Search Results (4,599)

Non-communicable diseases (NCDs) are the leading global cause of death, causing over 43 million deaths in 2021, including 18 million premature deaths, disproportionately affecting low- and middle-income countries. NCDs also incur significant economic losses, estimated at USD 7 trillion from 2011 to 2025, despite low prevention costs. This study evaluated body mapping indicators: body mass index (BMI), waist circumference, and waist-to-hip ratio—for predicting NCD risk, including hypertension, diabetes, and cardiovascular diseases, using data from a nationally representative survey in Ghana. The study sampled 5775 participants via multistage stratified sampling, ensuring proportional representation by region, urban/rural residency, age, and gender. Ethical approval and informed consent were obtained. Anthropometric and biochemical data, including height, weight, waist and hip circumferences, blood pressure, fasting glucose, and lipid profiles, were collected using standardized protocols. Data analysis was conducted with STATA 17.0, accounting for complex survey design. Significant sex-based differences were observed: men were taller and lighter, while women had higher BMI and waist/hip circumferences. NCD prevalence increased with age, peaking at 60–69 years, and was higher in females. Lower education and marital status (widowed, divorced, separated) correlated with higher NCD prevalence. Obesity and high waist circumference strongly predicted NCD risk, but individual anthropometric measures lacked screening accuracy. Integrated screening and tailored interventions are recommended for improved NCD detection and management in resource-limited settings. Full article

3D point cloud object tracking plays a critical role in fields such as autonomous driving and robotics, making the security of these models essential. Adversarial attacks are a key approach for studying the robustness and security of tracking models. However, research on the generalization of adversarial attacks for 3D point-cloud-tracking models is limited, and the frequency-domain information of the point cloud’s geometric structure is often overlooked. This frequency information is closely related to the generalization of 3D point-cloud-tracking models. To address these limitations, this paper proposes a novel adversarial method for 3D point cloud object tracking, utilizing frequency-domain attacks based on the importance of frequency bands. The attack operates in the frequency domain, targeting the low-frequency components of the point cloud within the search area. To make the attack more targeted, the paper introduces a frequency band importance saliency map, which reflects the significance of sub-frequency bands for tracking and uses this importance as attack weights to enhance the attack’s effectiveness. The proposed attack method was evaluated on mainstream 3D point-cloud-tracking models, and the adversarial examples generated from white-box attacks were transferred to other black-box tracking models. Experiments show that the proposed attack method reduces both the average success rate and precision of tracking, proving the effectiveness of the proposed adversarial attack. Furthermore, when the white-box adversarial samples were transferred to the black-box model, the tracking metrics also decreased, verifying the transferability of the attack method. Full article

Accurate diagnosis of sinusitis is essential due to its widespread prevalence and its considerable impact on patient quality of life. While multiple imaging techniques are available for detecting maxillary sinus, computed tomography (CT) remains the preferred modality because of its high sensitivity and spatial resolution. Although recent advances in deep learning have led to the development of automated methods for sinusitis classification, many existing models perform poorly in the presence of complex pathological features and offer limited interpretability, which hinders their integration into clinical workflows. In this study, we propose a hybrid deep learning framework that combines EfficientNetB0, a convolutional neural network, with the Swin Transformer, a vision transformer, to improve feature representation. An attention-based fusion module is used to integrate both local and global information, thereby enhancing diagnostic accuracy. To improve transparency and support clinical adoption, the model incorporates explainable artificial intelligence (XAI) techniques using Gradient-weighted Class Activation Mapping (Grad-CAM). This allows for visualization of the regions influencing the model’s predictions, helping radiologists assess the clinical relevance of the results. We evaluate the proposed method on a curated maxillary sinus CT dataset covering four diagnostic categories: Normal, Opacified, Polyposis, and Retention Cysts. The model achieves a classification accuracy of 95.83%, with precision, recall, and F1 score all at 95%. Grad-CAM visualizations indicate that the model consistently focuses on clinically significant regions of the sinus anatomy, supporting its potential utility as a reliable diagnostic aid in medical practice. Full article

Advances in sensor technology have significantly improved the efficiency and precision of agricultural spraying. Unmanned aerial vehicles (UAVs) are widely utilized for applying plant protection products (PPPs) and fertilizers, offering enhanced spatial control and operational flexibility. This study evaluated the performance of an autonomous UAV-based precision spraying system that applies variable rates based on zone levels defined in a prescription map. The system integrates real-time kinematic global navigation satellite system positioning with a proximity-triggered spray algorithm. Field experiments on a rice field were conducted to assess spray accuracy and fertilization efficacy with liquid fertilizer. Spray deposition patterns on water-sensitive paper showed that the graded strategy distinguished among zone levels, with the highest deposition in high-spray zones, moderate in medium zones, and minimal in no-spray zones. However, entry and exit deviations—used to measure system response delays—averaged 0.878 m and 0.955 m, respectively, indicating slight lags in spray activation and deactivation. Fertilization results showed that higher application levels significantly increased the grain-filling rate and thousand-grain weight (both p < 0.001), but had no significant effect on panicle number or grain count per panicle (p > 0.05). This suggests that increased fertilization primarily enhances grain development rather than overall plant structure. Overall, the system shows strong potential to optimize inputs and yields, though UAV path tracking errors and system response delays require further refinement to enhance spray uniformity and accuracy under real-world applications. Full article

Accurate preoperative staging of bladder cancer on MRI remains challenging because visual reads vary across observers. We investigated a multiparametric MRI (mpMRI) radiomics approach to predict muscle invasion (≥T2) and prospectively tested it on a validation cohort. Eighty-four patients with urothelial carcinoma underwent 1.5-T mpMRI per VI-RADS (T2-weighted imaging and DWI-derived ADC maps). Two blinded radiologists performed 3D tumor segmentation; 37 features per sequence were extracted (LifeX) using absolute resampling. In the training cohort (n = 40), features that differed between non-muscle-invasive and muscle-invasive tumors (Mann–Whitney p < 0.05) underwent ROC analysis with cut-offs defined by the Youden index. A compact descriptor combining GLRLM-LRLGE from T2 and GLRLM-SRLGE from ADC was then fixed and applied without re-selection to a prospective validation cohort (n = 44). Histopathology within 6 weeks—TURBT or cystectomy—served as the reference. Eleven T2-based and fifteen ADC-based features pointed to invasion; DWI texture features were not informative. The descriptor yielded AUCs of 0.934 (training) and 0.871 (validation) with 85.7% sensitivity and 96.2% specificity in validation. Collectively, these findings indicate that combined T2/ADC radiomics can provide high diagnostic accuracy and may serve as a useful decision support tool, after multicenter, multi-vendor validation. Full article

This paper presents a novel adversarial Convolutional Neural Network (ConvNet) method for generating adversarial perturbations in 3D point clouds, enabling gradient-free robustness evaluation of object detection systems at inference time. Unlike existing iterative gradient methods, our approach embeds the ConvNet directly into the detection pipeline at the voxel feature level. The ConvNet is trained to maximize detection loss while maintaining perturbations within sensor error bounds through multi-component loss constraints (intensity, bias, and imbalance terms). Evaluation on a Sparsely Embedded Convolutional Detection (SECOND) detector with the KITTI dataset shows 8% overall mean Average Precision (mAP) degradation, while CenterPoint on NuScenes exhibits 24% weighted mAP reduction across 10 object classes. Analysis reveals an inverse relationship between object size and adversarial vulnerability: smaller objects (pedestrians: 13%, cyclists: 14%) show higher vulnerability compared to larger vehicles (cars: 0.2%) on KITTI, with similar patterns on NuScenes, where barriers (68%) and pedestrians (32%) are most affected. Despite perturbations remaining within typical sensor error margins (mean L2 norm of 0.09% for KITTI, 0.05% for NuScenes, corresponding to 0.9–2.6 cm at typical urban distances), substantial detection failures occur. The key novelty is training a ConvNet to learn effective adversarial perturbations during a one-time training phase and then using the trained network for gradient-free robustness evaluation during inference, requiring only a forward pass through the ConvNet (1.2–2.0 ms overhead) instead of iterative gradient computation, making continuous vulnerability monitoring practical for autonomous driving safety assessment. Full article

Detecting surface cracks on sugarcane is a critical step in ensuring product quality control, with detection precision directly impacting raw material screening efficiency and economic benefits in the sugar industry. Traditional methods face three core challenges: (1) complex background interference complicates texture feature extraction; (2) variable crack scales limit models’ cross-scale feature generalization capabilities; and (3) high computational complexity hinders deployment on edge devices. To address these issues, this study proposes a lightweight sugarcane surface crack detection model, SCS-YOLO (Surface Cracks on Sugarcane-YOLO), based on the YOLOv10 architecture. This model incorporates three key technical innovations. First, the designed RFAC2f module (Receptive-Field Attentive CSP Bottleneck with Dual Convolution) significantly enhances feature representation capabilities in complex backgrounds through dynamic receptive field modeling and multi-branch feature processing/fusion mechanisms. Second, the proposed DSA module (Dynamic SimAM Attention) achieves adaptive spatial optimization of cross-layer crack features by integrating dynamic weight allocation strategies with parameter-free spatial attention mechanisms. Finally, the DyHead detection head employs a dynamic feature optimization mechanism to reduce parameter count and computational complexity. Experiments demonstrate that on the Sugarcane Crack Dataset v3.1, compared to the baseline model YOLOv10, our model achieves mAP50:95 to 71.8% (up 2.1%). Simultaneously, it achieves significant reductions in parameter count (down 19.67%) and computational load (down 11.76%), while boosting FPS to 122 to meet real-time detection requirements. Considering the multiple dimensions of precision indicators, complexity indicators, and FPS comprehensively, the SCS—YOLO detection framework proposed in this study provides a feasible technical reference for the intelligent detection of sugarcane quality in the raw materials of the sugar industry. Full article

The accurate assessment of Chinese bayberry (Myrica rubra) maturity is critical for intelligent harvesting. This study proposes a novel cascaded framework combining instance segmentation and multi-feature regression for accurate maturity detection. First, a lightweight SOLOv2-Light network is employed to segment each fruit individually, which significantly reduces computational costs with only a marginal drop in accuracy. Then, a multi-feature extraction network is developed to fuse deep semantic, color (LAB space), and multi-scale texture features, enhanced by a channel attention mechanism for adaptive weighting. The maturity ground truth is defined using the a*/b* ratio measured by a colorimeter, which correlates strongly with anthocyanin accumulation and visual ripeness. Experimental results demonstrated that the proposed method achieves a mask mAP of 0.788 on the instance segmentation task, outperforming Mask R-CNN and YOLACT. For maturity prediction, a mean absolute error of 3.946% is attained, which is a significant improvement over the baseline. When the data are discretized into three maturity categories, the overall accuracy reaches 95.51%, surpassing YOLOX-s and Faster R-CNN by a considerable margin while reducing processing time by approximately 46%. The modular design facilitates easy adaptation to new varieties. This research provides a robust and efficient solution for in-field bayberry maturity detection, offering substantial value for the development of automated harvesting systems. Full article

Decision-making and planning in eco-wellness tourism can vary depending on time, resources, and the perspectives of stakeholders, as it is often challenging to generalize the results of decision-making models across different scenarios. Hence, the primary objective of this study was to propose a scenario-based framework for optimising eco-wellness tourism development. For this purpose, maps of 26 factors affecting the evaluation of nature-based eco-wellness tourism, including water, climatic, and kinetic therapies, were used in the Ardabil province of Iran. Weighted criteria maps are integrated into suitability maps for various wellness tourism products under different scenarios, ranging from very pessimistic to very optimistic, using the Ordered Weighted Averaging (OWA) operator. Then, to identify areas of consensus, scenario-based maps for water, climate, and kinetic therapies are combined. In the very pessimistic (optimistic) scenario, climate-only therapy accounts for 0.91% (2.23%), water-only therapy for 1.07% (8.44%), and kinetic-only therapy for 3.5% (5.81%) of the area. The most significant expansion is observed in areas integrating all three therapies—climate, water, and kinetic—which increase from 3.23% in the very pessimistic scenario to 14.5% in the very optimistic scenario. The findings have substantial insights for policymakers, tourism planners, and investors in developing and promoting unique eco-wellness experiences that benefit tourists. The methodical approach and choice of data and parameters in the study can be inspirational and adjustable for relevant studies. Full article

Assessing the quality of groundwater, a primary source of water in many sectors, is of paramount importance. To this end, modeling the geospatial distribution of chemical contaminants in groundwater can be of great utility. Machine learning (ML) models are being increasingly used to overcome the shortcomings of conventional predictive techniques. We report here a systematic review of the nature and utility of various supervised and unsupervised ML models during the past two decades of machine learning groundwater hazard mapping (MLGHM). We identified and reviewed 284 relevant MLGHM journal articles that met our inclusion criteria. Firstly, trend analysis showed (i) an exponential increase in the number of MLGHM studies published between 2004 and 2025, with geographical distribution outlining Iran, India, the US, and China as the countries with the most extensively studied areas; (ii) nitrate as the most studied target, and groundwater chemicals as the most frequently considered category of predictive variables; (iii) that tree-based ML was the most popular model for feature selection; (iv) that supervised ML was far more favored than unsupervised ML (94% vs. 6% of models) with tree-based category—mostly random forest (RF)—as the most popular supervised ML. Secondly, compiling accuracy-based comparisons of ML models from the explored literature revealed that RF, deep learning, and ensembles (mostly meta-model ensembles and boosting ensembles) were frequently reported as the most accurate models. Thirdly, a critical evaluation of MLGHM models in terms of predictive accuracy, along with several other factors such as models’ computational efficiency and predictive power—which have often been overlooked in earlier review studies—resulted in considering the relative merits of commonly used MLGHM models. Accordingly, a flowchart was designed by integrating several MLGHM key criteria (i.e., accuracy, transparency, training speed, number of hyperparameters, intended scale of modeling, and required user’s expertise) to assist in informed model selection, recognising that the weighting of criteria for model selection may vary from problem to problem. Lastly, potential challenges that may arise during different stages of MLGHM efforts are discussed along with ideas for optimizing MLGHM models. Full article

Species distribution models (SDMs) have become an important tool to inform conservation and pest surveillance programs about the potential biological invasion of insect pests. Nonetheless, to be operational, SDMs need to incorporate multiple environmental covariates and a representative number of occurrence points depicting the species’ ecological niche. The algorithm of choice, model of choice, and comparison can also have a great effect on the final prediction output. We created a dataset based on previously published records, plus 36 new occurrences and 37 environmental predictors, to generate the first global ensemble distribution model for Aulacaspis yasumatsui. We employed a strategy that aggregates SDMs with the best performance (i.e., greater accuracy) from six different algorithms, resulting in an averaged and weighted model, i.e., the ensemble model. We then selected models from algorithms whose true skill statistic (TSS) was above 0.5 in order to map the potential global distribution of A. yasumatsui. Our results suggest that covariate selection and the individual model algorithms used in the ensemble may be more important for achieving an accurate SDM than the number of occurrence points. Full article

Agricultural drought, increasingly intensified by climate change, poses a significant threat to food security and water resources in semi-arid regions, including Türkiye’s Konya Closed Basin. This study evaluates six satellite-derived indices—Vegetation Health Index (VHI), Vegetation Condition Index (VCI), Temperature Condition Index (TCI), Precipitation Condition Index (PCI), Evapotranspiration Condition Index (ETCI), and Soil Moisture Condition Index (SMCI)—to monitor agricultural drought (2001–2024) and proposes a drought vulnerability map using a novel Drought Vulnerability Index (DVI). Integrating Moderate Resolution Imaging Spectroradiometer (MODIS), Climate Hazards Center InfraRed Precipitation with Station (CHIRPS), and Land Data Assimilation System (FLDAS) datasets, the DVI combines these indices with weighted contributions (VHI: 0.27, ETCI: 0.25, SMCI: 0.22, PCI: 0.26) to spatially classify vulnerability. The results highlight severe drought episodes in 2001, 2007, 2008, 2014, 2016, and 2020, with extreme vulnerability concentrated in the southern and central basin, driven by prolonged vegetation stress and soil moisture deficits. The DVI reveals that 38% of the agricultural area in the basin is classified as moderately vulnerable, while 29% is critically vulnerable—comprising 22% under high vulnerability and 7% under extreme vulnerability. The proposed drought vulnerability map offers an actionable framework to support targeted water management strategies and policy interventions in drought-prone agricultural systems. Full article

In security applications, visible-light pedestrian detectors are highly sensitive to changes in illumination and fail under low-light or nighttime conditions, while infrared sensors, though resilient to lighting, often produce blurred object boundaries that hinder precise localization. To address these complementary limitations, we propose a practical multimodal pipeline—Adaptive Energy–Gradient–Contrast (EGC) Fusion with AIFI-YOLOv12—that first fuses infrared and low-light visible images using per-pixel weights derived from local energy, gradient magnitude and contrast measures, then detects pedestrians with an improved YOLOv12 backbone. The detector integrates an AIFI attention module at high semantic levels, replaces selected modules with A2C2f blocks to enhance cross-channel feature aggregation, and preserves P3–P5 outputs to improve small-object localization. We evaluate the complete pipeline on the LLVIP dataset and report Precision, Recall, mAP@50, mAP@50–95, GFLOPs, FPS and detection time, comparing against YOLOv8, YOLOv10–YOLOv12 baselines (n and s scales). Quantitative and qualitative results show that the proposed fusion restores complementary thermal and visible details and that the AIFI-enhanced detector yields more robust nighttime pedestrian detection while maintaining a competitive computational profile suitable for real-world security deployments. Full article

High-performance deep learning models require extensive computational resources and datasets, making their ownership protection a pressing concern. To address this challenge, we focus on advancing model security through robust watermarking mechanisms. In this work, we propose a novel deep neural network watermarking method that embeds ownership information directly within the image feature space. Unlike existing approaches that often suffer from low embedding success rates and significant performance degradation, our method leverages convolutional kernels with orthogonal preferences to extract multiperspective features, which are then linearly mapped at the output layer for watermark embedding. Furthermore, we introduce an orthogonal regularization constraint into the loss function to increase the watermark robustness. This constraint enforces orthogonality in both convolutional and fully connected layer weights, suppresses redundancy in hidden layer representations, and minimizes interference between the watermark and the model’s original feature space. Through these innovations, we significantly improve the embedding reliability and preserve model integrity. Experimental results obtained on ResNet-18 and ResNet-101 demonstrate a 100% watermark detection rate with less than 1% performance impact, underscoring the practical security value of our approach. Comparative analysis further validates that our method achieves superior harmlessness and effectiveness relative to state-of-the-art techniques. These contributions highlight the role of our work in strengthening intellectual property protection and the trustworthy deployment of deep learning models. Full article

Mountain settlements represent culturally rich but environmentally fragile landscapes, shaped by enduring processes of ecological adaptation and human resilience. In western Sichuan, Jiarong Tibetan villages, with their distinctive integration of defensive stone towers and settlements, embody this coupling of culture and the environment. We hypothesize that settlement cores in these villages were shaped by natural environmental factors, with subsequent expansion reinforced by the cultural significance of towers. To test this, we applied a micro-scale spatial–environmental framework to four sample villages in Suopo Township, Danba County. High-resolution World Imagery (Esri, 0.5–1 m, 2022–2023) was classified via a Random Forest algorithm to generate detailed land-use maps, and a 100 × 100 m fishnet grid extracted topographic metrics (elevation, slope, aspect) and accessibility measures (distances to streams, roads, towers). Geographically weighted regression (GWR) was then used to examine how slope, elevation, aspect, proximity to water and roads, and tower distribution affect settlement patterns. The results show built-up density peaks on southeast-facing slopes of 15–30°, at altitudes of 2600–2800 m, and within 50–500 m of streams, co-locating with historic watchtower sites. Based on these findings, we propose four zoning strategies—a Core Protected Zone, a Construction And Development Zone, an Ecological Conservation Zone, and an Industry Development Zone—to balance preservation with growth. The resulting policy recommendations offer actionable guidance for sustaining traditional settlements in complex mountain environments. Full article