Search Results (3,722)

Eucalyptus plantations are expanding rapidly in southern China, delivering economic benefits but also posing ecological risks, which creates a pressing need for precise, municipal-scale monitoring. Mapping eucalyptus with sub-meter resolution imagery, however, is confronted by two main challenges: (1) the pronounced multi-scale heterogeneity of fragmented stands, and (2) the difficulty in achieving precise boundary delineation due to shadowed and complex canopy edges. To address these, this study makes two primary contributions. First, we present the Eucalyptus Semantic Segmentation Dataset (ESSD)—a high-quality, pixel-level annotated dataset that includes geographic coordinates to support reproducible research. Second, we propose SDCNet, a task-specific deep learning network optimized for eucalyptus mapping. SDCNet incorporates a redesigned SD-ASPP module that leverages Deep Over-parameterized Convolution (DO-Conv) to capture multi-scale features, alongside a novel Coordinated Self-Attention Mechanism (CSAM) to enhance the accuracy of canopy boundary detection. Ablation studies confirm the effectiveness of each component. In benchmark tests against seven state-of-the-art semantic segmentation models, SDCNet achieves superior performance, obtaining a per-class Intersection over Union (IoU) of 88.83% and an F1-score of 93.81% for eucalyptus—an improvement of +2.24% in IoU and +1.71% in F1-score over the strongest baseline. Applied to Nanning City, SDCNet produces the first 0.3 m resolution eucalyptus distribution map for the region. This map reveals a critical finding: within the watershed of the Xiyunjiang Reservoir—Nanning’s primary drinking water source—eucalyptus plantations cover more than 50% of the forested area. This result provides the first quantitative, high-resolution evidence of potential hydrological risk at a municipal scale. Our work establishes an integrated framework that bridges advanced remote sensing with actionable forest governance, offering scientifically grounded support for ecological risk assessment and sustainable land-use policy. Full article

Maintaining stable molding quality in hydraulic injection molding machines is difficult because the internal state of molten resin cannot be directly observed and varies with material properties and operating conditions. This difficulty is intensified by variations in hydraulic characteristics caused by oil temperature changes. This study proposes an adaptive feedforward control (AFC) framework that improves injection velocity tracking while utilizing AFC learning parameters as indicators of resin state. AFC is implemented as a multi-frequency feedforward controller whose parameters are updated through repetitive injection cycles. To overcome the limited learning duration within a single injection shot, a shot-to-shot compensation mechanism accumulates and transfers learning results across consecutive shots. Experiments are conducted on a hydraulic injection molding machine using polypropylene materials with different viscosities. The results show that the converged AFC learning parameters vary systematically with material changes and correspond to differences in molded product appearance. Furthermore, by adjusting the cylinder temperature of another material, the AFC parameters converge to values close to those of a reference material, resulting in similar molded products. These findings demonstrate that AFC learning parameters reflect variations in resin state and can serve as practical state indicators for aligning molding conditions. Full article

The method of images (MoI) is a valuable technique for solving certain electrostatic boundary value problems consisting of charge density near conductor(s). We developed and validated an inquiry-based tutorial on MoI to help students learn to identify the problems involving symmetry in which MoI is applicable and then apply it by finding the correct image charge configuration. We implemented the inquiry-based tutorial accompanied by pretest and posttest, across three instructors’ classes to evaluate student learning. We also conducted think-aloud interviews with advanced physics students, which helped us gain insights into their problem-solving strategies, evaluate their understanding developed through the tutorial and make necessary refinements to the MoI tutorial. The study identified common student difficulties, which were subsequently integrated into the inquiry-based tutorial as a guide to provide support to students. One important finding is that advanced students have common difficulties related to physics concepts similar to those found in introductory physics courses. The performance difference in the pretest administered after lecture-based instruction and the posttest administered after working through the tutorial reflects students’ ability to apply what they learned from the inquiry-based tutorial compared to traditional lecture. Another important and unanticipated finding of this study is the potential impact of the framing of the inquiry-based tutorial and accompanying tests by one of the instructors on the engagement and performance of students. In particular, the instructor of one of the classes offered students a small amount of extra credit for engaging with the inquiry-based tutorial and tests, explicitly noting that these activities were not part of the current course syllabus and were primarily conducted to support physics education research. This kind of framing likely influenced students’ motivation and engagement, which underscores how the way the instructor frames the inquiry-based instructional tasks to their students can have a significant impact on student performance. Overall, this iterative multi-year design-based comparative research with mixed-method triangulation provides valuable insights on the challenges involved in such studies that educators and researchers alike can greatly benefit from. Full article

Mathematics is a diverse discipline that requires a variety of cognitive abilities and presents varying levels of difficulty. Understanding how different cognitive profiles relate to specific patterns of mathematical performance is important for developing effective educational interventions. This study extends our previous research, in which we identified subgroups of children with mathematical difficulties based on their cognitive abilities. We examined 146 Israeli elementary school children in grades 3 and 4, classified into four subgroups: Reading Accuracy Difficulties (RAD), Mild Mathematical Difficulties (MMD), Non-Verbal Reasoning Difficulties (NVRD), and Typically Developing children (TD). Participants were assessed on arithmetic facts, computational fluency, procedural skills, estimation, and numeration. We observed varied performance patterns among subgroups. The RAD group showed the most severe impairments across all mathematical domains, along with reading comorbidity and cognitive difficulties. The MMD group, which maintained intact cognitive skills, faced notable challenges in computation, performing significantly below the TD group but better than the RAD group. The NVRD group, despite limitations in nonverbal reasoning, outperformed other difficulty groups on fact retrieval and estimation. Performance on multiplication and division tasks consistently followed a hierarchical pattern across all difficulty groups, with the RAD group facing the greatest challenges. These findings demonstrate that mathematical difficulties vary across cognitive profiles and that distinguishing between profiles through targeted assessment enables the development of differentiated interventions tailored to each learner’s specific cognitive profile. Full article

Digital transformation in the interior design industry has opened new opportunities for innovation; however, many cost-conscious homeowners still face difficulties in selecting and customizing design packages that achieve a balance between overall cost and sustainable quality. Existing interior design platforms lack seamless support and often require homeowners to invest considerable time and effort to tailor services to their needs while staying within budget. To address these challenges, this paper explores the use of machine learning to build a predictive modelling framework that supports personalized and value-driven interior design recommendations. The proposed approach uses a hybrid recommendation system that combines content-based and collaborative filtering. It also incorporates lightweight techniques such as TF–IDF (Term Frequency–Inverse Document Frequency) and logistic regression to more effectively capture user preferences, budget limits, and several interior-design service categories. Primary data was collected from small to medium-sized interior design companies. To demonstrate the proposed approach, a user-friendly web application tool is developed to integrate machine learning-enabled recommendation services. The resulting solution provides access to professional interior design services, enhancing customization and customer satisfaction while reducing the time and effort required from homeowners. To validate and compare the performance of the proposed approach, several machine learning models including Random Forest, XGBoost and KNN (K-Nearest Neighbors) were tested using standard metrics such as accuracy, precision, recall, and ROC-AUC (Receiver Operating Characteristic-Area Under the Curve). The proposed logistic regression hybrid model achieved the strongest overall results, with an accuracy of 83.62%. These findings demonstrate the significant contribution of this work to enhancing personalization and accessibility in the interior design sector via machine learning-enabled recommendation systems. The proposed approach bridges the gap between expert-level services and financial limits, making it a practical choice for cost-conscious homeowners. Full article

The Automated Essay Scoring (AES) systems confront two fundamental challenges: opaque “black-box” decision-making that limits educator trust, and insufficient validation across linguistically diverse educational contexts. This study proposes IRT-AESF, an innovative framework that bridges educational measurement theory and artificial intelligence by integrating item response theory (IRT) with deep learning. The framework generates three theoretically grounded psychometric parameters: student ability, item difficulty, and item discrimination, which provide transparent and interpretable explanations for scoring decisions. We rigorously evaluated IRT-AESF through 5-fold cross-validation on three large-scale datasets comprising 41,328 authentic essays from English and Chinese educational settings, including both classroom assessments and high-stakes examinations. Results demonstrate statistically significant improvements over competitive baseline models, achieving an 8.4% relative increase in quadratic weighted kappa while maintaining robust cross-lingual performance. This research advances the development of transparent, trustworthy automated assessment systems that deliver not only scores but meaningful diagnostic insights for educational practice. Full article

Canine cognitive dysfunction (CCD) is a progressive neurodegenerative condition affecting aging dogs, characterized by impairments in learning, memory, spatial orientation, and behavior. Despite its substantial negative impact on dogs’ quality of life and owners’ emotional well-being, CCD is frequently underrecognized or diagnosed at a late stage. This study explored how challenges in CCD recognition and veterinary communication influence dog owners’ ability to identify symptoms and make informed decisions about care. Semi-structured interviews were conducted with 22 dog owners whose dogs were suspected of having CCD, based on elevated scores on the Canine Cognitive Dysfunction Rating Scale (CCDR) and owner-reported behavioral changes. Interview data were analyzed using reflexive thematic analysis. Four main themes emerged: (1) difficulties in recognizing CCD-related symptoms, (2) communication challenges between owners and veterinarians, (3) owners’ adaptation to gradually emerging symptoms, and (4) the emotional and practical burden of caregiving. Owners frequently interpreted behavioral changes as normal aging or other health problems, which delayed the recognition of cognitive decline. Participants also described limited guidance from veterinary professionals regarding CCD, contributing to uncertainty, emotional distress, and challenges in end-of-life decision-making. Together, these findings suggest that owners’ experiences follow a progressive caregiving trajectory, from initial symptom uncertainty to increasing emotional and practical burden. Improving awareness of CCD, strengthening veterinary communication, and providing targeted support for caregivers may facilitate earlier recognition and more effective management of cognitive decline, ultimately benefiting both dogs and the people who care for them. Full article

Creative tourism is increasingly discussed as a pathway for tourism development in rural and peripheral destinations, yet empirical evidence remains uneven and is still drawn mainly from contexts where it is already explicitly labelled and institutionally supported. This article examines whether and how creative tourism-aligned practices are present in Kupiškis District, a peripheral rural municipality in north-eastern Lithuania where creative tourism has not been formally institutionalised as a tourism development category. The study adopts a qualitative single-case design combining a multi-stakeholder focus group and semi-structured interviews with municipal, intermediary, and private-sector actors. The findings reveal a meaningful but weakly integrated experiential base shaped by educational activities, water-based leisure, symbolic narratives, routes, and micro-entrepreneurial initiatives. Although these practices are rarely named locally as creative tourism, they display several of its defining characteristics, including participatory learning, host involvement, small-scale interaction, and local embeddedness. The study suggests that the main development challenge lies not in the absence of creative resources, but in limited coordination, weak articulation, and the difficulty of translating dispersed practices into coherent and consistently bookable visitor experiences. The article conceptualises this condition as a latent experiential portfolio and, in doing so, makes three contributions: it offers a sensitising concept for describing pre-consolidation stages of creative tourism where relevant practices exist but remain only partly articulated; it supports a practice-based rather than label-based identification of creative tourism in weakly institutionalised settings; and it extends the empirical scope of creative tourism research to a peripheral rural case in the Baltic region. Full article

Lead contamination in urban soils, primarily from deteriorating lead-based paint, poses a significant health risk in the United States. These soils often serve as major sources of exposure, making them critical targets for remediation efforts. To guide such strategies, preliminary risk assessments are necessary to evaluate lead bioaccessibility in the soil and identify key soil properties influencing lead speciation. In this study, a novel machine learning approach was co-developed with an artificial intelligence assistant, Claude Sonnet, developed by Anthropic, to design a predictive model that overcomes the difficulties of conducting experimental bioaccessibility models. Data was compiled from published sources (n = 640), as well as an internal analysis of soils sampled across three large cities in the United States (n = 30), to use as a validation model. While our final model’s prediction accuracy was good (R² = 0.95), it initially did not perform as expected on our internal dataset, indicating a fundamental domain shift. Further analysis revealed complications with outliers, data availability, and data consistency that resulted in poor performance. When optimization was applied to the validation model, our final prediction accuracy improved (R² = 0.84). Here, we conclude the importance of data availability and consistency in heavy-metal soil bioaccessibility studies to build a generalizable predictive model. Full article

This study proposes a data-driven framework with post hoc interpretability analysis for one-step-ahead crystal diameter prediction in the Czochralski (CZ) silicon single-crystal growth process. To address the strong multivariable coupling, nonlinear dynamics, variable-specific delays, and difficulty of online measurement in CZ growth, the maximal information coefficient (MIC) was first used to screen key auxiliary variables from industrial process data. The Grey Wolf Optimizer (GWO) was then employed for multi-variable delay estimation and feature alignment, and a hybrid temporal convolutional network (TCN)–long short-term memory (LSTM) model was constructed to combine local temporal feature extraction with long-term dependency learning. Four input configurations were designed according to whether lag alignment and diameter history were included, and the proposed TCN-LSTM was systematically compared with standalone TCN and LSTM models. The results show that both diameter history and delay alignment improve prediction performance. Under the current single-run evaluation protocol, the TCN-LSTM configurations yielded lower prediction errors than the corresponding TCN and LSTM models under the same input settings. Under the withlag-withY configuration, the TCN-LSTM model achieved MSE = 0.00259, RMSE = 0.05087, MAE = 0.03949, and R² = 0.96982. After GWO-based hyperparameter optimization, the best TCN-LSTM configuration further improved to MSE = 0.00239, RMSE = 0.04894, MAE = 0.03651, and R² = 0.97207. SHAP-based analysis was further used to provide a post hoc interpretation of the relative contributions of key process variables to diameter variation. Overall, the proposed framework provides a data-driven prediction approach and may support subsequent process analysis and optimization in industrial CZ growth. Full article

While generative AI becomes increasingly available in higher education, faculties find it challenging to design, implement, and evaluate AI-enabled personalized learning systems within accreditation-constrained professional curricula. This method paper describes ADAPT (Assessment-Driven AI for Personalized Tutoring), a home-grown AI tutoring and remediation ecosystem implemented in a required PharmD immunology course. Using standard learning management (Canvas) and assessment (ExamSoft) platforms, a 20-item quiz mapped to six immunology mastery domains (N = 34; mean 69.1%, SD 17.9; Cronbach’s α = 0.73) was used to trigger tiered, structured generative AI remediation at both individual student and cohort levels. Instructional impact was evaluated using reliability indices, item-level difficulty analyses, and paired pre/post-assessment comparisons. Following AI-guided remediation, mean performance increased to 79.8% (+10.7 percentage points), variability decreased (SD 14.4), and assessment reliability improved (ExamSoft KR-20 0.87) compared with the diagnostic exam, the first midterm exam, and the final exam, respectively. Item difficulty stabilized (mean ≈ 0.80), with sustained retention of targeted concepts on the final examination. ADAPT provides a replicable, low-cost methodological blueprint for faculties to independently construct assessment-driven AI tutoring systems and lays the foundational steps for future AI-based predictive analysis workflow for at-risk students. Full article

Diagnosis of cancer is one of the hardest problems faced in modern medicine and involves integrating different data sources such as medical images, genomic profiles and clinical records. Traditional machine learning methods have difficulty handling the high-dimensional and complex correlation properties of multimodal medical data. In view of this, we propose a new Quantum-Enhanced Multimodal Fusion Network (QEMFN) framework to break through traditional image–text matching based on quantum computing principles for CT imaging with genomic sequencing data and EHR information. Our approach utilizes variational quantum circuits for feature encoding, quantum kernel methods for crossmodal attention, and hybrid quantum–classical architectures for final classification. We realize the framework using Google Cirq quantum computing library and validate it on publicly available datasets including TCIA (The Cancer Imaging Archive), TCGA (The Cancer Genome Atlas), and MIMIC-III clinical database. The matched multimodal cohort comprises 847 lung cancer patients, 623 colorectal cancer patients, and 401 liver cancer patients with complete imaging, genomic, and clinical records, assembled via de-identified patient ID linkage across the three archives. The experiment takes steps toward the realization of quantum-enhanced diagnostic systems and offers a path for subsequent experimental confirmation. We theoretically analyze the potential quantum advantage, present detailed implementation details using Cirq, and describe a roadmap to clinical translation for quantum-enhanced diagnostic tools. Full article

This paper evaluates the impact of a Service-Learning (SL) project designed to promote vocations in Civil Engineering. Two university students from UPM presented their Final Degree Projects to 73 high school students at a rural school in Torrelaguna (Madrid, Spain). A mixed-methods approach was used, with pre- and post-activity surveys for the high school students and a focus group with the university presenters. The quantitative results show that knowledge of the profession rose from 7% to 41% and specific interest in the degree doubled from 4% to 8%, although the perception of the field’s high difficulty remained largely unchanged. The activity was rated very positively by 85% of attendees. Qualitative analysis revealed that the university students, who began with low expectations, significantly improved their capacity for improvisation and adaptive communication through audience interaction. The experience also reinforced their vision of engineering’s social impact by connecting it to the youths’ daily realities. The study concludes that the near-peer SL model is a promising tool, generating bidirectional benefits. Full article

Precipitation nowcasting is a critical part of meteorological services and applications. Recently, mainstream research has been focused on adopting deep learning-based models to generate the predictions, yet existing deep learning models face challenges with blurry predictions that fail to capture high-frequency meteorological details, difficulty modeling both local correlations and long-range spatial dependencies, and a fundamental signal–noise confusion within the diffusion process that degrades structural fidelity. In this paper, we propose FADiff, a novel frequency-aware diffusion model based on a hybrid CNN–Transformer network for radar-based precipitation nowcasting. A hybrid CNN–Transformer backbone is first designed to integrate the CNNs with the Transformers, jointly enabling the local and global feature extraction capability of the meteorological dynamics. Subsequently, a novel Frequency-Aware Module (FAM) is proposed to mitigate signal–noise confusion. By transforming features into the frequency domain via the Discrete Cosine Transform (DCT), the FAM performs content-adaptive filtering with a learnable gating mechanism, which is designed to suppress noise-dominant frequency components while benefiting high-frequency signals corresponding to real meteorological structures. Finally, these components are embedded within a latent diffusion model to form an end-to-end nowcasting framework. Extensive experiments on the CIKM and SEVIR datasets demonstrate that the proposed FADiff outperforms state-of-the-art methods across a comprehensive suite of evaluation metrics. Significantly, under high-intensity precipitation thresholds, FADiff exhibits remarkable robustness and stability, presenting its superior capability in generating meteorologically critical structures with high fidelity. Full article

The anomalous logging responses caused by complex geological and downhole engineering conditions, which can be the expansion of a borehole, the formation of fractures, and the mud intrusion, usually result in the absence of some important curves and undermine the accuracy of the reservoir evaluation. The strong nonlinearity and non-stationarity of the log curves remain problematic to conventional interpolation and statistical techniques; the traditional models do not take into account any sequential relationship between points along the depth axis, whereas the deep sequence models can only regress on the points, which limits their capability of ensuring the overall geological consistency. In order to resolve these difficulties, this paper introduces a Geology-Balanced Time Series Conditional Generative Adversarial Network (GC-TSGAN) in which the lithological data is converted into an initial state in the form of prior conditions and is input into both the generator and the discriminator. The model uses LSTM to learn depth-sequential dependencies and a BCE GAN-based adversarial loss to achieve distributional consistency and local morphological fidelity. Hyperparameter tuning is used with the help of random search and Bayesian optimization. The logging data of 41 wells in the B Basin, Chad, are experimented using GC-TSGAN alongside baseline models such as RF, XGBoost, LSTM and ANN; GC-TSGAN is proven to be much better than baseline models in terms of the RMSE, MAE, and squares of predicate and value. The findings confirm that the proposed model can effectively reconstruct log curves with high precision even in a complicated geological environment, thereby providing quality data for performing geological modeling and evaluating the reservoirs. Full article