Search Results (4,508)

Deep neural network-based approaches have obtained remarkable progress in monaural speech enhancement. Nevertheless, current cutting-edge approaches remain vulnerable to complex acoustic scenarios. We propose a Symmetric Combined Convolution Network with ConvLSTM (SCCN) for monaural speech enhancement. Specifically, the Combined Convolution Block utilizes parallel convolution branches, including standard convolution and two different depthwise separable convolutions, to reinforce feature extraction in depthwise and channelwise. Similarly, Combined Deconvolution Blocks are stacked to construct the convolutional decoder. Moreover, we introduce the exponentially increasing dilation between convolutional kernel elements in the encoder and decoder, which expands receptive fields. Meanwhile, the grouped ConvLSTM layers are exploited to extract the interdependency of spatial and temporal information. The experimental results demonstrate that the proposed SCCN method obtains on average 86.00% in STOI and 2.43 in PESQ, which outperforms the state-of-the-art baseline methods, confirming the effectiveness in enhancing speech quality. Full article

Objectives: To address the challenges of subjectivity, misdiagnosis and underdiagnosis in post-traumatic stress disorder (PTSD), this study proposes an objective auxiliary diagnostic method based on P300 signals. Existing studies largely rely on conventional P300 features, lacking the systematic integration of event-related potential (ERP) priors and facing limitations in spatiotemporal feature modeling. Methods: Using common spatiotemporal pattern (CSTP) analysis and quantitative evaluation, we revealed significant spatiotemporal differences in P300 signals between PTSD patients and healthy controls. ERP prior information was then extracted and integrated into a hybrid architecture combining transformer encoders and a convolutional neural network (CNN), enabling joint modeling of long-range temporal dependencies and local spatial patterns. Results: The proposed P300 spatiotemporal transformer-CNN (P300-STTCNet) achieved a classification accuracy of 93.37% in distinguishing PTSD from healthy controls, markedly outperforming traditional approaches. Conclusions: Significant spatiotemporal differences in P300 signals exist between PTSD and healthy control groups. The P300-STTCNet model effectively captures PTSD-related spatiotemporal features, demonstrating strong potential for electroencephalogram-based objective auxiliary diagnosis. Full article

Turbidity is a crucial indicator for evaluating water quality. This study obtained the long-term spatial distribution of water turbidity across Northeast China from 1985 to 2023. A combination of the geographically and temporally weighted regression (GTWR) model, the Lindeman, Merenda, and Gold (LMG) method, and statistical data analysis methods were employed to quantify the spatiotemporal impacts of driving factors on turbidity changes. The stepwise regression model was able to credibly estimate turbidity, achieving a low RMSE of 18.432 Nephelometric Turbidity Units (NTU). Temporal variations in turbidity showed that 69.90% of lakes exhibited a decreasing trend. Spatial variations revealed that lakes with significantly increased turbidity were predominantly concentrated in the Songnen and Sanjiang Plains, whereas lakes with lower turbidity were situated in the Eastern Mountains regions and Liaohe Plain. Temporal changes were closely associated with socioeconomic development and anthropogenic interventions implemented by governments on the aquatic environment. Vegetation coverage, precipitation, and elevation demonstrated significant contributions (exceeding 16.39%) to turbidity variations in the Lesser Khingan and Eastern Mountains regions, where natural factors played a more dominant role. In contrast, cropland area, wind speed, and impervious surface area showed higher contribution rates of above 14.00% in the Songnen, Sanjiang, and Liaohe Plains, where anthropogenic factors were dominant. These findings provide valuable insights for informed decision-making in water environmental management in Northeast China and facilitate the aquatic ecosystem sustainability under human activities and climate change. Full article

ADHD classification has traditionally relied on accelerometer-derived tabular features, which summarise static activity but fail to capture spatial-temporal patterns, potentially limiting model performance. We developed a multimodal deep learning framework that transforms raw accelerometer signals into images and integrates them with clinical tabular data, enabling the joint exploration of dynamic activity patterns and static clinical characteristics. Data were collected from children aged 7–13 years, including accelerometer recordings from Apple Watches and clinical measures from standardised questionnaires. Deep learning models for image feature extraction and multiple fusion strategies were evaluated to identify the most effective representation and integration method. Our analyses indicated that combining activity images with clinical variables facilitated the classification of ADHD, with the ViT-BiLSTM model using cross-attention fusion achieving the highest performance. These findings suggest that multimodal learning can become a robust approach to ADHD classification by leveraging complementary information from activity dynamics and clinical data. Our framework and code will be made publicly available to support reproducibility and future research. Full article

In recent years, with the continuous development of information technology, network security issues have become increasingly prominent. Intrusion detection has garnered significant attention in the field of network security protection due to its ability to detect anomalies in a timely manner. However, existing intrusion detection methods often fail to effectively capture spatiotemporal correlations in traffic and struggle with imbalanced, high-dimensional feature spaces—problems that become even more pronounced under complex network environments—ultimately leading to low identification accuracy and high false-positive rates. To address these challenges, this paper proposes a spatiotemporal correlation-based intrusion detection method that utilizes feature space transformation and Euclidean distance. Specifically, the method first considers the relationship between the characteristics of different operating systems and attack behaviors through feature space transformation and integration. Then, it constructs a graph structure between samples using Euclidean distance and captures the spatiotemporal correlations between samples by combining graph convolutional networks with bidirectional gated recurrent unit networks. Through this design, the model can deeply mine the spatial and temporal features of network traffic, thereby improving classification accuracy and detection efficiency for network attacks. Experimental results show that the proposed model significantly outperforms existing intrusion detection approaches across multiple evaluation metrics, including accuracy, weighted precision, weighted recall, and weighted F1 score. Full article

Urban parks play a crucial role in mitigating urban heat stress and maintaining ecological stability through their cold island effect (PCIE). However, studies examining how multidimensional urban morphology influences these effects, particularly from a diurnal perspective in island cities, remain limited. This study investigates 30 representative urban parks within a typical island city, exploring how two-dimensional and three-dimensional spatial morphological factors affect four key PCIE indicators: park cooling intensity (PCI), park cooling gradient (PCG), park cooling area (PCA) and park cooling efficiency (PCE) across different times of day and night. The results reveal that: (1) coastal zones exhibit significantly lower land surface temperature (LST) than inland zones, with peak LST occurring at 5:00 p.m.; (2) the four cold island indicators follow a diurnal pattern of 5:00 p.m. > 1:00 a.m. > 7:00 a.m.; (3) morphological construction factors—such as building density (BD) and built-up proportion (BP)—positively contribute to cooling effects at 7:00 a.m., while park perimeter (PP) enhances cooling performance at both 5:00 p.m. and 1:00 a.m. Additionally, vegetation characteristics surrounding parks, including the normalized difference vegetation index (NDVI) and green space proportion (GP), influence daytime cooling in directions opposite to those of the aforementioned construction-related factors. These findings offer valuable insights into the temporal dynamics and spatial determinants of urban park cooling in island cities, providing a scientific basis for scientifically informed park planning and contributing to healthier and more sustainable urban development. Full article

Identifying urban functional areas increasingly relies on data-driven approaches that utilize multimodal spatial information. There is a growing focus on purpose-oriented functional area identification with greater policy relevance. This paper proposes a data-driven methodology to identify functional areas from the perspective of bicycle users. To achieve this, line-based road network units were defined around bicycle stations, and spatial–temporal data such as Origin–Destination flows and Point of Interest information were semantically integrated to delineate functional areas. An experiment was conducted on 2628 public bicycle stations in Seoul, Republic of Korea, for May 2022, and a total of five functional areas were identified via a Co-Matrix Factorization-based fusion approach. Additionally, the proposed method was validated through visual evaluation and comparison with actual bicycle usage data. The results demonstrate that by simultaneously incorporating spatial–temporal information and latent connectivity, this approach identifies bicycle-friendly areas, even with low observed usage, highlighting its potential for policy applications. Full article

Cough is a key symptom reflecting respiratory health, with its frequency and pattern providing valuable insights into disease progression and clinical management. Objective and reliable cough detection systems are therefore of broad significance for healthcare and remote monitoring. However, existing algorithms often struggle to jointly model spatial and temporal information, limiting their robustness in real-world applications. To address this issue, we propose a cough recognition framework based on frequency-modulated continuous-wave (FMCW) radar, integrating a deep convolutional neural network (CNN) with a Self-Attention mechanism. The CNN extracts spatial features from range-Doppler maps, while Self-Attention captures temporal dependencies, and effective data augmentation strategies enhance generalization by simulating position variations and masking local dependencies. To rigorously evaluate practicality, we collected a large-scale radar dataset covering diverse positions, orientations, and activities. Experimental results demonstrate that, under subject-independent five-fold cross-validation, the proposed model achieved a mean F1-score of $0.974\pm 0.016$ and an accuracy of $99.05\pm 0.55$ %, further supported by high precision of $98.77\pm 1.05$ %, recall of $96.07\pm 2.16$ %, and specificity of $99.73\pm 0.23$ %. These results confirm that our method is not only robust in realistic scenarios but also provides a practical pathway toward continuous, non-invasive, and privacy-preserving respiratory health monitoring in both clinical and telehealth applications. Full article

As a critical ecological barrier and key dryland agricultural zone in China, the Loess Plateau is faced with acute tensions between food security risks arising from cropland abandonment (CA) and the imperatives of ecological conservation. Yet, existing research has failed to adequately capture the long-term, high-spatiotemporal-resolution dynamics of abandonment in this region or to quantitatively couple its driving mechanisms with implications for food security. To address these gaps, this study establishes a high-precision identification system for CA tailored to the Plateau’s complex topographic conditions, distinguishing among interannual abandonment, multiyear abandonment, conversion to forest/grassland, and reclamation. Leveraging long-term data from 2000 to 2023 and integrating the Mann–Kendall test with the random forest algorithm, we examine the spatiotemporal trajectories, driving forces, and food security consequences of CA. Guided by a “type differentiation–grade classification–temporal tracking” framework, the analysis reveals a marked transition in dominant drivers from “socioeconomic factors” to “topographic–climatic factors.” It further identifies an “increasing loss–slowing growth” effect of abandonment on grain production, alongside a “pressure alleviation” trend in per capita carrying capacity. The results showed that: (1) Between 2000 and 2023, the area of CA on the Loess Plateau expanded from 2.72 million ha to 6.96 million ha, with high-grade abandonment (≥8 years) accounting for 58.9% of the total and being spatially concentrated in the hilly–gully regions of northern Shaanxi and eastern Gansu; (2) The Grain for Green Project (GFGP) peaked at approximately 340,000 hectares in 2018, followed by a slight decline, but has generally remained at around 300,000 hectares since then; (3) The reclamation rate of CA remained between 5% and 12% during 2003–2015, with minimal overall fluctuations, but after 2016, it gradually increased and peaked at 23.4% in 2022; (4) In terms of driving forces, population density (14.99%) was the primary determinant in 2005, whereas by 2020, slope (15.43%) and mean annual precipitation (15.63%) emerged as core factors; and (5) Grain yield losses attributable to abandonment increased from less than 100 t to nearly 450 t, though the growth rate slowed after 2016, accompanied by gradual alleviation of pressure on per capita carrying capacity. Overall, the study offers robust empirical evidence to inform cropland protection, food security strategies, and sustainable agricultural development policies on the Loess Plateau. Full article

In recent years, the powerful feature extraction capabilities of deep learning have attracted widespread attention in the field of bearing fault diagnosis. To address the limitations of single-modal and single-channel feature extraction methods, which often result in incomplete information representation and difficulty in obtaining high-quality fault features, this paper proposes a dual-channel parallel multimodal feature fusion model for bearing fault diagnosis. In this method, the one-dimensional vibration signals are first transformed into two-dimensional time-frequency representations using continuous wavelet transform (CWT). Subsequently, both the one-dimensional vibration signals and the two-dimensional time-frequency representations are fed simultaneously into the dual-branch parallel model. Within this architecture, the first branch employs a combination of a one-dimensional convolutional neural network (1DCNN) and a bidirectional gated recurrent unit (BiGRU) to extract temporal features from the one-dimensional vibration signals. The second branch utilizes a dilated convolutional to capture spatial time–frequency information from the CWT-derived two-dimensional time–frequency representations. The features extracted by both branches were are input into the feature fusion layer. Furthermore, to leverage fault features more comprehensively, a channel attention mechanism is embedded after the feature fusion layer. This enables the network to focus more effectively on salient features across channels while suppressing interference from redundant features, thereby enhancing the performance and accuracy of the dual-branch network. Finally, the fused fault features are passed to a softmax classifier for fault classification. Experimental results demonstrate that the proposed method achieved an average accuracy of 99.50% on the Case Western Reserve University (CWRU) bearing dataset and 97.33% on the Southeast University (SEU) bearing dataset. These results confirm that the suggested model effectively improves fault diagnosis accuracy and exhibits strong generalization capability. Full article

The dairy industry faces challenges from mastitis, which affects milk quality. Somatic Cell Counts (SCCs) are key indicators of udder health, subclinical mastitis presence, and legal thresholds. However, limited research has explored geographic disparities and temporal patterns in SCCs across the USA, despite their critical role in informing targeted herd management strategies, optimizing policy interventions, and ensuring consistent milk quality standards. This study aimed to examine temporal trends and geographic disparities in median weighted SCCs (mwSCCs) across USA states. This study analyzes SCC data using records from the Dairy Herd Improvement Association across 42–45 states between 2011 and 2023. State-level differences in mwSCCs were examined, with temporal changes assessed using percent differences between 2011 and 2023. Moran’s I and Local Indicators of Spatial Association (LISA) were used to identify spatial clusters of states with high and low mwSCCs. The mwSCCs decreased by 24.8%, from 234,000 cells/mL in 2011 to 176,000 cells/mL in 2023, with significant reductions in Virginia and Georgia, while Tennessee and South Carolina had minimal declines. However, Texas, California, and Colorado saw increases, with Colorado rising by 147.9%. Spatial clustering revealed high mwSCCs in the southeast and low levels in the northeast, highlighting the need for region-specific strategies. Full article

Heavy-duty diesel trucks (HDDTs) are recognized as significant sources of air pollutants and greenhouse gases (GHGs) along freight corridors in port cities. Despite their impact, few studies have provided detailed spatiotemporal insights into their emissions within port-adjacent highway systems. This study presents a high-resolution, hourly emission inventory at the road-segment level for six major expressways in Shanghai, one of China’s leading port cities. The emission estimates are derived using a locally adapted COPERT V model, calibrated with HDDT GPS trajectory data and detailed road network information from OpenStreetMap. The inventory quantifies emissions of CO₂, NO_x, CO, PM, and VOCs, highlighting distinct temporal and spatial variation patterns. Weekday emissions consistently exceed those of weekends, with three prominent traffic-related peaks occurring between 5:00–7:00, 10:00–12:00, and 14:00–16:00. Spatial analysis identifies the G1503 and S20 expressways as major emission corridors, with S20 exhibiting particularly high emission intensity relative to its length. Combined spatiotemporal patterns reveal that weekday emission hotspots are more concentrated, reflecting typical freight activity cycles such as morning dispatch and afternoon return. The findings provide a scientific basis for formulating more precise emission control measures targeting HDDT operations in urban port environments. Full article

In the field of water process engineering, accurately predicting the total nitrogen (TN) concentration distribution in the Semi-Enclosed Bay area is of great importance for water quality assessment, pollution control, and scientific management. Due to the coupling of multiple influencing factors, the pollution process is complex, and traditional monitoring methods struggle to achieve large-scale, long-term real-time observation. Although numerical simulations can reproduce TN transport processes, they are computationally expensive and have low prediction efficiency. To address this, this study develops a deep learning hybrid model that integrates a Temporal Convolutional Network (TCN) and a Long Short-Term Memory (LSTM) network, referred to as the TCN-LSTM-Hybrid Model, to predict the spatiotemporal distribution of TN concentration fields in Shenzhen Bay. Comparative experiments show that this model outperforms traditional models such as TCN, LSTM, GRU, and MLP in terms of prediction accuracy and spatial generalization, offering higher computational efficiency and breaking through the limitations of “point-based prediction” by achieving “field-based prediction,” thereby providing a new path for pollutant simulation in complex ocean environments, supporting more informed decision making in ocean and coastal management. Full article

In this study, we propose a novel hybrid framework for assessing the invasiveness of an in-house dataset of 114 pathologically proven lung adenocarcinomas presenting as subsolid nodules on Computed Tomography (CT). Nodules were classified into group 1 (G1), which included atypical adenomatous hyperplasia, adenocarcinoma in situ, and minimally invasive adenocarcinomas, and group 2 (G2), which included invasive adenocarcinomas. Our approach includes a three-way Integration of Visual, Spatial, and Temporal features with Attention, referred to as I-VISTA, obtained from three processing algorithms designed based on Deep Learning (DL) and radiomic models, leading to a more comprehensive analysis of nodule variations. The aforementioned processing algorithms are arranged in the following three parallel paths: (i) The Shifted Window (SWin) Transformer path, which is a hierarchical vision Transformer that extracts nodules’ related spatial features; (ii) The Convolutional Auto-Encoder (CAE) Transformer path, which captures informative features related to inter-slice relations via a modified Transformer encoder architecture; and (iii) a 3D Radiomic-based path that collects quantitative features based on texture analysis of each nodule. Extracted feature sets are then passed through the Criss-Cross attention fusion module to discover the most informative feature patterns and classify nodules type. The experiments were evaluated based on a ten-fold cross-validation scheme. I-VISTA framework achieved the best performance of overall accuracy, sensitivity, and specificity (mean ± std) of 93.93 ± 6.80%, 92.66 ± 9.04%, and 94.99 ± 7.63% with an Area under the ROC Curve (AUC) of 0.93 ± 0.08 for lung nodule classification among ten folds. The hybrid framework integrating DL and hand-crafted 3D Radiomic model outperformed the standalone DL and hand-crafted 3D Radiomic model in differentiating G1 from G2 subsolid nodules identified on CT. Full article

Post-fire soil and vegetation changes can intensify erosion and sediment yield by altering the factors controlling the runoff–infiltration balance. Erosion barriers (EBs) are widely used in hydrological and forest restoration to mitigate erosion, reduce sediment transport, and promote vegetation recovery. However, precise spatial assessments of their effectiveness remain scarce, requiring validation through operational methodologies. This study evaluates the impact of EB on post-fire vegetation recovery at two temporal and spatial scales: (1) Remotely Piloted Aircraft System (RPAS) imagery, acquired at high spatial resolution but limited to a single acquisition date coinciding with the field flight. These data were captured using a MicaSense RedEdge-MX multispectral camera and an RGB optical sensor (SODA), from which NDVI and vegetation height were derived through aerial photogrammetry and digital surface models (DSMs). (2) Sentinel-2 satellite imagery, offering coarser spatial resolution but enabling multi-temporal analysis, through NDVI time series spanning four consecutive years. The study was conducted in the area of the Luna Fire (northern Spain), which burned in July 2015. A paired sampling design compared upstream and downstream areas of burned wood stacks and control sites using NDVI values and vegetation height. Results showed slightly higher NDVI values (0.45) upstream of the EB (p < 0.05), while vegetation height was, on average, ~8 cm lower than in control sites (p > 0.05). Sentinel-2 analysis revealed significant differences in NDVI distributions between treatments (p < 0.05), although mean values were similar (~0.32), both showing positive trends over four years. This study offers indirect insight into the functioning and effectiveness of EB in post-fire recovery. The findings highlight the need for continued monitoring of treated areas to better understand environmental responses over time and to inform more effective land management strategies. Full article