Search Results (1,250)

To address the challenges of difficult feature extraction and suboptimal parameter configuration for cyclotron ion source fault diagnosis in complex environments, this study proposes an intelligent diagnostic framework integrating Kernel Principal Component Analysis (KPCA), an Improved Sparrow Search Algorithm (ISSA), and a Support Vector Machine (SVM). The KPCA algorithm is employed for dimensionality reduction to handle the highly nonlinear nature of fault data. Regarding algorithmic evolution, the basic SSA is enhanced by integrating dynamic weights, opposition-based learning, and Cauchy mutation strategies, which effectively overcome the diagnostic bottlenecks inherent in cyclotron scenarios. Furthermore, the ISSA facilitates the global adaptive optimization of key SVM parameters, eliminating the stochasticity of empirical tuning and fundamentally enhancing the model’s robustness. Experimental results across 30 independent tests demonstrate that the KPCA-ISSA-SVM model achieves an average accuracy of 97.6% in multi-class fault detection. Compared with other classic diagnostic models, the proposed framework exhibits superior precision and stability, providing an effective technical approach with significant engineering value for the precise monitoring of ion source statuses. Full article

Cloud computing is one of the essential computing platforms for modern enterprises. A total of 84 percent of large businesses use cloud computing services in 2025 to enable remote working and higher flexibility of operation with reduction in the cost of operation. Cloud environments are dynamic and multitenant, often demanding high computational resources for real-time processing. However, the cloud system’s behavior is subjected to various kinds of anomalies in which patterns of data deviate from the normal traffic. The varieties of anomalies that exist are performance anomalies, security anomalies, resource anomalies, and network anomalies. These anomalies disrupt the normal operation of cloud systems by increasing the latency, reducing throughput, frequently violating service level agreements (SLAs), and experiencing the failure of virtual machines. Among all anomalies, virtual machine failures are one of the potential anomalies in which the normal operation of the virtual machine is interrupted, resulting in the degradation of services. Virtual machine failure happens because of resource exhaustion, malware access, packet loss, Distributed Denial of Service attacks, etc. Hence, there is a need to detect the chances of virtual machine failures and prevent it through proactive measures. Traditional machine learning techniques often struggle with high-dimensional data and nonlinear correlations, ending up with poor real-time adaptation. Hence, quantum machine learning is found to be a promising solution which effectively deals with combinatorially complex and high-dimensional data. In this paper, a novel quantum-enhanced support vector machine (QSVM) is designed as an optimized binary classifier which combines the principles of both quantum computing and support vector machine. It encodes the classical data into quantum states. Feature mapping is performed to transform the data into the high-dimensional form of Hilbert space. Quantum kernel evaluation is performed to evaluate similarities. Through effective optimization, optimal hyperplanes are designed to detect the anomalous behavior of virtual machines. This results in the exponential speed-up of operation and prevents the local minima through entanglement and superposition operation. The performance of the proposed QSVM is analyzed using the QuCloudSim 1.0 simulator and further validated using expected value analysis methodology. Full article

The uneven spatial distribution of data elements poses challenges to regional equity and sustainable development. To unmask spatial dynamics obscured by traditional macro-divisions, this study evaluates data element development across China’s Eight Comprehensive Economic Regions from 2013 to 2022. Using the entropy weight method, Dagum Gini coefficient, Kernel Density Estimation, and spatial autocorrelation models, the results indicate that while the overall development index exhibits a sustained upward trend, inter-regional differences remain the dominant source of spatial inequality. This disparity is primarily driven by the persistent gap between advanced coastal and lagging inland regions. Notably, spatial trajectories diverge significantly: the Eastern Coastal region exhibits coordinated integration, whereas severe internal polarization appears in the Middle Reaches of the Yellow River and the Southwest. Furthermore, the spatial spillover of data elements remains bounded by physical geography. By highlighting these meso-level structural fault lines, this study provides precise empirical evidence for formulating targeted, basin-specific interventions to bridge the digital divide. Full article

Scanning electrochemical microscopy (SECM) provides spatially resolved electrochemical information but is constrained by long acquisition times arising from dense spatial sampling requirements. This work investigates whether physics-informed signal representations can improve neural reconstruction of SECM approach curve signals from sparse measurements. We propose an exponential function-based Neural Tangent Kernel (NTK) framework in which SECM signals are encoded using deterministic exponential feature mappings aligned with diffusion-controlled electrochemical dynamics. A layer-wise NTK checkpointing mechanism is employed to filter covariantly insignificant components during training, reducing redundancy while preserving dominant signal modes. The method is evaluated on synthetically generated SECM signals designed to replicate characteristic approach curve behavior. Quantitative performance is assessed using root mean square error (RMSE), mean absolute error (MAE), relative error (%), and the coefficient of determination (R²). Compared to a random Gaussian (Fourier feature) baseline (RMSE = 0.0952, MAE = 0.0547, Rel.Err = 17.68%), the proposed exponential mappings achieve consistently lower reconstruction error, with the best configuration yielding RMSE = 0.0858, MAE = 0.0375, and relative error = 11.10% under identical training conditions. Results demonstrate that incorporating physically motivated exponential feature representations into NTK-aware learning improves reconstruction fidelity and stability for low-dimensional electrochemical signals, highlighting the potential of physics-informed kernel methods for accelerated SECM data acquisition. Full article

To tackle the challenges of high computational expense, limited detection accuracy, and imbalanced detection performance across multi-scale targets in rice disease identification within complex natural environments, we propose the Rice Disease Deformable Detection Transformer (RDD-DETR). This model serves as a full-scale detection framework based on the Deformable Detection Transformer (Deformable DETR). The model introduces a Rectified Linear Unit (ReLU)-enhanced lightweight linear attention module, which uses differentiated position coding and ReLU kernel mapping to reduce computational complexity. A cross-layer dynamic fusion and inter-layer supervision module is designed to break the serial dependence in decoders and strengthen interlayer supervision, enabling the decoder to generate more accurate and robust target representations. Furthermore, we design an optimization mechanism for sub-scale positioning loss to substantially boost detection accuracy across all target scales. Experiments on our custom RiceLeafDisease-RSOD dataset demonstrate that RDD-DETR achieves an average precision (AP) at Intersection over Union (IoU) threshold 0.5:0.95 of 0.7363 across all categories, surpassing the baseline model by 6.09%. Notably, detection accuracy improves by 6.10% for small targets, 6.61% for medium targets, and 5.42% for large targets. Evaluated on the validation set (671 images with 2482 labeled bounding boxes), the model achieves an AP at IoU threshold 0.5 of 0.9684 while reducing computational cost by 37.41% (from 136.02 to 85.1 Giga Floating Point Operations, GFLOPs) compared to the original Deformable DETR. These results validate RDD-DETR as an effective solution for accurate and efficient real-time rice disease monitoring in complex field environments. Full article

Against the backdrop of large-scale integration of renewables into the power grid, frequent load-following operation of thermal power units substantially increases the difficulty of controlling boiler NOx emissions. Accurate forecasting of boiler NOx emissions is crucial for guiding efficient and clean operation under such flexible operating conditions. However, under frequent load-following conditions, NOx dynamics are highly nonlinear and non-stationary, making it challenging to achieve accurate prediction using only time-domain information. To address these issues, we propose DTTE-Net, a time–frequency feature fusion framework for predicting SCR-inlet NOx concentration in coal-fired boilers. DTTE-Net consists of three components: a time-domain branch, a frequency-domain branch, and a gated feature fusion module. The time-domain branch captures short-term fluctuations and long-range temporal dependencies, while the frequency-domain branch extracts complementary spectral representations to enhance the characterization of non-stationary fluctuations. The gated feature fusion module then adaptively integrates the two-domain features by using a gated mechanism and produces the NOx concentration forecast. In addition, a Gaussian kernel-based loss is introduced to improve robustness to nonlinear error structures. Experiments on real distributed control system data from a 660 MW ultra-supercritical coal-fired unit show that DTTE-Net outperforms existing baseline models, achieving lower forecasting errors and higher R². Full article

General Matrix Multiplication (GEMM) is a fundamental computational kernel in scientific computing, serving as the foundation for numerous complex tasks. However, in practical applications, the performance of GEMM is often constrained by irregular matrix dimensions and the diversity of hardware architectures. In particular, when processing small and irregular matrices, GEMM typically exhibits reduced computational efficiency. To address these challenges, this paper proposes a GEMM acceleration method based on an adaptive core grouping strategy. The method consists of two key components: a core grouping mechanism that alleviates workload imbalance among multi-core CPUs, and an adaptive block partitioning algorithm that dynamically selects optimal tiling schemes according to the matrix dimensions, achieving both load balance and cache-friendly data access. Experimental results on the Kunpeng CPU platform demonstrate that the proposed method achieves significant performance improvements compared to the Kunpeng KML math library, reaching a peak acceleration of up to 2.1× and an average speedup of 1.64×. These results validate the effectiveness and efficiency of the proposed approach in handling small and irregular matrix computation scenarios. Full article

Personalized itinerary planning for large-scale passengers under resource constraints is a critical challenge in enhancing the operational efficiency and service quality of cruise tourism. Traditional clustering methods, which primarily rely on geometric similarity, often fail to address the intricate coupling between passenger preferences and finite venue capacities, lacking predictive capability for the ultimate planning quality. To overcome these limitations, this study proposes a novel bio-inspired data-driven hybrid optimization framework for the cruise itinerary planning task unit partition. The framework innovatively integrates a Genetic Balanced Clustering Algorithm (GBCA) for multi-objective passenger grouping, Kernel Principal Component Analysis (KPCA) for feature extraction from preference data, an improved Adaptive Spiral Flying Sparrow Search Algorithm (ASFSSA) for hyperparameter optimization, and a Kernel Extreme Learning Machine (KELM) for data-driven prediction of itinerary planning quality. This synergy enables the framework to dynamically allocate venue capacities based on group preferences and optimize partitioning towards maximizing overall benefits, ensuring load balance and fairness. Extensive experiments on simulated cruise scenarios demonstrate that the proposed framework significantly outperforms conventional methods, improving segmentation quality by at least 40% while exhibiting superior convergence speed and stability. This work provides a scalable, intelligent solution for complex resource-constrained scheduling problems, showcasing the effective application of bio-inspired data-driven methodologies in engineering optimization. Full article

As autonomous driving technology progresses, efficient and accurate object detectors are able to detect pedestrians, vehicles, road signs, and obstacles in real time, thereby enhancing driving safety and serving as a part of autonomous driving. However, the performance of such object detectors is limited and cannot be leveraged to satisfy modern autonomous driving systems. To address this issue, we develop an object detection network for autonomous driving scenarios, SST-YOLO, which is based on YOLOv8. First, we propose a Sobel Convolution & Convolution (SCC) module to enhance the backbone, which incorporates a SobelConv branch to explicitly model gradient-based edge information and improve structural feature representation. In addition, we replace the original path aggregation feature pyramid network (PAFPN) with a Small Object Augmentation Pyramid Network (SOAPN), which integrates SPDConv and CSP-OmniKernel modules to strengthen multi-scale feature fusion and enhance small object representation. Finally, a Task-Adaptive Decomposition & Alignment Head (TADAHead) is designed, which employs task decomposition, dynamic deformable convolution, and classification-aware modulation to decouple tasks and achieve adaptive spatial alignment, thereby improving detection accuracy and robustness in complex scenarios. Experiments on the public autonomous driving dataset KITTI show that our proposed method outperforms the baseline YOLOv8 model. Compared with the baseline results, mAP@0.5:0.95 ranges from 65.1% to 69.2%, which indicates that the proposed SST-YOLO network can achieve object detection for autonomous cars. Full article

Time–space fractional diffusion equations are widely used to model anomalous transport in heterogeneous biological tissues, where memory effects, spatial nonlocality, and coefficient variability are intrinsically coupled. However, existing numerical approaches typically treat these aspects in isolation, and a fully discrete framework that simultaneously accounts for heterogeneity, long-memory effects, and computational efficiency remains lacking. In this work, a fully discrete numerical method is developed and analyzed. The method integrates heterogeneous diffusion coefficients and memory-efficient temporal discretization within a unified variational framework. It combines a finite element approximation of a spectral fractional elliptic operator with an implicit $L^1$ discretization of the Caputo derivative enhanced by a sum-of-exponentials approximation of the memory kernel. Unconditional stability, preservation of a discrete energy structure, and a fully discrete error estimate are established, explicitly separating temporal, spatial, and kernel approximation errors. The proposed approach reduces memory complexity from $\mathcal{O}\left(N\right)$ to $\mathcal{O}(logN)$ without compromising accuracy. Numerical experiments confirm the theoretical convergence rates, demonstrate stable behavior across all tested configurations, and illustrate the impact of heterogeneous coefficients on anomalous transport dynamics. Full article

Multi-agent swarm collaboration, inspired by the collective behaviors of biological swarms in nature, has wide applications in dynamic open environments. However, hybrid action spaces in multi-agent reinforcement learning (MARL) present a critical challenge: the inherent coupling between discrete and continuous actions severely undermines policy stability and convergence, especially under dynamic topologies. Existing methods fail to decouple this coupling, leading to suboptimal policies and unstable training. This paper addresses the core problem of action coupling under dynamic topologies, proposing a Parametrized Graph Convolution Reinforcement Learning (P-DGN) method. Operating within the actor–critic framework, P-DGN decouples the optimization pathways for hybrid actions, with a biomimetic observation design inspired by starling flock behaviors: each agent only observes the states of its seven nearest neighbors to achieve efficient local interaction and global collaboration. Its actor network uses multi-head attention to build dynamic relation kernels, develops temporal relation regularization (TRR) to improve policy consistency across time steps, and generates continuous actions with a Gaussian policy. Meanwhile, P-DGN’s critic network, based on deep Q-network (DQN), evaluates Q-values for discrete actions to guide optimal choices. We evaluate P-DGN in two different multi-agent cooperative environments. Experimental results show that compared with parametrized deep Q-network (P-DQN) and DQN baseline, the proposed method has faster convergence speed and stronger training stability. Moreover, with dense rewards, P-DGN agents learn emergent tactics like encirclement. Overall, P-DGN offers a new approach for optimizing hybrid action spaces in multi-agent systems within open, dynamic environments, balancing theoretical generality with practical utility, and its biomimetic design provides a biologically plausible framework for multi-agent swarm collaboration. Full article

Understanding the spatiotemporal dynamics and underlying drivers of invasive species is crucial for moving beyond descriptive monitoring to predictive management. The red imported fire ant (Solenopsis invicta Buren, RIFA) continues to spread globally, yet studies often lack the seasonal and cross-habitat resolution needed to explain the puzzling heterogeneity of infestations within urban landscapes—such as the stark contrast between high-density agricultural zones and low-density urban green spaces. To address this gap, we conducted a four-season, city-wide survey of 129 sites across four dominant habitat types (farmlands, fishponds, orchards, and urban green spaces) in Guangzhou, a core city of the GBA. Using inverse distance weighting interpolation, kernel density estimation, and spatial autocorrelation, we sought to examine not only the spatial patterns of RIFA distribution but also its potential contributing factors. Our analysis points to three key observations. First, the occurrence level of RIFA appears to follow a significant gradient (farmlands > fishponds > orchards > urban green spaces), suggesting that idle agricultural lands may serve as core reservoirs. Second, we observed a pronounced seasonal bimodal pattern, with peak infestation indices in spring and autumn—a dynamic that seems closely associated with agricultural disturbance cycles. Third, spatial analysis (Global Moran’s I = 0.346, p < 0.001) revealed significant clustering, with “high-high” clusters concentrated in peripheral suburban districts. Notably, abandoned or idle farmlands emerged as a potentially important factor, possibly acting as dispersal hubs that help bridge these spatial and temporal peaks and offering one explanation for how local outbreaks may spread across the landscape. Collectively, these findings suggest that RIFA distribution may not be driven solely by static habitat suitability or climate; instead, they point to the importance of considering the dynamic interplay between land-use legacies (such as abandonment), seasonal agricultural practices, and spatial connectivity. By elucidating these drivers, this study refines the theoretical framework of urban invasion biology and provides a replicable, evidence-based control paradigm. We suggest implementing a “zoned, seasonal, and pathway-specific” management strategy that prioritizes suburban farmland complexes during critical seasons and targets abandoned lands for intervention, offering a path towards more sustainable and precise regional RIFA control in the GBA and beyond. Full article

Plastic pollution poses a major environmental threat to coastal ecosystems, particularly in enclosed and semi-enclosed seas where limited water exchange promotes debris accumulation. This study presents a high-resolution spatial analysis of coastal plastic debris along the Khachmaz coastline in the western Caspian Sea. The analysis integrates unmanned aerial vehicle (UAV) imagery, YOLO-based deep learning detection, and spatial statistical methods. High-resolution UAV orthophotos enabled the automated detection of individual plastic debris items, which were converted into spatial point data for further analysis. Spatial patterns were assessed using areal density estimation, nearest neighbor analysis, kernel density estimation, and Ripley’s L-function to examine clustering across multiple spatial scales. A total of 2389 plastic debris items were identified within 0.0439 km², corresponding to an average density of 54,382 items per km². The results show that plastic debris is unevenly distributed, forming distinct clusters with four primary accumulation hotspots. Significant clustering occurs at spatial scales up to 20 m, with the strongest aggregation observed at distances below 5 m. Spatial overlay analysis indicates a strong association between plastic debris, reed-dominated coastal vegetation, and proximity to the shoreline, suggesting the potential role of localized retention processes and shoreline dynamics in debris accumulation. The combined use of UAV-based deep learning and spatial statistical analysis provides an integrated application framework for monitoring coastal plastic debris and supports targeted, sustainability-oriented coastal management strategies in the Caspian Sea region. Full article

Background: Timely prehospital management is critical for survival after traumatic injury. In rapidly growing metropolises, emergency medical service (EMS) systems often struggle to provide equitable care amid urban sprawl and traffic congestion. This study investigated spatiotemporal inequalities in trauma-related EMS response in a rapidly expanding capital city (Astana, Kazakhstan) to inform healthcare optimization and urban health equity. Methods: We analyzed a five-year population-based dataset of 26,073 trauma-related EMS calls recorded between 2020 and 2024. Spatial patterns were examined using Kernel Density Estimation (KDE) and Getis–Ord Gi* hotspot analysis. Road-network modeling assessed accessibility at 3, 5, and 10 min thresholds using a GIS-based network analyst framework. Results: Males accounted for 60.1% of utilization and had higher clinical severity (hospitalization rate: 45.5% vs. 40.3%, p < 0.001). Demand peaked at 20:00, coinciding with peak traffic. The mean total response time was 21.63 min, and only 16.9% of calls met the 10 min benchmark. Significant accessibility gaps were found in the Baikonur district (61.4% delay rate). Conclusions: The findings demonstrate that while the EMS system provides broad geographic coverage, it suffers from systemic spatiotemporal bottlenecks. Targeted infrastructure expansion in underserved peripheral districts and the implementation of dynamic deployment models are necessary to enhance urban health equity and reduce preventable mortality in expanding metropolitan areas. Full article

This study assesses regional science and technology (S&T) innovation efficiency across 30 Chinese provinces from 2011 to 2022, incorporating a sustainable development perspective. Employing a non-oriented global frontier super-slack-based measure (SBM) model that accounts for undesirable outputs, along with kernel density estimation, cluster analysis, and Moran’s I, the research investigates the spatiotemporal evolution of innovation dynamics. The findings demonstrate a marked upward trend, with the national average efficiency score rising from 0.260 to 0.703. Temporally, efficiency advanced through three stages: an initial period of universally low efficiency, a phase of widening disparities, and a final stage of overall improvement and stabilization. Spatial analysis reveals a persistent “strong in the east, weak in the west” disequilibrium; however, absolute β-convergence tests indicate a significant reduction in regional disparities (p < 0.05). Kernel density estimation reveals a shift from a polarized “pyramid” shape to a more balanced “spindle-shaped” distribution. This is evidenced by a decrease in kurtosis and a rightward shift in the median. Spatial autocorrelation, as measured by the Global Moran’s I, evolved from a statistically insignificant distribution in 2011 to a strong positive correlation (0.223, p < 0.05) by 2022. This progression reflects a transition from isolated “unipolar” hubs to integrated “multi-center block linkages.” The results suggest that, although polarization is diminishing and the national innovation baseline is improving, policy efforts should prioritize the development of emerging innovation corridors to address the remaining east–west divide. Full article