Search Results (1,375)

Background/Objective: This study aimed to assess the prognostic significance of pretreatment nutritional and systemic inflammatory indices (IIs), and body composition parameters in patients with locally advanced cervical cancer (LACC) treated with chemoradiation and brachytherapy. The goal was to identify key predictors of clinical outcomes, such as local control (LC), metastasis-free survival (MFS), disease-free survival (DFS), and overall survival (OS), using machine learning techniques. Materials and methods: A retrospective analysis of 173 patients with LACC treated between 2007 and 2021 was conducted. The study utilized machine learning techniques, including LASSO regression and Classification and Regression Tree (CART) analysis, to identify significant predictors of outcomes. Clinical data, tumor-related parameters, and treatment factors, along with IIs and body composition metrics (e.g., sarcopenic obesity), were incorporated into the models. Model performance was evaluated using ROC curves and AUC values. Results: Among 173 patients, hemoglobin (Hb) levels, ECOG performance status, and total protein emerged as primary prognostic indicators across multiple endpoints. For 2-year LC, patients with Hb >11.9 g/dL had a rate of 95.1% compared to 73.6% in those with lower levels, with further stratification by ECOG status, ANRI, and total protein refining predictions. For 5-year LC, rates were 83.1% for Hb >11.5 g/dL and 43.3% for lower levels. For 2-year MFS, ECOG 0 patients had an 88.1% rate compared to 73.8% for ECOG ≥ 1. In 2-year OS, Hb > 11.9 g/dL predicted a 95.1% rate, while ≤11.9 g/dL correlated with 74.0%. IIs (ANRI, SIRI, MLR) demonstrated predictive value only within specific patient subgroups defined by the primary prognostic indicators. The model showed strong predictive accuracy, with AUCs ranging from 0.656 for 2-year MFS to 0.851 for 2-year OS. Conclusions: These findings underscore the value of integrating traditional prognostic factors with emerging markers to enhance risk stratification in LACC. The use of machine learning techniques like LASSO and CART demonstrated strong predictive capabilities, highlighting their potential to refine individualized treatment strategies. Prospective validation of these models is warranted to confirm their utility in clinical practice. Full article

Background: Maternal postpartum depression (PPD) is a major psychological problem affecting mothers, newborns, and their families after childbirth. This study investigated the factors influencing maternal PPD and developed a predictive model using machine learning. Methods/Design: In this study, we applied machine learning techniques to identify significant predictors of PPD and to develop a model for classifying individuals at risk. Data from 2570 subjects were analyzed using the Korean Early Childhood Education and Care Panel (K-ECEC-P) dataset as of January 2025, utilizing Python version 3.12.8. Results: We compared the performance of a decision tree classifier, random forest classifier, AdaBoost classifier, and logistic regression model using metrics such as precision, accuracy, recall, F1-score, and area under the curve. The logistic regression model was selected as the best model. Among the 13 features analyzed, conflict with a partner, stress, and the value of children emerged as significant predictors of PPD. Discussion: Conflict with a partner and stress levels emerged as the strongest predictors. Higher levels of conflict and stress were associated with an increased likelihood of PPD, whereas a higher value of children reduced this risk. Maternal psychological status and environmental features should be managed carefully during the postpartum period. Full article

This study focuses on optimizing C2 yields in the oxidative coupling of methane (OCM), a pivotal process for sustainable chemical production. By harnessing advanced machine learning (ML) techniques, this research aimed to predict C2 yields and identify the factors that drive catalytic performance. The Extra Trees Regressor emerged as the most effective model after a comprehensive evaluation across multiple datasets and methodologies. Key to the method was the use of an innovative Aggregated Catalyst Physicochemical Descriptor (ACPD) and stratified cross-validation, which effectively addressed feature complexity and target skewness. Hyperparameter optimization using Modified Sequential Model-Based Optimization (SMBO) further enhanced the model’s performance, achieving optimized R² values of 61.7%, 75.9%, and 92.0% for datasets A, B, and C, respectively, with corresponding reductions in the Mean Squared Error (MSE) and Root Mean Squared Error (RMSE). Additionally, SHAP (SHapley Additive exPlanations) analysis provided a detailed understanding of the model’s decision-making process, revealing the relative importance of individual features and their contributions to the predictive outcomes. This research not only achieved state-of-the-art predictive accuracy, but also deepened our understanding of the underlying chemical dynamics, offering practical guidance for catalyst design and operational optimization. These findings mark a significant advancement in catalysis, paving the way for future innovations in sustainable chemical manufacturing. Full article

Traditional quantitative genetic models in forestry often overlook the influence of an individual’s genes on neighboring trees. However, genetic competition models help bridge this gap. Competition varies among populations, over time, and across environments, yet forest breeders rarely monitor these dynamics or their effects on selected genotypes. We investigated the effects of competition on genetic variances, breeding value accuracy, and selection response in 14 Pinus taeda L. progeny tests using spatial (Spa) and spatial-competition (Spa-Comp) individual-tree mixed models. Our analysis covered traits such as diameter at breast height (DBH), total height (TH), and stem straightness (STR) across ages (3–21 years) and sites (altitude, soil texture, drainage). DBH was more affected by genetic competition than TH and STR, with effects varying across ages and sites. Direct-competition genetic correlations were negative for DBH from age 5 onward but positive for TH, reducing total heritable variance for DBH (<43.1%) while increasing for TH (<95.7%). Genetic competition accounted for less than 26% of direct additive variance. For DBH, the Spa-Comp model slightly improved breeding value accuracy (<~4%), while Spa inflated selection response (<3.83 percentage points), yet rank changes were minimal (common selected trees > 89%). These findings indicate that while competition inflates genetic gains, its impact on selection efficiency is minimal. Full article

To address the inefficiency and significant errors in the manual measurement of phenotypic parameters of Phoebe zhennan seedlings, a non-destructive automated method based on a 3D point cloud was proposed for extracting phenotypic parameters of stem and leaves following stem and leaf segmentation. First, the processed point cloud image was aligned using the Sample Consensus Initial Aligment (SAC-IA) and Iterative Closest Point (ICP) algorithms to generate a three-dimensional model of the seedlings. The stem point cloud was extracted from the model using the median normalized growth vector-based search (MNVG) method, with the current growth vector refined based on previous growth points and vectors. These corrective processes enhanced the accuracy of stem extraction. The leaves were separated from the stem through streamlined projection, after which the remaining leaf point cloud was individually extracted using the density-based spatial clustering of applications with noise (DBSCAN) algorithm. The extracted stem data were used to measure stem length and stem diameter, and for each extracted leaf, leaf length, width, and area were measured, yielding accuracies of 97.7%, 93.2%, 96.4%, 88.02%, and 85.84%, respectively. The results of this study provide a valuable reference for forest breeding and the cultivation of high-quality tree seedlings. Full article

Forest ecosystems play a pivotal role in the global carbon cycle and climate change mitigation. Forest aboveground biomass (AGB), a critical indicator of carbon storage and sequestration capacity, has garnered significant attention in ecological research. Recently, uncrewed aerial vehicle-borne laser scanning (ULS) technology has emerged as a promising tool for rapidly acquiring three-dimensional spatial information on AGB and vegetation carbon storage. This study evaluates the applicability and accuracy of UAV-LiDAR technology in estimating the spatiotemporal dynamics of AGB and vegetation carbon storage in Robinia pseudoacacia (R. pseudoacacia) plantations in the gully regions of the Loess Plateau, China. At the sample plot scale, optimal parameters for individual tree segmentation (ITS) based on the canopy height model (CHM) were determined, and segmentation accuracy was validated. The results showed root mean square error (RMSE) values of 13.17 trees (25.16%) for tree count, 0.40 m (3.57%) for average tree height (AH), and 320.88 kg (16.94%) for AGB. The regression model, which links sample plot AGB with AH and tree count, generated AGB estimates that closely matched the observed AGB values. At the watershed scale, ULS data were used to estimate the AGB and vegetation carbon storage of R. pseudoacacia plantations in the Caijiachuan watershed. The analysis revealed a total of 68,992 trees, with a total carbon storage of 2890.34 Mg and a carbon density of 62.46 Mg ha⁻¹. Low-density forest areas (<1500 trees ha⁻¹) dominated the landscape, accounting for 94.38% of the tree count, 82.62% of the area, and 92.46% of the carbon storage. Analysis of tree-ring data revealed significant variation in the onset of growth decline across different density classes of plantations aged 0–30 years, with higher-density stands exhibiting delayed growth decline compared to lower-density stands. Compared to traditional methods based on diameter at breast height (DBH), carbon storage assessments demonstrated superior accuracy and scientific validity. This study underscores the feasibility and potential of ULS technology for AGB and carbon storage estimation in regions with complex terrain, such as the Loess Plateau. It highlights the importance of accounting for topographic factors to enhance estimation accuracy. The findings provide valuable data support for density management and high-quality development of R. pseudoacacia plantations in the Caijiachuan watershed and present an efficient approach for precise forest carbon sink accounting. Full article

Flowering intensity is an important parameter to predict and control fruit yield. However, its estimation is often based on subjective evaluations of fruit growers. This study explores the application of the YOLO framework for flowering intensity estimation. YOLO is a popular computer vision solution for object-detecting tasks. It was applied to detect flowers in different studies. Still, it requires manual annotation of photographs of flowering trees, which is a complex and time-consuming process. It is hard to distinguish individual flowers in photos due to their overlapping and indistinct outlines, false positive flowers in the background, and the density of flowers in panicles. Our experiment shows that the small dataset of images (320 × 320 px) is sufficient to achieve an accuracy of 0.995 and 0.994 mAP@50 for YOLOv9m and YOLOv11m using aggregated mosaic augmentation. The AI-based method was compared with the manual method (flowering intensity estimation, 0–9 scale). The comparison was completed using data analysis and the MobileNetV2 classifier as an evaluation model. The analysis shows that the AI-based method is more effective than the manual method. Full article

The objective of this study was to evaluate the influence of the mean individual volume per tree (MIV) on the productivity of forwarder machines and the production cost in eucalyptus plantations located in southern Bahia, Brazil. MIV positively influenced the productivity and production costs, promoting a more attractive cost in the latter when the individual volume per tree increased. The machine’s productivity for MIV of 0.13 m³ was 42.06 cubic meters per effective working hour (m³Ewh⁻¹), while the productivity for the MIV of 0.58 m³ reached 60.97 m³Ewh⁻¹, corresponding to an increase of 42.59% between the minimum and maximum MIV classes. The extracted cost (m³) decreased by 30.12% from USD 2.49 to 1.74, respectively, when comparing the minimum and maximum MIV classes. The coefficient of determination obtained in the forwarder productivity modeling was significant (R² = 92%), indicating the machine’s productivity can be explained by the mean individual volume per tree. The highest forwarder yields in the highest average volume per tree (MIV) classes provided better energy efficiency indices for the machine; that is to say, when the forwarder became more productive, the ratio between fuel consumption per cubic meter of timber harvested decreased, providing better performance for the respective index. There was a difference in extraction costs of USD 147.83 per hectare between the lowest and highest productivity forests (MIV varying from 0.15 to 0.58). The mechanical availability and mean operational efficiency of all forwarders evaluated were above 80%, which contributed to effective machine productivity performance. Maintenance and repairs represented the largest portion of operational costs (33.59%), followed by labor (22.49%), depreciation (14.33%), and fuel (10.11%). Full article

Walking is a fundamental human activity, and analyzing its complexities is essential for understanding gait abnormalities and musculoskeletal disorders. This article delves into the classification of gait phases using advanced machine learning techniques, specifically focusing on dividing these phases into five distinct subphases. The study utilizes data from 100 individuals obtained from an open-access platform and employs two distinct training methodologies. The first approach adopts stratified random sampling, where 80% of the data from each subphase are allocated for training and 20% for testing. The second approach involves participant-based splitting, training on data from 80% of the individuals and testing on the remaining 20%. Preprocessing methods such as Min–Max Scaling (MMS), Standard Scaling (SS), and Principal Component Analysis (PCA) were applied to the dataset to ensure optimal performance of the machine learning models. Several algorithms were implemented, including k-Nearest Neighbors (k-NNs), Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), Naive Bayes (Gaussian, Bernoulli, and Multinomial) (NB), Linear Discriminant Analysis (LDA), and Quadratic Discriminant Analysis (QDA). The models were rigorously evaluated using performance metrics like cross-validation score, Mean Squared Error (MSE), Root Mean Squared Error (RMSE), accuracy, and $R^2$ score, offering a comprehensive assessment of their effectiveness in classifying gait phases. In the five subphases analysis, RF again performed strongly with a 94.95% accuracy, an RMSE of 0.4461, and an $R^2$ score of 90.09%, demonstrating robust performance across all scaling methods. Full article

Pre-trained foundation models, trained on large-scale datasets, have demonstrated significant success in a variety of downstream vision tasks. Parameter-efficient fine-tuning (PEFT) methods aim to adapt these foundation models to new domains by updating only a small subset of parameters, thereby reducing computational overhead. However, the effectiveness of these PEFT methods, especially in the context of forestry remote sensing—specifically for individual tree detection—remains largely unexplored. In this work, we present a simple and efficient PEFT approach designed to transfer pre-trained transformer models to the specific tasks of tree crown detection and species classification in unmanned aerial vehicle (UAV) imagery. To address the challenge of mitigating the influence of irrelevant ground targets in UAV imagery, we propose an Adaptive Salient Channel Selection (ASCS) method, which can be simply integrated into each transformer block during fine-tuning. In the proposed ASCS, task-specific channels are adaptively selected based on class-wise importance scores, where the channels most relevant to the target class are highlighted. In addition, a simple bias term is introduced to facilitate the learning of task-specific knowledge, enhancing the adaptation of the pre-trained model to the target tasks. The experimental results demonstrate that the proposed ASCS fine-tuning method, which utilizes a small number of task-specific learnable parameters, significantly outperforms the latest YOLO detection framework and surpasses the state-of-the-art PEFT method in tree detection and classification tasks. These findings demonstrate that the proposed ASCS is an effective PEFT method, capable of adapting the pre-trained model’s capabilities for tree crown detection and species classification using UAV imagery. Full article

This study aims to develop a method for predicting walnut (Juglans regia L.) yield based on the walnut orchard point cloud model, addressing issues such as low efficiency, insufficient accuracy, and high costs in traditional methods. The walnut orchard point cloud is reconstructed using unmanned aerial vehicle (UAV) images, and the semantic segmentation technique is applied to extract the individual walnut tree point cloud model. Furthermore, the tree height, canopy projection area, and volume of each walnut tree are calculated. By combining these morphological features with statistical models and machine learning methods, a prediction model between tree morphology and yield is established, achieving prediction accuracy with a mean absolute error (MAE) of 2.04 kg, a mean absolute percentage error (MAPE) of 17.24%, a root mean square error (RMSE) of 2.81 kg, and a coefficient of determination (R²) of 0.83. This method provides an efficient, accurate, and economically feasible solution for walnut yield prediction, overcoming the limitations of existing technologies. Full article

Scanning forests with LiDAR is an efficient method for conducting forest resource surveys, including estimating tree diameter at breast height (DBH), canopy height, and segmenting individual trees. This study uses three-dimensional (3D) forest test data and point cloud data simulated by the Helios++ V1.3.0 software, and proposes a voxelized trunk extraction algorithm to determine the trunk location and the vertical structure of single tree trunks in forest areas. Firstly, the voxel-based shape recognition algorithm is used to extract the trunk structure of tree point clouds, then the random sample consensus (RANSAC) algorithm is used to solve the vertical structure connectivity problem of tree trunks generated by the above method, and the Alpha Shapes algorithm is selected among various point cloud surface reconstruction algorithms to reconstruct the surface of tree point clouds. Then, building on the tree surface model, a light projection scene is introduced to locate the tree trunk coordinates at different heights. Finally, the convex hull of the trunk bottom is solved by the Graham scanning method. Accuracy assessments show that the proposed single-tree extraction algorithm and the forest vertical structure recognition algorithm, when applied within the light projection scene, effectively delineate the regions where the vertical structure distribution of single tree trunks is inconsistent. Full article

Small non-coding molecules known as microRNAs (miRNAs) play a critical role in disease diagnosis, treatment, and prognosis evaluation. Traditional wet-lab methods for validating miRNA–disease associations are often time-consuming and inefficient. With the advancement of high-throughput sequencing technologies, deep learning methods have become effective tools for uncovering potential patterns in miRNA–disease associations and revealing novel biological insights. Most of the existing approaches focus primarily on individual molecular behavior, overlooking interactions at the multi-molecular level. Conventional graph neural network (GNN) models struggle to generalize to heterogeneous graphs, and as network depth increases, node representations become indistinguishable due to over-smoothing, resulting in reduced predictive performance. GONNMDA first integrates similarity features from multiple data sources and applies noise reduction to obtain a reconstructed, comprehensive similarity representation. It then constructs heterogeneous graphs and applies a root–tree hierarchical alignment, along with an ordered gating message-passing mechanism, effectively addressing the challenges of heterogeneity and over-smoothing. Finally, a multilayer perceptron is employed to produce the final association predictions. To evaluate the effectiveness of GONNMDA, we conducted extensive experiments where the model achieved an AUC of 95.49% and an AUPR of 95.32%. The results demonstrate that GONNMDA outperforms several recent state-of-the-art methods. In addition, case studies and survival analyses on three common human cancers—breast cancer, rectal cancer, and lung cancer—further validate the effectiveness and reliability of GONNMDA in predicting miRNA–disease associations. Full article

Mutation is one of the most important drivers of viral evolution and genome variability, allowing viruses to potentially evade host immune responses and develop drug resistance. In the context of COVID-19, local genomic surveillance of circulating virus populations is therefore critical. The goals of this study were to describe the distribution of different SARS-CoV-2 lineages, assess their genomic differences, and infer virus importation events in Bangladesh. We individually aligned 1965 SARS-CoV-2 genome sequences obtained between April 2020 and June 2021 to the Wuhan-1 sequence and used the resulting multiple sequence alignment as input to infer a maximum likelihood phylogenetic tree. Sequences were assigned to lineages as described by the hierarchical Pangolin nomenclature scheme. We built a phylogeographic model using the virus population genome sequence variation to infer the number of virus importation events. We observed thirty-four lineages and sub-lineages in Bangladesh, with B.1.1.25 and its sub-lineages D.* (979 sequences) dominating, as well as the Beta variant of concern (VOC) B.1.351 and its sub-lineages B.1.351.* (403 sequences). The earliest B.1.1.25/D.* lineages likely resulted from multiple introductions, some of which led to larger outbreak clusters. There were 570 missense mutations, 426 synonymous mutations, 18 frameshift mutations, 7 deletions, 2 insertions, 10 changes at start/stop codons, and 64 mutations in intergenic or untranslated regions. According to phylogeographic modeling, there were 31 importation events into Bangladesh (95% CI: 27–36). Like elsewhere, Bangladesh has experienced distinct waves of dominant lineages during the COVID-19 pandemic; this study focuses on the emergence and displacement of the first wave-dominated lineage, which contains mutations seen in several VOCs and may have had a transmission advantage over the extant lineages. Full article

UAV LiDAR and digital aerial photogrammetry (DAP) have shown great performance in forest inventory due to their advantage in three-dimensional information extraction. Many studies have compared their performance in individual tree segmentation and structural parameters extraction (e.g. tree height). However, few studies have compared their performance in tree species classification. Therefore, we have compared the performance of UAV LiDAR and DAP-based point clouds in individual tree species classification with the following steps: (1) Point cloud data processing: Denoising, smoothing, and normalization were conducted on LiDAR and DAP-based point cloud data separately. (2) Feature extraction: Spectral, structural, and texture features were extracted from the pre-processed LiDAR and DAP-based point cloud data. (3) Individual tree segmentation: The marked watershed algorithm was used to segment individual trees on canopy height models (CHM) derived from LiDAR and DAP data, respectively. (4) Pixel-based tree species classification: The random forest classifier (RF) was used to classify urban tree species with features derived from LiDAR and DAP data separately. (5) Individual tree species classification: Based on the segmented individual tree boundaries and pixel-based classification results, the majority filtering method was implemented to obtain the final individual tree species classification results. (6) Fused with hyperspectral data: LiDAR-hyperspectral and DAP-hyperspectral fused data were used to conduct individual tree species classification. (7) Accuracy assessment and comparison: The accuracy of the above results were assessed and compared. The results indicate that LiDAR outperformed DAP in individual tree segmentation (F-score 0.83 vs. 0.79), while DAP achieved higher pixel-level classification accuracy (73.83% vs. 57.32%) due to spectral-textural features. Fusion with hyperspectral data narrowed the gap, with LiDAR reaching 95.98% accuracy in individual tree classification. Our findings suggest that DAP offers a cost-effective alternative for urban forest management, balancing accuracy and operational costs. Full article