Search Results (188)

Spatial chromatic instability is currently one of the most robust methods for improving solutions proposed for image-based fire detection systems. Real flames exhibit erratic, turbulent local color variations, providing a more reliable discriminative signal than global color information alone, especially in visually ambiguous non-fire situations. This study proposes a generalizable feature representation based on the Spatial Chromatic Instability Index (ICCS) to measure local RGB variations (ICCS_R, ICCS_G, ICCS_B, and ICCS_T). Two public datasets comprising both fire image files and non-fire imagery were used. The Hilbert–Schmidt Independence Criterion (HSIC) and Silhouette coefficient analysis were used to quantify the statistical dependence between feature sets and the resulting cluster separation. To evaluate the practical discriminatory performance of spatial chromatic instability, three classifiers, i.e., Logistic Regression, Linear SVM, and Random Forest, were employed. To verify the proposed approach’s effectiveness, three deep learning models, Swin Transformer, MobileViT, and ViT-Base-16, were also employed for cross-checking. Performance metrics demonstrated that integrating ICCS features into global color features improved classification. Logistic Regression performed best overall on the Kaggle dataset when local ICCS features were included, achieving an accuracy of 0.935 and an F1-score of 0.958. For the Mendeley dataset, Linear SVM achieved an accuracy of 0.862 and an F1-score of 0.881. The ICCS is a robust, easy-to-understand, and fast approach for identifying fires. It has real potential in early warning systems, mainly due to its limited requirements for computing power. Full article

Breast cancer is the most commonly diagnosed cancer in women, with early detection playing a critical role in clinical outcomes. Mammography remains the standard screening modality, producing X-ray images used to assess mammographic density, a key indicator of the proportion of fibroglandular tissue within the breast. The Breast Imaging-Reporting and Data System (BI-RADS) classification system is widely used to report density across four qualitative categories. High density can obscure malignancies and is independently associated with elevated breast cancer risk. Manual interpretation of mammographic density is prone to subjectivity and inter-observer variability, and supervised learning-based estimation methods trained on subjective labels may reflect this inherent subjectivity. This work proposes an unsupervised framework for quantitative breast density estimation that requires no labeled data in its core pipeline. Expert labels are used exclusively to calibrate post hoc discretization thresholds for binary classification, enabling comparison with supervised methods in the literature. The main contributions include: (i) an adaptive Region of Interest (ROI) extraction algorithm, (ii) a Convolutional Neural Network (CNN) based unsupervised segmentation pipeline tuned for mammographic density separation, (iii) a novel confidence metric for identifying unreliable segmentation outputs, (iv) a label correction mechanism for low-confidence cases, and (v) a confidence-filtered majority voting scheme for per-patient classification. The framework is evaluated on two public datasets, namely DDSM and INbreast, with segmentation performance yielding Silhouette scores exceeding 0.92. Agreement with expert labels reaches 71.43% and 79.28% for DDSM and INbreast, respectively. Image-level clustering quality assessment confirms effective unsupervised labeling, with Silhouette scores averaging 0.57 for DDSM and 0.50 for INbreast. The proposed framework provides a practical and non-subjective model for quantitative breast density estimation, with potential utility as a decision-support tool for radiologists that can be considered in clinical practice after further investigation. Full article

The Rio Santiago basin is one of the most environmentally stressed river systems in Mexico, with persistent organic, nutrient, microbial, surfactant, and metal contamination. This study develops a near-term quantum machine learning workflow for environmental monitoring and water-pollution profiling using multivariate records from 13 stations between 2009 and 2022. QML is evaluated here because quantum feature maps can define nonlinear, interaction-rich kernels that remain executable on present quantum hardware, providing an alternative representation to compare with classical PCA, RBF, UMAP, and HDBSCAN baselines rather than a presumed computational advantage. After quality screening, log transformation, standardization, and domain-guided feature selection, pollution profiles are evaluated across PCA, RBF spectral clustering, UMAP/KMeans, UMAP/HDBSCAN, a simulated ZZ-style quantum feature-map kernel, and Qiskit Runtime hardware evaluations of the same kernel concept. The initial cleaned-data results show that classical PCA clustering identifies broad lower-load, high organic/surfactant, and rain-season solids/microbial profiles. UMAP/HDBSCAN provides the strongest cleaned full-sample nonlinear baseline, with a silhouette score of 0.568 after excluding 177 noise samples. The simulated quantum-kernel representation separates station-linked gradients, while matched n = 650 stability diagnostics show near-identical quantum-kernel clustering across random initializations (mean ARI = 0.994 for cleaned data) but retain the RBF kernel as the strongest nonlinear comparator. Two 24-sample Qiskit hardware runs and two matched 8-record hardware checks provide proof-of-execution evidence. The analysis is framed as a controlled representation study, not as a claim of quantum advantage. Full article

Composite-score estimation (or assessment auditing) and student profiling are two fundamental tasks in Educational Data Mining (EDM). However, existing studies often treat them as separate problems, typically adopting a sequential pipeline in which clustering is first performed and then used for downstream estimation. Such a fragmented paradigm limits the interaction between latent student-group structures and supervised outcome signals, particularly in low-data educational scenarios. To address this limitation, this study proposes “MTL-Frame”, an end-to-end multi-task learning framework that jointly optimizes student profiling and composite-score estimation. MTL-Frame integrates prototype-based contrastive clustering with context-aware regression to directly inject student profile priors into grade estimation. A dispersion regularization and dynamic loss weighting ensure training stability. Experiments conducted on a real-world blended English-course dataset involving 429 university students show that MTL-Frame outperforms representative single-task regression baselines, including XGBoost, Random Forest, SVR, and LSTM, achieving an RMSE of 1.7532, an MAE of 0.8168, and R² = 0.9812. While this high R² partly reflects the model’s ability to learn the deterministic scoring aggregation, the performance remains strong even when the final exam score is excluded from the inputs (R² = 0.9681), confirming genuine estimation capability. Compared to the strongest single-task baseline (XGBoost), MTL-Frame reduces RMSE by 38.2%. The model also obtains a Silhouette Score of 0.3562, indicating its ability to generate meaningful student profiles while maintaining strong estimation accuracy. These results demonstrate that integrating unsupervised profiling priors into supervised estimation can improve model robustness and provide actionable insights for differentiated instructional intervention. Full article

This study investigates the effect of stabilizing axial load transfer to the bit on mechanical-specific energy during horizontal well drilling. To analyze drilling regimes, field data on WOB, ROP, RPM, TOB, and MSE were used and processed using z-score standardization, outlier removal based on the IQR criterion, and k-means clustering. The selected number of clusters was determined using the elbow method and silhouette analysis; after filtering, the dataset included 1750 observations, and the six-cluster solution was selected for exploratory interpretation. It was found that the lowest MSE values were characteristic of clusters 0, 1, and 5, among which cluster 5 demonstrated the most favorable combination of WOB, ROP, and energy efficiency. Clustering the modeled data confirmed the possibility of identifying drilling regimes with reduced MSE under a stabilized-load scenario. The predicted MSE reduction should be interpreted as a scenario-based, idealized model-based estimate obtained under quasi-steady assumptions rather than as a field-validated performance gain. The results may be used to support the selection of rational drilling parameters and to guide the further development of drilling control systems for horizontal well drilling. Full article

Lead isotope ratios are frequently used in archaeometric provenance analysis; however, the overlap of isotopic fields within the Andean metallogenic belt complicates reliable provenance determination. This study presents a reproducible fidelity-based kernel method for the unsupervised clustering of Andean lead-isotope data and investigates whether a quantum-mechanical similarity space can reveal geologically significant structures beyond the classical Euclidean partition. A dataset of 1522 measurements of ²⁰⁶Pb/²⁰⁴Pb, ²⁰⁷Pb/²⁰⁴Pb, and ²⁰⁸Pb/²⁰⁴Pb was analyzed using a fidelity-based quantum kernel based on a three-qubit Pauli feature map and compared with classical K-means clustering, Gaussian mixture models, and Ward’s agglomerative clustering under various preprocessing strategies and cluster counts. The optimal quantum kernel setup achieved the highest silhouette score at k = 2. However, because analytical uncertainties were not consistently reported across all the compiled sources, an uncertainty-weighted similarity could not be applied. Geological insights indicate that this binary division separates less radiogenic, arc-related compositions from more radiogenic and thorogenic crustal signatures, a contrast that broadly follows the west-to-east crustal-contamination gradient across the Andes. Conversely, the traditional four-cluster approach provides more detailed subdivisions that align with the previously identified isotopic provinces. The reported separation reflects the geometry of the quantum feature space rather than any hardware-level speed-up, as this work represents only a simulation approach. Overall, these findings support a hierarchical and complementary approach to analyzing Pb isotope origins, in which quantum kernel clustering provides robust large-scale separation and classical clustering enhances regional understanding. Full article

The Fifth Industrial Revolution (Industry 5.0) requires human-centric mechanisms that preserve the integrity, reproducibility, and interpretability of AI-driven decisions in smart manufacturing. Injection molding generates heterogeneous, imbalanced, and weakly labeled process data, posing reliability and integrity risks to data-driven quality control. This study proposes an integrity-verified and reproducibility-instrumented secure machine learning framework for operating-regime analysis in injection molding that integrates (i) SHA-256-based data-integrity verification at ingestion, (ii) Pearson correlation-based feature selection, and (iii) a Gaussian Mixture Model (GMM) under a passive-adversary threat model with Transport Layer Security (TLS)-secured transmission. Evaluated on real industrial data (n = 6719 cycles, seven process variables), correlation-based feature selection retained four non-redundant variables and improved the GMM Silhouette Score from 0.274 ± 0.075 (all features) to 0.323 ± 0.014 (95% CI [0.318, 0.329]), a +18.2% relative improvement (paired t(29) = 3.39, p = 0.002; Cohen’s d = 0.62; Wilcoxon p = 0.022), while lowering the Davies–Bouldin Index from 1.63 to 1.17. The Silhouette standard deviation of 0.014 over 30 seeds meets the σ ≤ 0.02 reproducibility target. The GMM resolves four interpretable operating regimes—one low-load regime consistent with nominal operation and three elevated-load regimes (left-side, right-side, and bilateral)—with operator-readable per-variable signatures. Relative to hard-partition and projection baselines, the GMM is not Silhouette-optimal but provides an interpretable, generative regime model that meets the σ ≤ 0.02 reproducibility target. The framework operationalizes human-centric manufacturing security as measurable integrity, reproducibility, and interpretability. Full article

Bipolar fuzzy sets provide an effective framework for representing both positive and negative aspects of information. The necessity of a mathematically rigorous and valid distance measure in bipolar fuzzy environments motivates us to introduce a new real-valued function on the set of bipolar fuzzy sets defined over both discrete and continuous universes of discourse. The proposed function is shown to define a valid metric on the set of bipolar fuzzy sets, as it satisfies all the metric axioms. The metric induced by the real-valued function is inspired by the Canberra distance, and it can effectively quantify the dissimilarity between bipolar fuzzy sets in a normalized and interpretable manner. The practical utility of the proposed metric is demonstrated in a pattern recognition problem, where it successfully recognizes an unknown pattern using known bipolar fuzzy patterns. Using the proposed metric, a bipolar fuzzy C-means clustering algorithm is developed for sentiment analysis. The time complexity of the aforementioned algorithm is also analysed. Experiments conducted on the IMDb Movie Review Dataset demonstrate that the proposed algorithm outperforms k-means, fuzzy C-means, and intuitionistic fuzzy C-means algorithms. The proposed bipolar fuzzy C-means algorithm achieves an accuracy of 90.04%, a precision of 90.51%, a recall of 89.01%, an F1-score of 89.75%, a Root mean square error of 0.1191, and a Silhouette score of 0.75. The findings establish that the proposed metric and the associated bipolar fuzzy clustering approach provide a robust and effective framework of handling sentiment data associated with simultaneous positive and negative opinions. Full article

Background: Advances in monitoring systems featuring wearable sensors, computer vision, and artificial intelligence (AI) have been increasingly used in sports science and rehabilitation practices as a means of movement pattern analysis, injury prevention, and training optimization. These technologies are becoming essential components of athlete-performance analysis and rehabilitation-monitoring systems designed to support biomechanical assessment, athlete development, and movement-quality evaluation. Athlete-performance analysis and rehabilitation monitoring increasingly rely on intelligent multimodal sensing systems capable of continuously evaluating movement quality, biomechanical patterns, training execution, and recovery progress. Human activity recognition (HAR) serves as a key enabling technology for these applications by providing automated assessment of human movement using wearable and vision-based sensing modalities. Therefore, the purpose of this study was to develop and evaluate an attention-based multimodal framework that integrates wearable inertial sensing and RGB video analysis for robust athlete-performance assessment and rehabilitation monitoring through accurate recognition of human movement patterns. Methods: Athlete-performance analysis and rehabilitation monitoring combining inertial sensor data and RGB-based visual information was introduced. Inertial signals were segmented with adaptive windowing, whereas silhouette refinement was performed to analyze motion structures from visual inputs in support of athlete-performance analysis and rehabilitation monitoring. Temporal, spatial, and motion features such as trajectory, orientation, and skeleton-based space-time representations were calculated from multimodal inputs. The proposed framework was designed to capture complex movement dynamics associated with rehabilitation exercises and sports-related motion patterns across heterogeneous sensing environments. Extracted features were then combined and optimized with a multimodal feature fusion approach, while the Ranger optimization algorithm was utilized during the process. An attention-based deep learning classifier was implemented to classify movement activities. Results: The results showed that the proposed framework reached accuracy scores of 88.40% and 87.96% on the VIDIMU dataset and the UTD-MHAD dataset respectively. Recognition performance across both inertial and vision-based modalities provided greater robustness than single-modality solutions. The integration of wearable sensing and computer vision modalities further improved the ability of the framework to analyze complex movement behaviors under varying execution conditions and environmental variations. Conclusion: The proposed multimodal framework provides a foundation for intelligent athlete-performance and rehabilitation-monitoring systems by integrating wearable sensing, computer vision, and attention-based artificial intelligence for robust movement analysis. The findings highlight its potential to support biomechanical assessment, movement-quality evaluation, training-performance monitoring, rehabilitation tracking, and injury-risk management in modern sports and healthcare environments. Full article

This study presents a hybrid artificial intelligence system for latent cardiovascular risk stratification based on publicly available clinical and laboratory data. The proposed system integrates data preprocessing, auxiliary target modeling, latent phenotyping using UMAP and Gaussian mixture models, fuzzy logic-based risk integration, and multilevel predictive modeling. The key contribution of the system is the construction of a proxy target reflecting latent risk progression by combining phenotypic structure, probabilistic indicators, and mortality-related anchor points. Experimental evaluation was conducted on the NHANES dataset. The final analytical cohort included 78,822 adult participants, and the modeling set was divided into training, validation, and test subgroups using a stratified 70/15/15 design. The proposed PhaseFuzzy Hybrid model achieved an accuracy of 0.8390, a balanced accuracy of 0.7302, an F1-score of 0.5225, an MCC of 0.4203, an ROC-AUC of 0.8489, a PR-AUC of 0.5014, and a best LogLoss value of 0.4290 on the test set. The latent phenotyping step also demonstrated acceptable internal validity with a silhouette coefficient of 0.4138 and a confidence of 0.8800. The results demonstrate that the proposed framework identifies hidden cardiometabolic risk factors and provides an interpretable, scalable, and calibration-aware framework for latent cardiometabolic risk stratification and population-level screening. Full article

This paper presents a non-learning-based, seed-dependent, semi-automatic pedestrian candidate generation pipeline for LiDAR point clouds. The proposed method is designed to support 3D annotation workflows by reducing irrelevant candidate clusters while improving the reliability of pedestrian candidate selection under distance-dependent point sparsity. The pipeline integrates distance-aware DBSCAN clustering, Single Template Matching (STM), and Centralized Point Augmentation (CPA). First, LiDAR points within the camera field of view are preprocessed, and pedestrian candidate clusters are generated using DBSCAN parameters configured according to distance intervals. Ground-snapping-based bounding-box refinement and height-based filtering are then applied to improve geometric consistency and reduce non-pedestrian candidates. In the second stage, STM compares PCA-aligned projected silhouettes of candidate clusters with a seed pedestrian template to suppress false positives. To address silhouette instability caused by sparse mid-range pedestrian points, CPA adds centroid-contracted points in the projection-relevant plane before template matching. Experiments on pedestrian-containing frames from the KITTI dataset show that STM improves precision from 27.6% to 60.5% and increases the F1-score from 36.8% to 51.4% compared with the initial DBSCAN-based candidate generation stage. The final CPA configuration improves recall from 44.7% to 46.7% and the overall F1-score from 51.4% to 52.1%, while revealing a precision–recall trade-off. Supplementary IoU analysis shows that the final DBSCAN–STM–CPA configuration maintains meaningful spatial overlap with pedestrian ground-truth boxes, achieving 88.9% at 3D IoU ≥ 0.10 and 81.6% at BEV IoU ≥ 0.25. Runtime analysis further shows that height-based filtering reduces the average per-frame processing time from 151.5 ms to 125.1 ms, while the final CPA configuration introduces only a small overhead, resulting in 126.2 ms per frame. These results demonstrate that the proposed DBSCAN–STM–CPA pipeline can provide reliable pedestrian candidates for semi-automatic 3D labeling without requiring class-specific detector training. Full article

Background and Objectives: Autoimmune thyroiditis (AIT) is often reported patients with PCOS, and may co-occur with altered metabolic risk markers. The aims of this study were to assess baseline differences according to thyroid autoimmunity status, evaluate adjusted associations between thyroid autoimmunity and metabolic parameters, examine associations with PCOS phenotype distribution, and perform k-means clustering to explore data-driven subgroups and their autoimmune enrichment. Materials and Methods: We performed a retrospective cohort study of 651 women with PCOS, comparing those without AIT (n = 506) versus with AIT (n = 145). Associations between AIT and continuous outcomes (HDL; composite metabolic score) were evaluated using robust linear regression with HC3 standard errors and age modeled with a natural cubic spline (3 knots). The association between AIT and phenotype A was assessed via logistic regression with exponentiated coefficients (odds ratios). Unsupervised phenotyping used k-means clustering with silhouette analysis across k = 2…6. Results: Patients with AIT were older (median 40 vs. 35 years; p = 0.021). Phenotype distribution differed by AIT status (overall p = 0.029), with phenotype A less frequent among AIT-positive women (27% vs. 40%). In adjusted robust regression, AIT was associated with lower HDL by β = −4.34 mg/dL (95% CI −9.18 to 0.51; p = 0.081), while obesity (−7.04 mg/dL; p < 0.001) and diabetes (−6.47 mg/dL; p = 0.004) were associated with lower HDL. AIT was not associated with the composite metabolic score (β = −0.005; 95% CI −1.22 to 1.21; p = 0.994), whereas obesity was associated with higher score (β = 1.76; p = 0.003) and urban residence with lower score (β = −0.94; p = 0.011). In logistic regression, AIT was associated with lower odds of phenotype A (OR 0.63; 95% CI 0.41–0.97; p = 0.038), and hypertension was associated with higher odds of phenotype A (OR 1.91; 95% CI 1.20–3.04; p = 0.006). Silhouette analysis supported k=3 clusters (silhouette 0.349), and AIT prevalence was highest in cluster 3 (26.4%) versus clusters 1 (19.9%) and 2 (18.3%). Conclusions: AIT was associated with lower odds of phenotype A, and showed a borderline association with lower HDL-cholesterol but not with a composite metabolic score. Data-driven clustering identified a subgroup with higher autoimmune burden. Full article

Rice crop residue burning (RCRB) in India constitutes a major annual environmental crisis, contributing significantly to regional air pollution, greenhouse gas emissions, and public health deterioration across the Indo-Gangetic Plain. Despite growing policy attention, a systematic, data-driven understanding of the diverse perspectives—agricultural, environmental, economic, and socio-political—expressed across multiple textual sources remains lacking. This study proposes a large language model (LLM)-driven topic modeling pipeline leveraging TopicGPT, an instruction-tuned prompting framework, to extract and evaluate high-level thematic insights from heterogeneous text corpora related to RCRB in India. Our pipeline integrates four sequential stages—topic generation, topic refinement, multi-label topic assignment with grounded evidence, and assignment correction—operated via a locally deployed LLM through the Ollama inference framework. Post-extraction, we evaluate topic quality using ten quantitative metrics encompassing embedding-based coherence, inter-topic diversity, Silhouette score, Davies–Bouldin index, Calinski–Harabasz score, and distribution entropy, among others. Results demonstrate that the proposed pipeline effectively recovers semantically coherent and diverse topic structures from multi-source text data, offering actionable insights for policymakers and researchers addressing RCRB. Full article

Interpreting complex, non-linear Interferometric Synthetic Aperture Radar (InSAR) displacement time-series data for infrastructure risk assessment remains a significant geotechnical challenge. This is particularly evident in regions with established road and railway infrastructures, where the primary objective is monitoring the entire network to ensure safety and operational continuity. Because landslide displacement is a highly complex process affected by a combination of internal geological conditions and external triggers, time-series data inherently encode non-linear trends and periodic fluctuations. To address this, a data-driven framework utilizing a sliding-window transformation to engineer temporal-kinematic features is proposed, providing a broader framework for the contextualization of slope stability assessment from a network perspective. This is paired with Principal Component Analysis (PCA) for dimensionality reduction and evaluated across four unsupervised architectures: K-means, Self-Organising Maps (SOMs), Hybrid SOM-K-means, and PCA-K-means. The comparative evaluation reveals that the PCA-K-means pipeline performed best, offering a highly efficient and scalable workflow. The analysis revealed that the optimized PCA-K-means architecture successfully captured 79.20% of the kinematic variance across the first two principal components. Furthermore, it achieved a robust Between-Cluster-to-Total-Sum-of-Squares (BCSS/TSS) ratio of 71.70%, an optimal Silhouette Score of 0.320, and a low Quantisation Error (QE) of 0.90, demonstrating superior spatial separation and geometric accuracy compared to traditional heuristic methods. When cross-validated against static topographic susceptibility models, the dynamic kinematic clusters exhibited a 23% spatial convergence at the polar bounds of risk, successfully grounding the algorithm’s predictions in physically verified geomorphological features. Relying on the statistical volatility of displacements, this optimal model successfully partitioned the data into five distinct geotechnical risk classes, ranging from stable (Class A) to extreme risk (Class E). The results demonstrate that the developed dynamic framework provides a highly reliable, actionable tool for proactive, large-scale slope stability and infrastructure risk assessment. Full article

This study investigates the impact of different types of personal protective equipment (PPE), specifically Powered Air-Purifying Respirators (PAPRs) and traditional N95 masks with face shields, on the physiological stress responses of healthcare workers (HWs) during the COVID-19 pandemic. Utilizing an interventional randomized crossover trial design, the research encompasses a simulation phase with ten participants followed by field testing involving thirty frontline healthcare professionals in a tertiary-care hospital setting. Heart rate (HR) and movement data were collected through smartwatches, while trained observers recorded the duration and nature of various activities undertaken during simulations. Data analysis employed statistical techniques, including Principal Component Analysis (PCA) and t-Distributed Stochastic Neighbor Embedding (t-SNE), to explore potential correlations between PPE type, HR, and movement. Clustering validation measures such as the Calinski–Harabasz, Davies–Bouldin, and Silhouette scores were applied to evaluate the difference between each type of PPE. The results indicated no significant differentiation in HR responses between the two PPE types. However, because HR may lack the sensitivity to fully capture variations in cognitive load or stress, these findings should be interpreted as an exploratory baseline. Additionally, no clear distinctions were observed regarding individual user responses or the activities performed, even when considering movement data. Although the findings imply non-inferiority of the examined PPE, future research including heart rate variability as a more comprehensive indicator of stress would be informative. This research contributes valuable insights into PPE selection and its implications for healthcare worker performance and well-being in high-stress environments, ultimately aiming to inform guidelines and training programs to enhance healthcare delivery during infectious disease outbreaks. Full article