Search Results (2,118)

Mean Shift is a flexible, non-parametric clustering algorithm that identifies dense regions in data through gradient ascent on a kernel density estimate. Its ability to detect arbitrarily shaped clusters without requiring prior knowledge of the number of clusters makes it widely applicable across diverse domains. However, its quadratic computational complexity restricts its use on large or high-dimensional datasets. Numerous acceleration techniques, collectively referred to as Fast Mean Shift strategies, have been developed to address this limitation while preserving clustering quality. This paper presents a systematic theoretical analysis of these strategies, focusing on their computational impact, pairwise combinability, and mapping onto distinct stages of the Mean Shift pipeline. Acceleration methods are categorized into seed reduction, neighborhood search acceleration, adaptive bandwidth selection, kernel approximation, and parallelization, with their algorithmic roles examined in detail. A pairwise compatibility matrix is proposed to characterize synergistic and conflicting interactions among strategies. Building on this analysis, we introduce a decision framework for selecting suitable acceleration strategies based on dataset characteristics and computational constraints. This framework, together with the taxonomy, combinability analysis, and scenario-based recommendations, establishes a rigorous foundation for understanding and systematically applying Fast Mean Shift methods. Full article

Mesoscale convective systems (MCSs) play a pivotal role in the occurrence of severe weather phenomena, with convective cells constituting their fundamental elements. The precise identification of these cells from satellite imagery is crucial yet presents significant challenges, including issues related to merging errors and sensitivity to threshold parameters. This study introduces a novel detection algorithm for convective cells that leverages H-maxima transformation and incorporates multichannel data from the FY-2F satellite. The proposed method utilizes H-maxima transformation to identify seed points while maintaining the integrity of core structural features, followed by a novel neighborhood labeling method, region growing and adaptive merging criteria to effectively differentiate adjacent convective cells. The neighborhood labeling method improves the accuracy of seed clustering and avoids “over-clustering” or “under-clustering” issues of traditional neighborhood criteria. When compared to established methods such as RDT, ETITAN, and SA, the algorithm demonstrates superior performance, attaining a Probability of Detection (POD) of 0.87, a False Alarm Ratio (FAR) of 0.21, and a Critical Success Index (CSI) of 0.71. These results underscore the algorithm’s efficacy in elucidating the internal structures of convective complexes and mitigating false merging errors. Full article

Building clustering is a key challenge in cartographic generalization, where the goal is to group spatially related buildings into semantically coherent clusters while preserving the true distribution patterns of urban structures. Existing methods often rely on either spatial distance or building feature similarity alone, leading to clusters that sacrifice either accuracy or spatial continuity. Moreover, most deep learning-based approaches, including graph attention networks (GATs), fail to explicitly incorporate spatial distance constraints and typically restrict message passing to first-order neighborhoods, limiting their ability to capture long-range structural dependencies. To address these issues, this paper proposes LA-GATs, a multi-feature constrained and spatially adaptive building clustering network. First, a Delaunay triangulation is constructed based on nearest-neighbor distances to represent spatial topology, and a heterogeneous feature matrix is built by integrating architectural spatial features, including compactness, orientation, color, and height. Then, a spatial distance-constrained attention mechanism is designed, where attention weights are adjusted using a distance decay function to enhance local spatial correlation. A second-order neighborhood aggregation strategy is further introduced to extend message propagation and mitigate the impact of triangulation errors. Finally, spectral clustering is performed on the learned similarity matrix. Comprehensive experimental validation on real-world datasets from Xi’an and Beijing, showing that LA-GATs outperforms existing clustering methods in both compactness, silhouette coefficient and adjusted rand index, with up to about 21% improvement in residential clustering accuracy. Full article

Multispectral LiDAR point clouds, which integrate both geometric and spectral information, offer rich semantic content for scene understanding. However, due to data scarcity and distributional discrepancies, existing methods often struggle to balance accuracy and efficiency in complex urban environments. To address these challenges, we propose DA-GSGTNet, a novel segmentation framework that integrates Gated Stratified Graph Transformer Blocks (GSGT-Block) with Dynamic Aggregation Transition Down (DATD). The GSGT-Block employs graph convolutions to enhance the local continuity of windowed attention in sparse neighborhoods and adaptively fuses these features via a gating mechanism. The DATD module dynamically adjusts k-NN strides based on point density, while jointly aggregating coordinates and feature vectors to preserve structural integrity during downsampling. Additionally, we introduce a relative position encoding scheme using quantized lookup tables with a Euclidean distance bias to improve recognition of elongated and underrepresented classes. Experimental results on a benchmark multispectral point cloud dataset demonstrate that DA-GSGTNet achieves 86.43% mIoU, 93.74% mAcc, and 90.78% OA, outperforming current state-of-the-art methods. Moreover, by fine-tuning from source-domain pretrained weights and using only ~30% of the training samples (4 regions) and 30% of the training epochs (30 epochs), we achieve over 90% of the full-training segmentation accuracy (100 epochs). These results validate the effectiveness of transfer learning for rapid convergence and efficient adaptation in data-scarce scenarios, offering practical guidance for future multispectral LiDAR applications with limited annotation. Full article

Urban park green spaces (UPGSs) play a critical role in enhancing residents’ quality of life, particularly for older adults. However, inequities in accessibility and resource distribution remain persistent challenges in aging urban areas. To address this issue, this study takes Gulou District, Nanjing City, as an example and proposes a comprehensive framework to evaluate the overall quality of UPGSs. Furthermore, an enhanced Gaussian two-step floating catchment area (2SFCA) method is introduced that incorporates (1) a multidimensional park quality score derived from an objective evaluation system encompassing ecological conditions, service quality, age-friendly facilities, and basic infrastructure; and (2) a Gaussian distance decay function calibrated to reflect the walking and public transit mobility patterns of the older adults in the study area. The improved method calculates the accessibility values of UPGSs for older adults living in residential communities under the walking and public transportation scenarios. Finally, factors influencing the social equity of UPGSs are analyzed using Pearson correlation coefficients. The experimental results demonstrate that (1) high-accessibility service areas exhibit clustered distributions, with significant differences in accessibility levels across the transportation modes and clear spatial gradient disparities. Specifically, traditional residential neighborhoods often present accessibility blind spots under the walking scenario, accounting for 50.8%, which leads to insufficient accessibility to public green spaces. (2) Structural imbalance and inequities in public service provision have resulted in barriers to UPGS utilization for older adults in certain communities. On this basis, targeted improvement strategies based on accessibility characteristics under different transportation modes are proposed, including the establishment of multi-tiered networked UPGSs and the upgrading of slow-moving transportation infrastructure. The research findings can enhance service efficiency through evidence-based spatial resource reallocation, offering actionable insights for optimizing the spatial layout of UPGSs and advancing the equitable distribution of public services in urban core areas. Full article

Small and medium-sized enterprises (SMEs) drive economic growth but face barriers in adopting AI for creative digital marketing, particularly in underserved U.S. markets. This study investigates an AI-driven unified advisory platform to enable strategic digital marketing in these communities. Integrating modules such as MarketRadar (customer insights, benchmarking) with StrategicCoaching and ComplianceTools, it supports data-driven campaign design, pricing, and engagement. Using mixed methods, we interviewed 13 SME owners/managers in Houston’s underserved neighborhoods and surveyed 172 platform users across three U.S. states. Results show that SMEs using multiple modules achieved higher customer acquisition and revenue than standalone users, with qualitative insights revealing creative repositioning and refinement despite limited budgets. Trust elements like PeerBenchmarks and ComplianceAlerts boosted uptake. Our study advances digital marketing literature by evidencing how AI platforms and cross-module collaboration catalyze innovation, decision-making, and sustainable growth in U.S. contexts, with caution for broader extrapolation. It offers recommendations for policymakers and SaaS providers on inclusive transformation in resource-constrained settings. Full article

Aiming at the problems of high complexity in source domain data, inaccessibility of target domain data, and unknown fault patterns in real-world industrial scenarios for mechanical fault diagnosis, this paper proposes a Feature Decomposition-based Source-Free Universal Domain Adaptation (FD-SFUniDA) framework for mechanical equipment fault diagnosis. First, the CBAM attention module is incorporated to enhance the ResNet-50 convolutional network for extracting feature information from source domain data. During the target domain adaptation phase, singular value decomposition is applied to the weights of the pre-trained model’s classification layer, orthogonally decoupling the feature space into a source-known subspace and a target-private subspace. Then, based on the magnitude of feature projections, a dynamic decision boundary is constructed and combined with an entropy threshold mechanism to accurately distinguish between known and unknown class samples. Furthermore, intra-class feature consistency is strengthened through neighborhood-expanded contrastive learning, and semantic weight calibration is employed to reconstruct the feature space, thereby suppressing the negative transfer effect. Finally, extensive experiments under multiple operating conditions on rolling bearing and reciprocating mechanism datasets demonstrate that the proposed method excels in addressing source-free fault diagnosis problems for mechanical equipment and shows promising potential for practical engineering applications in fault classification tasks. Full article

Objectives: Prevention of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and the disease COVID-19 is a public health priority. The efficacy of non-pharmaceutical interventions such as wearing face masks to prevent SARS-CoV-2 infection has been well established in controlled settings. However, evidence for the effectiveness of face masks in preventing SARS-CoV-2 transmission within real-world settings is limited and mixed. The present systematic review evaluated the effectiveness of face mask policies and mask wearing to prevent SARS-CoV-2 transmission and COVID-19 in real-world settings. Methods: Following PRISMA guidelines, scientific databases, and gray literature, were searched through June 2023. Inclusion criteria were as follows: (1) studies/reports written in or translated to English; (2) prospectively assessed incidence of SARS-CoV-2 or COVID-19; (3) assessed the behavior and/or policy of mask-wearing; and (4) conducted in community/public settings (i.e., not laboratory). Studies were excluded if they did not parse out data specific to the effect of mask wearing (behavior and/or policy) and subsequent SARS-CoV-2 transmission or COVID-19 disease or if they relied solely on statistical models to estimate the effects of mask wearing on transmission. A total of 2616 studies were initially identified, and 470 met inclusion and exclusion criteria for full-text review. The vote counting method was used to evaluate effectiveness, and risk of bias was assessed using JBI critical appraisal tools. Results: A total of 79 unique studies met the final inclusion criteria, and their data were abstracted and evaluated. Study settings included community/neighborhood settings (n = 34, 43%), healthcare settings (n = 30, 38%), and school/universities (n = 15, 19%). A majority of studies (n = 61, 77%) provided evidence to support the effectiveness of wearing face masks and/or face mask policies to reduce the transmission of SARS-CoV-2 and/or prevention of COVID-19. Effectiveness of mask wearing did not vary substantially by study design (67–100%), type of mask (77–100%), or setting (80–91%), while 85% of masking policies specifically reported a benefit. Conclusions: This systematic literature review supports public health recommendations and policies that encourage the public to wear face masks to reduce the risk of SARS-CoV-2 infection and COVID-19 in multiple real-world settings. Effective communication strategies are needed to encourage and support the use of face masks by the general public, particularly during peak infection cycles. Full article

Several studies have reported methods for signal similarity measurement. However, none of the reported methods consider temporal peak-shape features. In this paper, we formalize signal similarity using mathematical concepts and define a new distance function between signals that considers temporal peak-shape characteristics, providing higher precision than current similarity measurements. This distance function addresses latent geometric characteristics in quotient spaces that are not addressed by existing methods. We include an example of using this method on discrete MEG recordings, known for their high spatial and temporal resolution, which were recorded in neighborhoods of extreme points in a cross-area projection of brain activity. Full article

The flexible job shop scheduling problem (FJSP) becomes significantly more complex when real-world factors such as due dates, sequence-dependent setup times, and processing times are considered as multiple criteria. This study presents a hybrid scheduling approach that combines a genetic algorithm (GA) and variable neighborhood search (VNS), where several dispatching rules are used to create the initial population and improve exploration. The multiple objectives are to minimize makespan, total tardiness, and total setup time while improving overall production efficiency. To test the proposed approach, standard FJSP datasets were extended with due dates and setup times for two different environments. Due dates were generated using the Total Work Content (TWK) method. This study also introduces a dynamic scheduling framework that addresses dynamic events such as machine breakdowns and new job arrivals. A rescheduling strategy was developed to maintain optimal solutions in dynamic situations. Experimental results show that the proposed hybrid framework consistently performs better than other methods in static scheduling and maintains high performance under dynamic conditions. The proposed method achieved 6.5% and 2.59% improvement over the baseline GA in two different environments. The results confirm that the proposed strategies effectively address complex, multi-constraint scheduling problems relevant to Industry 4.0 and smart manufacturing environments. Full article

The sultanate of Oman has joined other nations in promoting sustainability, guided by Oman Vision 2040 and the Oman National Spatial Strategy. Oman now focuses on developing more human-centered cities, enhancing community well-being, boosting the local economy, and increasing investments. This study addresses a research gap by examining the social and economic impact of the sustainable neighborhood “Al-Mouj” on the nearby urban area “Al-Mawaleh North” to maximize sustainability benefits. It analyzes how a sustainable neighborhood influences the economy, society, quality of life, and overall well-being. The study also identifies key factors driving the growth of sustainable practices in society and the economy. It has four main objectives in terms of answering the research question, primarily through surveys of community members and business owners, and by analyzing land use development around Al-Mouj. Data collection methods include literature review, case study, questionnaires, and interviews. Data analysis employs spatial, statistical, and thematic techniques. Responses from 515 participants are examined to ensure reliable results. Ethnographic methods are used to gain insights from open-ended questionnaire responses and interviews. The results confirm that Al-Mouj’s mixed-use development and sustainability features positively influence mental and physical health and stimulate economic activity within the local community. This study provides decision-makers and urban planners valuable insights into sustainable neighborhoods’ social and economic impacts when developed as open communities. It highlights the challenges of following international NSAT standards, which do not fully address local concerns. Full article

Background: Cardiovascular disease (CVD) is the leading global cause of death and is shaped by interacting biological, environmental, lifestyle, and social factors. Traditional models often treat risk factors in isolation and may miss dependencies among exposures and biomarkers. Objective: To map interdependencies among environmental, social, behavioral, and biological predictors of CVD risk using Bayesian network models. Methods: A cross-sectional analysis was conducted using NHANES 2017–2018 data. After complete-case procedures, the analytic sample included 601 adults and 22 variables: outcomes (systolic/diastolic blood pressure, total/LDL/HDL cholesterol, triglycerides) and predictors (BMI, C-reactive protein (CRP), allostatic load, Dietary Inflammatory Index, income, education, age, gender, race, smoking, alcohol, and serum lead, cadmium, mercury, and PFOA). Spearman’s correlations summarized pairwise associations. Bayesian networks were learned with two approaches: Grow–Shrink (constraint-based) and Hill-Climbing (score-based, Bayesian Gaussian equivalent score). Network size metrics included number of nodes, directed edges, average neighborhood size, and Markov blanket size. Results: Correlation screening reproduced expected patterns, including very high systolic–diastolic concordance (p ≈ 1.00), strong LDL–total cholesterol correlation (p = 0.90), inverse HDL–triglycerides association, and positive BMI–CRP association. The final Hill-Climbing network contained 22 nodes and 44 directed edges, with an average neighborhood size of ~4 and an average Markov blanket size of ~6.1, indicating multiple indirect dependencies. Across both learning algorithms, BMI, CRP, and allostatic load emerged as central nodes. Environmental toxicants (lead, cadmium, mercury, PFOS, PFOA) showed connections to sociodemographic variables (income, education, race) and to inflammatory and lipid markers, suggesting patterned exposure linked to socioeconomic position. Diet and stress measures were positioned upstream of blood pressure and triglycerides in the score-based model, consistent with stress-inflammation–metabolic pathways. Agreement across algorithms on key hubs (BMI, CRP, allostatic load) supported network robustness for central structures. Conclusions: Bayesian network modeling identified interconnected pathways linking obesity, systemic inflammation, chronic stress, and environmental toxicant burden with cardiovascular risk indicators. Findings are consistent with the view that biological dysregulation is linked with CVD and environmental or social stresses. Full article

Community detection is a crucial technique for uncovering latent network structures, analyzing group behaviors, and understanding information dissemination pathways. Existing methods predominantly rely on static graph structural features, while neglecting the intrinsic dynamic patterns of information diffusion and nonlinear attenuation within static networks. To address these limitations, we propose DAMA, a community detection model that integrates dynamic propagation-aware feature modeling with adaptive multi-hop structural aggregation. First, an Information Flow Matrix (IFM) is constructed to quantify the nonlinear attenuation of information propagation between nodes, thereby enriching static structural representations with nonlinear propagation dynamics. Second, we propose an Adaptive Sparse Sampling Module that adaptively retains influential neighbors by applying multi-level propagation thresholds, improving structural denoising and preserving essential diffusion pathways. Finally, we design a Hierarchical Multi-Hop Aggregation Framework, which employs a dual-gating mechanism to adaptively integrate neighborhood representations across multiple hops. This approach enables more expressive structural embeddings by progressively combining local and extended topological information. Experimental results demonstrate that DAMA achieves better performance in community detection tasks across multiple real-world networks and LFR-generated synthetic networks. Full article

The secretary bird optimization algorithm is a recently developed swarm intelligence method with potential for solving nonlinear and complex optimization problems. However, its performance is constrained by limited global exploration and insufficient local exploitation. To address these issues, an enhanced variant, ORSBOA, is proposed by integrating an optimal neighborhood perturbation mechanism with a reverse learning strategy. The algorithm is evaluated on the CEC2019 and CEC2022 benchmark suites as well as four classical engineering design problems. Experimental results demonstrate that ORSBOA achieves faster convergence, stronger robustness, and higher solution quality than nine state-of-the-art algorithms. Statistical analyses further confirm the significance of these improvements, validating the effectiveness and applicability of ORSBOA in solving complex optimization tasks. Full article

As cities strive for human-centered and fine-tuned development, Agent-Based Modeling (ABM) has emerged as a powerful tool for simulating pedestrian behavior and optimizing walkable neighborhood design. This study presents a comparative bibliometric analysis of ABM applications in block-scale walkability research from 2015 to 2024, drawing on both Chinese- and English-language literature. Using visualization tools such as VOSviewer, the analysis reveals divergences in national trajectories, methodological approaches, and institutional logics. Chinese research demonstrates a policy-driven growth pattern, particularly following the introduction of the “15-Minute Community Life Circle” initiative, with an emphasis on neighborhood renewal, age-friendly design, and transit-oriented planning. In contrast, international studies show a steady output driven by technological innovation, integrating methods such as deep learning, semantic segmentation, and behavioral simulation to address climate resilience, equity, and mobility complexity. The study also classifies ABM applications into five key application domains, highlighting how Chinese and international studies differ in focus, data inputs, and implementation strategies. Despite these differences, both research streams recognize the value of ABM in transport planning, public health, and low-carbon urbanism. Key challenges identified include data scarcity, algorithmic limitations, and ethical concerns. The study concludes with future research directions, including multimodal data fusion, integration with extended reality, and the development of privacy-aware, cross-cultural modeling standards. These findings reinforce ABM’s potential as a smart urban simulation tool for advancing adaptive, human-centered, and sustainable neighborhood planning. Full article