Search Results (16,822)

Industrial-grade printed circuit boards (PCBs) exhibit high structural order and inherent geometric symmetry, where minute surface defects essentially constitute symmetry-breaking anomalies that disrupt topological integrity. Detecting these anomalies is quite challenging due to issues like scale variation and low contrast. Therefore, this paper proposes a symmetry-aware object detection framework, DAS-YOLO, based on an improved YOLOv11. The U-shaped adaptive feature extraction module (Def-UAD) reconstructs the C3K2 unit, overcoming the geometric limitations of standard convolutions through a deformation adaptation mechanism. This significantly enhances feature extraction capabilities for irregular defect topologies. A semantic-aware module (SADRM) is introduced at the backbone and neck regions. The lightweight and efficient ESSAttn improves the distinguishability of small or weak targets. At the same time, to address information asymmetry between deep and shallow features, an iterative attention feature fusion module (IAFF) is designed. By dynamically weighting and calibrating feature biases, it achieves structured coordination and balanced multi-scale representation. To evaluate the validity of the proposed method, we carried out comprehensive experiments using publicly accessible datasets focused on PCB defects. The results show that the Recall, mAP@50, and mAP@50-95 of DAS-YOLO reached 82.60%, 89.50%, and 46.60%, respectively, which are 3.7%, 1.8%, and 2.9% higher than those of the baseline model, YOLOv11n. Comparisons with mainstream detectors such as GD-YOLO and SRN further demonstrate a significant advantage in detection accuracy. These results confirm that the proposed framework offers a solution that strikes a balance between accuracy and practicality in addressing the key challenges in PCB surface defect detection. Full article

Multiple Unmanned Aerial Vehicle (UAV) collaborative coverage path planning is widely applied in fields such as regional surveillance. However, optimizing the trade-off between deployment costs and task execution efficiency remains challenging. To balance resource costs and execution efficiency with an uncertain number of UAVs, this paper analyzes the characteristics of irregular mission areas and formulates a bi-level optimization model for multi-UAV collaborative CPP. The model aims to minimize both the number of UAVs and the total path length. First, in the upper level, an improved Best Fit Decreasing algorithm based on binary search is designed. Straight-line scanning paths are generated by determining the minimum span direction of the irregular regions. Task allocation follows a longest-path-first, minimum-residual-range rule to rapidly determine the minimum number of UAVs required for complete coverage. Considering UAV’s turning radius constraints, Dubins curves are employed to plan transition paths between scanning regions, ensuring path feasibility. Second, the lower level transforms the problem into a Multiple Traveling Salesman Problem that considers path continuity, range constraints, and non-overlapping path allocation. This problem is solved using an Improved Biased Random Key Genetic Algorithm. The algorithm employs a variable-length master–slave chromosome encoding structure to adapt to the task allocation of each UAV. By integrating biased crossover operators with 2-opt interval mutation operators, the algorithm accelerates convergence and improves solution quality. Finally, comparative experiments on mission regions of varying scales demonstrate that, compared with single-level optimization and other intelligent algorithms, the proposed method reduces the required number of UAVs and shortens the total path length, while ensuring complete coverage of irregular regions. This method provides an efficient and practical solution for multi-UAV collaborative CPP in complex environments. Full article

By addressing the challenges of management difficulties, insufficient integration of driver analysis, and single-dimensional analysis in the governance of illegal land use and illegal construction (collectively referred to as the “Two Illegalities”) under rapid urbanization, this study designs and implements a GIS-based governance system using Xiamen City as the study area. First, we propose a standardized data-processing workflow and construct a comprehensive management platform integrating multi-source data fusion, spatiotemporal visualization, intelligent analysis, and customized report generation, effectively lowering the barrier for non-professional users. Second, utilizing methods integrated into the platform, such as Moran’s I and centroid trajectory analysis, we deeply analyze the spatiotemporal evolution and driving mechanisms of “Two Illegalities” activities in Xiamen from 2018 to 2023. The results indicate that the distribution of “Two Illegalities” exhibits significant spatial clustering, with hotspots concentrated in urban–rural transition zones. The spatial morphology evolved from multi-core diffusion to the contraction of agglomeration belts. This evolution is essentially the result of the dynamic adaptation between regional economic development gradients, urbanization processes, and policy-enforcement synergy mechanisms. Through a modular, open technical architecture and a “Data-Technology-Enforcement” collaborative mechanism, the system significantly improves information management efficiency and the scientific basis of decision-making. It provides a replicable and scalable technical framework and practical paradigm for similar cities to transform “Two Illegalities” governance from passive disposal to active prevention and control. Full article

Accurate measurement of material mechanics parameters is crucial for evaluating process quality and product reliability and is a major challenge in the development of 3D heterogeneous integration technology. Aiming to perform high-accuracy measurements of the elastoplastic nonlinear constitutive parameters of microelectronic materials using the nanoindentation testing technique, we take advantage of a neural network to construct a forward characterization model to characterize these response characteristic parameters for different materials, design an improved algorithm for obtaining a reverse iterative solution of the forward characterization model, and develop a material mechanics parameter measurement method to solve overdetermined equations using the least-squares method. This method was further improved by addressing the issues of algorithm stability and solution uniqueness, achieving high-precision and fast reverse solutions for elastoplastic constitutive parameters. The relative error of the material parameters is less than 3% (95% confidence interval), the maximum error is less than 8%, and the inversion convergence error of the key indentation response characteristic parameters is less than 0.1%. The difference between the measured material parameters and the theoretical model in the influence on the process stress of TCV (through ceramic via) products is verified through finite element simulation. Full article

In nanometer integrated-circuit (IC) manufacturing, advanced technology scaling has intensified the effects of process variations on circuit reliability and performance. Random fluctuations in parameters such as threshold voltage, channel length, and oxide thickness further degrade design margins and increase the likelihood of functional failures. These variations often lead to rare circuit failure events, underscoring the importance of accurate yield estimation and robust design methodologies. Conventional Monte Carlo yield estimation is computationally infeasible as millions of simulations are required to capture failure events with extremely low probability. This paper presents a novel reliability-based circuit design optimization framework that leverages deep transfer learning to improve the efficiency of repeated yield analysis in optimization iterations. Based on pre-trained neural network models from prior design knowledge, we utilize model fine-tuning to accelerate importance sampling (IS) for yield estimation. To improve estimation accuracy, adversarial perturbations are introduced to calibrate uncertainty near the model decision boundary. Moreover, we propose a cascaded batch Bayesian optimization (CBBO) framework that incorporates a smart initialization strategy and a localized penalty mechanism, guiding the search process toward high-yield regions while satisfying nominal performance constraints. Experimental validation on SRAM circuits and amplifiers reveals that CBBO achieves a computational speedup of 2.02×–4.63× over state-of-the-art (SOTA) methods, without compromising accuracy and robustness. Full article

Background: Intraoral radiography remains highly operator-dependent, with small deviations in beam angulation or receptor placement leading to geometric distortions, diagnostic inaccuracies, and repeated exposures. This pilot study introduces and evaluates a gyroscopic-guided, laser-assisted radiographic device designed to standardize cone positioning and improve the geometric reliability of bisecting-angle intraoral radiographs. Methods: Eighteen dental graduates and practitioners performed periapical radiographs on phantom models using a charge-coupled device (CCD) sensor over six months. Each participant obtained six standardized projections with and without the device, yielding 200 analysable radiographs. Radiographic linear measurements included tooth height (occluso–apical dimension) and tooth width (mesio-distal diameter), which were compared with reference values obtained using the paralleling technique. Radiographic errors—including cone cut, elongation, proximal overlap, sliding occlusal plane deviation, and apical cut—were recorded and compared between groups. Results: Use of the gyroscopic-guided device significantly enhanced geometric accuracy. Height measurements showed a strong correlation with reference values in the device group (r = 0.942; R² = 0.887) compared with the non-device technique (r = 0.767; R² = 0.589; p < 0.0001). Width measurements demonstrated similar improvement (device: r = 0.878; R² = 0.770; non-device: r = 0.748; R² = 0.560; p < 0.0001). Overall, the device reduced technical radiographic errors by approximately 62.5%, with significant reductions in cone cut, elongation, proximal overlap, sliding occlusal plane errors, and tooth-centering deviations. Conclusions: Integrating gyroscopic stabilization with laser trajectory guidance substantially improves the geometric fidelity, reproducibility, and diagnostic quality of intraoral radiographs. By minimizing operator-dependent variability, this innovation has the potential to reduce repeat exposures and enhance clinical diagnostics. Further clinical trials are recommended to validate performance in patient-based settings. Full article

In constrained waters, multi-USV cooperative encirclement of highly maneuverable targets is strongly affected by partial observability as well as obstacle and boundary constraints, posing substantial challenges to stable cooperative control. Existing deep reinforcement learning methods often suffer from low exploration efficiency, pronounced policy oscillations, and difficulties in maintaining the desired encirclement geometry in complex environments. To address these challenges, this paper proposes an adaptive difference-based multi-agent policy gradient method (MAADPG) under the centralized training and decentralized execution (CTDE) paradigm. MAADPG deeply integrates potential-field-inspired geometric guidance with a multi-agent deterministic policy gradient framework. Specifically, a guidance module generates geometrically interpretable candidate actions for each pursuer. Moreover, a difference-driven adaptive action adoption mechanism is introduced at the behavior policy execution level, where guided actions and policy actions are locally compared and the guided action is adopted only when it yields a significantly positive return difference. This design enables MAADPG to select higher-quality interaction actions, improve exploration efficiency, and enhance policy stability. Experimental results demonstrate that MAADPG consistently achieves fast convergence, stable coordination, and reliable encirclement formation across representative pursuit–encirclement scenarios, including obstacle-free, sparsely obstructed, and densely obstructed environments, thereby validating its applicability and stability for multi-USV encirclement tasks in constrained waters. Full article

The increasing biomedical and conservation interest in porcine species has driven the development of advanced in vitro follicle culture systems designed to preserve genetic diversity and accurately model key stages of folliculogenesis. This study assessed a three-dimensional (3D) alginate-based system for the in vitro culture of porcine preantral follicles, aiming to overcome the structural limitations of conventional two-dimensional (2D) methods. A total of six experimental groups were established, consisting of group-cultured (four follicles/well) or individually cultured (one follicle/well) follicles maintained either without alginate (0%) or encapsulated in 0.5% or 1% alginate for 14 days in media supplemented with FSH, EGF, and IGF-I, with LH added from day 9. Follicular development was assessed by morphometric evaluation, image-based and histological analyses, and quantification of steroid hormones in media collected every 48 h. Group-cultured follicles encapsulated in 0.5% alginate most effectively maintained their 3D architecture, reached the largest diameters, and progressed more uniformly compared with other groups. In contrast, follicles cultured without alginate rapidly lost structural integrity, showed granulosa cell migration, and decreased in size, whereas those encapsulated in 1% alginate exhibited restricted growth. Estradiol and testosterone concentrations increased over time in the 0.5% alginate group, were lowest without alginate, and intermediate in 1% alginate. Individually cultured follicles exhibited reduced growth and lower total hormone production compared with group-cultured follicles; however, when normalized per-follicle, steroid secretion, particularly in the 0.5% alginate group, was enhanced, indicating increased steroidogenic efficiency on a per-follicle basis. These findings indicate that 0.5% alginate provides an optimal balance between structural support and physiological steroidogenesis during preantral follicle culture. This 3D system improves the biological relevance of porcine follicle culture and may support future applications in reproductive biology, conservation, and genetic resource preservation. Full article

With the increasingly prominent demand for building energy efficiency and occupant-centric design, accurate and reliable personal thermal comfort models (PTCMs) are playing an important role in various residential and energy applications (e.g., building energy-saving design, indoor environmental regulation, and health and well-being improvement). In recent years, data-driven and artificial intelligence (AI) technologies have attracted considerable attention in the field of personal thermal comfort modeling. This study systematically reviews recent progress in data-driven personal thermal comfort modeling, emphasizing contact-based and non-contact data collection ways, correlation analysis of feature data, modeling methods based on machine learning and deep learning. Considering the high cost and limited scale of collection experiments, as well as noise, ambiguity, and individual differences in subjective feedback, special attention is put on the data-efficient thermal comfort modeling in data scarcity scenarios using a transfer learning (TL) strategy. Characteristics and suitable occasions of four transfer methods (model-based, instance-based, feature-based, and ensemble methods) are summarized to provide a deep perspective for practical applications. Furthermore, integration of PTCM into building environment control is summarized from aspects of the integration framework, modeling method, control strategy, actuator, and control effect. Performance of the integrated systems is analyzed in terms of improving personal thermal comfort and promoting building energy efficiency. Finally, several challenges faced by PTCMs and future directions are discussed. Full article

Path planning for multiple four-way shuttles in high-density warehousing is frequently hampered by efficiency-degrading conflicts, particularly head-on deadlocks. To address this challenge, this paper proposes a multi-agent reinforcement learning (MARL) framework based on Proximal Policy Optimization (PPO). The core of our approach is a novel Cooperative Avoidance Reward Mechanism (CARM), which employs a dual-component reward structure. This structure integrates a distance-guided reward to ensure efficient navigation towards targets and a cooperative avoidance reward that uses both immediate and delayed returns to incentivize implicit collaboration. This design effectively resolves conflicts and mitigates the policy instability often caused by traditional collision penalties. Experiments in a 20 × 20 grid simulation environment demonstrated that, compared to a rule-based A* and Conflict-Based Search (CBS) algorithms, the proposed method reduced the average travel distance and total time by 35.8% and 31.5%, respectively, while increasing system throughput by 49.7% and maintaining a task success rate of over 95%. Ablation studies further confirmed the critical role of CARM in achieving stable multi-agent collaboration. This work offers a scalable and efficient data-driven solution for real-time path planning in complex automated warehousing systems. Full article

Reciprocating compressors, which serve as core equipment in the petrochemical and natural gas transmission sectors, operate under prolonged variable loads and high-frequency impact conditions. Critical components, such as valves and piston rings, are prone to failure. Existing fault diagnosis methods suffer from inadequate spatio-temporal feature extraction and neglect spatio-temporal correlations. To address this, this paper proposes a spatio-temporal feature fusion-based fault diagnosis method for reciprocating compressors. This method constructs a spatio-temporal feature fusion model (STFFM) comprising three principal modules: First, a spatio-temporal feature extraction module employing a multi-layered stacked bidirectional gated recurrent unit (BiGRU) with batch normalisation to uncover temporal dependencies in long-term sequence data. A graph structure is constructed via k-nearest neighbours (KNN), and an enhanced graph isomorphism network (GIN) is integrated to capture spatial domain fault information variations. Second, the spatio-temporal bidirectional attention-gated fusion module employs a bidirectional multi-head attention mechanism to enhance temporal and spatial features. It incorporates a cross-modal gated update mechanism and learnable weight parameters to dynamically retain the highly discriminative features. Third, the classification output module enhances the model’s generalisation capability through multi-layer fully connected layers and regularisation design. Research findings demonstrate that this approach effectively integrates spatio-temporal coupled fault features, achieving an average accuracy of 99.14% on an experimental dataset. This provides an effective technical pathway for the precise identification of faults in the critical components of reciprocating compressors. Full article

Background/Objective: This systematic review aims to evaluate ex vivo brain slice models in glioblastoma (GBM) research, with a specific focus on tumour invasion, tumour–microenvironment interactions, and therapeutic response. Methods: A systematic search looking for studies employing ex vivo organotypic brain slice models in GBM research was conducted across multiple databases (January 2010–July 2025) in accordance with PRISMA guidelines. The study was registered in PROSPERO database (CRD420251138341). Inclusion criteria encompassed patient-derived brain slices, hybrid rodent–human slice co-cultures, and microfluidic-integrated ex vivo platforms designed to assess tumour invasion, microenvironmental interactions and therapeutic responses. Exclusion criteria included reviews, abstracts, conference proceedings, in vivo-only studies, purely in vitro models without organotypic integration, and studies not focused on GBM. Results: Twenty-six studies met the inclusion criteria. Among these, 18/26 (69%) investigated GBM invasion, 18/26 (69%) evaluated therapeutic responses, and 5/26 (19%) examined tumour–microenvironment interactions, with several studies spanning multiple domains. Across platforms, organotypic slices consistently recapitulated key features of GBM biology—including perivascular and white-matter-aligned invasion, stromal–immune interactions, and patient-specific drug sensitivity—while engineered systems enhanced perfusion and exposure control. Methodological variability, particularly regarding slice preparation, oxygenation and viability assessment, limits direct comparability between studies. Conclusions: Organotypic brain slice models represent an extremely relevant tool for translational investigations of GBM biology and treatment response. However, substantial methodological heterogeneity together with limited standardisation hamper reproducibility and cross-study validation. Future work should focus on enhancing reproducibility and harmonising protocols to support the development of clinically meaningful precision oncology strategies. Full article

Accurately determining actual energy consumption is essential for guiding technological developments in the transport sector, assessing vehicle development outcomes, and designing effective energy and climate policies. Although laboratory driving cycles such as the WLTP provide standardized benchmarks, they do not reflect the complex interactions between human behavior, environmental conditions, and vehicle dynamics under real-world operating conditions. This article presents an integrated framework for assessing long-term, actual energy carrier consumption in four main vehicle categories: internal combustion engine vehicles (ICEVs), hybrid electric vehicles (HEVs), hydrogen fuel cell electric vehicles (H2EVs), and battery electric vehicles (BEVs). The entire discussion here is based on the results of data analysis from natural operation using the so-called vehicle energy footprint. This framework provides a method for determining the average energy carrier consumption for each group of vehicles with the specified drivetrains. This information formed the basis for assessing the total energy demand for the operation of the analyzed vehicle types in normal operation. The simulations show that among mid-range passenger vehicles, ICEVs are the most energy-intensive in normal operation, followed by H2EVs and HEVs, and BEVs are the least. This study highlights the methodological challenges and implications of accurately quantifying energy consumption. The presented method for assessing energy demand in vehicle operation can be useful for manufacturers, consumers, fleet operators, and policymakers, particularly in terms of energy efficiency, emission reduction, and public health protection. Full article

Traffic state estimation (TSE) is a core task in intelligent transportation systems (ITSs) that seeks to infer key operational parameters—such as speed, flow, and density—from limited observational data. Existing methods often face challenges in practical deployment, including limited estimation accuracy, insufficient physical consistency, and weak generalization capability. To address these issues, this paper proposes a hybrid estimation framework that integrates multi-agent reinforcement learning (MARL) with the Lighthill–Whitham–Richards (LWR) traffic flow model. In this framework, each roadside detector is modeled as an agent that adaptively learns fundamental diagram (FD) parameters—the free-flow speed and jam density—by fusing local detector measurements with global CAV trajectory sequences via an interactive attention mechanism. The learned parameters are then passed to an LWR solver to perform sequential (rolling) prediction of traffic states across the entire road segment. We design a reward function that jointly penalizes estimation error and violations of physical constraints, enabling the agents to learn accurate and physically consistent dynamic traffic state estimates through interaction with the physics-based LWR environment. Experiments on simulated and real-world datasets demonstrate that the proposed method outperforms existing models in estimation accuracy, real-time performance, and cross-scenario generalization. It faithfully reproduces dynamic traffic phenomena, such as shockwaves and queue waves, demonstrating robustness and practical potential for deployment in complex traffic environments. Full article

The hyperspectral image (HSI) is rich in spectral information and has important applications in the field of ground objects classification. However, HSI data have high dimensions and variable spatial–spectral features, which make it difficult for some models to adequately extract the effective features. Recent studies have shown that fusing spatial and spectral features can significantly improve accuracy by exploiting multi-dimensional correlations. Based on this, this article proposes a spectral integration and focused attention network (SIFANet) with a two-branch structure. SIFANet captures the local spatial features and global spectral dependencies through the parallel-designed spatial feature extractor (SFE) and spectral sequence Transformer (SST), respectively. A cross-module attention fusion (CMAF) mechanism dynamically integrates features from both branches before final classification. Experiments on the Salinas dataset and Xiong’an hyperspectral dataset show that the overall accuracy on these two datasets is 99.89% and 99.79%, which is higher than the other models compared. The proposed method also had the lowest standard deviation of category accuracy and optimal computational efficiency metrics, demonstrating robust spatial–spectral feature integration for improved classification. Full article