Search Results (653)

Multi-access edge computing (MEC) has been widely recognized as a promising solution for alleviating the computational burden on edge devices, particularly in supporting fast and real-time processing of resource-intensive applications. In this paper, we propose a decentralized offloading decision strategy based on multi-agent deep reinforcement learning (MADRL), aiming to minimize the overall task completion latency experienced by edge devices. Our proposed scheme adopts a grant-free access mechanism during the initialization of offloading in a fully decentralized manner, which serves as the key feature of our strategy. As a result, determining the optimal offloading factor becomes significantly more challenging due to the simultaneous access attempts from multiple edge devices. To resolve this problem, we consider a discrete action space-based deep reinforcement learning (DRL) approach, termed deep Q network (DQN), to enable each edge device to learn a decentralized computation offloading policy based solely on its local observation without requiring global network information. In our design, each edge device dynamically adjusts its offloading factor according to its observed channel state and the number of active users, thereby balancing local and remote computation loads adaptively. Furthermore, the proposed MADRL-based framework jointly accounts for user association and offloading decision optimization to mitigate access collisions and computation bottlenecks in a multi-user environment. We perform extensive computer simulations using MATLAB R2023b to evaluate the performance of the proposed strategy, focusing on the task completion latency under various system configurations. The numerical results demonstrate that our proposed strategy effectively reduces the overall task completion latency and achieves faster convergence of learning performance compared with conventional schemes, confirming the efficiency and scalability of the proposed decentralized approach. Full article

Biportal endoscopic spinal surgery (BESS) is a minimally invasive technique that is widely used in human spinal procedures; however, its standardized methodology and anatomical adaptation for veterinary applications have not yet been established. This study aimed to develop a reproducible experimental framework for performing BESS in dogs and evaluate its technical feasibility. A thoracic intervertebral disc disease model was created by injecting a fluorescently dyed artificial disc material containing methylene blue into the T12–13 intervertebral space of 13 medium-sized canine cadavers. Portal locations were determined using a computed tomography-based measurement method, and instruments specifically designed for BESS were used to perform mini-hemilaminectomies of the accessory process. The artificial disc material was successfully removed in all cases with clear visualization of the spinal cord and nerve roots. The mean portal insertion angle and distance were 31.00 ± 2.79° and 32.95 ± 3.05 mm, respectively, and the average residual material volume was 6.89% ± 1.66% of the initially inserted volume. Surgical time significantly decreased as the surgeon’s experience increased. These results demonstrate the successful methodological standardization of BESS tailored to canine thoracic anatomy and provide foundational data supporting its potential as a minimally invasive spinal surgery technique for future clinical veterinary applications. Full article

This study presents an integrated decision support system (DSS) designed to optimize real-time reservoir operation during typhoons by balancing flood control and water supply. The system combines ensemble quantitative precipitation forecasts (QPF) from WRF/MM5 models, a physically based rainfall–runoff model (KW-GIUH), and a three-stage optimization algorithm for reservoir release decisions. Eighteen ensemble rainfall members are processed to generate 6 h inflow forecasts, which serve as inputs for determining adaptive outflow strategies that consider both storage requirements and downstream flood risks. The DSS was tested using historical typhoon events—Talim, Saola, Trami, and Kong-rey—at the Tseng-Wen Reservoir in Taiwan. Results show that the KW-GIUH model effectively reproduces hydrograph characteristics, with a coefficient of efficiency around 0.80, while the optimization algorithm successfully maintains reservoir levels near target storage, even under imperfect rainfall forecasts. The mean deviation of reservoir water levels from the recorded to the target values is less than 0.18 m. The system enhances operational flexibility by adjusting release rates according to the proposed outflow index and flood-stage classification. During major storms, the DSS effectively allocates storage space for incoming floods while maximizing water retention during recession periods. Overall, the integrated framework demonstrates strong potential to support real-time reservoir management during extreme weather conditions, thereby improving both flood mitigation and water-supply reliability. Full article

Signal intersections are key nodes in urban road traffic networks, and real-time queue length information serves as a core performance indicator for formulating effective signal management schemes in modern adaptive traffic signal control systems, thereby enhancing traffic efficiency. In this study, a roadside Light Detection and Ranging (LiDAR) sensor is employed to acquire 3D point cloud data of vehicles in the road space, which acts as an important method for queue length detection. However, during queue-length detection, vehicles in different lanes are prone to occlusion because of the straight-line propagation of laser beams. This paper proposes a queue-length detection method based on variations in vehicle point cloud features to address the occlusion of queue-end vehicles during detection. This method first preprocesses LiDAR point cloud data (including region-of-interest extraction, ground-point filtering, point cloud clustering, object association, and lane recognition) to detect real-time queue lengths across multiple lanes. Subsequently, the occlusion problem is categorized into complete occulusion and partial occlusion, and corresponding processing is performed to correct the detection results. The performance of the proposed queue length detection method was validated through experiments that collected real-world data from three urban road intersections in Suzhou. The results indicate that this method’s average accuracy can reach 99.3%. Furthermore, the effectiveness of the proposed occlusion handling method has been validated through experiments. Full article

Background/Objectives: The segmentation of three-dimensional radiological images constitutes a fundamental task in medical image processing for isolating tumors from complex datasets in computed tomography or magnetic resonance imaging. Precise visualization, volumetry, and treatment monitoring are enabled, which are critical for oncology diagnostics and planning. Volumetric analysis surpasses standard criteria by detecting subtle tumor changes, thereby aiding adaptive therapies. The objective of this study was to develop an enhanced, interactive Graphcut algorithm for 3D DICOM segmentation, specifically designed to improve boundary accuracy and 3D modeling of breast and brain tumors in datasets with heterogeneous tissue intensities. Methods: The standard Graphcut algorithm was augmented with a clustering mechanism (utilizing k = 2–5 clusters) to refine boundary detection in tissues with varying intensities. DICOM datasets were processed into 3D volumes using pixel spacing and slice thickness metadata. User-defined seeds were utilized for tumor and background initialization, constrained by bounding boxes. The method was implemented in Python 3.13 using the PyMaxflow library for graph optimization and pydicom for data transformation. Results: The proposed segmentation method outperformed standard thresholding and region growing techniques, demonstrating reduced noise sensitivity and improved boundary definition. An average Dice Similarity Coefficient (DSC) of 0.92 ± 0.07 was achieved for brain tumors and 0.90 ± 0.05 for breast tumors. These results were found to be comparable to state-of-the-art deep learning benchmarks (typically ranging from 0.84 to 0.95), achieved without the need for extensive pre-training. Boundary edge errors were reduced by a mean of 7.5% through the integration of clustering. Therapeutic changes were quantified accurately (e.g., a reduction from 22,106 mm³ to 14,270 mm³ post-treatment) with an average processing time of 12–15 s per stack. Conclusions: An efficient, precise 3D tumor segmentation tool suitable for diagnostics and planning is presented. This approach is demonstrated to be a robust, data-efficient alternative to deep learning, particularly advantageous in clinical settings where the large annotated datasets required for training neural networks are unavailable. Full article

Polar sea ice is undergoing rapid change, with recent record-low extents in both hemispheres, raising the demand for skillful predictions from days to seasons for navigation, ecosystem management, and climate risk assessment. Accurate sea ice prediction is essential for understanding coupled climate processes, supporting safe polar operations, and informing adaptation strategies. Physics-based numerical models remain the backbone of operational forecasting, but their skill is limited by uncertainties in coupled ocean–ice–atmosphere processes, parameterizations, and sparse observations, especially in the marginal ice zone and during melt seasons. Statistical and empirical models can provide useful baselines for low-dimensional indices or short lead times, yet they often struggle to represent high-dimensional, nonlinear interactions and regime shifts. This review synthesizes recent progress of DL for key sea ice prediction targets, including sea ice concentration/extent, thickness, and motion, and organizes methods into (i) sequential architectures (e.g., LSTM/GRU and temporal Transformers) for temporal dependencies, (ii) image-to-image and vision models (e.g., CNN/U-Net, vision Transformers, and diffusion or GAN-based generators) for spatial structures and downscaling, and (iii) spatiotemporal fusion frameworks that jointly model space–time dynamics. We further summarize hybrid strategies that integrate DL with numerical models through post-processing, emulation, and data assimilation, as well as physics-informed learning that embeds conservation laws or dynamical constraints. Despite rapid advances, challenges remain in generalization under non-stationary climate conditions, dataset shift, and physical consistency (e.g., mass/energy conservation), interpretability, and fair evaluation across regions and lead times. We conclude with practical recommendations for future research, including standardized benchmarks, uncertainty-aware probabilistic forecasting, physics-guided training and neural operators for long-range dynamics, and foundation models that leverage self-supervised pretraining on large-scale Earth observation archives. Full article

The experiences and repercussions of the cross-border migration process on family life have not yet been synthesized. This study aimed to synthesize the best available qualitative findings on this theme. A systematic review of qualitative evidence with meta-synthesis was conducted. Articles were identified according to predefined extraction criteria in the first half of 2025, across seven databases: Web of Science, MEDLINE/PubMed, PsycINFO, LILACS, CINAHL, SCOPUS, and Social Science Citation Index. Two researchers independently screened and appraised the reports, assessing methodological quality and systematically recording and analyzing relevant information. A protocol was registered in PROSPERO (ID: CRD42024505655). Fifty studies were included, and three main themes emerged: (a) living in multiple possible contexts, where space and relationships influence family functionality, including reduced family time due to long working hours, substance use, fear of losing cultural roots, new financial responsibilities, and the desire to return to the country of origin; (b) challenges and repercussions on family life after migration, such as increased family conflicts, mental health problems, separation, and loss of ties; (c) strategies for maintaining family functioning, including role adjustment, strengthening of family ties, and support through cultural and religious practices. Families undergoing migration face multiple challenges in their new environments, revealing the complexity of adapting to diverse cultural and social contexts. These findings highlight the need to address the emotional and social demands of migrant families to improve well-being and integration. Understanding these dynamics allows healthcare professionals to design culturally sensitive interventions that promote reception and inclusion. Full article

Background: Most older adults prefer to age in place. Technology-assisted monitoring can enhance safety while maintaining independence. However, there is limited understanding of older adult end users’ preferences and experiences. Methods: In this interpretive phenomenological study, we interviewed eight older adults, with and without dementia, to understand their lived experiences with monitoring technology and its impact on self-identity, independence, and aging-in-place. Results: We found that older adults use pragmatic strategies to process the meaning of life as “monitored” individuals, reflected in four themes: (1) freedom to age in place, (2) the need for active and integrated intervention, (3) individualized approaches to technology based on temperament, usefulness, and worldview, and (4) a sense of changing situations while remaining unchanged. Adaptive techniques for older adults with dementia successfully elicited complex thoughts and desires when participants were given sufficient time and space. Conclusions: As technology-assisted monitoring becomes more common, it is imperative to understand the perspectives of older adult end users. Focusing on lived experiences offers valuable insights to ensure technology-assisted monitoring interventions are effective and accepted as older adults navigate changes in their capabilities and endeavor to age in place. Full article

We present a new method for mapping global gas flaring using a multiyear spatio-temporal database of VIIRS Nightfire (VNF) nighttime infrared detections from the Suomi NPP, NOAA-20, and NOAA-21 satellites. The method is designed to resolve closely spaced industrial combustion sources and to produce a stable, physically meaningful flare catalog suitable for long-term monitoring and emissions analysis. The method combines adaptive spatial aggregation of high-temperature detections with a hierarchical clustering that super-resolves individual flare stacks within oil and gas fields. Post-processing yields physically consistent flare footprints and attraction regions, allowing separation of closely spaced sources. Flare clusters are assigned to operational categories (e.g., upstream, midstream, LNG) using prior catalogs combined with AI-assisted expert interpretation. In this step, a multimodal large language model (LLM) provides contextual classification suggestions based on geospatial information, high-resolution daytime imagery, and detection time-series summaries, while final attribution is performed and validated by domain experts. Compared with annual flare catalogs commonly used for national flaring estimates, the new catalog demonstrates substantially improved performance. It is more selective in the presence of intense atmospheric glow from large flares, identifies approximately twice as many active flares, and localizes individual stacks with ~50 m precision, resolving emitters separated by ~400–700 m. For the well-defined class of downstream flares at LNG export facilities, the catalog achieves complete detectability. These improvements support more accurate flare inventories, facility-level attribution, and policy-relevant assessments of gas flaring activity. Full article

Timely and accurate detection of forest fires through unmanned aerial vehicle (UAV) remote sensing target detection technology is of paramount importance. However, multiscale targets and complex environmental interference in UAV remote sensing images pose significant challenges during detection tasks. To address these obstacles, this paper presents FF-Mamba-YOLO, a novel framework based on the principles of Mamba and YOLO (You Only Look Once) that leverages innovative modules and architectures to overcome these limitations. Specifically, we introduce MFEBlock and MFFBlock based on state space models (SSMs) in the backbone and neck parts of the network, respectively, enabling the model to effectively capture global dependencies. Second, we construct CFEBlock, a module that performs feature enhancement before SSM processing, improving local feature processing capabilities. Furthermore, we propose MGBlock, which adopts a dynamic gating mechanism, enhancing the model’s adaptive processing capabilities and robustness. Finally, we enhance the structure of Path Aggregation Feature Pyramid Network (PAFPN) to improve feature fusion quality and introduce DySample to enhance image resolution without significantly increasing computational costs. Experimental results on our self-constructed forest fire image dataset demonstrate that the model achieves 67.4% mAP@50, 36.3% mAP@50:95, and 64.8% precision, outperforming previous state-of-the-art methods. These results highlight the potential of FF-Mamba-YOLO in forest fire monitoring. Full article

This study presents an integrated, cost-aware artificial intelligence (AI) meta-modelling framework for mine-to-mill optimisation that couples high-fidelity simulation with data-driven predictive modelling. Using over three million scenarios generated in the Integrated Extraction Simulator (IES), the framework quantifies how upstream design parameters such as burden, spacing, hole diameter, and explosive density propagate through screening, crushing, stockpiling, and grinding to affect downstream costs and throughput. Random Forest-based meta-models achieved predictive accuracies above 90%, enabling the rapid evaluation of technical and financial trade-offs across the mining value chain. Stage-wise cost models were formulated for drilling, blasting, comminution, and material handling to link process variables to costs per tonne. The results reveal clear non-linear cost responses: finer fragmentation reduces the total comminution cost despite higher explosive expenditure, while SAG mill load and speed exhibit U-shaped cost relationships with distinct optimal operating windows. By combining physics-based simulations, machine learning, and cost integration, the framework transforms traditional stage-wise optimisation into a holistic, financially informed decision-support system. The proposed methodology supports real-time, AI-enabled digital twins capable of adaptive mine-to-mill optimisation, paving the way for more efficient and sustainable resource extraction. Full article

Bearing fault diagnosis is essential for ensuring the safe and reliable operation of rotating machinery. However, accurate and timely fault identification with limited data remains a significant challenge. This study proposes a novel node-incremental-based multisource domain adaptation (NiMDA) approach for bearing fault diagnosis. The method employs a cloud model to adaptively extract fault-sensitive information while accounting for uncertainties across multiple wavelet packet decomposition levels. Subsequently, node incremental domain adaptation (NiDA) is used to construct a base classifier utilizing limited labeled data from both target and source domains. This approach reduces discrepancies between marginal and conditional distributions across different domain feature spaces during the node-increment process, resulting in a compact domain-adaptation structure. Robust diagnostic performance is achieved through parallel ensemble learning of NiDAs across multiple source domains. The experimental results demonstrate that NiMDA significantly outperforms state-of-the-art bearing fault diagnosis methods in few-shot scenarios, achieving improvements of 30.52%, 42.31%, 10.31%, 26.08%, 25.59%, and 7.98% over WDCNN, MCNN-LSTM, Bayesian-RF, DM-RVFLN, Five-shot, and ESCN, respectively, while maintaining satisfactory diagnostic speed. Full article

To cope with the highly stochastic nature of wind speed, we explored the development of a predictive methodology. Considering an absence of studies pertaining to wind speed prediction that utilise state-of-the-art fuzzy models, the proposed approach adopted a novel higher-order Takagi–Sugeno–Kang fuzzy model intermixed with variational mode decomposition. The novelty of the predictive fuzzy model arises from the enhancement of rule consequents to include generalised terms and the incorporation of model complexity into the training scheme. To optimise the model, two approaches are considered: an adaptive differential evolution and a surrogate-based optimisation algorithm. The evolutionary approach employed two populations and a dual mutation scheme. The surrogate-based optimisation employed a Bayesian framework by fitting a Gaussian process model to the objective function. The latter approach yielded accurate predictive results while rapidly reducing the training time of the fuzzy model. A sequential wrapper-based algorithm was developed to effectively determine the feature space. The variational mode decomposed wind speed data were predicted individually, using an associated optimised fuzzy model. The proposed method was applied to a real-world wind speed dataset with exceptional approximation results. Comparisons with several artificial intelligence models highlighted the effectiveness and statistical significance of the methodology. Full article

Passenger-gathering behavior often triggers safety incidents such as stampedes due to overcrowding, posing significant challenges to public order maintenance and passenger safety. Traditional early warning algorithms for passenger-gathering behavior typically perform only global modeling of image appearance, neglecting the analysis of individual passenger actions in practical 3D physical space, leading to high false-alarm and missed-alarm rates. To address this issue, we decompose the modeling process into two stages: human pose estimation and gathering behavior recognition. Specifically, the pose of each individual in 3D space is first estimated from images, and then fused with global features to complete the early warning. This work focuses on the former stage and aims to develop an accurate and efficient human pose estimation model capable of real-time inference on resource-constrained devices. To this end, we propose a 3D human pose estimation framework that integrates a hybrid spatio-temporal Transformer with three collaborative agents. First, a reinforcement learning-based architecture search agent is designed to adaptively select among Global Self-Attention, Window Attention, and External Attention for each block to optimize the model structure. Second, a feedback optimization agent is developed to dynamically adjust the search process, balancing exploration and convergence. Third, a quantization agent is employed that leverages quantization-aware training (QAT) to generate an INT8 deployment-ready model with minimal loss in accuracy. Experiments conducted on the Human3.6M dataset demonstrate that the proposed method achieves a mean per joint position error (MPJPE) of 42.15 mm with only 4.38 M parameters and 19.39 GFLOPs under FP32 precision, indicating substantial potential for subsequent gathering behavior recognition tasks. Full article

Thought processes in the brain occur as it continually modifies its use of energy. This review integrates research findings from molecular neurology, vascular physiology and non-equilibrium thermodynamics to create a comprehensive perspective on thinking as a coordinated energy process. Data shows that there is a relationship between the processing of information and metabolism throughout all scales, from the mitochondria’s electron transport chain to the rhythmic changes in the microvasculature. Through the cellular level of organization, mitochondrial networks, calcium (Ca²⁺) signals from astrocytes and the adaptive control of capillaries work together to maintain a state of balance between order and dissipation that maintains function while also maintaining the ability to be flexible. The longer-term regulatory mechanisms including redox plasticity, epigenetic programs and organelle remodeling may convert short-lived states of metabolism into long-lasting physiological “memory”. As well, data indicates that the cortical networks of the brain appear to be operating close to their critical regimes, which will allow them to respond to stimuli but prevent the brain from reaching an unstable energetic state. It is suggested that cognition occurs as the result of the brain’s ability to coordinate energy supply with neural activity over both time and space. Providing a perspective of the functional aspects of neurons as a continuous thermodynamic process creates a framework for making predictive statements that will guide future studies to measure coherence as a key link between energy flow, perception, memory and cognition. Full article