Search Results (3,017)

Multi-UAV Cooperative Target Search (MCTS) is a critical task in low-altitude sensing applications, requiring agents to efficiently explore unknown environments under complex constraints. However, traditional search methods are mostly unscalable and perform poorly in dynamic multi-UAV environments. As a promising alternative, Reinforcement Learning (RL) has emerged to overcome these limitations by enabling agents to learn adaptive policies directly from environmental interactions. A key limitation is that current RL methods lack efficient exploration, which is a critical bottleneck preventing UAVs from finding more targets. To address this limitation, we propose a novel method named AEQMIX, which integrates trajectory entropy maximization into QMIX, an advanced Multi-Agent Reinforcement Learning (MARL) method, to encourage efficient exploration. We formulate the MCTS problem as a Decentralized Partially Observable Markov Decision Process (Dec-POMDP) and design a multi-objective reward function. To mitigate the intractability of density estimation in high-dimensional spaces, we employ a nonparametric particle-based entropy estimator to quantify the spatial diversity of UAV trajectories. This entropy estimate is utilized as an intrinsic reward, incentivizing agents to maximize the distance between their trajectories and those of their neighbors. Extensive simulations demonstrate that AEQMIX significantly outperforms baseline reinforcement learning and traditional optimization methods in terms of search rate, coverage efficiency, and collision avoidance. Compared with DNQMIX, AEQMIX improves the search rate and coverage rate by 9.52% and 11.54%, respectively, while reducing the average collision count by 70.59% in the (40 × 40) environment. Full article

This study presents a data-driven framework for determining the optimal gear tooth surface modification (crowning) to improve tolerance to angular misalignment (in-plane and out-of-plane). A nonlinear tooth contact analysis (TCA) model was employed to accurately predict the contact path evolution of meshing gears under different combinations of tooth modification amounts and misalignment angles. An accurate dataset consisting of 530 simulated helical gear meshing configurations was generated. Based on these simulation results, a Gaussian Process Regression (Kriging) surrogate model was developed to establish the relationship between tooth modification, misalignment parameters, and contact behavior. The validated surrogate model enables rapid prediction of gear contact characteristics and interpolation within the design space, thereby supporting efficient surrogate-assisted design exploration without requiring repeated computationally intensive TCA simulations. The proposed framework identifies the minimum modification required to maintain acceptable contact conditions, and provides an efficient tool for improving misalignment tolerance and supporting robust gear design. Full article

This paper presents a G-Agent, a large language model (LLM)-driven multi-agent framework that automates the optimization workflow for an axisymmetric cavity-based scramjet combustor. The framework integrates a supersonic compressible reacting flow solver with the Qwen3-VL-2B-Instruct model. It consists of four specialized agents: Interactor, Runner, Corrector, and Optimizer. The Interactor parses user requirements and generates simulation input files. The Runner manages mesh generation, solver configuration, and simulation execution. The Corrector diagnoses failed cases by analyzing fault logs and applies corrective actions. The Optimizer coordinates the optimization process using a trust-region response surface method to maximize thrust. The framework employs Latin hypercube sampling (LHS) to explore the design space defined by three key geometric parameters: isolator length, cavity depth, and fuel injector position. Without manual intervention beyond initial specifications, the G-Agent successfully conducted multiple optimization iterations. Starting from a baseline thrust of 489.4 N, the optimized configuration achieved 523.5 N after three iterations, reaching a relative improvement of 6.97%. Our proposed agent achieves closed-loop control of the entire optimization process, significantly lowering the technical barrier and human effort in scramjet combustor design. Full article

This paper presents a systematic reward engineering methodology for training a Proximal Policy Optimization (PPO) quadrotor navigation policy in the Webots simulator, using a hierarchical architecture in which a PID controller handles low-level stabilization and a PPO policy issues velocity commands. We document the complete evolution of a composite ten-term reward function across seven versions (v5 through v11) and retrain the key versions with multiple independent training seeds. The multi-seed study revises the single-seed history: penalty-dominated configurations (v8, v10) fail across all seeds, while the strongest historical version proves seed-sensitive (v11: 32.2 +/− 15.8%). An ablation removing the continuous distance-shaping term from v11 yields 0% success across seven seeds, identifying that term as necessary for convergence. We further isolate a previously hidden co-factor: with the library-default exploration-noise initialization (sigma_0 = 1.0), sampled actions saturate the bounded action space, the exploration variance receives no learning gradient, and curriculum progression deadlocks regardless of reward design; initializing sigma_0 = 0.37 restores gradient flow. With this correction and a deterministic evaluation-gated curriculum, the final configuration is evaluated across the full curriculum rather than at a single operating point: across five independent training seeds under a deterministic protocol, it attains 95.0% ± 6.2% navigation success at Stage 0 conditions (2 m targets, no obstacles), 89.6% ± 6.9% at Stage 1 conditions (4 m, one obstacle), and 48.4% ± 10.8% at Stage 2 conditions (7 m, three obstacles). Reporting this difficulty curve, rather than a single headline value, exposes a substantial generalization gap whose dominant failure mode is obstacle collision (45–52% of episodes at Stage 2). Matched retraining of Soft Actor-Critic and TD3 baselines under identical reward and curriculum conditions yields one completed seed each both baselines show non-monotonic difficulty curves, and at Stage 2 conditions, TD3 (64.0%) exceeds PPO (48.4% ± 10.8%) while SAC (43.0%) falls just below it, whereas at Stage 0, PPO (95.0%) leads both, so the ranking is operating point-dependent on the current single-seed evidence. We conclude that a continuous shaping gradient and the exploration-noise initialization, interacting with the curriculum advancement criterion, determine convergence in continuous control deep reinforcement learning, and that reward polarity by itself does not. Full article

Promoting the name ‘Gulf of America’ at the US federal level for a region historically identified as the ‘Gulf of Mexico’ transformed a local toponym into a global media controversy. This study analyzes how 110 preservice teachers from the Bachelor’s Degree in Primary Education at the University of Zaragoza interpret the political and ideological components of these mediatized discourses and explores the potential of this controversy for developing critical literacy. Employing a qualitative, interpretive, and critical research design, the students analyzed news articles, social media posts, memes, videos, and AI-generated responses following Cassany’s framework for critical comprehension. The content analysis of 132 narrative productions using ATLAS.ti version 9.0.20.0, generated 430 coding units organized into four categories: territory and identity (102); controversies and intentionality (99); power and ideology (142); and credibility and discourse impact (87). The results indicate an incipient shift from a naturalized reading of space toward its political interpretation: the students identify symbolic appropriations and power asymmetries, although tensions between multiperspectivity and relativism persist, alongside a partial attribution of neutrality to artificial intelligence. The controversy emerges as a useful educational context for incorporating the reading of territory, its names, and its representations into critical literacy. Full article

Digital computing-in-memory (DCIM) provides deterministic floating-point computation but incurs substantial area and power overhead from replicated mantissa multipliers and adder trees. This work proposes an error-recoverable BF16 DCIM arithmetic unit that jointly approximates a 2-bit multiplier and the first adder stage. For the 11 × 11 input, the multiplier outputs 0111 instead of the Baseline 1111, converting the error from +6 to −2 and fixing the product MSB to 0. This enables the first adder stage to be reduced from 4 bits to 3 bits. A lightweight flag detects the same error condition and is reused as a carry input for local compensation, avoiding a separate multi-bit correction circuit. Hierarchical design-space exploration selected the 0111 approximation with carry compensation at bit position 1. Transistor-level evaluation showed reductions of 14.81% in transistor count and 28.56% in average power relative to the Baseline. Across ResNet18, VGG16-BN, and AlexNet on CIFAR-10 and CIFAR-100, the Proposed scheme achieved the lowest BF16-referenced Layer NRMSE and Logit NRMSE among the evaluated Baseline, DIMC-S-derived, LSAC OR+SXAFA-derived, and Proposed schemes, while the Top-1 accuracy difference relative to the Baseline remained within −0.02%p to +0.12%p. These results demonstrate an improved hardware–accuracy trade-off without retraining or data rearrangement. Full article

Structural design codes provide safe procedures for verifying steel–concrete composite beams but do not directly guide engineers toward cost-effective configurations. This study aims to develop and evaluate a surrogate-assisted framework that combines a Multilayer Perceptron neural network with Bayesian Optimization for the preliminary flexural-resistance and material-cost optimization of simply supported steel–concrete composite beams designed according to the Brazilian code NBR 8800. A dataset containing 20,000 beam configurations and 15 input variables was generated using a Python-based analytical routine that implements the NBR 8800 provisions for the positive bending resistance of composite beams. The generated dataset was used to train a Multilayer Perceptron neural network to predict the design bending resistance. The trained surrogate model was then integrated with Bayesian Optimization to search a discrete design space comprising commercial steel profiles, concrete slab thicknesses, shear connector quantities, and connector diameters. The selected neural network architecture achieved validation MAE and RMSE values of 2.128 kN·m and 3.013 kN·m, respectively, with an $R^2$ of 0.9999. In ten benchmark scenarios, the BO–MLP framework identified candidate solutions using only 60 objective-function evaluations. This corresponds to 3% of the evaluation budget adopted for GA and PSO and approximately 0.057% of the configurations examined by exhaustive search. Despite this limited sampling budget, the resulting candidate solutions presented an average optimality gap of approximately 12.1% relative to the global reference. In computational terms, GA and PSO required approximately 4.1 and 4.9 times the execution time of BO–MLP, respectively, while exhaustive search required approximately 18.4 times the execution time. Overall, the proposed framework offers a computationally efficient means of exploring discrete composite-beam configurations and identifying cost-competitive candidate solutions. Direct NBR 8800 verification showed that seven of the ten selected candidates satisfied the resistance requirement, while three presented resistance-to-demand ratios slightly below unity. Therefore, the framework should be used as a preliminary screening tool, with the selected configurations subsequently verified using the complete code-based procedure. Within the restricted structural domain investigated, the framework can support preliminary decisions related to positive bending resistance and material cost. Full article

Machine-to-machine and Internet of Things endpoints operate in physically accessible environments, motivating decapsulation-path hardening against an adversary with full code access. We present PQ-WB-KEM, a feasibility study that is, to our knowledge, the first systematic exploration of the table-based white-box design space for a NIST-standardized lattice key-encapsulation mechanism (ML-KEM-768, FIPS 203); prior white-box post-quantum work targets hash-based SPHINCS+ and multivariate hidden field equations (HFE; 256 GB), while the only earlier lattice-based white-box is custom and non-standardized. Because the base multiply runs in the number-theoretic transform (NTT) domain, where the secret operand $\widehat{s}=\mathrm{NTT}\left(s\right)$ is full-range over ${\mathbb{Z}}_q$, coefficient smallness does not shrink the tables. We map the design space with two verified lookup-only constructions: a shared full multiply table (Construction A, a measured 22.16 MB base, 25.57 MB core) and per-component tables with the secret baked in (Construction B, 7.67 MB base, 11.08 MB core), with the base tables being about 11,600× (A) and 33,400× (B) smaller than the 2022 256 GB HFE white box. Three-share arithmetic masking drives the measured first-order differential computation analysis (DCA) correlation to near the noise floor (${\rho }_{\max }=0.011$, versus $0.85$ unmasked). The projected deployment overhead is ≈47×, anchored on the native-C protected primitive measured with its mask-generation random number generator (RNG) randomness included ($4.30\times$, times an ≈11× embedded cache factor); the RNG-excluded harness yields the $17\times$ lower bound. We delimit scope honestly: against the full white-box adversary this construction does not achieve key confidentiality because the base multiply forms the clear product coordinates $p_0,p_1$ before masking and these yield linear equations for the secret; every positive result holds only against strictly weaker adversaries, and the work maps the lattice white-box design space rather than delivering a fully white-box key-encapsulation mechanism. Full article

In advanced manufacturing, designing multi-pulse composite driving waveforms for piezoelectric inkjet (PIJ) printing presents a constrained, high-dimensional, physical black-box optimization challenge. The feasible jetting region within the 12-dimensional parameter space is highly sparse; furthermore, traditional unconstrained optimization algorithms are prone to triggering nozzle flooding or actuator fatigue damage. To overcome this bottleneck, this paper proposes CA-TuRBO-m, a closed-loop collaborative architecture based on classifier-assisted multi-trust region Bayesian optimization. This architecture reconstructs the deposition morphology features on the substrate into a composite visual feedback source that implicitly incorporates fluid dynamics. Furthermore, it repurposes a Random Forest classifier into a dynamically iterating physical safety topological gating mechanism to actively intercept high-risk parameter combinations. Simultaneously, a multi-trust-region parallel exploration mechanism is introduced to balance global exploration and local exploitation. Experimental results demonstrate that over 200 online physical printing iterations, the proposed architecture reduces the number of invalid prints leading to system failures to an average of 3.8, achieving a high effective sampling rate of 98.1%. Without relying on complex fluid dynamic models, this approach enables precise morphological control over droplets of varying sizes and mitigates printing defects, successfully achieving multi-target adaptive regulation within a limited budget on a single physical platform. Full article

Mobile charging stations can deliver energy at the point of demand, but their isolated battery-to-battery DC–DC stages must accommodate independent source and load battery-voltage variation. This study develops a hierarchical, domain-wide analytical framework for a fixed-hardware 20 kW silicon-carbide phase-shifted full-bridge converter with a four-diode rectifier. The independently varied terminal domain spans 586–840 V at the source and 495–738 V at the load. The framework combines rated-power coverage, constraint-resolved derating, modeled semiconductor-loss screening, analytical commutation-capacitance budgeting, deterministic sensitivity assessment, and selected-point switching-level refinement. For four screened transformer turns ratios, nominal area-based rated-power can reach 95%. However, a three-point leakage-inductance sensitivity changes the nominal ordering at −10%, showing that the sub-one-percentage-point coverage separation does not establish a robust unique ratio. Selected-point commutation-cell and full-converter simulations show that the analytical added-capacitance screening bound is useful for rapid screening but can be optimistic near difficult high-source-voltage and light-load conditions. The full-converter results also retain high-capacitance light-load cases in which target power is not reachable at the phase-shift-domain boundary. The proposed evidence hierarchy therefore supports rapid candidate screening, identifies sensitive boundaries, and directs detailed switching refinement without claiming a universal transformer-ratio optimum or replacing hardware measurements. Full article

Urban public spaces in cold-climate cities commonly face the challenge of seasonal vitality attenuation. Taking the central urban area of Shenyang as a case study, this paper constructs a HEVA four-dimensional framework based on “spatial diagnosis, mechanism analysis, and design response.” By integrating Multiscale Geographically Weighted Regression (MGWR) with GIS spatial analysis, the study reveals the spatial heterogeneity and driving mechanisms of winter vitality attenuation in linear green spaces. The findings are threefold: (1) Winter wind fields induce significant local wind-chill effects that severely suppress winter stay vitality in green spaces; (2) MGWR results show that greenery coverage exhibits a predominantly positive effect (approximately 81% of sample points have positive coefficients), bus stop density exhibits a “bifurcated spatial pattern”, with positive coefficients at approximately 53% of sample points and negative at the remaining 47%, indicating a highly localized effect., commercial service density is positive across the entire study area (100% positive), building density is predominantly negative (approximately 87%), and road network density has a relatively weak effect; (3) Based on the above mechanisms, a three-pronged elastic design strategy system is proposed, encompassing “climate-adaptive regulation, functional composite implantation, and regional cultural response.” This study explores a data-driven, mechanism-guided geospatial design pathway for the renewal of underperforming spaces in cold-climate cities. The generalizability of the methodological framework warrants further validation through multi-city and multi-seasonal data. Full article

Against the dual background of ICH (intangible cultural heritage) revitalization and urban stock space renewal, the renovation of traditional craft workshops has shifted from limited workshop repair to comprehensive space creation that balances craft protection, cultural dissemination, and sustainable operation. While existing scholarship has explored the functional composition and qualitative design strategies of ICH workshops, there remains a notable research gap in quantitative spatial performance evaluation frameworks tailored to craft production constraints, and the actual contribution of spatial design to living heritage transmission lacks objective measurement tools. This study takes craftsmanship-oriented ICH workshops as the core research object. Based on field investigations, multi-subject questionnaires, and expert consultations, 14 tertiary indicators are selected from three dimensions: production and safeguarding, experience and dissemination, and operation and development, to construct a spatial performance evaluation system for living heritage transmission. The Analytic Hierarchy Process (AHP) is adopted to determine the weight of each indicator. Taking the Yuezhou Fan ICH workshop as an empirical case, this study conducts a quantitative comparison of spatial performance before and after renovation. The results show that the comprehensive performance score of the workshop after renovation has increased by approximately 109.7% compared with that before renovation, among which the production and safeguarding dimension have the most significant improvement, verifying the rationality and practicability of the evaluation system. Theoretically, this study extends the application scope of built environment performance evaluation to the field of craft heritage spaces and establishes a closed-loop logic of “quantitative diagnosis—deficiency identification—targeted optimization” for workshop renovation. Based on the evaluation results, this paper proposes a progressive optimization path of “consolidating production baseline—upgrading experience scenarios—empowering diversified operation”, which provides a generalizable quantitative framework and practical reference for the spatial renovation and performance evaluation of similar craftsmanship-oriented ICH workshops. Full article

The generation of aerosols with narrow droplet-size distributions remains a key challenge in liquid atomization technologies used in agricultural, chemical-processing, and environmental applications. This study presents an experimental investigation of spray characteristics produced by an inertial rotary atomizer equipped with an internal hydrodynamic flow-conditioning system. The experiments were conducted using a Box–Behnken experimental design and Response Surface Methodology (RSM). Fifteen experimental runs, including three center-point replicates, were performed to evaluate the combined effects of the operating parameters. Liquid flow rate, rotor rotational speed, and spraying height were selected as independent variables. The response variables included the characteristic droplet diameters (d₁₀, d₅₀ and d₉₀), the Span coefficient, and droplet deposition density (N). Quadratic regression models were fitted to the experimental data to explore the influence of the operating parameters on spray characteristics; however, statistical diagnostics indicated limited predictive capability, and the models were therefore used primarily for exploratory interpretation of response trends within the investigated design space. The experimental results indicated that rotor speed exhibited the strongest tendency to influence droplet-size characteristics within the investigated operating range, while increasing liquid flow rate was associated with larger droplet diameters, consistent with the expected effect of increased liquid-film thickness. Within the investigated atomizer configuration, relatively narrow droplet-size distributions were experimentally observed under selected operating conditions. These observations are consistent with the hypothesis that internal hydrodynamic flow conditioning may contribute to liquid-film destabilization and subsequent breakup. However, its independent contribution cannot be isolated from the present experiments because an otherwise identical baseline atomizer without the flow-conditioning element was not tested. Within the model-predicted favorable operating region (liquid flow rate of 1.0 × 10⁻⁶ m³·s⁻¹, rotor rotational speed of 4600–5100 min⁻¹, and spraying height of 30 cm), the fitted response-surface model predicted a volume median droplet diameter of approximately 64 μm. Separately, the minimum experimentally observed Span coefficient was approximately 0.58, indicating a relatively narrow deposited-droplet-size distribution within the investigated operating range. This model-predicted region was not independently verified by a dedicated confirmation experiment and therefore should not be interpreted as an experimentally validated optimum. The proposed physical interpretation considers hydrodynamic flow conditioning as a plausible additional mechanism contributing to spray uniformity, although its quantitative validation requires dedicated flow diagnostics and CFD analysis. The obtained results characterize the spray behavior of the developed atomizer within the investigated operating domain and provide an experimental basis for future comparative studies aimed at quantifying the independent contribution of the internal flow-conditioning system. These findings provide experimental evidence supporting further investigation of this concept and may contribute to the development of rotary atomizers for precision agricultural spraying and other engineering applications requiring controlled droplet-size distributions. Full article

As China’s urbanization shifts toward quality-oriented development, urban regeneration increasingly prioritizes the perceived quality of public spaces to enhance urban vitality and advance sustainable urban living. This study takes Zhengzhou’s Dongfeng Canal, a revitalized urban core waterfront, as a case to develop a human–machine collaborative analytical framework for exploring nonlinear relationships between visual environmental features and human spatial quality perception. By integrating 779 geolocated panoramic images with volunteers’ subjective rating data, this study adopts deep learning-based semantic segmentation to quantify eight objective visual indicators (e.g., greenness, color diversity, spatial structure). A random forest (RF) model links these indicators to three perceptual dimensions: scenic beauty, safety, and recreational value. Adopting explainable artificial intelligence (SHAP and PDPs), the results indicate that: (1) greenness is positively associated with positive perceptions but exhibits a significant threshold effect; (2) color diversity and waterfront accessibility substantially improve user experience, while excessive uniformity and extreme openness negatively affect perceived spatial quality. These findings challenge the simplistic linear “more-is-better” assumption in urban design and highlight the value of balanced, context-sensitive spatial interventions. This study provides evidence-based, segment-specific strategies for urban waterfront regeneration, advancing people-centered planning that integrates ecological functionality, social inclusivity, and long-term sustainability via Geospatial Artificial Intelligence (GeoAI) and geospatial analytics. Full article

Vertical surface light sources, widely applied in public spaces, easily trigger discomfort glare due to direct visual exposure. As a core lighting parameter, background luminance ($L_b$) strongly regulates glare perception, yet relevant research mainly focuses on single-variable analysis for horizontal lighting. The mechanisms through which $L_b$ influences discomfort glare in the presence of vertical surface light sources remain insufficiently understood. This study takes $L_b$, and vertical light source luminance ($L_{sv}$)-induced luminance contrast ($L_{contrast}$) as core variables, and combines subjective glare assessment and pupil diameter monitoring to explore their independent and coupled effects on vertical glare perception and visual adaptation. The results indicate that $L_{contrast}$, $L_b$, and their interaction all exert significant effects on subjective glare perception. The interaction effect suggests that the glare induced by one factor intensifies as the level of the other factor increases. In addition, the luminance of vertical light sources influences visual adaptation levels. Vertical illuminance at the eye ($E_v$) shows a stronger association with subjective glare responses under the present experimental conditions, supporting its potential as a saturation-related indicator for vertical surface light sources. Among the variables examined, $L_{contrast}$ exerts the strongest influence on discomfort glare. Furthermore, the pupil diameter change rating (PDCR) shows higher sensitivity to subtle visual stress under low $L_b$ conditions. These findings provide preliminary support for refining discomfort glare evaluation of vertical surface light sources and inform future research on their application and design across diverse lighting environments. Full article