Search Results (2,032)

Accurate color classification plays a critical role across diverse fields, from textile manufacturing and environmental monitoring to biomedical diagnostics. This study introduces a machine-learning-driven approach to spectral color sensing using SENSIPATCH, a compact, wearable sensor system; while SENSIPATCH integrates multiple sensing modalities, including bioimpedance, electrochemical, thermal, humidity, and vibrational sensors, this work specifically utilizes its spectrometer module, which comprises multi-wavelength LEDs and photodiodes. Targeting the classification of 100 standardized PANTONE colors, the proposed framework is evaluated under controlled lighting conditions to ensure repeatable spectral acquisition. The experimental design includes both firm and loose contact scenarios to emulate variability in wearable placement. A structured data-preprocessing pipeline involving baseline correction, bootstrapping, and Z-score normalization was employed to enhance signal quality and improve model generalization. Five machine learning models were evaluated: Random Forest, SVM, MLP, CNN, and LSTM. The MLP demonstrated the strongest classification performance. Notably, the MLP achieved consistent accuracy across both contact conditions, indicating robustness against sensor placement variations. These results highlight the feasibility of compact LED-based wearable spectroscopy for reliable color classification under controlled measurement conditions, providing a baseline for future extensions to more diverse lighting conditions. Full article

Many cities adopt greening strategies to reduce contamination from combined sewer overflows (CSOs). Nonetheless, quantifying the impact of urban greening on CSO-affected water quality at the city scale remains challenging. To address this challenge, this work leveraged supervised learning to link water swimmability with the greening of a CSO shed (the drainage area of a CSO outfall), using New York City (NYC) as a case study. Random forest classification models were built to predict water swimmability after rainfall at 46 sites in NYC water bodies impacted by CSOs. A 14-feature model (AUROC =0.81, accuracy = 0.78) revealed that greening improved local water quality. However, water flow speed, antecedent rain depth, and CSO shed area were also influential. A simplified four-feature model (AUROC = 0.8, accuracy = 0.75) explored links between levels of greening and the probability of non-swimmable waters ($P_{ns}$) following different 18 h rainfall depths. Increased greening was found to be most impactful in reducing $P_{ns}$ for CSO sheds discharging to water bodies with flow speeds < 6 cm/s. For CSO sheds discharging to water bodies with flow speeds $\ge$ 14.7 cm/s, urban greening had no impact on $P_{ns}$. The work illustrates the utility of supervised learning in supporting citywide decisions regarding urban greening investments. Full article

The mechanical behavior of aqueduct structures exhibits highly complex characteristics during prestress tensioning, making it difficult for the traditional double-control method to accurately predict and real-time control the key stresses. To improve the construction safety of prestressed tensioning and the prediction accuracy of structural prestress responses, this study develops a rapid structural mechanical property prediction method based on machine learning. Taking prestressed aqueducts as the research object, a system of “finite element simulation—sample generation—machine learning prediction” is established. Firstly, multiple groups of tensioning parameter combinations are designed via Latin hypercube sampling, and the stress responses are obtained through finite element analysis to form a high-quality training sample library. Subsequently, critical structural features are extracted based on mesh reconstruction, and stress prediction models are established using the K-Nearest Neighbors (KNN) and Random Forest algorithms respectively; the prediction performance of both models is compared and validated against finite element simulation results. Furthermore, the prediction outputs of the optimal machine learning model were used to analyze the stress distribution and potential stress concentration issues of the structure during the tensioning process. The comparative analysis results indicate that the Random Forest model performs best in terms of stress prediction accuracy and stability, and its prediction results are highly consistent with those of the finite element method. Compared with traditional finite element condition analysis, the machine learning model can complete multi-condition stress prediction in a shorter time. Leveraging its high-efficiency prediction capability, local high-stress areas of the structure in the tensioning construction scheme can be identified, thereby providing effective optimization schemes to improve the stress distribution. The mechanical response prediction method for the prestress tensioning process of aqueducts, with machine learning as the core, constructed in this paper realizes the rapid and reliable prediction of key stresses throughout the entire prestress tensioning process. This method can be applied to assist in optimizing tensioning construction schemes and construction monitoring, providing a practical technical solution for safety control of aqueduct structures during the prestress construction stage. Full article

Air pollution caused by fine particulate matter (PM_2.5) poses a serious public health threat in many South Asian megacities where monitoring networks remain limited. Lahore, Pakistan—frequently ranked among the world’s most polluted cities—still lacks reliable short-term PM_2.5 forecasting systems. This study develops a performance-weighted ensemble machine learning framework that integrates satellite observations, meteorological reanalysis data, and ground monitoring measurements to improve daily PM_2.5 prediction. Eleven predictor variables were processed using a unified Google Earth Engine pipeline, including MODIS aerosol optical depth, Sentinel-5P trace gases (CO, NO₂, SO₂), and ERA5 meteorological parameters. Four tree-based machine learning algorithms—Random Forest, XGBoost, LightGBM, and CatBoost—were trained using daily observations from 2019 to 2023. Model evaluation using an independent 2024 dataset showed strong predictive capability, with Random Forest achieving R² = 0.77 (RMSE = 24.75 µg m⁻³), XGBoost R² = 0.76 (RMSE = 26.32 µg m⁻³), CatBoost R² = 0.73 (RMSE = 30.39 µg m⁻³), and LightGBM R² = 0.70 (RMSE = 32.75 µg m⁻³). To further enhance performance, the best models were combined into a weighted ensemble (RF 0.5, XGBoost 0.3, and CatBoost 0.2), which produced the highest validation accuracy (R² = 0.77; RMSE = 23.37 µg m⁻³). Statistical testing using paired t-tests and Diebold–Mariano tests confirmed that the ensemble significantly reduced forecast errors compared with individual models. Feature importance analysis revealed that surface pressure, temperature, CO, and NO₂ were the most influential predictors of PM_2.5 variability. The proposed framework demonstrates that combining satellite data, reanalysis meteorology, and ground observations through ensemble learning can provide accurate and scalable air quality forecasting for data-limited urban environments. Full article

Background/Objectives: Postoperative pulmonary complications (PPCs) following abdominal surgery are associated with prolonged hospitalization, delayed recovery, and increased mortality. Because nursing surveillance is essential for early detection and timely intervention, this study aimed to develop a holistic nursing surveillance decision support system integrating PPC risk prediction with structured nursing action recommendations. Methods: In this retrospective cohort study, electronic medical record (EMR) data from approximately 6900 adult patients who underwent abdominal surgery at a single institution between January 2015 and September 2023 were analyzed. The study protocol was approved by the Institutional Review Board, and the requirement for informed consent was waived because of the retrospective study design. PPC risk was predicted using a tabular multilayer perceptron (MLP) encoder with SHapley Additive exPlanations (SHAP)-based feature weighting and a random forest classification head optimized via Optuna. Class imbalance was addressed using weighted sampling, class weighting in BCE(Binary Cross Entropy) With Logits Loss, and decision-threshold optimization. For clinical decision support, a large language model generated structured nursing surveillance recommendations in an action–evidence–rationale JSON format and was aligned through supervised fine-tuning (SFT) using human-evaluated cases. Results: The prediction model achieved an AUROC of 0.810, with an accuracy of 0.811, precision of 0.547, and recall of 0.545. In expert evaluation, the SFT-aligned model improved recommendation quality, reducing incorrect nursing actions from 19.3% to 8.0%. Conclusions: The proposed system demonstrates the feasibility of an end-to-end nursing surveillance decision support framework linking PPC risk prediction with structured clinical recommendations. The findings suggest its potential to support more accurate risk prediction and more actionable nursing surveillance for patients undergoing abdominal surgery. Full article

Accurately identifying medium- and low-yield farmlands (MLYF) and diagnosing their constraints are essential for targeted improvement of productivity and national food security. However, traditional evaluation is usually limited by coarse spatial resolution and high labor costs, and a methodological gap remains between large-scale MLYF classification and system constraints diagnosis. To address the current methodological gaps, this study developed a comprehensive framework to determine the spatial distribution of MLYF in northern China and clarify their key constraints. The framework combined the Spatio-Temporal Random Forest (STRF) algorithm with vegetation indices (VIs), climate, and soil data to delineate MLYF and uses interpretable machine learning to diagnose major constraints. The model showed high explanatory power and ensured the reliability of attribution results. The results showed that MLYF exhibited obvious spatial heterogeneity, accounting for 48.66% of the total cultivated land in the study area. These MLYF are primarily concentrated in the northwestern Loess Plateau (LP), the central Along the Great Wall (ATGW) region, and the peripheries of the Huang-Huai-Hai (HHH) Plain. In addition to spatial classification, our analysis revealed significant differences in constraint mechanisms: soil structural, nutrient, and salinization constraints predominantly restrict productivity in the HHH Plain, whereas water stress and soil erosion are the primary drivers of yield gaps in the LP and ATGW regions. These findings provide new data and insights for understanding the spatial heterogeneity of farmland quality in typical dryland agricultural regions in northern China, and offer a scientific basis for targeted land improvement and regional agricultural sustainability. Full article

Odour recognition with low-cost gas sensors is challenging in open-air settings due to the non-specificity of the sensors and environmental variability. This can be mitigated by incorporating additional information into the classification process. This paper investigates odour-image multimodality in two case-studies of increasing complexity: banana ripening in open-air environment and strawberry ripening in a glasshouse environment. Data were collected using custom acquisition platforms equipped with cameras and MOX gas sensors operated with temperature modulation. For the visual modality, image classification (MobileNetV3) and object detection (YoloV5) models are trained. For the odour modality, established classical machine learning methods (Random Forest, XGBoost, SVM and Logistic Regression) and neural networks (1D-CNN, LSTM, MLP, and ELM) are employed. Each modality is analysed independently and together to critically assess scenarios in which combining modalities provides a clear advantage over using either modality alone. Results show that models trained on odour data achieve high accuracy in controlled environments but underperform in more dynamic open-air settings. Image-based models are sensitive to the image quality in all environments; however, they are more robust when deployed in different environments. Lastly, it is demonstrated that decision fusion consistently increases the accuracy, by as much as +12.36% in the banana ripening and +3.63% in the strawberry ripening scenario. Where decision fusion does not improve classification accuracy significantly, it is shown that the multimodal approach can still be leveraged to identify high-confidence predictions by selecting samples where both modalities agree on the label. Full article

Falls are a leading cause of paediatric injuries, yet school-based prevention relies heavily on subjective observation rather than objective biomechanical assessment. This paper introduces the Safe Fall framework, integrating a judo-inspired educational programme with an occlusion-robust computer vision pipeline to quantify safe falling strategies. We analysed video recordings of 285 schoolchildren using a multi-stage architecture combining YOLOv8 for detection, SAM 2 for segmentation, and MMPose for skeletal tracking. The intervention yielded significant improvements in 60% of kinematic metrics ($p<0.05$), most notably a $+61.4\%$ increase in descent rate and expanded rolling ranges, indicating a shift from hazardous “freezing” behaviours to controlled energy dissipation. Unsupervised clustering confirmed a migration of students towards safe motor profiles, while a Random Forest classifier achieved an accuracy of 98.3% and an AUC of 0.998 in distinguishing fall quality. These findings demonstrate that integrating pedagogical training with automated vision modelling provides a scalable and evidence-based approach for reducing injury risk in real-world school environments. Full article

Leakage identification in district heating networks is challenging because leakage-induced transient pressure waves often overlap with pressure disturbances triggered by routine operations such as valve regulation, pump speed variation, and emergency shut-off. In addition, the scarcity of high-quality labeled leakage samples limits the robustness of data-driven models under small-sample conditions. To address these issues, this study proposes a compact and moderately interpretable framework for multi-condition identification from transient pressure-wave signals, integrating signal preprocessing, handcrafted statistical feature extraction, multiclass ReliefF-based feature selection, and class-wise generative adversarial network augmentation in the selected feature space. A dataset containing four representative conditions, namely leakage, valve regulation, pump speed regulation, and emergency valve shut-off, was constructed using an integrated indoor district heating network testbed. After Hampel-based spike suppression and zero-phase Butterworth band-pass filtering within 0.5 to 300 Hz, time- and frequency-domain statistical features were extracted, and a compact subset was selected by multiclass ReliefF. A class-wise generative adversarial network was then used to augment the training set in feature space, while all evaluations were performed strictly on real samples. The results show that feature-space augmentation improves robustness and generalization under operational disturbances and noise. Using random forest as the representative classifier, Accuracy and Macro-F1 increased from 0.960 to 0.985, while leakage recall improved from 0.920 to 0.980. Further comparisons confirmed that the ReliefF-selected subset outperformed representative alternatives such as LASSO and mRMR. Overall, the proposed framework provides an effective solution for distinguishing leakage events from operational disturbances and offers practical support for online monitoring and intelligent operation of district heating networks. Full article

This study examines the increasing concern regarding teacher job satisfaction, which has a direct impact on retention, instructional quality, and student outcomes. Traditionally, teacher satisfaction has been evaluated through questionnaires, which present limitations in terms of data efficiency and analyses. In this study, machine learning techniques were applied to data from the PISA 2022 teacher questionnaire in Morocco (N = 2998 lower-secondary teachers). Two multiclass classification targets were defined: overall job satisfaction (SATJOB_class) and satisfaction with the teaching profession (SATTEACH_class), each categorised into three balanced classes: low (<−0.5), medium (−0.5 to 0.5), and high (>0.5) classes. The methodology comprised four key stages. Initially, comprehensive pre-processing was conducted to address missing values, retaining features with fewer than 300 missing entries and applying mode imputation. Subsequently, nine classifiers, including logistic regression, K-nearest neighbours, multinomial naïve Bayes, support vector machine, decision tree, random forest, XGBoost, AdaBoost, and a feed-forward Artificial Neural Network, were evaluated using identical train/test splits and hyperparameter tuning. Third, the model performance was assessed using accuracy, precision, recall, and F1-score. Finally, the feature importance was derived from tree-based and permutation methods. The results indicated that XGBoost outperformed the other models for SATJOB_class with an accuracy (0.61), precision (0.62), recall (0.61), and F1-score (0.61), followed by Random Forest (accuracy = 0.59), Logistic Regression (accuracy = 0.59), and AdaBoost (accuracy = 0.59). For SATTEACH_class, Random Forest led with accuracy (0.59), followed closely by XGBoost (0.58), ANN (0.57), and AdaBoost (0.56). Key predictors of teacher job satisfaction included workload-related variables and school-environment factors, which consistently emerged as the most important features across the best-performing models. The methodology and open-source pipeline provide a reproducible framework for evidence-based interventions to improve teacher retention and instructional quality, offering valuable insights for policymakers and educational administrators. Full article

The increasing risk of air pollution in closed areas like passenger vehicles requires smart and real-time air quality reading solutions. Gases such as carbon monoxide (CO)—which is colorless and odorless and is produced by exhaust systems—air conditioners, and combustion sources are very dangerous to health because they can cause respiratory distress and poisoning at high levels. Traditional in-vehicle CO monitoring systems use a single-point sensor and a fixed threshold, which are insufficient in a dynamic cabin environment subject to factors such as vehicle size, ventilation rate, number of occupants, and incoming traffic. To address these drawbacks, this paper proposes a new E-Nose system with Virtual Sensor-Augmented Embedded Intelligence to estimate the CO concentration in vehicle cabins in real time. The system combines data from cheap gas sensors and improves it using virtual sensor machine learning models trained to predict or enhance sensor responses in real time. Embedded intelligence, deployed locally on edge hardware, supports low-latency processing, dynamic calibration, and noise filtering to respond to fluctuating environmental conditions adaptively. This architecture enables more accurate, robust, and context-aware estimation of CO levels compared to traditional threshold-based methods. Experimental validation across varied vehicular scenarios demonstrates superior precision and responsiveness, providing timely warnings even under complex dispersion patterns. Classifier Gradient Boosting, which builds an ensemble of weak learners sequentially, matched the Random Forest with 99.94% training and 98.59% model accuracy, confirming its strong predictive capability. The system is designed to be cost-effective, scalable, and easily integrable into modern automotive platforms. This study also contributes to the field of smart ecological recording and demonstrates the effectiveness of the virtual sensor-enhanced embedded system as an effective way to improve passenger safety by providing pre-emptive on-board air quality monitoring. Full article

Background: Laryngeal cancer (LC), a common subtype of head and neck cancers (HNC), is most frequently represented by laryngeal squamous cell carcinoma (LSCC). Prognosis largely depends on early detection; however, traditional prognostic tools, including tumor-node-metastasis (TNM) staging, often show limited predictive accuracy. Artificial intelligence (AI), including machine learning (ML), natural language processing, and deep learning (DL), has emerged as a promising approach to improving cancer diagnosis, prognosis, and treatment planning by analyzing clinical data and medical imaging. Objective: This systematic review assesses the role of AI in prognosis, recurrence prediction, and treatment outcomes in LC. Methods: PubMed, MEDLINE, Scopus, Web of Science, IEEE Xplore, and ScienceDirect were searched up to January 2025. A total of 1062 records were identified; after title/abstract screening and full-text assessment, 29 studies were included. Eligible studies involved adult patients with LC and applied AI to diagnose, prognose, predict recurrence, or assess treatment outcomes using human datasets. Study quality and risk of bias were evaluated using the QUADAS-2 and QUIPS. Results: The 29 included studies were mostly retrospective, with sample sizes ranging from 10 to 63,000 patients. Most focused on LSCC, with a higher prevalence in males. The studies utilized various AI techniques, including deep learning models such as convolutional neural networks (CNNs) and DeepSurv, as well as ML algorithms like random survival forest, gradient boosting machines, random forest, k-nearest neighbors, naïve Bayes, and decision trees. AI models demonstrated strong prognostic performance, surpassing Cox regression and TNM staging in predicting survival and recurrence. Several studies reported outcomes related to treatment, such as chemotherapy response, occult lymph node metastasis, and the need for salvage surgery. Methodological quality varied, with biases related to patient selection and confounding factors. Conclusions: AI has the potential to improve prognosis estimation, recurrence prediction, and treatment outcome assessment in LC. However, although AI can be a helpful addition to clinical decision-making, more prospective studies, external validation, and standardized evaluation are necessary before these technologies can be confidently adopted in everyday clinical practice. Full article

The study aims to analyze comprehensive effects of site quality class (SQC), stand density index (SDI), and species composition (SC) on biomass growth. Based on 5872 observations from 2040 permanent sample plots of Chinese fir (Cunninghamia lanceolata (Lamb.) Hook.) plantations from successive national forest resource inventories, five classical growth equations were employed and nonlinear regression and dummy variables were used for modeling. A dominant height (DH) growth model was first developed to determine SQC, followed by a series of stand biomass (SB) growth models incorporating SQC, SDI, and SC (pure vs. mixed stands). Growth differences among different classes or categories were analyzed using inflection age and optimal rotation age. The results show that Korf equation performed best for both DH and SB growth models; SDI contributed the most to SB growth, followed by SQC, with their interaction accounting for over half of the total contribution. Mixed stands grew faster than pure stands; higher SQC was associated with faster growth and earlier attainment of inflection age and optimal rotation age. The productivity increased with rising SDI, but the rate of increase gradually diminished. Different optimal rotation ages should be determined for pure and mixed stands across different SQCs. Reasonable adjustment of harvesting age and control of stand density represent the greatest potential for improving forest productivity. Full article

This study investigates the relevant literature on applications of Artificial Intelligence (AI) for wood as a material using a systematic review and screening process. The Web of Science (WoS) database identified 50 peer-reviewed publications dealing with AI applications for wood as a material. Bibliometrix and VOSviewer software were used to evaluate publication trends, country contributions, keyword co-occurrences, and AI application areas. Based on these analyses, an annual growth rate of 23.28% between 2014 and 2025 (November) in publications published per year was measured and an average of 6.92 citations per publication was observed as of November 2025. Most notably, a considerable increase in AI-focused research after 2023 was identified. Before 2022, work done using AI tools (such as neural networks, deep learning, and others) did not necessarily use the term AI and hence were not found by our search. China, Canada, and Poland were the countries with the highest number of publications. The leading journals with publications on AI applications for wood as a material were Forests and Wood Material Science and Engineering. The most frequently occurring keywords in the publications reviewed were “AI,” “machine learning,” and “deep learning.” In general, according to the publications reviewed, AI applications for wooden materials improved productivity, material evaluation, and quality assurance. The findings highlighted the impact of AI on the sector and show that AI will change the industry. Full article

Ecological restoration—whether active or passive—includes forest development, forest rehabilitation, and a range of other activities that contribute to ecosystem services. To provide a formal framework, we hypothesized how does reforestation (through different forestry practices) affect the conservation of soil functionality? That is, how does reforestation/afforestation/forest restoration improve soil quality? And, specifically, how do they improve physical properties (such as structural stability, infiltration) and chemical properties (such as acidity, electrical conductivity)? For this purpose, we conducted a bibliometric analysis review of the peer-reviewed scientific literature and research reports of numerous articles in order to compile a large database of forest restoration studies, with an emphasis on the Mediterranean region. The final focus was to obtain conclusions about how it affects soil quality. Overall, our examination confirms that deforestation drives a decline in soil carbon and nitrogen, subsequently impairing microbial activity. Consequently, forest removal frequently leads to accelerated erosion, nutrient depletion, and compaction. In contrast, reforestation acts as a critical intervention, stabilizing soil structure, reestablishing fertility, and enhancing soil quality overall. Additionally, three case studies are synthetically presented concerning the short-, medium-, and long-term results of forest restoration projects carried out mainly in central and northern Spain. These cases corroborate the significant role of forest restoration in the control and enhancement of ecosystem services, particularly in relation to soil improvement, the enhancement of hydrological regulation processes within watersheds (runoff, infiltration, erosion), landscape amelioration, and the socio-economic aspects of rural environments. Ultimately, forest restoration is established as a necessary and essential practice in ecological restoration efforts to counteract the impacts of anthropogenic activities. Full article