Search Results (1,584)

This paper presents a physics-guided machine learning algorithm for classifying femur fracture presence and subtype using non-ionising radiofrequency (RF) spectral data. Multi-sensor S-parameter responses were generated from a femur phantom model across 1.0–3.0 GHz, producing 104 specimens representing intact bone and three fracture geometries. An exploratory, effect-size-driven band-selection algorithm identified a compact discriminative region between 1.74 and 1.90 GHz. Interpretable classifiers, including k-nearest neighbours (KNN), decision trees, linear discriminant analysis, and Naïve Bayes, were evaluated under strict specimen-level hold-out protocols to prevent data leakage. The KNN algorithm achieved 99.3% frame-level accuracy and 100% specimen-level accuracy for binary fracture detection while maintaining strong robustness in multiclass subtype classification, validated through sensor ablation and leave-one-subtype-out testing. The results demonstrate that compact, interpretable algorithms operating on band-limited RF spectra can achieve reliable, radiation-free fracture classification, supporting future development of continuous and edge-deployable monitoring systems. Full article

This study investigates the feasibility of acoustic signal analysis for the assessment of weld bead quality in the shielded metal arc welding (SMAW) process. The work focuses on comparing time-domain acoustic signals and time–frequency spectrogram representations for the classification of welds as accepted or rejected according to standard welding inspection criteria. Two key acoustic descriptors, the fundamental frequency (F₀) and the harmonics-to-noise ratio (HNR), were extracted and analyzed to evaluate statistical differences between the two weld quality classes. Statistical tests, including Anderson–Darling, Levene, ANOVA, and Kruskal–Wallis (α = 0.05), revealed significant differences between accepted and rejected welds. Accepted welds exhibited a bimodal HNR distribution associated with transient arc instability at the beginning and end of the bead, whereas rejected welds showed more uniform acoustic behavior throughout the process. Subsequently, the acoustic data were represented using both audio signals and spectrograms and used as inputs for ten supervised machine learning models, including Support Vector Classifier (SVC), Logistic Regression (LR), k-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), Extra Trees (ET), Gradient Boosting (GB), and Naïve Bayes (NB). The results demonstrate that spectrogram-based representations significantly outperform time-domain signals, achieving accuracies of 0.95–0.96, ROC-AUC values above 0.95, and false positive and false negative rates below 6%. These findings indicate that, while scalar acoustic descriptors provide statistically significant insight into weld quality, time–frequency representations combined with machine learning enable a more robust and reliable framework for automated non-destructive evaluation, particularly in manual SMAW processes under realistic operating conditions. Full article

A novel flexible single-parameter polynomial distribution is presented in this study. The forms of hazard rate and density functions are examined. Additionally, exact formulas for a number of numerical characteristics of distributions are obtained. Stochastic ordering, the moment technique, the maximum likelihood, and a Bayesian analysis of this novel distribution based on type II censored data are used to derive the extreme order statistics. We construct Bayes estimators and the associated posterior risks using a variety of loss functions, such as the generalized quadratic, entropy, and Linex functions. Since tractable analytical formulations of these estimators are unattainable, we suggest using a simulation technique based on Markov chain Monte-Carlo (MCMC) to examine their performance. Furthermore, we construct maximum likelihood estimators given initial values for the model’s parameters. Additionally, we use integrated mean square error and Pitman’s proximity criteria to compare their performance with that of the Bayesian estimators. Lastly, we apply the new family to many real-world datasets to show its versatility, and we model cancer survival data using this new distribution to explain our methodology. Full article

Objective: The present study aimed to compare muscle thickness and physical performance in different functional tests predicting falls between older adults with low and high fall risk. Methods: Seventy-one community-dwelling older women (74.5 ± 8.5 years old) volunteered for this study. The Berg Balance Scale (BBS) was used to stratify the sample as low and high risk for fall (BBS cutoff = ≥ 50 points). The performance in the Timed Up and Go Test (TUGT), 5-repetition sit-to-stand test (5xSST), 3 m walk test (3mWT), and 3 m backward walk test (3mBWT) was assessed. The elbow flexor and knee extensor muscle thickness were obtained by ultrasound (USD). A linear mixed model analysis was used to determine between-group differences in functional mobility and muscle thickness, and Bayesian analysis was applied to check the probability to replicate the same results (i.e., the magnitude of the evidence). Results: The low-fall-risk group exhibited significantly better performance only in 3mWT (mean difference = 0.84 s [95% CI: 0.40 to 1.29 s]; p = 0.001) and 3mBWT (mean difference = 1.54 s [95% CI: 0.21 to 2.85 s]; p = 0.024). The Bayes Factor (BF) for performance on the 3mWT and 3mBWT shows that the low-fall-risk group has a probability of 98.7% (BF10 = 77.3) and 99.7% (BF10 = 368), respectively, of performing better than the high-fall-risk group. Conclusions: Based on inferential and Bayesian analysis, the performance in 3mWT and that in 3mBWT were classified as very strong to excellent instruments, respectively, for differentiating older women with high fall risk. Full article

Accurate prediction of compost maturity is vital for ensuring quality, safety, minimum substrate weight loss and agronomic performance of compost products. In this study, eight supervised machine learning (ML) classification models including Random Forest, Logistic Regression, Decision Tree, Gaussian and Multinomial Naive Bayes, K-Nearest Neighbors, Support Vector Machine, and AdaBoost were systematically evaluated for their ability to predict compost maturity using three key indicators: cation exchange capacity (CEC), carbon to nitrogen ratio (C/N), and humic acid (HA) content. A dataset comprising 756 samples (4 composting/vermicomposting systems × 7 treatments × 9 time points × 3 replicates) was generated. To reduce replicate-induced variability and ensure robust machine learning analysis, triplicates were averaged at each time point, resulting in 252 effective observations used for model development. Pearson correlation and heatmap analysis indicated strong interdependencies among CEC, HA, total nitrogen (TN) and organic matter (OM) content, confirming their collective utility in compost maturity classification. Model performance was assessed based on classification metrics (accuracy, precision, recall, F₁-score) and regression-based error indicators, including mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), and coefficient of determination (R²). Ensemble models, particularly RF and AdaBoost, showed the highest predictive accuracy (up to 0.98) and lowest error rates (e.g., MAE < 0.05, RMSE < 0.1, R² > 0.95) when predicting CEC and C/N-based maturity classes. HA-based predictions showed slightly lower precision and higher variance across models. Full article

This study proposes an integrated software model for automatic document classification and metadata generation based on the Dublin Core standard to address the issue of rapid and consistent management of archival documents in a digital environment. This approach combines the stages of receiving incoming documents, converting them to text using optical character recognition (OCR), image preprocessing (binarization, deskew, noise reduction), and text cleaning and vectorization (TF–IDF) into a single pipeline. In the document classification stage, the Bidirectional Encoder Representations from Transformers (BERT) model with a context-sensitive transformer architecture is used, along with classical machine learning models (Logistic Regression, Naive Bayes, Support Vector Machine) and an ensemble approach (LightGBM), to increase the accuracy by modeling the document content at a deep semantic level. Experiments were conducted on the RVL-CDIP dataset, and the OCR efficiency was evaluated using the Character Error Rate (CER) indicator, and the classification results were evaluated using the accuracy, precision, recall and F1-score metrics. The results confirmed the high stability and generalization ability of the BERT (accuracy, 95.1%; F1, 95.0%) and LightGBM (accuracy, 93.2%; F1, 93.2%) models. In the final stage, OCR, NER, and classification outputs are automatically organized into Dublin Core metadata elements (Title, Creator, Date, Description, Subject, Type, Format, Language) and exported in JSON/XML formats. This automation significantly reduces manual cataloging effort and improves indexing and retrieval efficiency in digital archival systems. Full article

Background/Objectives: Glioblastoma is the most common and aggressive primary malignant brain tumor in adults, characterized by infiltrative growth and poor prognosis. Achieving maximal resection without inducing neurological deficits remains a challenge in glioblastoma surgery. While 5-aminolevulinic acid-based fluorescence-guided surgery supports intraoperative tumor visualization, its reliability is limited by patient variability and weak fluorescence signals. This study proposes a machine learning framework to enhance fluorescence-guided surgery sensitivity by analyzing surgical microscope images at the pixel level. Methods: Fluorescence-mode neurosurgical microscope images of synthetic samples with known Protoporphyrin IX (PPIX) concentrations were used to train three classifiers (Support Vector Machine, Naïve Bayes, Neural Network) for pixel-wise fluorescence detection. In parallel, three contrastive-learning-based Variational Autoencoders (VAE, $\beta$ = 1, 2, 3) were evaluated for detecting weak fluorescence beyond visual perception. Additionally, a regression model was trained to relate pixel features to PPIX concentration. The best-performing VAE ($\beta$ = 1) was subsequently trained on real intraoperative data, and its detection sensitivity was compared to annotations from four experienced surgeons. Results: The proposed model achieved the highest detection rates on synthetic test data when calibrated for 99% specificity. Applied to real intraoperative images, the model revealed fluorescent areas substantially larger than those marked by experienced surgeons. In non-5-ALA control cases, minimal false positives were observed, indicating a specificity exceeding 99.9%. The regression model reliably quantified PPIX concentration in synthetic samples ($R^2=0.92$). Conclusions: By enabling more sensitive and objective fluorescence detection, this approach offers a valuable tool for improving surgical decision-making and facilitating safer, more extensive tumor resections. Full article

Fusarium ear rot (FER) caused by Fusarium verticillioides is a major constraint on global maize production. The genetic basis of FER resistance is not yet fully understood, and the development of effective breeding strategies for improving FER resistance is still a critical priority. In the present study, a collection of 254 CIMMYT tropical maize lines genotyped with 955,690 high-quality SNPs was used to conduct genome-wide association studies (GWAS), complemented by QTL (quantitative trait locus) mapping in two recombinant inbred line populations. Additionally, genomic prediction (GP) exploring various statistical models and SNP selection schemes was implemented to optimize predictive accuracy for improving FER resistance. The broad-sense heritability estimates of FER resistance were 0.69–0.86 in the CML panel across six environments and 0.39–0.69 in the two RIL populations. At a p-value threshold of 2.61 × 10⁻⁷, GWAS identified 18 SNPs significantly associated with FER resistance across six environments, and in single environment analyses, their phenotypic variance explained (PVE) values ranged from 0.68 to 13.75%, with 13 SNPs exceeding a PVE of 5%. At a p-value threshold of 1 × 10⁻⁵, an additional 37 SNPs were detected, clustering within seven environmentally stable regions identified in at least two environments. Furthermore, 13 haplotype blocks exhibiting significant phenotypic differences were identified within these stable regions, with PVE values ranging from 2.39 to 15.24%, 9 of which exceeded 5%. QTL mapping in the two RIL populations revealed 27 moderate-effect QTLs at a LOD threshold of 2.5, including four detected repeatedly across environments, though only one QTL overlapped with the GWAS-identified region. Moderate genomic prediction accuracies of FER severity were achieved across models, with GBLUP and BayesB outperforming other models, and the prediction accuracies of these two models in the three populations were all around 0.5. Integrating the significant SNP set from genetic mapping results with a 100-SNP background set enhanced the stability of cross-population predictions. These results implied that FER resistance in tropical maize is controlled by multiple genomic regions with small-to-moderate genetic effects, whereas the consistency of genomic regions detected by GWAS and QTL mapping is low. Genomic prediction incorporating regions identified across different genetic backgrounds emerges as a promising tool for accelerating FER resistance breeding. Full article

Sustainable groundwater management is essential for water security and human health protection. Fluoride contamination is a serious concern for the sustainable drinking water supply in many parts of Pakistan, including Balochistan, where arid climate conditions and geological formations support the enrichment of fluoride. The toxic nature of fluoride contamination has resulted in negative health impacts on the local population. Conventional geostatistical techniques are usually ineffective to delineate the nonlinear relationships that affect the distribution of fluoride. This study aims to develop a machine learning-driven spatial modelling framework for classifying the spatial distribution of fluoride contamination in groundwater across the study area. The model will help to understand the spatial variability of fluoride contamination and its controlling factors, essential for effective mitigation and early warning systems. Physiochemical elements were used as predictive features in this study, utilizing a unified feature importance framework combining hydrogeochemical analysis, spatial distribution assessment, and ensemble SHAP-based interpretation to identify consistent predictors. Model performance was evaluated using a nested cross-validation framework, followed by validation on an independent geology-informed spatial holdout test set to ensure realistic generalization. Among machine learning models, the Logistic Regression (LR), Support Vector Classifier (SVC), XGBoost (XGB), Decision Tree (DT), Gaussian Naïve Bayes (GNB), and K-Nearest Neighbours (KNN) were evaluated. Support Vector Classifier (SVC) demonstrated a high predictive performance. On the independent spatial holdout dataset, SVC achieved an overall accuracy of 0.75 and an area under the receiver operating characteristic curve (AUC) of 0.821. In addition to classification, a human health risk assessment was conducted using chronic daily intake (CDI) and hazard quotient (HQ) calculations for children and adults, identifying several high-risk water supply schemes. The prediction maps successfully delineated high-risk fluoride points across specific areas, offering a tool for sustainable groundwater management. This study helps to achieve a Sustainable Development Goal (Clean Water and Sanitation, SDG#6) and promotes long-term sustainable planning in water-stressed areas by integrating spatial machine learning mapping and health risk assessment. Full article

This research investigates the optimization of surface integrity in powder-mixed electrical discharge machining (PMEDM) through the innovative use of Jatropha biodielectric fluid enhanced with titanium dioxide (TiO₂) nanoparticles. A comprehensive experimental framework was developed using design expert software (DOE) with Response Surface Methodology (RSM) to systematically analyze the machining of AISI D2 tool steel using copper electrodes. The study examined five critical process parameters, gap current (Ip), pulse-on duration (Ton), pulse-off time (Toff), gap voltage (V), and powder concentration, evaluating their combined effects on surface roughness (SR), surface crack density (SCD), and residual stress characteristics. Advanced characterization techniques including scanning electron microscopy (SEM) were employed to analyze surface topography and subsurface microstructural changes. The optimization process successfully identified optimal machining conditions of current = 9 A, Ton = 100 µs, Toff = 10 µs, and gap voltage = 65 V, achieving exceptional surface quality with a minimum surface roughness of 3.22 µm. Remarkably, these optimized parameters resulted in crack-free surfaces with zero surface crack density and minimal residual stress values across the 2θ range of 90° to 180°. To enhance predictive capabilities, supervised machine learning algorithms were implemented to model surface roughness behavior. Comparative analysis of classification algorithms demonstrated that Support Vector Machine (SVM), k-Nearest Neighbors (kNNs), and Gaussian Naïve Bayes achieved superior performance with F1-scores of 0.88 and prediction accuracies of 90%. The integration of sustainable Jatropha biodielectric with TiO₂ nanoparticles represents a significant advancement in environmentally conscious precision machining, while the machine learning approach establishes a robust framework for intelligent process optimization and quality prediction in advanced manufacturing applications. Full article

Postoperative stroke is a serious and fatal condition that often affects elderly surgical patients. This rare but severe complication arises from complex interactions between comorbidities, physiologic instability and demographic disturbances that traditional risk tools often fail to capture.This study aims to develop and validate a machine learning model with an improved ability to predict the risk of postoperative stroke in elderly patients utilising the comprehensive clinical and demographic ICU data from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. External validation was performed on MIMIC-III and the eICU Collaborative Research Database, with eICU being the primary validation set. We identified postoperative surgical intensive care unit (SICU) patients aged 55 years or older from all databases. A strict temporal window of the first 24 h of ICU admission was applied across all three datasets while extracting features like laboratory measurements and vital sign summaries in order to ensure that all predictor values were derived from a fixed observation period at the beginning of ICU stay. After preprocessing, applying Multivariate Imputation by Chained Equations (MICE) imputation and initial screening of 88 candidate variables, 20 clinically meaningful predictors were selected through a multistage feature selection pipeline incorporating RFECV and permutation importance. SHAP analysis and LIME analysis were used for interpretability. We evaluated ten machine learning techniques, including Logistic Regression, Decision Tree, Random Forest, K-Nearest Neighbors (KNNs), Support Vector Machine (SVM–RBF Kernel), Gradient Boosting (GBDT), Neural Network, XGBoost, CatBoost, Naive Bayes. Among them, Random Forest demonstrated strong predictive performance by achieving an AUROC of 0.8072 (95% CI [0.7890, 0.8253]) on the internal validation set. The model also achieved AUROC of 0.7557 (95% CI [0.7267, 0.7794]) and 0.9144 (95% CI [0.8893, 0.9378]) on the external validation sets eICU and MIMIC-III, respectively. Mean systolic blood pressure, Elixhauser score, minimum calcium, and minimum INR (PT) were consistently identified as the most influential predictors through both SHAP analysis and LIME analysis, thus strengthening model interpretability. Our findings suggest that a Random Forest-based predictive model can provide an accurate and generalisable prediction of postoperative stroke in elderly ICU patients using routinely collected physiologic and laboratory data. This also supports early risk stratification and targeted postoperative monitoring. Full article

Chronic kidney disease (CKD) is a global healthcare issue that highlights the need for early identification for better quality of life for patients. This study evaluates various machine learning (ML) classifiers on datasets from UCI and self-collected sources in search of the best methods for CKD classification. This review examines commonly used ML models like support vector machine, K-nearest neighbor, naïve Bayes, decision trees, random forest, logistic regression and boosting-based ensemble methods. The results demonstrated the highest performance of ensemble methods. Despite these promising results, challenges related to model integration and interpretability still exist. Transparent models that are reliable and efficient are suitable for enhancement of clinical application(s). By overcoming these challenges, the work highlights importance of ML for CKD detection and treatment paving the way for artificial intelligence (AI)-driven healthcare solutions that are both effective and trustworthy. Full article

Change-point models deal with ordered data sequences. Their primary goal is to infer the locations where an aspect of the data sequence changes. In this paper, we propose and implement a nonparametric Bayesian model for clustering observations based on their constant-wise change-point profiles via a Gibbs sampler. Our model incorporates a Dirichlet process on the constant-wise change-point structures to cluster observations while simultaneously performing multiple change-point estimation. Additionally, our approach controls the number of clusters in the model, not requiring specification of the number of clusters a priori. Satisfactory clustering and estimation results were obtained when evaluating our method under various simulated scenarios and on a real dataset from single-cell genomic sequencing. Our proposed methodology is implemented as an R package called BayesCPclust and is available from the Comprehensive R Archive Network. Full article

As the global aging population increases, the early detection and prevention of Alzheimer’s disease (AD) have become important in public health. To solve the problems of subjectivity and low timeliness of traditional assessment methods, this paper proposes a multimodal dementia prevention system that combines physiological sensing, a gamification interface, and a classification model. The system includes an interactive joystick to measure pulse and blood pressure. A Chinese music game app increases the participation of the elderly and reduces their sense of rejection through gamification interaction. After the physiological data were standardized by Z-score, they were input into three small sample classifiers (Gaussian Naïve Bayes, Fisher Linear Discriminant Analysis, and Logistic Regression) for the binary classification of AD. The system performance was evaluated using the Leave-One-Out cross-validation method. Experimental results show that Logistic Regression performed best in situations with extremely small samples and class imbalance, with an F1-score of 0.700, which was higher than the other two. Dynamic features and model fusion technologies need to be integrated to further enhance the clinical application potential of the system in the early prediction of dementia. Full article

The need for effective inventory management in the transition from “Just-in-Time” to “Just-in-Case” supply chain strategies was addressed by developing a machine learning model to predict inventory backorders. Using a large store keeping unit dataset, five supervised learning algorithms, namely, logistic regression, random forest, k-nearest neighbours, Naïve Bayes, and gradient boosting, were implemented with Python 3.13 Data imbalance was managed using the synthetic minority over-sampling technique, while power transformation was applied to improve data distribution and model performance. Among the models, random forest demonstrated the highest prediction accuracy at 98% and a strong receiver operating characteristic score of 0.897, making it the best model for backorder prediction. This approach enhances supply chain resilience and proactive inventory control, enabling manufacturers to mitigate risks of stockouts and optimize resource planning. It is necessary to incorporate advanced balancing techniques, hyperparameter tuning, and cross-validation methods to improve predictive performance further. Full article