Search Results (67)

As the complexity, scale, and nonlinearity of modern engineering optimization problems continue to increase, traditional optimization algorithms face significant challenges in achieving high solution accuracy, fast convergence, and robust performance. To address these issues, this paper proposes a Rural Tourism Migration-based Improved Equilibrium Optimizer (RTM-IEO), aiming to enhance the global search capability and adaptive balance between exploration and exploitation. Specifically, an adaptive lens imaging opposition-based learning strategy is introduced to effectively expand the search space and maintain population diversity. A dynamic elite-guided elimination mechanism is designed to strengthen exploitation capability and accelerate convergence by reconstructing inferior individuals using high-quality solutions. In addition, a multi-stage rural tourism migration strategy is developed to dynamically regulate the search behavior across different optimization phases, enabling a more flexible and efficient search process. The effectiveness of the proposed algorithm is comprehensively validated on the CEC2021 and CEC2022 benchmark suites, where RTM-IEO demonstrates superior performance in terms of convergence accuracy, convergence speed, and robustness compared with several representative state-of-the-art algorithms. The statistical superiority of the proposed method is further confirmed through Friedman mean ranking and Wilcoxon rank-sum tests. To further evaluate its practical applicability, RTM-IEO is applied to the sustainable economic dispatch problem of a microgrid integrating renewable energy sources, including wind power and photovoltaic generation, along with energy storage systems and controllable units. The optimization objective simultaneously considers economic cost minimization and sustainable operation requirements, such as improving renewable energy utilization and reducing dependence on fossil-fuel-based generation. Experimental results indicate that the proposed method achieves a significant reduction in daily operating cost (exceeding 52% compared with benchmark algorithms), while effectively promoting low-carbon energy utilization and enhancing overall system sustainability. Overall, the proposed RTM-IEO provides an efficient and reliable optimization framework for addressing complex global optimization problems, particularly in scenarios requiring a coordinated balance between economic performance and sustainable development. Full article

Accurate and robust detection of leaf diseases is a key enabler for precision agriculture and large-scale crop health monitoring. Despite the strong generalization of modern one-stage detectors (e.g., YOLOv8), two domain-specific challenges remain: (i) weak or blurry lesion boundaries hinder precise localization, and (ii) low color contrast between diseased and healthy tissues forces models to rely on subtle texture patterns rather than salient shapes. To tackle these challenges, we reframe the core agricultural disease detection task as the identification of “asymmetric morphological anomalies” and propose a domain-tailored enhancement framework. First, we introduce an Edge Enhancement Module (EEM) that explicitly strengthens boundary-aware representations. Inspired by the natural symmetry of healthy leaves, our EEM is specifically designed to capture symmetry-breaking boundary discontinuities and localized asymmetric edges caused by disease lesions. Our method enhances edge and texture cues that are indicative of disease lesions, which often exhibit local asymmetries and boundary discontinuities. The EEM includes a Differential Normalized Pooling Block (DNPB) that highlights edge responses through discrepancies between max pooling and average pooling, which also models cross-group edge correlations. Second, the Lightweight Texture-Sensitive Feature Enhancement (LTSFE) mechanism amplifies texture-discriminative channels under low-contrast conditions by leveraging complementary global statistics and efficient channel mixing, all with negligible computational overhead. We evaluated our method on a self-constructed dataset of 106,434 images with 225,640 annotations covering diverse crops. Experiments show that the proposed method achieves state-of-the-art accuracy (81.54% mAP@0.5:0.95) while maintaining real-time inference (142 FPS), consistently outperforming strong baselines. Ablations confirm the effectiveness and complementarity of EEM and LTSFE, demonstrating that domain-specific architectural design, inspired by biological symmetry, can substantially improve agricultural vision systems. Full article

Tea bud detection is a fundamental prerequisite for accurate tea yield estimation and intelligent mechanical harvesting. However, existing detection methods face several critical challenges, including ineffective extraction of multi-scale features, weak feature saliency for small tea bud targets, and the prevalent imaging issue in which the central regions of tea images are in focus while peripheral areas suffer from defocus blur. These factors collectively result in a high rate of missed detections, severely limiting detection accuracy and subsequent application performance. To overcome these technical bottlenecks, this paper proposes a novel tea bud detection framework, termed REB-Tea, which integrates image clarity optimization with multi-scale feature enhancement. First, the Restormer image restoration network is employed to improve overall image clarity and enhance the discriminative representation of tea bud features. Subsequently, a bidirectional feature pyramid network (BiFPN) structure and an efficient multi-scale attention (EMA) mechanism are incorporated into the neck of the YOLOv5 model to strengthen multi-scale feature fusion and guide the network to focus on fine-grained tea bud features across different scales, thereby improving detection performance for small and densely distributed targets. Experimental results based on 10-fold cross-validation demonstrate that the proposed REB-Tea model achieves an average mAP₅₀ of 95.5% on the Longjing 43 tea test set, representing a 9.9 percentage point improvement over the baseline YOLOv5 model, and Welch’s independent two-sample t-test verifies that this accuracy increment is highly statistically significant. Moreover, the model exhibits reliable detection performance across different tea varieties, including Cuifeng and Fuding White Tea. Specifically, the mAP₅₀ reaches 88.3% on Cuifeng, which shares similar appearance characteristics with Longjing, and 78.1% on Fuding White Tea, which has noticeably different appearance characteristics from Longjing. These results confirm the effectiveness of the REB-Tea framework in addressing challenges such as out-of-focus blurring, weak feature saliency, and multi-scale feature extraction. Overall, the proposed approach significantly enhances tea bud detection accuracy in natural environments and provides robust technical support for intelligent tea harvesting applications. Full article

Introduction: Patients are increasingly aware of ways to manage their own health—especially regarding chronic diseases—along with the fundamental factors that should be present in well-organized and patient-oriented healthcare organizations. Due to the fact that the image of healthcare organizations depends on patients’ opinions, healthcare organizations are continuously improving and transforming their processes to increase patient satisfaction. This study aimed to analyze the relationship between patients’ opinions about the public hospitals in which they were treated and selected factors, including socio-demographic characteristics, previous hospital experiences, sources of information, and satisfaction with hospitalization in Poland. Methods: A cross-sectional survey was conducted among patients hospitalized in eight public hospitals in Wrocław. A self-developed questionnaire included two sections: (I) opinions about the hospital (11 items) and (II) expectations and satisfaction (12 items). Questionnaires were distributed in person. Data were analyzed using descriptive and inferential statistics, including correlation and chi-square tests. Results: Hospital image was shaped mainly by interpersonal factors, particularly staff kindness (82.9%), access to specialists (75.4%), and a sense of safety (54.4%). Women were more likely than men to seek information about hospitals before admission (47.6% vs. 39.3%; p = 0.021). A positive correlation was found between patient expectations and satisfaction with hospitalization (ρ = 0.425; p < 0.001). Media exposure played a minor role in shaping hospital image (22.1%), while personal recommendations and previous experience were the dominant sources of influence. Conclusions: Patients’ assessments of hospital image are determined primarily by relational and communication factors rather than infrastructural or technical aspects. Sociodemographic characteristics, such as gender and previous contact with the institution, may moderate these perceptions. The findings highlight the need to strengthen patient-centered care models, improve communication competencies among health professionals, and develop transparent institutional communication strategies. Full article

This study aims to explore the role of digital public relations in enhancing the corporate image of educational institutions by focusing on Bayan College in the Sultanate of Oman. The study is based on a central question regarding the effectiveness of social media platforms in improving the institution’s image among its audience, particularly students. To achieve its objectives, the study employed the descriptive and analytical method using a questionnaire tool, with a sample of 662 students from various academic disciplines at the college. The results showed that Instagram was the most widely used social media platform and that digital public relations played an effective role in strengthening the college’s image. The findings also indicated no statistically significant differences attributable to gender or academic specialization, while differences were found based on academic year. The study recommends adopting effective digital communication strategies and enhancing the use of social platforms to build a positive and sustainable institutional image. Full article

Although the Love Evolution Algorithm (LEA) has achieved encouraging results in optimization tasks, several shortcomings still limit its effectiveness when solving high-dimensional multimodal problems. In particular, the fixed interaction threshold, stochastic reflection mechanism, and convergence-biased role evolution process may weaken population diversity and reduce the coordination between exploration and exploitation during evolution. To overcome these issues, this paper develops a Multi-Strategy Improved Love Evolution Algorithm (MILEA) under a phase-oriented cooperative evolutionary framework. First, a diversity-enhanced reflection mechanism is incorporated to enlarge the search region and dynamically regulate evolutionary dispersion during the early search stage. Second, an adaptive acceptance threshold strategy is introduced to adjust pairwise interaction behaviors according to the evolutionary state, thereby improving search flexibility and adaptability. Third, an elite-guided role evolution mechanism is designed to strengthen local exploitation and guide the population toward promising regions more efficiently. Furthermore, a probability-based collaborative update scheme is employed to coordinate multiple search behaviors adaptively while preserving the same computational complexity order as the original LEA framework. To evaluate the effectiveness of the proposed algorithm, extensive experiments are conducted on the CEC2017 and CEC2022 benchmark suites. The experimental results indicate that MILEA exhibits competitive optimization performance with respect to convergence behavior, solution accuracy, and optimization stability when compared with several advanced metaheuristic algorithms. Relative to the original LEA, the proposed method obtains improved average fitness values on most benchmark functions and significantly suppresses result fluctuations on several multimodal and hybrid optimization problems, indicating enhanced robustness during repeated independent runs. In addition, statistical evaluations based on the Wilcoxon signed-rank test and Friedman ranking analysis further support the reliability of the proposed optimization framework. To verify its practical applicability, MILEA is also applied to Otsu-based multi-threshold image segmentation tasks. Experimental results evaluated by PSNR, SSIM, and FSIM demonstrate that the proposed algorithm can generate high-quality segmentation results and preserve important structural image information. Overall, the proposed MILEA provides an effective optimization framework for both benchmark optimization and practical image segmentation applications. Full article

Background: Proximal lower-extremity muscle strengthening is an important conservative intervention for patellofemoral pain syndrome (PFPS), as these muscle groups play critical roles in femoral stabilization and knee valgus control. However, evidence remains limited regarding the effectiveness of muscle strengthening in improving lower-extremity axial alignment through modulation of femoral neck anteversion, femoral internal rotation, and tibial external rotation. Therefore, the present study aimed to determine whether a strengthening protocol targeting the quadriceps and hip external rotator and hip abductor muscles could improve knee alignment and reduce bone torsion in young adults with patellofemoral pain syndrome. Methods: This prospective interventional cohort study implemented a muscle strengthening protocol in ten university students with PFPS. Outcomes included femoral neck anteversion angle (FNA), tibial tubercle–trochlear groove distance (TT–TG), tibial external torsion angle (TET), and the knee Q-angle, assessed via 3D reconstruction of computed tomography (3D-CT) images. Pre- and post-intervention data were analyzed using the Shapiro-Wilk test for normality and repeated-measures ANOVA (p < 0.05; 95% confidence interval). Results: Muscle strengthening improved lower-limb axial alignment, with reductions observed across all measures post-intervention. Mean changes were 0.68 ± 1.26° for FNA (p = 0.0626); 1.51 ± 0.97 mm for TT–TG (p = 0.0001); 1.38 ± 3.36° for TET (p = 0.2231); and 1.14 ± 1.52° for the Q-angle. Statistically significant improvements were observed for TT–TG and the Q-angle. Conclusions: Proximal muscle strengthening improved knee valgus and axial lower-limb alignment, as evidenced by significant reductions in Q angle and TT–TG distance. Reductions in femoral neck anteversion (FNA) and tibial external torsion angle (TET) were observed. However, these differences were not statistically significant. These findings support muscle strengthening as a noninvasive strategy for improving lower-limb alignment in individuals with patellofemoral pain syndrome. Full article

Gastronomic festivals play an important role in the development of tourist destinations by strengthening destination image, competitiveness, and visitor loyalty. This study examines how the perceived quality of the gastronomic festival Belmužijada influences visitor satisfaction, behavioral intentions (recommendation and revisit intentions), and the destination image of Svrljig. The research is based on a quantitative approach using a standardized questionnaire. The collected data were analyzed in SPSS through descriptive statistics, a one-sample t-test, Pearson correlation, and regression analyses. The reliability of the measurement scales was confirmed using Cronbach’s alpha coefficient. The results indicate that visitors perceive Belmužijada as an authentic gastronomic experience that contributes to the preservation of local tradition and culture. The perceived quality of the gastronomic offer and festival organization has a statistically significant positive effect on visitor satisfaction, which further influences their willingness to recommend the festival. In addition, the perceived positive impact of the festival on destination image significantly affects revisit intention. The findings highlight the importance of gastronomic festivals in shaping destination image and fostering visitor loyalty, particularly in rural and less developed tourism areas. Full article

With the rapid development of digital technologies, augmented reality (AR) has created new possibilities for the presentation and dissemination of cultural heritage. However, conventional digital guide systems in historic districts are typically dominated by static information delivery, lacking interactivity and user engagement, which limits their effectiveness in enhancing public understanding of historic architectural environments and related cultural knowledge. To address this limitation, this study focuses on historic architectural districts and proposes a narrative-based AR cultural exploration approach embedded in real architectural space. The Hubu Mountain historic architectural district in Xuzhou, China, was selected as the case study. First, grounded theory was employed to systematically analyze the cultural resources of the district and extract key cultural narrative elements. Based on these elements, a design framework for a narrative AR cultural exploration system was constructed. Subsequently, a mobile AR interactive system was developed using the Unity 2022.3 LTS and Vuforia Engine 10. A total of 80 participants were recruited and randomly assigned to either an experimental or a control group. Cultural knowledge tests, an immersive experience scale, and a dissemination intention scale were used to evaluate the outcomes, and the collected data were analyzed statistically. The results indicate that, compared with a conventional text–image guide condition, the narrative AR exploration condition significantly improved participants’ cultural cognition and dissemination intention. Specifically, the experimental group achieved significantly higher post-test scores in cultural knowledge than the control group, and a significant between-group difference was also observed in dissemination intention. In terms of immersive experience, although the experimental group reported higher mean scores than the control group, the difference did not reach statistical significance, showing only a possible improving trend. These findings suggest that an integrated narrative AR cultural exploration condition can enhance public understanding of historic architectural districts and strengthen the communication potential of heritage experiences in real built environments. This study provides a digital interpretation approach for historic architectural districts and offers empirical support for the use of AR-based interactive systems in architectural heritage communication and public engagement. Full article

Accurate cloud and cloud shadow segmentation is a critical prerequisite for remote sensing image preprocessing. However, this task remains challenging due to the directional continuity of projected cloud shadows, the radiometric ambiguity between low-reflectance shadows and other dark surfaces, and the difficulty of preserving semantic consistency and fine boundaries in complex scenes. To address these issues, this paper proposes a Directional Statistical Fusion Network (DSFNet) based on an enhanced DeepLabV3+ architecture. Specifically, a Directional Scale Refinement Module (DSRM) is introduced in parallel with Atrous Spatial Pyramid Pooling to strengthen the representation of direction-sensitive cloud-shadow structures and multi-scale cloud regions. An Adaptive Statistical Context Attention (ASCA) module is further designed to perform robust feature modulation by jointly exploiting global statistics, edge-aware statistics, and median-based normalization, thereby suppressing anomalous responses under heterogeneous backgrounds. In the decoder, an Adaptive Grouped Multi-scale Fusion (AGMF) module is employed to adaptively fuse shallow detail features and high-level semantic features through discrepancy-guided grouped gating, improving structural consistency and boundary recovery. In addition, a hybrid loss is adopted to further optimize segmentation. Experiments on the GF1_WHU dataset show that DSFNet achieves 76.97% mIoU, demonstrating strong effectiveness and robustness in complex remote sensing scenes. Full article

Measles remains one of the most contagious infectious diseases globally and continues to pose substantial public health risks despite decades of effective vaccination. This narrative review examines both classical and contemporary computational approaches used for measles monitoring, prediction, and control, with particular attention given to the emerging role of artificial intelligence (AI). We synthesized findings from 46 studies; 31 focused directly on measles and 15 on methodologically relevant studies from related infectious diseases (COVID-19, influenza, malaria), selected through searches of PubMed, Scopus, Web of Science, IEEE Xplore, and preprint servers, conducted between June and December 2025. Traditional compartmental models (SIR, SEIR, MSEIR), statistical tools (ARIMA, SARIMA), and seroepidemiological analysis provide transparent, well-characterized frameworks for estimating transmission dynamics and simulating intervention scenarios. Spatial modeling, network analysis, and Monte Carlo simulations have added geographic granularity to outbreak characterization. More recently, AI and machine learning (ML) methods, including supervised algorithms (Random Forest, XGBoost, SVM), deep learning architectures (CNN, LSTM), and hybrid mechanistic ML models, have shown improved predictive performance by integrating multiple data sources: epidemiological records, demographic profiles, mobility patterns, and behavioral indicators. AI-based approaches appear most valuable for high-dimensional risk prediction and image-based diagnostic tasks, while classical models retain clear advantages for policy-oriented scenario analysis. However, no AI-based or hybrid model identified in this review has been adopted into routine national measles surveillance or used for vaccination policy decisions at scale. Important challenges remain: data quality varies across settings, model generalizability cannot be assumed, and computational infrastructure disparities limit deployment in high-burden regions. Explainable AI, federated learning, workforce training for model interpretation, and integration of vaccination registries with mobility and genomic surveillance data represent concrete future directions for strengthening computational support for measles elimination. Full article

Background/Objectives: Sex estimation from craniofacial morphology is a fundamental component of biological profile construction in forensic anthropology. Population-specific reference data for Thai individuals derived from computed tomography (CT) remain limited, and direct comparisons between discriminant function analysis (DFA) and machine learning classifiers are frequently complicated by inconsistent validation protocols. This study aimed to characterize sexual dimorphism in CT-derived craniofacial measurements, compare the classification performance of DFA, support vector machine (SVM), and random forest (RF) under a unified validation protocol, and demonstrate their practical application in a forensic context. Methods: CT images from 300 Thai adults (150 males, 150 females; age range 20–90 years) were obtained from Srinagarind Hospital, Khon Kaen University. Eight linear craniofacial measurements spanning the cranial vault, facial skeleton, nasal aperture, and orbital region were obtained from each case. DFA, SVM, and RF were developed and compared under a unified leave-one-out cross-validation protocol. Classification performance was assessed using accuracy, AUC, and Matthews correlation coefficient (MCC). Results: Seven of eight measurements exhibited statistically significant sexual dimorphism, with facial breadth and nasal height demonstrating the greatest dimorphism. DFA achieved the highest classification accuracy of 85.7%, AUC of 0.924, and MCC of 0.713, incorporating five measurements into the canonical function. SVM and RF achieved comparable accuracy of 84.7% and 84.0%, respectively. All three classifiers correctly classified both forensic application cases with high confidence. Conclusions: CT-derived craniofacial measurements provide a reliable basis for sex estimation in Thai adults. The convergence of performance across all three classifiers under a unified internal validation protocol strengthens confidence in the internally validated performance estimates. The derived discriminant function equation and saved machine learning models constitute a complementary and immediately applicable toolkit for CT-based forensic sex estimation in the Thai population. Full article

Pig behavior statistics can reflect their health status. Conventional approaches depend on manual observation to derive behavioral information from video recordings, a process that demands substantial time and human effort. To overcome these limitations in indoor intensive farming environments, this study introduces an effective approach for recognizing pig behaviors, employing an enhanced YOLOv8n architecture. The approach utilizes advanced object detection algorithms to automatically identify pig behaviors, including stand, lie, eat, fight, and tail-bite, from overhead video footage of the enclosure. First, images of daily pig behaviors are collected using cameras to build a pig behavior dataset. To boost detection accuracy, the SE attention mechanism is embedded within the feature extraction backbone of the YOLOv8n network to enhance its representational capacity, strengthening the model’s capacity to grasp overarching contextual information and improve the expressiveness of extracted features. The GIoU loss function is employed during training to reduce computational cost and accelerate model convergence. Moreover, integrating Ghost convolution into the backbone significantly reduces both computational complexity and the total number of parameters. The experimental findings reveal that the optimized YOLOv8n model contains just 1.71 million parameters, marking a 42.93% reduction relative to the baseline model. Its floating-point operations total 5.0 billion, indicating a 38.27% decrease, while the mean average precision (mAP@50) reaches 96.8%, surpassing the original by 2.6 percentage points. Compared with other widely used YOLO-based object detection frameworks, the proposed approach achieves notably higher accuracy while requiring significantly lower computational resources and model complexity. Full article

Rapid agricultural expansion threatens water security in one of the world’s largest hydroelectric systems, the Itaipu dam, located on the Brazil–Paraguay border. Yet regional hydrological responses to land cover change and climate variability remain insufficiently characterized at management-relevant scales. The Upper Paraná River Basin (UPRB), which sustains agriculture, hydropower, and municipal water supply across both countries, exemplifies this challenge as accelerating cropland conversion raises concerns about long-term water availability. This study investigates hydrological transitions and their statistical associations with land cover changes in the Itaipu study region from 2002 to 2023. We integrate GRACE/GRACE-FO (Gravity Recovery and Climate Experiment Follow-On), Terrestrial Water Storage Anomalies (TWSAs), MODIS (Moderate Resolution Imaging Spectroradiometer) land cover, CHIRPS (Climate Hazards Group InfraRed Precipitation with Station data) precipitation, and LandScan population density using Pettitt’s breakpoint test and Mann–Kendall trend analysis to detect temporal breakpoints and quantify co-variability between hydrology and land surface dynamics. Together, these methods identify a significant basin-wide shift in TWSAs in mid-2009, with storage increases of 151.6 cm at Itaipu and 103.1 cm at Yguazú Reservoir. Over the study period, cropland expanded from 13.5% to 37.9% of total land cover, while savanna declined from 28.1% to 24.2%. After 2009, correlations between land cover and TWSAs strengthened substantially, particularly for wetlands (r = 0.88), croplands (r = 0.73), and savannas (r = −0.81; all p < 0.001), indicating strong coupling between landscape transformation and basin-scale storage variability. Principal Component Analysis shows land use change explains 39–41% of TWSA variance, exceeding hydroclimatic contributions. Granger causality analysis reveals bidirectional coupling between wetlands and water storage at Itaipu, while cropland and savanna dynamics exert predictive influence on downstream hydrology in the Yguazú basin. Water balance decomposition further indicates a post-2009 regime shift, with residual storage transitioning from −10.6 to +4.7 and 78% greater runoff generation per unit precipitation, consistent with reduced infiltration capacity. Together, these findings underscore intensifying land–water feedback and the need for adaptive watershed management under expanding agriculture and climate variability. Full article

In public safety scenarios, the precise detection and positioning of prohibited weapons such as firearms and knives along with the involved personnel are the core pre-requisite technologies for violent risk warning and emergency response. However, in security surveillance scenarios, there are common problems such as object occlusion, difficulty in capturing small-sized weapons, and complex background interference, which lead to the shortcomings of existing general object detection models in the tasks of detecting and locating security-related objects, including poor adaptability, low detection accuracy, and insufficient robustness in complex scenarios. Therefore, this paper proposes a threat object detection framework for security scenarios (PDGV-DETR) based on adaptive dynamic convolution and cross-scale semantic fusion, specifically optimized for the detection and positioning tasks of weapons and personnel objects in static security surveillance images. This research focuses on category recognition at the object level and pixel-level spatial positioning, and does not involve the classification and identification of violent behaviors based on temporal information. There are clear technical boundaries and scene limitations between the two. This framework is optimized through three core modules: designing a dynamic hierarchical channel interaction convolution module to reduce computational complexity while enhancing the ability to detect occluded and incomplete objects; constructing an improved bidirectional hybrid feature pyramid network, combining the cross-scale fusion module to strengthen multi-scale feature expression, and adapting to the simultaneous detection requirements of small weapon objects and large personnel objects; and introducing a global semantic weaving and elastic feature alignment network to solve the problem of low discrimination between objects and complex backgrounds. Under the same experimental configuration, the proposed model is verified against current mainstream models on typical datasets: on a dataset of 2421 conflict scene personnel violent images, the peak average precision mAP50 of PDGV-DETR reached 85.9%. Through statistical verification, compared with the baseline model RT-DETR with an average value ± standard deviation of 0.840 ± 0.007, the average value ± standard deviation of PDGV-DETR reached 0.858 ± 0.004, demonstrating statistically significant performance improvement, with a p-value less than 0.01. This model can accurately complete the task of locating the object area of personnel, and compared with the deformable DETR, the accuracy improvement rate reached 15.1%.; on the weapon-specific dataset OD-WeaponDetection, the mAP for gun and knife detection reached 93.0%, improving by 2.2% compared to RT-DETR. Compared to the performance fluctuations of other general object detection models in complex security scenarios, PDGV-DETR not only has better detection and positioning accuracy for security-related objects, but also significantly improves the generalization and stability of the model. The results show that PDGV-DETR effectively balances the accuracy of positioning, detection, and computational efficiency, accurately completing end-to-end detection and positioning of weapon and personnel objects in static security surveillance images, demonstrating highly competitive performance in the detection and positioning of security-related objects in security scenes, providing core object-level pre-processing technology support for scenarios such as public area monitoring, intelligent video monitoring, and early warning of violent risks, and providing basic data for subsequent violent behavior recognition based on temporal data. Full article