Search Results (872)

Deep-mining operations are increasingly challenged by severe thermal hazards, which have become a critical bottleneck for achieving safe, efficient, and sustainable mineral extraction. While research on deep-mine cooling and heat hazard mitigation has proliferated, the field lacks a systematic, critical review that explicitly examines these advances through the lens of sustainability science. To address this gap, this study conducted a comprehensive bibliometric analysis of 432 publications (1994–2024) retrieved from the Web of Science Core Collection. The methodology employs Bibliometrix, Vosviewer, and CiteSpace to map the intellectual landscape, research hotspots, and evolving frontiers of the field. The results reveal a clear three-stage development trajectory and identify China, the USA, South Africa, and Canada as leading contributors, with national research emphases on ventilation, energy conservation, and refrigeration, respectively. Crucially, keyword clustering and burst detection uncover a notable paradigm shift: the focus has moved from isolated cooling techniques toward integrated, multi-objective strategies—including geothermal energy co-exploitation, phase-change material applications, and system-level energy optimization—signaling a growing alignment with resource efficiency and low-carbon mining principles. However, a critical finding is that the literature remains predominantly techno-centric, overwhelmingly evaluating performance through operational energy savings while largely neglecting life-cycle environmental impacts, holistic sustainability assessment metrics, and the influence of policy drivers. This review thus not only provides a structured overview of the domain, but, more importantly, exposes these critical knowledge gaps. We argue that future research must pivot toward a multi-dimensional sustainability framework that integrates technical, economic, and environmental dimensions, thereby guiding the next generation of research toward truly sustainable deep-mining practices. Full article

Maritime search and rescue is an important component of emergency response frameworks and primarily relies on Unmanned Aerial Vehicles (UAVs) for maritime object detection. However, maritime accidents frequently occur in low-visibility environments, such as foggy or low-light conditions, which lead to low contrast, blurred object boundaries, and degraded texture representations. Most existing maritime object detection algorithms are developed for natural light scenes, and their performance deteriorates markedly when deployed directly in low-visibility environments, primarily due to reduced image quality that hinders feature extraction and semantic information aggregation. Although several studies incorporate image enhancement techniques prior to detection to improve image quality, these approaches often introduce significant additional computational overhead, limiting their practical deployment on UAV platforms. To tackle these challenges, this paper proposes a lightweight model built upon a recent YOLO framework, termed Multi-Scale Adaptive YOLO (MSA-YOLO), for maritime detection using UAVs in low-visibility environments. The proposed model systematically optimizes the backbone, neck, and detection head networks. Specifically, an improved StarNet backbone is designed by integrating Efficient Channel Attention (ECA) mechanisms and multi-scale convolutional kernels, which strengthen feature extraction capability while maintaining low computational overhead. In the neck network, a high-frequency enhanced residual block branch is inserted into the C3k2 module to capture richer detailed information, while depthwise separable convolution is utilized to further reduce computational cost. Moreover, a non-parametric attention module is incorporated into the detection head to adaptively optimize features in the classification and regression branches. Finally, a joint loss function that combines bounding box regression, classification, and distribution focal losses is utilized to improve detection accuracy and training stability. Experimental results on the constructed AFO, Zhoushan Island, and Shandong Province datasets demonstrate that, relative to YOLOv11-s, MSA-YOLO reduces model parameters and FLOPs by 52.07% and 41.36%, respectively, while achieving improvements of 1.11% and 1.33% in mAP@0.5:0.95 and mAP@0.5. These results indicate that the proposed method effectively balances computational efficiency and detection accuracy, rendering it suitable for practical maritime search and rescue applications in low-visibility environments. Full article

Early non-invasive correction of neonatal auricular deformities is highly dependent on timely and precise diagnosis. However, clinical practice is often compromised by the subjectivity of visual assessments and the lack of objective tracking metrics, which frequently leads to missed optimal treatment windows. To address these challenges, we developed an interpretable deep learning-based diagnostic system for the automated screening and fine-grained classification of these deformities. Methodologically, a large-scale, multi-source dataset (n = 4644) was curated to support model training. The system pairs an automated object detector (YOLOv11) for background-reduced region-of-interest isolation with a cascaded classification pipeline optimized via ConvNeXt-Tiny. Crucially, we introduced a supervised contrastive learning module to project high-dimensional morphological features into a continuous severity score, enabling quantitative longitudinal tracking of therapeutic efficacy. To evaluate generalization and robustness, the framework underwent rigorous evaluation across three independent real-world cohorts and one controlled synthetic stress test. The system achieved 88.2% accuracy (Area Under the Curve (AUC): 0.949) in binary screening and 87.4% accuracy (macro-AUC: 0.976) in multi-class subtyping on the internal baseline. To enhance interpretability and build clinical trust, Gradient-weighted Class Activation Mapping (Grad-CAM) was utilized to explore the spatial distribution of the model’s attention, which frequently aligned with key anatomical landmarks. Furthermore, the learned severity scores robustly quantified post-intervention improvements (p = 0.0004), effectively capturing subtle anatomical normalization. While validation for rare subtypes remains underpowered, and the severity score currently functions mainly as a learned morphological similarity index requiring future clinical calibration, this study ultimately provides an objective and standardized web-based tool to facilitate the early intervention and precision management of neonatal auricular anomalies. Full article

Recently, there has been great interest in AI-based approaches for de novo design of novel drug candidates. However, the generation of useful lead drug candidate compounds requires more than predicting engagement with the desired protein target. Candidate molecules must also be anchored in the real world of medicinal chemistry for their synthesis and modification as well as satisfying multiple drug development-related criteria. Here, we present Nevermore, an AI target-conditioned, database-grounded workflow for prioritizing candidate ligands from large compound libraries. Nevermore uses a geometry-aware protein–ligand affinity oracle to score target-specific binding and perform sparse integer edits in count-based Morgan fingerprint space. Nevermore then retrieves the most structurally similar molecules from public chemical databases. This design enables multi-objective search over predicted affinity and absorption, distribution, metabolism, excretion, and toxicity (ADMET) proxies while keeping all candidates anchored to valid database compounds. We evaluated Nevermore’s performance across three biologically distinct targets: Menin, a protein-interaction target relevant to leukemia; SARS-CoV-2 M^pro, a viral cysteine protease relevant to antiviral discovery; and epidermal growth factor receptor (EGFR), a kinase-superfamily oncology target with extensive experimentally tested compounds. Nevermore retrieved candidate sets with favorable predicted affinity–property trade-offs. These results support database-grounded fingerprint steering as a practical computational strategy for lead prioritization and for generating testable molecular hypotheses, although the prioritized candidates remain predictions, requiring follow-up experimental validation. Full article

Directly coupled electrodynamic vibrators are widely used in vibration testing due to their ability to generate large propulsive forces. However, increasing the propulsive force typically requires higher driving currents, which leads to significant electrical heat generation and thermal management challenges in the armature coil. To address this issue, this study proposes a multi-objective parameter optimization framework for the design of armature coils in high-propulsive-force electrodynamic vibration tables. Two optimization objectives are formulated based on electromagnetic and thermal considerations: minimization of electrical heat generation in the armature coil; and improvement in cooling capability, characterized by the ratio between the cooling water channel area and the conductive cross-sectional area. The key geometric parameters of the coil, including winding configuration and cross-sectional dimensions, are treated as design variables. The resulting multi-objective optimization problem is solved using a multi-objective particle swarm optimization (MOPSO) algorithm to obtain a set of Pareto-optimal solutions that balance the two competing thermal objectives. The present work focuses on the pre-design-stage optimization of the armature coil after the rated propulsive force and geometric envelope of the vibrator have been specified. A representative high-propulsive-force electrodynamic vibrator is analyzed as a case study. Finite element thermal simulations show that the selected Pareto-optimal design reduces the peak armature-coil temperature by approximately 9.7–36.6% compared with the other investigated coil configurations under the same propulsive force condition. The proposed method provides an efficient approach for the thermally constrained parameter design of high-power electrodynamic vibrator armature coils. Full article

To address the challenges of detecting sugar orange fruits in complex natural orchard environments—where fruits are frequently occluded by leaves and branches and may be mutually occluded due to dense growth, leading to missed detections, false positives, and low detection confidence—we propose an improved algorithm based on YOLOv8n, named YOLO-FSEP. A Spatial-Channel Synergistic Attention (SCSA) module is introduced into the main network to enhance feature extraction capabilities; the IoU loss function is replaced with Focal_SIOU to improve the detection accuracy for difficult samples; and an SE attention mechanism is embedded in the detection head, with the addition of a P6 high-resolution detection layer to optimize multi-scale object performance. Experimental results on a self-built sugar orange dataset show that, compared to the baseline YOLOv8n, the improved model achieves a 0.9% increase in accuracy, a 1.3% increase in recall, and a 3.2% increase in mAP50-95, while maintaining an inference speed of 62.6 FPS. To evaluate the model under dynamic conditions, we performed a 200-frame continuous test of the 3D localization pipeline on a laptop with a RealSense D435i camera. The average YOLO inference time was 49.90 ms, post-processing (depth extraction and 3D coordinate conversion) took 0.24 ms, and the total processing time was 50.15 ms. Given that the typical response time for a robotic arm’s single positioning operation is 100–200 ms, this real-time performance meets the dynamic localization requirements of sugar orange harvesting. Full article

Against the backdrop of global decarbonization in energy-intensive industries, the primary aluminum sector has become a critical field for deep industrial decarbonization due to its high electricity consumption, large share of indirect carbon emissions, and complex mitigation pathways. This challenge is particularly salient in regions endowed with abundant renewable resources while hosting concentrated industrial electricity demand, where coordinated mitigation across technological upgrading and energy system transformation has broad practical relevance. Using Xining in Qinghai Province, China, a renewable-rich region, as an illustrative case, this study systematically examines the major carbon mitigation pathways in the primary aluminum industry, including mining, alumina production, electrolytic cell retrofitting, power system coordination, and carbon capture, utilization, and storage (CCUS). A multi-objective optimization model is developed to minimize marginal abatement costs (MAC) while maximizing technological application performance, and the sequential unconstrained minimization technique (SUMT) is employed to optimize mitigation pathways under short-, medium-, and long-term scenarios. The results show that, in the short term (before 2030), emission reduction mainly relies on improvements in electrolysis efficiency, leading to a mitigation pattern dominated by reductions in electricity consumption per unit of output. In the medium term (before 2035), the pathway shifts from isolated process optimization to a coordinated strategy combining process upgrading with power decarbonization, exhibiting a structural mitigation pattern driven by synergy between the production side and the energy side. In the long term (before 2060), the pathway evolves toward a stage dominated by energy system reconfiguration and carbon utilization. With high shares of renewable electricity integration, DC power supply configurations, and energy storage support, primary aluminum production is expected to achieve deep decarbonization on the power side. This study provides a transferable analytical framework and policy-relevant insights for the low-carbon transition of energy-intensive industries in renewable-rich regions. Full article

Marine propulsion shaft alignment is affected by bearing offsets, hull deformation, thermal growth, and condition-dependent propeller and gear loads. An alignment scheme optimized for a single condition may therefore lead to unbalanced bearing reactions or excessive shaft-line deformation in service. To improve multi-condition alignment performance while reducing the reliance on repeated direct finite element evaluations during optimization, this study proposes a hybrid surrogate-assisted multi-objective optimization framework for a container-ship propulsion shafting system. A beam finite element model based on Euler–Bernoulli theory is established and numerically checked using jack-up calculations. Cold static, hot operating, and zero-pitch conditions are considered. Bearing-load uniformity, maximum coupling vertical offset, and maximum shaft slope are selected as objectives. According to response characteristics, an extremely randomized trees model is used for the nonlinear load-uniformity response, whereas response surface models are used for the smoother coupling-offset and shaft-slope responses. The Pareto front is obtained using multi-objective particle swarm optimization, and a compromise scheme is selected using entropy-weighted TOPSIS. For the investigated case, the preferred scheme reduces the three objectives by 44.36%, 38.62%, and 8.65%, respectively, relative to the pre-optimization scheme, and finite element recalculation gives prediction deviations below 5%. The proposed framework provides a practical reference for propulsion shaft alignment optimization under operating conditions. Full article

In order to study the optimal size and sealing performance of the foot-shaped slip ring for reciprocating seal, the loading method of fluid pressure penetration is used to simulate the effect of fluid medium pressure on the seal, and the multi-objective optimization of the geometry of the slip ring is carried out based on optimization software to obtain the best combination of parameters for the foot-shaped slip ring. The effects of slip ring geometry, pre-compression and working pressure on Von Mises stress and contact pressure were investigated using the finite element method. The results show that the optimized geometry of the foot-shaped slip ring can reduce the maximum contact stress on the main sealing surface from 108.5 MPa to 75.22 MPa (a reduction of 30.7%) and decrease the maximum Von Mises stress of the slip ring from 62.84 MPa to 41.57 MPa (a reduction of 33.8%), thereby greatly reducing the wear of the slip ring while ensuring reliable sealing. In the static sealing condition, a smaller pre-compression (1.2–1.3 mm) leads to stress concentration in the O-ring, and the recommended pre-compression range is 1.4–1.6 mm. In the dynamic sealing condition, the effect of pre-compression on the sealing performance is greater than that of reciprocating motion speed on the sealing performance, and the foot-shaped slip ring seal is found to be more suitable for low-speed operation at 0.1–0.2 m/s. The optimized design provides a data-driven methodology for enhancing the reliability and service life of reciprocating seals in high-pressure environments. Full article

This paper addresses the problem that high pixel-level segmentation accuracy does not necessarily lead to geometrically compact building boundaries in vectorized outputs. A multi-task directional field learning framework is proposed based on U-Net with a ResNet-50 encoder. The framework introduces directional field supervision and a mask-field alignment loss to jointly optimize building region prediction and local boundary orientation consistency. In addition, a mild topological simplification procedure with a fixed small tolerance is applied to reduce residual staircase-like artifacts during vectorization. Experiments on the WHU building dataset at 0.2 m and 0.3 m spatial resolutions show that the proposed framework produces compact vector representations while maintaining high overlap relative to the raster reference annotations. In the 0.2 m setting, directional field learning improves Boundary IoU compared with the Baseline U-Net, whereas the complete pipeline slightly reduces Mask IoU and F1-score due to the additional simplification step. In the 0.3 m setting, the complete method does not consistently outperform several baselines in conventional pixel-level metrics, but it shows a favorable trade-off between polygon compactness and vector overlap under raster-reference evaluation. These results indicate that the proposed method is more suitable for geometry-aware vector reconstruction and vector simplification than for maximizing general semantic segmentation accuracy. In particular, the average number of polygon vertices is substantially reduced while Vector IoU remains approximately 90–92%. To further address the limitation of evaluating only on the WHU dataset, an additional in-domain validation experiment was conducted on the JAX dataset, which contains more complex building appearances and scene variations. The results show that the proposed Directional Field + Mild DP pipeline consistently reduces polygon complexity on the JAX dataset while maintaining competitive vector overlap. The central objective of the proposed framework is not only to improve mask-level building extraction, but also to enhance boundary-oriented vector reconstruction by learning local boundary-direction consistency and reducing raster-induced polygonal redundancy. Full article

Human activity recognition—HAR—plays a crucial role in the lives of patients battling neurodegenerative diseases. These debilitating conditions, such as Alzheimer’s or Parkinson’s, affect individuals’ ability to perform daily tasks autonomously and safely. HAR technology offers an invaluable solution by enabling real-time monitoring and assistance, helping to maintain independence and quality of life for patients. Additionally, this technology provides a valuable data source for doctors and caregivers, allowing for more precise and personalized care, which can make a difference in managing and treating these neurodegenerative diseases. The objective of this review is to identify the contribution of Transfer Learning and Reinforcement Learning in supporting the processes of daily activity recognition, thus enhancing the quality of life for patients. As this is a trending topic, the literature surrounding it is quite dispersed, which is why this review aims to present the current line of research in this field. To carry out this analysis, the science tree paradigm was used, which establishes two fundamental stages of analysis. The first is delimited by scientometrics, where the leading countries in the application of such technologies can be identified. This review highlights the evolution in the use of transfer learning and reinforcement learning in HAR in the healthcare field, where these techniques have significantly improved the accuracy and adaptability of real-time monitoring systems. The studies reviewed indicate that transfer learning has allowed models to adapt to data variations without requiring large volumes of manual labeling, which is essential in clinical and patient monitoring contexts. Additionally, reinforcement learning has optimized decision-making in complex scenarios, enabling activity recognition systems to dynamically adjust monitoring parameters, enhancing detection and response to critical or unusual activities in multi-user environments. These advances demonstrate that, by integrating these approaches, greater personalization and robustness can be achieved in human activity recognition, thereby improving the quality of life for patients in clinical settings. Full article

As scientific workflows grow more complex and green computing becomes a priority, efficient multi-objective scheduling is essential to optimize makespan, cost, and energy consumption for large task graphs. However, existing methods often suffer from scalability bottlenecks and insufficient modeling of task dependencies, leading to degraded performance on large-scale workflows. This paper proposes HiGAT-AC, a framework that combines a hierarchical graph attention network with actor-critic reinforcement learning for scalable workflow scheduling in heterogeneous systems. HiGAT-AC splits large workflows into subgraphs via spectral clustering and uses a three-level hierarchy to capture local task dependencies, coordinate inter-subgraph information, and conduct global resource allocation. The actor-critic model employs Chebyshev scalarization to balance the three conflicting objectives. Experimental results show that HiGAT-AC achieves competitive composite scores across workflow scales from 500 to 1000 tasks, with scores reaching 0.954 on 500-task workflows and 1.000 on 1000-task workflows, while remaining stable above 0.70 across all scales. Compared with traditional and representative learning-based methods, HiGAT-AC exhibits favorable overall performance and relatively stable scalability on large task graphs, providing a promising solution for scientific workflow scheduling that balances performance and sustainability. Full article

Background: Sepsis remains one of the leading causes of hospital morbidity and mortality worldwide. While its epidemiology has been extensively investigated, the chronobiology of sepsis—the temporal patterns underlying its occurrence and outcomes—has received comparatively little attention, despite its potential relevance for anticipating clinical demand and optimizing healthcare resource allocation. Objective: To analyze trends in the epidemiology and chronobiology of hospital admissions for sepsis across a large healthcare region in Spain over a 21-year period. Design: Retrospective observational study based on clinical–administrative records. We included all patients ≥ 18 years who had a principal diagnosis of sepsis or septic shock admitted between 2001 and 2021, identified through ICD-9-CM and ICD-10-CM coding in the Spanish National Hospital Discharge Records Database. Annual incidence, in-hospital mortality, and temporal distribution of admissions and deaths were assessed. Joinpoint regression was used to evaluate trends, Fourier spectral analysis to identify dominant rhythms, and multi-harmonic cosinor models to test for circannual rhythmicity. Results: We identified 39,622 sepsis admissions. Hospital incidence increased significantly over time (annual percent change [APC]: +9.6%; p < 0.001), with two inflection points (2008 and 2014). In-hospital mortality decreased linearly from 42.1% in 2001 to 31.9% in 2021 (p < 0.001), despite a progressive increase in patient age. Chronobiological analyses revealed no significant circannual rhythm in incidence or mortality (cosinor p = 0.14), although mortality was disproportionately clustered in winter months (p < 0.001). In multivariable analyses, clinical and epidemiological variables were independent predictors of in-hospital mortality. Conclusions: Over the last two decades, sepsis incidence has risen steadily, whereas hospital mortality has declined. Although no regular biological rhythm was demonstrated, excess winter mortality suggests extrinsic seasonal influences. This study provides novel evidence by jointly examining the epidemiology and chronobiology of sepsis, and supports their integration into healthcare planning strategies. Full article

The success of DNA amplification in Polymerase Chain Reaction (PCR) devices inherently depends on the rapid and absolute zero-overshoot temperature control of thermoelectric cooler (TEC) systems. In the literature, metaheuristic algorithms employed for proportional–integral–derivative (PID) tuning typically operate within unconstrained search spaces, relying exclusively on time-domain error metrics like ITAE. This conventional approach causes ‘gradient blindness’ and neglects frequency-domain robustness, resulting in excessive temperature overshoots that violate biological safety limits and lead to enzyme denaturation. To solve this problem, we propose a hybrid frequency-time domain optimization framework. Utilizing a first order plus dead-time (FOPDT) model for TEC dynamics, the PID search space is analytically restricted via Ziegler–Nichol’s stability boundaries. Furthermore, Phase Margin (PM ≥ 45°) and absolute zero-overshoot conditions are integrated into the objective function as a strict penalty mechanism. Evaluations conducted with five distinct metaheuristic algorithms (PSO, GWO, WOA, ABC, and ACO) prove that while traditional unconstrained methods yield overshoots up to 19.04%, the proposed architecture successfully confines all optimization agents to a globally stable region, enabling specific algorithms like ABC, PSO, and WOA to achieve exactly 0.00% overshoot. Validated across a realistic multi-step PCR cycle (95–55–75 °C), the developed robust controller settles into the denaturation phase with a 0.00 °C peak error, guaranteeing biological sample safety and delivering a reliable control framework for rapid-cycle PCR platforms. Full article

Biomimetic optimizers are increasingly used to solve complex engineering problems, yet their performance depends strongly on how effectively they preserve diversity while maintaining selection pressure toward promising regions. In this study, the Starfish Optimization Algorithm (SFOA) is enhanced through fitness–distance-aware selection control, leading to two improved variants: Fitness–Distance Balance Starfish Optimization Algorithm (FDBSFOA) and Dynamic Fitness–Distance Balance Starfish Optimization Algorithm (dFDBSFOA). The proposed framework guides candidate selection using both solution quality and spatial diversity relative to the current best solution, while the dynamic variant further adapts this balance over the course of the search to improve exploration in early iterations and exploitation near convergence. The proposed methods are evaluated on the IEEE CEC2017, CEC2020, and CEC2022 benchmark suites under a unified maximum function evaluation budget, MaxFEs = 10,000 × D, with 21 independent runs, and are further validated on constrained engineering design problems. Performance is assessed using convergence behavior, robustness indicators, computational overhead, and nonparametric statistical tests. The results show that the proposed variants improve the robustness and search efficiency of baseline SFOA, with dFDBSFOA providing the most consistent overall performance while introducing a controlled and interpretable computational overhead. These findings suggest that diversity-aware selection can serve as an effective design principle for strengthening biomimetic optimization frameworks. The current study focuses mainly on continuous, single-objective, and stationary benchmark problems, while the engineering-design validation also includes constrained and discrete/integer-coded cases. Extending the proposed strategy to dynamic, noisy, large-scale mixed-integer, or multi-objective settings remains future work. Full article