Search Results (275)

Precision agriculture has become a major direction of agricultural technological development in recent decades, addressing efficiency, environmental, and economic challenges simultaneously. Input optimization based on site-specific data collection—particularly variable-rate nutrient application, precision irrigation systems, and targeted crop protection—has been shown to generate measurable cost and resource savings. The aim of the study is to explore and systematically evaluate the economic impacts influencing precision technology in crop production. Although the technical and environmental benefits of precision technologies are widely documented, their economic performance and farm-level profitability remain inconsistently interpreted. The study is based on a systematic literature review of peer-reviewed English-language journal articles retrieved from the Web of Science, Scopus, ScienceDirect, and JSTOR databases. Study selection and evaluation were conducted in accordance with the PRISMA 2020 methodological framework. The literature indicates that precision technologies achieve average input savings of 8–20% and yield increases of 2–6%, while reported return on investment (ROI) values typically range between 5% and 15%. Economic viability is strongly dependent on farm size, with most studies identifying profitability above 100–200 ha. Additional benefits include improved management of soil heterogeneity, enhanced nutrient-use efficiency, and reduced excess input application, although adoption remains constrained by high investment costs and technological complexity. Full article

Oil slicks pose a severe threat to marine ecosystems, making accurate and real-time detection increasingly urgent. Marine X-band radar has become an essential tool for oil slick monitoring due to its high temporal resolution and its ability to sensitively capture the damping of capillary waves on the sea surface caused by oil films. Building upon this, an unsupervised and lightweight SLIC-KMeans-GJO detection framework is proposed. The method first generates superpixels by using Simple Linear Iterative Clustering (SLIC) and then applies K-means clustering to extract region of interest (ROI). An improved Golden Jackal Optimizer (GJO) is adaptively initialized based on the grayscale distribution and information entropy. To enhance optimization performance, Lévy flight and stochastic perturbation mechanisms are incorporated to improve global exploration and local convergence precision. Experimental results demonstrate that the proposed method significantly outperforms conventional thresholding approaches and other intelligent optimization-based segmentation algorithms in terms of noise suppression, target identification accuracy, and discrimination precision for oil slick targets. It effectively mitigates over-segmentation and false detections while preserving fine edge details and the true spatial extent of oil slicks. The proposed framework offers a novel and practical solution for real-time oil slick monitoring, holding strong potential for operational maritime emergency response. Full article

Background/Objectives: Perirenal fat (PRF) constitutes a critical yet understudied component of the tumor microenvironment in clear cell renal cell carcinoma (ccRCC). While radiomics enables non-invasive tissue characterization, whether PRF-derived features can simultaneously predict both TNM stage and histological grade, and whether optimal peritumoral distances differ between these distinct biological targets, remains unexplored in the literature. Methods: This multi-cohort retrospective study included 474 histopathologically confirmed ccRCC patients from three independent datasets (2007–2023). Automated nnU-Net segmentation delineated tumors and kidneys. Concentric PRF regions were systematically generated at 1–10 mm radial distances, yielding 18 distinct regions of interest. From each ROI, 1409 radiomic features were extracted using PyRadiomics. Sequential feature selection employed correlation filtering, SHAP-guided elimination, and LASSO regularization. Multiple machine learning classifiers underwent hyperparameter optimization with rigorous cross-cohort validation. Results: Systematic ROI screening revealed target-specific optimal distances: 4 mm PRF for TNM staging versus 10 mm PRF for histological grading. For staging, the integrated model (tumor + PRF radiomics + clinical variables) achieved AUC 0.829 (95% CI 0.781–0.877), sensitivity 80.2%, and specificity 67.8%. For grading, the combined model achieved AUC 0.780 (95% CI 0.598–0.962), sensitivity 79.7%, and specificity 63.3%, significantly outperforming all single-compartment models (DeLong p < 0.001). Conclusions: This study establishes that PRF radiomics enables accurate simultaneous non-invasive prediction of both TNM stage and histological grade in ccRCC. The novel discovery that optimal peritumoral distances differ substantially by prediction target (4 mm versus 10 mm) suggests distinct biological underpinnings for stage- and grade-related microenvironmental alterations, with important methodological implications for radiomic model development in oncology. Full article

This study proposes a machine learning framework tailored to the institutional characteristics of Taiwan’s stock market, aiming to enhance forecasting accuracy for the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX). The model employs the Radius Neighbors Regressor with a dynamic radius-based similarity measure and integrates domain-specific features including technical indicators, volume–price relationships, and Qualified Foreign Institutional Investor (QFII) activity. A custom 60-day input window with a 20-day forecast horizon is applied to capture medium-term market dynamics. The framework was evaluated through extensive backtesting and real-world validation with the TAIEX Futures. The results demonstrate that the model achieves a peak directional accuracy of 85.1% under optimal parameter settings. Moreover, trading simulations confirm its practical viability, yielding a cumulative return on investment (ROI) of approximately 1600% during the short-term evaluation period (2023–2025) and nearly 2000% in the long-term evaluation (2019–2025), even after accounting for transaction costs and stop-loss mechanisms. These findings indicate that combining historical pattern similarity with institutional investor behavior substantially improves predictive power and profitability. Nevertheless, the framework remains constrained by its reliance on Taiwan-specific institutional features and historical trading data, limiting generalizability. Future research should extend applications to other markets while incorporating macroeconomic variables, corporate fundamentals, and news-driven signals to enhance adaptability. Full article

Background: Navigated repetitive TMS (nrTMS) is widely used for non-invasive mapping of cortical functions. Methodological improvement might be achieved by optimizing coil positioning based on electric-field modeling and augmented reality (AR)-guided neuronavigation to enhance spatial targeting accuracy and stimulation-induced language errors. Therefore, we compared electric-field-optimized, AR-guided nrTMS with conventional nrTMS using manually planned coil positioning. Methods: Twenty-eight healthy subjects underwent two MRI-guided left hemispheric nrTMS language mapping sessions. Each session used 10 Hz stimulation at a 100% resting motor threshold applied for 1.5 s per region of interest (ROI) during a synchronized object naming task. ROIs were defined according to the Corina cortical parcellation system. Manually defined and electric-field-optimized coil placements obtained using SimNIBS (v4.1.0) were applied; the optimized session was assisted by AR goggles. The primary outcome was the quantitative and categorical differences in cortical regions mapped as language-eloquent. Resting-state fMRI was acquired to provide a reference for comparing nrTMS-derived language maps. Outcomes: Electric-field-optimized nrTMS did not result in an increase in positively mapped ROIs. A different distribution of language errors was observed between sessions. Manual mapping roughly followed the extracted resting-state language and motor networks, whereas electric-field-optimized mapping might correspond less. Optimized coil positions were not always practically feasible. AR guidance improved target location accuracy. Conclusions: While AR was a useful addition to the TMS experiment, electric-field optimization did not translate into significant behavioral differences. However, altered distribution of language errors can give insight into underlying neurophysiological processes of rTMS. Full article

Objective: The aim of this study was to determine the optimal region-of-interest (ROI) pixel size for fractal dimension analysis on panoramic radiographs that best reflects implant stability assessed by resonance frequency analysis (ISQ) and to investigate whether implant stability can be directly estimated from radiographic images. Materials and Methods: This retrospective cross-sectional study included 65 patients for whom panoramic radiographs and resonance frequency analysis measurements were available. All panoramic images were converted to TIFF format and standardized to a resolution of 2627 × 1646 pixels. All radiographic images were obtained using the same panoramic imaging device and standardized acquisition protocol. Exposure parameters were adjusted within the manufacturer’s recommended range to ensure optimal image quality while maintaining methodological consistency across patients. During ROI selection, care was taken to avoid cortical bone margins, overlapping anatomical structures, and radiographic artifacts in order to ensure that the analyzed regions represented trabecular bone adjacent to the implant surface. Fractal dimension analysis was performed in the cervical peri-implant bone region, starting from the first bone–implant contact and extending apically, using three different ROI configurations. The ROI size was defined as 30 pixels apically and 10 pixels horizontally for FMD1, 30 × 20 pixels for FMD2, and 30 × 30 pixels for FMD3. Implant stability was assessed using ISQ values. Data distribution was evaluated using the Shapiro–Wilk test. Associations between ISQ and fractal dimension measurements were analyzed using Pearson and Spearman correlation analyses. Multiple linear regression models adjusted for age and sex were constructed to assess independent associations. Results: The mean age of the participants was 50.0 ± 9.9 years, and the mean ISQ value was 78.6 ± 5.9. The mean fractal dimension values were 1.466 ± 0.055 for FMD1, 1.595 ± 0.031 for FMD2, and 1.655 ± 0.046 for FMD3. No significant association was found between ISQ and FMD1 or FMD3. A weak positive correlation was observed between ISQ and FMD2; however, this association did not remain statistically significant after correction for multiple comparisons. In multiple linear regression analysis, ISQ was identified as an independent predictor of FMD2, but not of FMD1 or FMD3. Age and sex had no significant effect on fractal dimension measurements. Conclusions: Fractal dimension measurements derived from panoramic radiographs showed a weak association with implant stability that was dependent on the selected ROI pixel size. Among the evaluated configurations, the 30 × 20-pixel ROI at the cervical peri-implant region demonstrated the strongest association with ISQ values, suggesting that this ROI configuration showed the most consistent association with ISQ values among the tested ROI sizes. Full article

Accurate extraction of crop planting structures is important for crop area and yield estimation, but complex and fragmented cropping patterns with overlapping phenology in the Hetao Irrigation District hinder reliable crop discrimination. This study proposes a hierarchical workflow that integrates vegetation masking with multi-source feature optimization for crop mapping. First, dual-temporal Sentinel-2 imagery (May and August) is used to generate a vegetation region-of-interest(ROI) mask via Otsu thresholding applied to the Normalized Difference Vegetation Index (NDVI), combined with pixel-wise maximum-value fusion to reduce phenology-driven omissions and background interference. Second, within the vegetation mask, Sentinel-2 spectral, vegetation-index, and texture features are combined with Sentinel-1 synthetic aperture radar (SAR) backscatter and SAR texture features to construct a multi-source feature set. Random Forest(RF) feature-importance ranking is used to select an effective feature subset, and four classifiers (RF, support vector machine (SVM), eXtreme Gradient Boosting (XGBoost), and convolutional neural network (CNN)) are compared under the same training/validation setting. The vegetation extraction achieves an overall accuracy of 91% (Kappa = 0.80). Using Sentinel-2 features only, the optimized subset with CNN attains the best performance (overall accuracy = 95%, Kappa = 0.93). Adding Sentinel-1 SAR texture features provides an additional improvement (overall accuracy = 96%, Kappa = 0.94), particularly for classes prone to confusion in fragmented plots. Area proportions derived from the final map are consistent with statistical yearbook data (percentage errors: maize 3.45%, sunflower 2.66%, wheat 0.11%, tomato 0.92%) under the study conditions. This workflow supports practical crop-structure monitoring in complex irrigation districts. Full article

Accurate detection of small objects in video analytics is limited by low pixel resolution and insufficient visual cues. While software-based enhancements often fail to recover missing details, Pan–Tilt–Zoom (PTZ) cameras can physically increase spatial resolution through optical zoom. However, mechanical latency and configuration complexity hinder their real-time applicability. We propose ZoomPatch, a real-time video analytics framework tailored for small object detection. ZoomPatch actively schedules PTZ adjustments to capture optically enhanced subframes of regions of interest (ROIs) and fuses inference results back to the global reference frame. Specifically, it introduces a dynamic Cycle Length Proposer to adapt analysis cycles based on scene motion, and a Mixed Integer Linear Programming (MILP)-based Configuration Decider to determine the optimal sequence of pan, tilt, and zoom adjustments under time budget constraints. Simulation-based experimental evaluations across diverse workloads demonstrate that ZoomPatch significantly outperforms fixed-perspective, super-resolution (SR), and greedy baselines. Notably, in the detection task using YOLOv10, ZoomPatch improves the F1-score from 0.33 to 0.47 (a 42% increase) compared to the fixed-perspective baseline. Furthermore, ZoomPatch yields performance gains of 30% and 7% over the SR baseline (0.36) and the greedy baseline (0.44). Full article

This paper presents an integrated multi-modal framework for detecting hyperthyroidism-associated abnormalities, namely exophthalmos and thyroid-related neck swelling, through the joint analysis of frontal facial and neck images using a deep learning-based approach. The objective of this research is to develop an integrated AI framework that improves hyperthyroid-related abnormality detection by simultaneously analyzing facial images of both the eye and neck based on pattern clinical knowledge. The multi-modal framework mimics a biological visual mechanism by using a dual-pathway architecture that concurrently processes foveal-like details of the eyes and neck. It integrates these high-resolution visual embeddings with quantitative morphological measurements to simulate a clinician’s ability to fuse observation with physical assessment. The proposed system employs a multi-faceted decision-making process derived from three distinct data components: two from frontal face analysis and one from neck region analysis. Specifically, eye regions extracted from facial images are preprocessed using the YOLOv11s model. The proposed system leverages a dual-pathway processing architecture to extract comprehensive diagnostic features. For the eye dataset, the framework utilizes a face mesh-based eye landmark (FMEL) to extract both eye regions and perform eyes unfold processing. These regions are subsequently analyzed by the proposed sclera map unwrapping engine (SMUE) to derive quantitative sclera metrics from both the left and right eyes. To optimize classification, a dual-branch architecture is employed by integrating CNN visual embeddings with SMUE-derived statistical features through a feature fusion layer. Simultaneously, the neck processing path executes the neck region of interest (ROI) prediction {upper, lower} to segment critical regions for goiter assessment via the proposed neck $\mu -\sigma$ ensemble thresholding (NSET) algorithm. The experimental results demonstrate that the proposed algorithm for eye analysis achieved a mean average precision (mAP50) of 96.4%, with a specific mAP50 of 98.6% for the hyperthyroid class. Regarding quantitative scleral measurement, the SMUE process revealed distinct morphological differences, with the experimental data group exhibiting consistently higher pixel distances across the reference points compared with the normal group. Furthermore, the proposed NSET algorithm yielded the highest performance for swollen neck classification with an mAP50 of 92.0%, significantly outperforming the baseline deep learning models while maintaining lower computational complexity. Full article

To address the difficulty of accurately localizing automotive chassis bolts during the assembly process—caused by non-uniform illumination, limited camera installation space, and occlusions from the vehicle body structure—a fiducial-marker-based localization method is proposed. In this method, a concentric ring-shaped fiducial marker is affixed to the bottom of the assembly wrench, and its region of interest (ROI) is extracted using an HSV color space segmentation algorithm. To overcome interference from uneven lighting and insufficient brightness in industrial environments, an improved Retinex-based image enhancement algorithm is introduced, which significantly improves the robustness and accuracy of ROI extraction. The extracted ROI image is subjected to ellipse fitting, and the fitting process is optimized by incorporating the Leitz criterion. Experimental results show that the optimized ellipse fitting algorithm achieves higher accuracy and significantly enhances the reliability of fitting. Since perspective projection of spatial circles leads to displacement of the circle center, the actual projected center of the fiducial marker in the image is calculated by estimating the normal vector of the circular plane using vanishing lines and the ellipse parameter matrix. This enables spatial localization of the bolt end. The proposed method is validated by comparing the localization results with the theoretical coordinates of the bolt holes. Experimental results demonstrate that the method offers high localization accuracy and strong robustness, meeting the practical precision requirements for automatic bolt assembly in industrial applications. Full article

Background: Convenience stores face volatile demand and a direct trade-off between stock-outs and overstocking, both of which affect service levels and profitability. This study aims to optimize inventory management through a reproducible forecasting-and-optimization workflow, assessing its impact on return on investment (ROI) and operational metrics, such as fill rate and stockouts. Methods: The workflow integrates daily, store-level transactions with external covariates, constructs temporal and lag features, and trains a Random Forest (RF) model using chronological splitting and time-series validation. Daily forecasts are then aggregated to the monthly level and used as inputs to an inventory simulation and an ROI-based economic model. Building on this simulation, a Genetic Algorithm (GA) optimizes the parameters of a monthly replenishment policy, incorporating minimum-coverage constraints. Results: In testing, the forecasting model achieved a mean absolute percentage error (MAPE) below 13%, and the RF+GA scheme outperformed the 28-day moving average baseline (MA28) in ROI across all five stores, with an average improvement of 4.52 percentage points; statistical significance was confirmed using the Wilcoxon test. Conclusions: Overall, the RF+GA approach serves as a decision-support tool that generates monthly order quantities consistent with demand and operational constraints, delivering verifiable improvements in both economic and service metrics. Full article

Background/Objectives: Brain tumors are among the most severe neurological disorders, and their variability in size, morphology, and anatomical location complicates early and accurate diagnosis. Although magnetic resonance imaging (MRI) is the most reliable non-invasive modality for tumor detection, manual interpretation remains time-consuming, subjective, and susceptible to human error. This study aims to develop an optimization-driven hybrid machine learning framework for accurate and computationally efficient automatic brain tumor classification. Methods: The dataset includes 834 MRI images (583-training, 123-validation, 128-independent test). Because YOLOv11 detects tumor and non-tumor regions separately, the sample size doubled during region-based analysis, and all subsequent stages were conducted at the regions of interest (ROI) level. On the independent test set, YOLOv11 achieved 98.87% mAP@50, 98.54% precision, and 98.21% recall. The proposed framework combines automated tumor localization with image standardization using Gaussian noise reduction and bilinear interpolation. From the processed MR images, 39 entropy-based features were extracted. To enhance diagnostic performance and eliminate redundant information, the superb fairy-wren optimization algorithm (SFOA) was applied for feature selection and compared with particle swarm optimization (PSO), Harris hawk optimization (HHO), and puma optimization (PO). Final classification was primarily performed using k-nearest neighbors (kNN), while support vector machines (SVM) were used for comparative evaluation. Results: SFOA reduced the feature dimensionality from 39 to 5 features while achieving 99.20% classification accuracy on the independent test set. In comparison, PSO selected 10 features, HHO selected 6 features and PO selected 10 features, all achieving 98.45% accuracy. The best performance obtained with SVM was 98.45% accuracy (HHO-SVM), which remained lower than the 99.20% achieved by the proposed SFOA-kNN model. Conclusions: The results indicate that combining entropy-based feature extraction with SFOA-driven feature selection and kNN classification significantly enhances diagnostic accuracy while reducing computational complexity, highlighting the strong potential of the proposed framework for integration into computer-aided diagnosis systems to support clinical decision-making. Full article

Background/Objectives: Autism Spectrum Disorder (ASD) diagnosis is difficult due to heterogeneity. Current Time-series Transformer (TST) methods cannot capture both dynamic and global brain connectivity simultaneously, which limits ASD classification performance. Methods: We propose TwoTST, a dual-stream Transformer that combines raw Region of Interest(ROI) time series and Pearson correlation matrices(PCC).We pre-train the two TST branches via self-supervised learning by randomly masking ROIs and PCC, use contrastive learning and fine-tuning for feature alignment, evaluate five fusion strategies, and analyze relative parameter changes during fine-tuning. Results: Experiments were conducted on the ABIDE I dataset using the CC200 atlas. Contrastive learning, pre-training, and the dual-stream structure improve mean AUC by 3–6%, 3–7%, and 3–4% respectively. Attention Pooling is the optimal fusion strategy. Relative parameter changes are 0.32–0.44 for TST modules and 0.31–1.45 for contrastive projection heads. Conclusions: TwoTST effectively integrates dynamic and global connectivity for ASD identification. The proposed design outperforms single-stream models and provides a reliable approach for neuroimaging-based disorder classification. Full article

This experiment evaluated the productivity and economic viability of wheat under an integrated net house with a closed hydroponic irrigation system versus an open field. The objective was to assess this water-saving innovation under the Arabian Peninsula’s resource-constrained environments. The integrated system achieved markedly superior results, producing a grain yield of 13.0 t/ha—a 117% increase over the open-field yield of 6.0 t/ha. Biomass yield reached 40.0 t/ha versus 16.0 t/ha in open fields, a 150% improvement. These gains were attributed to controlled growing conditions and balanced nutrient delivery, which optimized plant performance and reduced environmental stress. The system also demonstrated significant savings in resources, offering enhanced resource-use efficiency per unit of production. The estimated total values of productivity and resource savings were substantial when adjusted to the land area conserved. For ROI, BCR, and IRR, hydroponic wheat production scored 3.13, 4.13, and 312.8% in season (1) vs. 1.97, 2.97, and 197.1% for open-field production. In season (2), hydroponics scored 1.62, 2.63, and 163.0% vs. 0.043, 1.04, and 4.32% for open fields. Higher yields in 2022/2023 resulted from 30 vs. 10 min/day of irrigation due to higher relative humidity reflecting higher rainfall in the first season. Full article

Purpose: This study develops a predictive model for radiation pneumonitis (RP) risk in lung cancer patients after volume-modulated arc therapy (VMAT) that leverages high-dimensional dosiomics and dose–volume histogram (DVH) features within IDLSS (incremental-dose interval-based lung subregion) lung subregions. Methods: We retrospectively analyzed data from 136 lung cancer patients treated with VMAT between 2015 and 2022, including 39 patients who developed RP greater than Grade 2. Using the IDLSS method, seven regions of interest (ROIs), including the Planning Target Volume (PTV), normal lung, and five subdivided lung areas, were delineated on pretreatment Computed Tomography (CT) images. DVH, radiomics, and dosiomics features were extracted from these ROIs and organized into nine distinct feature sets. A comprehensive pipeline was applied, integrating IDLSS-defined lung subregions, high-dimensional dosiomics features, LASSO-based feature selection, and SMOTE oversampling to address class imbalance in the training data. Logistic regression, random forest, and feedforward neural networks were constructed and optimized via tenfold cross-validation. Model performance across different feature sets was evaluated via the average AUC, F1 score, and other performance metrics. Results: LASSO regression revealed that BMI and volume within the 5–10 Gy and 10–20 Gy lung subregions were significant predictors of RP. The performance evaluation demonstrated that the dosiomics features consistently outperformed the DVH features across the models. Combining radiomics and dosiomics achieved the highest predictive accuracy (AUC = 0.91, ACC = 0.89, NPV = 0.95, PPV = 0.78, F1 score = 0.82, sensitivity = 0.88, specificity = 0.90). Applying SMOTE during training significantly improved sensitivity without compromising specificity, confirming the value of balancing strategies in enhancing model performance. Incorporating all the features together did not provide additional performance gains. Conclusions: Integrating radiomics and dosiomics features extracted from IDLSS-defined lung subregions significantly enhances the ability to predict RP after VMAT, surpassing traditional DVH metrics. The substantial contribution of dosiomics features highlights the importance of spatial dose heterogeneity in RP risk assessment. Full article