Search Results (75)

Accurate forecasting of cellular traffic in non-stationary environments remains a formidable challenge, as real-world traffic patterns dynamically evolve, emerge, and vanish over time. To tackle this, we propose a novel meta-learning framework, GMM-SCM-DCM, which features a Dynamic Component Management (DCM) mechanism. This framework employs a Gaussian Mixture Model (GMM) for probabilistic meta-feature representation. The core innovation, the DCM mechanism, enables online structural evolution of the meta-learner by dynamically splitting, merging, or pruning Gaussian components based on a bimodal similarity metric, ensuring sustained alignment with shifting data distributions. A Single-Component Mechanism (SCM) is utilized for precise base learner initialisation. To ensure a rigorous and realistic validation, we reconstructed the Telecom Italia Milan dataset by applying unsupervised clustering and meta-feature engineering to identify and label four distinct functional zones: residential, commercial, mixed use, and crucially, non-stationary areas. This curated dataset provides a critical testbed for non-stationary forecasting. Comprehensive experiments demonstrate that our model significantly outperforms traditional methods and meta-learning baselines, achieving a 9.3% reduction in MAE and approximately 70% faster convergence. The model’s superiority is further confirmed through extensive ablation studies, robustness tests across base learners and data scales, and successful cross-dataset validation on the Shanghai Telecom dataset, showcasing its exceptional generalization capability and practical utility for real-world network management. Full article

This paper presents a comprehensive review and theoretical analysis of integrating Cyclic Solvent Injection (CSI) with multilateral well (MLW) technologies to enhance heavy oil recovery. Given that many MLW configurations inherently exhibit symmetrical geometries, CSI–MLW integration offers structural advantages for fluid distribution. CSI offers a non-thermal mechanism for oil production through viscosity reduction, oil swelling, and foamy oil behaviour, but its application is often limited by poor sweep efficiency and non-uniform solvent distribution in conventional single-well configurations. In contrast, MLW configurations are effective in increasing reservoir contact and improving flow control but lack solvent-based enhancement mechanisms. In particular, symmetrical MLW configurations, such as dual-opposing laterals and evenly spaced fishbone laterals, can facilitate balanced solvent distribution and pressure profiles, thereby improving sweep efficiency and mitigating early breakthrough. By synthesizing experimental findings and theoretical insights from the existing literature, laboratory studies have reported that post-CHOPS CSI using a 28% C₃H₈–72% CO₂ mixture can recover about 50% of the original oil in place after six cycles, while continuous-propagation CSI (CPCSI) has achieved up to ~85% OOIP in 1D physical models. These representative values illustrate the performance spectrum observed across different CSI operational modes, underscoring the importance of operational parameters in governing recovery outcomes. Building on this foundation, this paper synthesizes key operational parameters, including solvent composition, pressure decline rate, and well configuration, that influence CSI performance. While previous studies have extensively reviewed CSI and MLW as separate technologies, systematic analyses of their integration remain limited. This review addresses that gap by providing a structured synthesis of CSI–MLW interactions, supported by representative quantitative evidence from the literature. The potential synergy between CSI and MLW is highlighted as a promising direction to overcome current limitations. By leveraging geometric symmetry in well architecture, the integrated CSI–MLW approach offers unique opportunities for optimizing solvent utilization, enhancing recovery efficiency, and guiding future experimental and field-scale developments. Such symmetry-oriented designs are also central to the experimental framework proposed in this study, in which potential methods, such as the microfluidic visualization of different MLW configurations, spanning small-scale visualization studies, bench-scale experiments on fluid and chemical interactions, and mock field setups with pipe networks, are proposed as future avenues to further explore and validate this integrated strategy. Full article

Detecting small moving objects under challenging lighting conditions, such as overexposure and underexposure, remains a critical challenge in computer vision applications including surveillance, autonomous driving, and anti-UAV systems. Traditional RGB-based detectors often suffer from degraded object visibility and highly dynamic illumination, leading to suboptimal performance. To address these limitations, we propose a novel RGB-Event fusion framework that leverages the complementary strengths of RGB and event modalities for enhanced small object detection. Specifically, we introduce a Temporal Multi-Scale Attention Fusion (TMAF) module to encode motion cues from event streams at multiple temporal scales, thereby enhancing the saliency of small object features. Furthermore, we design a Sparse Noisy Gated Attention Fusion (SNGAF) module, inspired by the mixture-of-experts paradigm, which employs a sparse gating mechanism to adaptively combine multiple fusion experts based on input characteristics, enabling flexible and robust RGB-Event feature integration. Additionally, we present RGBE-UAV, which is a new RGB-Event dataset tailored for small moving object detection under diverse exposure conditions. Extensive experiments on our RGBE-UAV and public DSEC-MOD datasets demonstrate that our method outperforms existing state-of-the-art RGB-Event fusion approaches, validating its effectiveness and generalization under complex lighting conditions. Full article

Small object detection in UAV-based remote sensing imagery is crucial for applications such as traffic monitoring, emergency response, and urban management. However, aerial images often suffer from low object resolution, complex backgrounds, and varying lighting conditions, leading to missed or false detections. To address these challenges, we propose DCS-YOLOv8, an enhanced object detection framework tailored for small target detection in UAV scenarios. The proposed model integrates a Dynamic Convolution Attention Mixture (DCAM) module to improve global feature representation and combines it with the C2f module to form the C2f-DCAM block. The C2f-DCAM block, together with a lightweight SCDown module for efficient downsampling, constitutes the backbone DCS-Net. In addition, a dedicated P2 detection layer is introduced to better capture high-resolution spatial features of small objects. To further enhance detection accuracy and robustness, we replace the conventional CIoU loss with a novel Scale-based Dynamic Balanced IoU (SDBIoU) loss, which dynamically adjusts loss weights based on object scale. Extensive experiments on the VisDrone2019 dataset demonstrate that the proposed DCS-YOLOv8 significantly improves small object detection performance while maintaining efficiency. Compared to the baseline YOLOv8s, our model increases precision from 51.8% to 54.2%, recall from 39.4% to 42.1%, $mA{P}_{0.5}$ from 40.6% to 44.5%, and $mA{P}_{0.5:0.95}$ from 24.3% to 26.9%, while reducing parameters from 11.1 M to 9.9 M. Moreover, real-time inference on RK3588 embedded hardware validates the model’s suitability for onboard UAV deployment in remote sensing applications. Full article

Plant disease segmentation has achieved significant progress with the help of artificial intelligence. However, deploying high-accuracy segmentation models in resource-limited settings faces three key challenges, as follows: (A) Traditional dense attention mechanisms incur quadratic computational complexity growth (O($n^{2}d$)), rendering them ill-suited for low-power hardware. (B) Naturally sparse spatial distributions and large-scale variations in the lesions on leaves necessitate models that concurrently capture long-range dependencies and local details. (C) Complex backgrounds and variable lighting in field images often induce segmentation errors. To address these challenges, we propose Sparse-MoE-SAM, an efficient framework based on an enhanced Segment Anything Model (SAM). This deep learning framework integrates sparse attention mechanisms with a two-stage mixture of experts (MoE) decoder. The sparse attention dynamically activates key channels aligned with lesion sparsity patterns, reducing self-attention complexity while preserving long-range context. Stage 1 of the MoE decoder performs coarse-grained boundary localization; Stage 2 achieves fine-grained segmentation by leveraging specialized experts within the MoE, significantly enhancing edge discrimination accuracy. The expert repository—comprising standard convolutions, dilated convolutions, and depthwise separable convolutions—dynamically routes features through optimized processing paths based on input texture and lesion morphology. This enables robust segmentation across diverse leaf textures and plant developmental stages. Further, we design a sparse attention-enhanced Atrous Spatial Pyramid Pooling (ASPP) module to capture multi-scale contexts for both extensive lesions and small spots. Evaluations on three heterogeneous datasets (PlantVillage Extended, CVPPP, and our self-collected field images) show that Sparse-MoE-SAM achieves a mean Intersection-over-Union (mIoU) of 94.2%—surpassing standard SAM by 2.5 percentage points—while reducing computational costs by 23.7% compared to the original SAM baseline. The model also demonstrates balanced performance across disease classes and enhanced hardware compatibility. Our work validates that integrating sparse attention with MoE mechanisms sustains accuracy while drastically lowering computational demands, enabling the scalable deployment of plant disease segmentation models on mobile and edge devices. Full article

We propose a novel Bayesian wavelet regression approach using a three-component spike-and-slab prior for wavelet coefficients, combining a point mass at zero, a moment (MOM) prior, and an inverse moment (IMOM) prior. This flexible prior supports small and large coefficients differently, offering advantages for highly dispersed data where wavelet coefficients span multiple scales. The IMOM prior’s heavy tails capture large coefficients, while the MOM prior is better suited for smaller non-zero coefficients. Further, our method introduces innovative hyperparameter specifications for mixture probabilities and scale parameters, including generalized logit, hyperbolic secant, and generalized normal decay for probabilities, and double exponential decay for scaling. Hyperparameters are estimated via an empirical Bayes approach, enabling posterior inference tailored to the data. Extensive simulations demonstrate significant performance gains over two-component wavelet methods. Applications to electroencephalography and noisy audio data illustrate the method’s utility in capturing complex signal characteristics. We implement our method in an R package, NLPwavelet (≥1.1). Full article

Combustion modeling using computational fluid dynamics (CFD) offers detailed insights into the flame structure and thermo-chemical processes. Furthermore, it has been extensively used in the past to optimize industrial furnaces. Despite the increasing computational power, the prediction of the reaction kinetics in flames is still related to high calculation times, which is a major drawback for large-scale combustion systems. To speed-up the simulation, artificial neural networks (ANNs) were applied in this study to calculate the chemical source terms in the flame instead of using a chemistry solver. Since one ANN may lack accuracy for the entire input feature space (temperature, species concentrations), the space is sub-divided into four regions/ANNs. The ANNs were tested for different fuel mixtures, degrees of turbulence, and air-fuel/oxy-fuel combustion. It was found that the shape of the flame and its position were well predicted in all cases with regard to the temperature and CO. However, at low temperature levels (<800 K), in some cases, the ANNs under-predicted the source terms. Additionally, in oxy-fuel combustion, the temperature was too high. Nevertheless, an overall high accuracy and a speed-up factor for all simulations of 12 was observed, which makes the approach suitable for large-scale furnaces. Full article

Recent advances in hyperspectral image (HSI) classification have demonstrated the effectiveness of hybrid architectures that integrate convolutional neural networks (CNNs) and Transformers, leveraging CNNs for local feature extraction and Transformers for global dependency modeling. However, existing fusion approaches face three critical challenges: (1) insufficient synergy between spectral and spatial feature learning due to rigid coupling mechanisms; (2) high computational complexity resulting from redundant attention calculations; and (3) limited adaptability to spectral redundancy and noise in small-sample scenarios. To address these limitations, we propose HyperTransXNet, a novel CNN-Transformer hybrid architecture that incorporates adaptive spectral-spatial fusion. Specifically, the proposed HyperTransXNet comprises three key modules: (1) a Hybrid Spatial-Spectral Module (HSSM) that captures the refined local spectral-spatial features and models global spectral correlations by combining depth-wise dynamic convolution with frequency-domain attention; (2) a Mixture-of-Experts Routing (MoE-R) module that adaptively fuses multi-scale features by dynamically selecting optimal experts via Top-K sparse weights; and (3) a Spatial-Spectral Tokens Enhancer (SSTE) module that ensures causality-preserving interactions between spectral bands and spatial contexts. Extensive experiments on the Indian Pines, Houston 2013, and WHU-Hi-LongKou datasets demonstrate the superiority of HyperTransXNet. Full article

Spatiotemporal fusion techniques can generate remote sensing imagery with high spatial and temporal resolutions, thereby facilitating Earth observation. However, traditional methods are constrained by linear assumptions; generative adversarial networks suffer from mode collapse; convolutional neural networks struggle to capture global context; and Transformers are hard to scale due to quadratic computational complexity and high memory consumption. To address these challenges, this study introduces an end-to-end remote sensing image spatiotemporal fusion approach based on the Mamba architecture (Mamba-spatiotemporal fusion model, Mamba-STFM), marking the first application of Mamba in this domain and presenting a novel paradigm for spatiotemporal fusion model design. Mamba-STFM consists of a feature extraction encoder and a feature fusion decoder. At the core of the encoder is the visual state space-FuseCore-AttNet block (VSS-FCAN block), which deeply integrates linear complexity cross-scan global perception with a channel attention mechanism, significantly reducing quadratic-level computation and memory overhead while improving inference throughput through parallel scanning and kernel fusion techniques. The decoder’s core is the spatiotemporal mixture-of-experts fusion module (STF-MoE block), composed of our novel spatial expert and temporal expert modules. The spatial expert adaptively adjusts channel weights to optimize spatial feature representation, enabling precise alignment and fusion of multi-resolution images, while the temporal expert incorporates a temporal squeeze-and-excitation mechanism and selective state space model (SSM) techniques to efficiently capture short-range temporal dependencies, maintain linear sequence modeling complexity, and further enhance overall spatiotemporal fusion throughput. Extensive experiments on public datasets demonstrate that Mamba-STFM outperforms existing methods in fusion quality; ablation studies validate the effectiveness of each core module; and efficiency analyses and application comparisons further confirm the model’s superior performance. Full article

The natural and sustainable ability of earthen building materials makes them highly valuable. Bio-stabilization involves using biological materials or processes in earthen construction to enhance the performance and characteristics of earthen materials. The main objective of bio-stabilization is to substitute high-energy-intensive building materials with more green, thermally efficient substitutions, ultimately reducing indirect emissions. The large-scale use of earth presents a viable alternative due to its extensive availability and, more importantly, its low embodied energy. The aim of this work is to investigate the thermal conductivity of earth stabilized with Opuntia Ficus-Indica (OFI), a natural biopolymer, and to assess how these properties vary based on mix design. A comparative analysis is performed to evaluate the thermal performance of bio-based polymer-stabilized earthen materials (S-30, S-40, D-30, and D-40) alongside natural biopolymer-stabilized earth (OFI-30 and OFI-40) under dry conditions, employing an experimental method. A scanning electron microscope was employed to examine the microstructure of bio-stabilized earthen materials from the samples. Statistical analysis was conducted on the collected data using ANOVA with a significance level of 0.05. The Tukey test was applied to identify specific mean pairings that demonstrate significant differences in the characteristics of the mixtures at each replacement level, maintaining a confidence interval of 95%. The experimental and statistical findings reveal that the OFI-30, D-40, and S-40 mixtures exhibit strong bonding with earthen materials and high thermal performance compared to all other mix designs in environmental samples. Additionally, these mix designs show further improvement in thermal performance in the dry conditions. Full article

Nowadays, recycling in pavement engineering is not a novelty. Utilization of recycled aggregates and other waste materials for the asphalt layers appeared as a well-established approach during the last decades, at least at a research level, in favor of preservation of natural resources, economical balance in road construction and reconstruction, and overall pavement sustainability. The focus on the asphalt layers does make sense based on the fact that these layers are to be more frequently replaced in the framework of periodical pavement maintenance or rehabilitation. Taking as a fact that mainly laboratory-scale studies and limited field trials have already proven the performance-based viability of using alternative materials in the asphalt layers, including waste plastic, waste glass, steel slag, waste tires in the form of rubber, reclaimed asphalt pavement (RAP), etc., this study tries to identify additional critical aspects and reasons why recycled materials are not consistently selected and uniformly applied during construction and reconstruction activities in real practice. A comprehensive discussion for interdisciplinary issues is provided with respect to (i) the challenge of comparing the performance of asphalt mixtures containing recycling materials with a reference condition status, related to mechanical testing, (ii) the aspect of recycled material availability versus peculiar conditions applied to some countries, related to socioeconomical issues, (iii) the unawareness of the actual lifecycle assessment of pavement structures with recycled mixtures, related to environmental assessment, and (iv) some legislative and health issues that could make pavement engineers reluctant to extensively use non-conventional materials. After a multi-parametric discussion, some useful remarks for fostering further research are given together with the ambition to bridge the gap between research and practice toward a greener future in pavement engineering. Full article

With the exponential growth of user-generated content on video-sharing platforms, the challenge of facilitating efficient searching and browsing of videos has garnered significant attention. To enhance users’ ability to swiftly locate and review pertinent videos, the creation of concise and informative video summaries has become increasingly important. Video-llama is an effective tool for generating video summarization, but it cannot effectively unify and optimize the modeling of temporal and spatial features and requires a lot of computational resources and time. Therefore, we propose MiLoRA-ViSum to more efficiently capture complex temporal dynamics and spatial relationships inherent in video data and to control the number of parameters for training. By extending traditional Low-Rank Adaptation (LoRA) into a sophisticated mixture-of-experts paradigm, MiLoRA-ViSum incorporates a dual temporal–spatial adaptation mechanism tailored specifically for video summarization tasks. This approach dynamically integrates specialized LoRA experts, each fine-tuned to address distinct temporal or spatial dimensions. Extensive evaluations of the VideoXum and ActivityNet datasets demonstrate that MiLoRA-ViSum achieves the best summarization performance compared to state-of-the-art models, while maintaining significantly lower computational costs. The proposed mixture-of-experts strategy, combined with the dual adaptation mechanism, highlights the model’s potential to enhance video summarization capabilities, particularly in large-scale applications requiring both efficiency and precision. Full article

The diversification of lineages sometimes exhibits patterns that are often described as ‘radiations’, which can be seen at various time scales, but researchers most often focus on a fast divergence of parental forms within short time spans. Adaptive radiations are widely discussed and have served as important showcases of Darwinian evolutionary processes. Other types of radiation have been identified, too, and several classifications have been suggested. Among these, ‘non-adaptive radiations’ remain controversial till today. Despite concerns on the conceptual basis of such a process, more and more cases of radiation that are described as ‘non-adaptive’ are published, and the continuously accumulating genetic/genomic data for more and more taxa seem to reveal extensive lineage diversification that is often not attributable to any apparent selective force. Given that allopatric divergence due to stochastic processes is presumably the cause of non-adaptive radiations, insular systems provide a rich pool of case studies. Using examples of lineage divergence from various taxa living on the Aegean islands, I discuss the processes leading to non-adaptive radiations in view of the alternative classifications of radiation by other authors, and show that such patterns may also result from a mixture of adaptive and non-adaptive processes. Full article

Traditional photovoltaic-powered forced air-cooling systems face significant challenges in balancing energy efficiency and thermal comfort due to temperature sensitivity, mechanical ventilation energy consumption, and spatial constraints. This study aims to enhance building energy efficiency by integrating a radiant cooling ceiling (RCC) with a phase change material (PCM) thermal storage system, addressing the limitations of traditional photovoltaic-powered cooling systems through optimized material design and dynamic energy management. A ternary PCM mixture (glycerol–alcohol–water) was optimized using differential scanning calorimetry (DSC), demonstrating superior latent heat storage (361.66 J/g) and phase transition temperature (1.91 °C) in the selected “Slushy Ice” formulation. A 3D transient thermal model and experimental validation revealed that the RCC system achieved 57% energy savings under quasi-steady operation, with radiative heat transfer contributing 55% of total cooling capacity. The system dynamically stores cold energy during peak photovoltaic generation and releases it via RCC during low-power periods, resolving the “cooling energy consumption paradox”. Key challenges, including PCM cycling stability and thermal response time mismatches, were identified, with future research directions emphasizing multi-scale simulations and intelligent encapsulation. This work provides a viable pathway for improving building energy efficiency while maintaining thermal comfort and for improving building energy efficiency in temperate zones, with future extensions to arid and tropical climates requiring targeted material and system optimizations. Full article

The 3D reconstruction of asphalt pavement macrotexture holds significant engineering value for pavement quality assessment and performance monitoring. However, conventional 3D reconstruction methods face challenges, such as high equipment costs and operational complexity, limiting their widespread application in engineering practice. Meanwhile, current deep learning-based monocular image reconstruction for pavement texture remains in its early stages. To address these technical limitations, this study systematically prepared four types of asphalt mixture specimens (AC, SMA, OGFC, and PA) with a total of 14 gradations. High-precision equipment was used to simultaneously capture 2D RGB images and 3D RGB-D point cloud data of the surface texture. An innovative multi-scale feature fusion CNN model was developed based on an encoder–decoder architecture, along with an optimized training strategy for model parameters. For performance evaluation, multiple metrics were employed, including root mean square error (RMSE = 0.491), relative error (REL = 0.102), and accuracy at different thresholds (δ = 1/2/3: 0.931, 0.979, 0.990). The results demonstrate strong correlations between the reconstructed texture’s mean texture depth (MTD) and friction coefficient (f₈) with actual measurements (0.913 and 0.953, respectively), outperforming existing methods. This confirms that the proposed CNN model achieves precise 3D reconstruction of asphalt pavement macrotexture, effectively supporting skid resistance evaluation. To validate engineering applicability, field tests were conducted on pavements with various gradations. The model exhibited excellent robustness under different conditions. Furthermore, based on extensive field data, this study established a quantitative relationship between MTD and friction coefficient, developing a more accurate pavement skid resistance evaluation system to support maintenance decision-making. Full article