the following findings: (1) system ratings strongly correlate with expert evaluations, verifying its validity for posture risk assessment; (2) the hybrid model successfully captures the complex mapping of expert-derived fatigue patterns, outperforming standalone CNN and LSTM models in fatigue prediction—by integrating CNN-based spatial feature extraction and LSTM-based temporal analysis—and accurately maps fatigue indexes while generating intervention recommendations. This study addresses the limitations of traditional manual evaluations (e.g., subjectivity, poor temporal resolution, and inability to capture cumulative risk), providing an engineered solution for WMSD prevention at these workstations and serving as a technical reference for occupational health management in labor-intensive industries. Full article

This study compares the performance of empirical and hybrid deep learning (DL) models in estimating daily potential evapotranspiration (PET) in the Nakdong River Basin (NRB), South Korea, with the FAO-56 Penman–Monteith (PM) method as a reference. Two empirical models, Priestley–Taylor (P-T) and Hargreaves–Samani (H-S), and two DL models, a standalone Long Short-Term Memory (LSTM) network and a hybrid Convolutional Neural Network Bidirectional LSTM with an attention mechanism, were trained on a meteorological dataset (1973–2024) across 13 meteorological stations. Four input combinations (C1, C2, C3, and C4) were tested to assess the model’s robustness under varying data availability conditions. The results indicate that empirical models performed poorly, with a basin-wide RMSE of 5.04–5.79 mm/day and negative NSE (−10.37 to −13.99), and are therefore poorly suited to NRB. In contrast, DL models achieved significant improvements in accuracy. The hybrid CNN-BiLSTM Attention Mechanism (C1) produced the highest performance, with R² = 0.820, RMSE = 0.672 mm/day, NSE = 0.820, and KGE = 0.880, which was better than the standalone LSTM (R² = 0.756; RMSE = 0.782 mm/day). The generalization of heterogeneous climates was also verified through spatial analysis, in which the NSE at the station level consistently exceeded 0.70. The hybrid DL model was found to be highly accurate in representing the temporal variability and seasonal patterns of PET and is therefore more suitable for operational hydrological modeling and water-resource planning in the NRB. Full article

Leaf area index (LAI) is a pivotal biophysical parameter linking vegetation physiological processes and macro-ecological functions. Accurate large-scale LAI estimation is indispensable for agricultural management, climate change research, and ecosystem modeling. However, existing methods fail to efficiently extract integrated spatial-spectral-temporal features and lack targeted modeling of spatio-temporal dependencies, compromising the accuracy of LAI products. To address this gap, we propose STC-DeepLAINet, a Transformer-GCN hybrid deep learning architecture integrating spatio-temporal correlations via the following three synergistic modules: (1) a 3D convolutional neural networks (CNNs)-based spectral-spatial embedding module capturing intrinsic correlations between multi-spectral bands and local spatial features; (2) a spatio-temporal correlation-aware module that models temporal dynamics (by “time periods”) and spatial heterogeneity (by “spatial slices”) simultaneously; (3) a spatio-temporal pattern memory attention module that retrieves historically similar spatio-temporal patterns via an attention-based mechanism to improve inversion accuracy. Experimental results demonstrate that STC-DeepLAINet outperforms eight state-of-the-art methods (including traditional machine learning and deep learning networks) in a 500 m resolution LAI inversion task over China. Validated against ground-based measurements, it achieves a coefficient of determination (R²) of 0.827 and a root mean square error (RMSE) of 0.718, outperforming the GLASS LAI product. Furthermore, STC-DeepLAINet effectively captures LAI variability across typical vegetation types (e.g., forests and croplands). This work establishes an operational solution for generating large-scale high-precision LAI products, which can provide reliable data support for agricultural yield estimation and ecosystem carbon cycle simulation, while offering a new methodological reference for spatio-temporal correlation modeling in remote sensing inversion. Full article

Spatial cognition refers to how people transform physical spatial information into mental representations and manipulate it to perform further spatial computation and reasoning. Previous research has demonstrated that the frame of reference (FOR) in physical space could distort spatial representations to influence the memory of spatial relations. However, it remains unclear whether FORs could also influence attentional allocation among the spatial representations. To address this issue, we examined the attentional shifting within or between different spatial regions, which were affected by the same versus different FORs. In Experiment 1, a modified double-rectangle cuing paradigm was adopted. Two human figures in complementary colors were presented to establish two object-centered spatial FORs, which divided the external space around the objects into a central region (influenced by two FORs) and two outer-side regions (primarily influenced by a single FOR). Cues and targets were presented in the same region or different regions. Results showed faster attentional shifting within the same region than between different regions. In Experiment 2, one human figure was replaced as a cross, and the within-region advantage was replicated. Overall, these findings suggest that object-centered FORs could be employed to collectively organize space and guide attentional allocation in the external space surrounding objects. Full article

The accurate and rapid estimation of ionospheric delays is essential for PPP-RTK positioning. While traditional spatial interpolation methods like Kriging rely solely on geographic correlations, they often fail to capture rapid temporal variations in the ionosphere. To overcome this limitation, this paper proposes a long short-term memory (LSTM)-based interpolation method for interpolating ionospheric delays between satellites. The method leverages both spatial and short-term temporal correlations to generate accurate ionospheric corrections at user locations. The model uses a sliding window approach, taking the most recent 10 min of historical data as input to predict ionospheric delays at the current epoch. Experimental validation using data from a reference network in Australia—with average and maximum baseline lengths of 280 km and 650 km, respectively—demonstrates that the proposed LSTM method achieves a centimeter-level interpolation accuracy, with RMS errors between 0.06 m and 0.07 m under both quiet and geomagnetic storm conditions, significantly outperforming the Kriging method (0.27–0.44 m). In PPP-RTK, the LSTM model achieved a 3D positioning accuracy of 8.99 cm RMS during quiet periods, representing improvements of 51.9% and 28.8% over the No Constraint and Kriging methods, respectively. Under geomagnetic storm conditions, it maintained a 3D RMS of 24.54 cm—over 44% more accurate than other methods—and reduced the average time-to-first-fix (TTFF) to just 7.0 min, a 39.1% improvement. This study provides a novel approach for ionospheric spatial interpolation, demonstrating a particular robustness even during geomagnetic storms. Full article

Abandoned mines, as emblematic heritage spaces in the process of deindustrialization, preserve collective production memory and serve as vital symbols of local identity. However, current redevelopment practices primarily emphasize physical restoration while overlooking the visual expression and interactive communication of regional culture. This study introduces an augmented reality (AR)–based visual narrative framework that integrates regional culture to bridge the gap between spatial renewal and cultural regeneration. Drawing on semiotics and spatial narrative theory, a multidimensional “space–symbol–memory” translation mechanism is constructed, and a coupling model linking tangible material elements with intangible cultural connotations is established. Supported by technologies such as simultaneous localization and mapping (SLAM), semantic segmentation, and level of detail (LOD) rendering, a multilayer “position–perception–presentation” module system is designed to achieve stable anchoring of virtual and physical spaces and enable multilevel narrative interaction. Through task-oriented mechanisms and user co-creation, the system effectively enhances immersion, cultural identity, and learning outcomes. Experimental validation in a representative mine site confirms the feasibility of the proposed framework. While the study focuses on a single case, the modular and mechanism-based design indicates that the framework can be adapted to cultural tourism, educational communication, and community engagement applications. The key innovation lies in introducing an iterative “evidence–experience–co-creation” model, providing a new methodological reference for the digital reuse of abandoned mines and the sustainable preservation of industrial heritage. Full article

Efficient spatial indexing is critical for processing large-scale remote sensing datasets (e.g., LiDAR point clouds, orthophotos, hyperspectral imagery). We present a bidirectional, hierarchical index based on the Polish PL-2000 coordinate reference system for (1) direct computation of a map-sheet identifier from metric coordinates (forward encoder) and (2) reconstruction of the sheet extent from the identifier alone (inverse decoder). By replacing geometric point-in-polygon tests with closed-form arithmetic, the method achieves constant-time assignment O(1), eliminates boundary-geometry loading, and enables multi-scale aggregation via simple code truncation. Unlike global spatial indices (e.g., H3, S2), a CRS-native, aligned with cartographic map sheets in PL-2000 implementation, removes reprojection overhead and preserves the legal sheet semantics, enabling the direct use of deterministic O(1) numeric keys for remote-sensing data and Polish archives. We detail the algorithms, formalize their complexity and boundary rules across all PL-2000 zones, and analyze memory trade-offs, including a compact 26-bit packing of numeric keys for nationwide single-table indexing. We also discuss integration patterns with the OGC Tile Matrix Set (TMS), ETL pipelines, and GeoAI workflows, showing how bidirectional indexing accelerates ingest, training and inference, and national-scale visualization. Although demonstrated for PL-2000, the approach is transferable to other national coordinate reference systems, illustrating how statutory map-sheet identification schemes can be transformed into high-performance indices for modern remote sensing and AI data pipelines. Full article

Deepfake audio refers to the generation of voice recordings using deep neural networks that replicate a specific individual’s voice, often for deceptive or fraud purposes. Although this has been an area of research for quite some time, deepfakes still pose substantial challenges for reliable true speaker authentication. To address the issue, we propose AudioFakeNet, a hybrid deep learning architecture that use Convolutional Neural Networks (CNNs) along with Long Short-Term Memory (LSTM) units, and Multi-Head Attention (MHA) mechanisms for robust deepfake detection. CNN extracts spatial and spectral features, LSTM captures temporal dependencies, and MHA enhances to focus on informative audio segments. The model is trained using Mel-Frequency Cepstral Coefficients (MFCCs) from the publicly available dataset and was validated on self-collected dataset, ensuring reproducibility. Performance comparisons with state-of-the-art machine learning and deep learning models show that our proposed AudioFakeNet achieves higher accuracy, better generalization, and lower Equal Error Rate (EER). Its modular design allows for broader adaptability in fake-audio detection tasks, offering significant potential across diverse speech synthesis applications. Full article

Nonlocal models offer a unified framework for describing long-range spatial interactions and temporal memory effects. The review briefly outlines several representative physical problems, including anomalous diffusion, material fracture, viscoelastic wave propagation, and electromagnetic scattering, to illustrate the broad applicability of nonlocal systems. However, the intrinsic global coupling and historical dependence of these models introduce significant computational challenges, particularly in high-dimensional settings. From the perspective of algorithmic strategies, the review systematically summarizes high-dimensional numerical methods applicable to nonlocal equations, emphasizing core approaches for overcoming the curse of dimensionality, such as structured solution frameworks based on FFT, spectral methods, probabilistic sampling, physics-informed neural networks, and asymptotically compatible schemes. By integrating recent advances and common computational principles, the review establishes a dual “problem review + method review” structure that provides a systematic perspective and valuable reference for the modeling and high-dimensional numerical simulation of nonlocal systems. Full article