Search Results (35,221)

Fetal health assessment is a crucial aspect of prenatal care, aimed at the early detection of potential complications to ensure optimal outcomes for both mother and child. Traditional methods, such as the visual analysis of cardiotocography (CTG) data by healthcare professionals, are valuable but often subjective and time-consuming. This work investigates the application of machine learning techniques, with a focus on ensemble learning, to enhance the accuracy and efficiency of fetal health classification based on CTG data. Genetic Algorithm (GA) is employed for optimal feature selection, identifying the most discriminative subset of CTG attributes to improve model performance and reduce computational complexity. We employ a combination of advanced machine learning models, including AdaBoost, Gaussian Naïve Bayes, Decision Tree, k-nearest neighbors (KNN), and Logistic Regression. The top two models were selected based on comprehensive performance metrics using the TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) method. These models were then integrated through ensemble learning approaches, such as stacking, Particle Swarm Optimization (PSO) weighted averaging, and soft voting, to improve prediction reliability. Our proposed stacking ensemble model achieves a remarkable accuracy of 97.9%, demonstrating its potential as a robust, data-driven tool for fetal health monitoring and the early identification of at-risk pregnancies. The results indicate that machine learning can effectively complement traditional fetal health assessment methods by providing an objective framework to support clinical decision-making. Full article

While hydroxypropyl methylcellulose (HPMC) is a promising plant-based alternative to gelatin, its industrial application is limited by poor mechanical properties and high production costs. In this study, high-performance HPMC-based hard capsules were developed using an HPMC/gellan gum/ι-carrageenan ternary system. The formulation and preparation process were optimized via single-factor experiments, response surface methodology, and low-field nuclear magnetic resonance analysis. Scanning electron microscopy was applied to characterize the microstructural evolution during disintegration. The optimized capsules exhibited rapid disintegration within 15 min across four pH media and satisfied the requirements of the Chinese Pharmacopoeia (2025). Drug dissolution profiles using cefradine and ranitidine hydrochloride showed over 85% cumulative release within 30 min, with similarity factors higher than 50 relative to commercial gelatin capsules under the tested conditions. This work provides a feasible and low-cost strategy for the industrial production of plant-based capsules and promotes the high-value utilization of polysaccharide-based capsule materials. Full article

Blockchain systems generate massive volumes of transactional data, yet most existing analytical approaches rely on query-based retrieval mechanisms that treat transactions as isolated records. In this paper, a trajectory-based framework for blockchain analysis is introduced where user activity is modeled as temporally ordered behavioral patterns. Four types of blockchain trajectories are formally defined: miner reward trajectories, sender value-and-fee trajectories, receiver value trajectories, and sender–receiver interaction trajectories. Unlike traditional query frameworks, trajectories are treated as first-class analytical objects, explicitly constructed and returned as outputs, thereby enabling structured temporal reasoning over blockchain behavior. To demonstrate the practicality of the approach, the proposed trajectory functions are implemented in Python 3.12 and experiments are conducted using real data from the Ethereum blockchain. Compared with conventional query-based approaches that return isolated transactions, the experimental results show that the proposed trajectory-based framework enables a more systematic identification of temporal behavioral patterns, including persistent miner dominance, recurrent zero-value interactions, sender–receiver role reversals and sender dominance by sending the highest values across several periods. The results show that trajectory-based modeling provides a systematic lens for uncovering temporal and structural regularities that are not readily observable through conventional query techniques. This work establishes a formal foundation for behavioral blockchain analytics and opens new research directions in centralization measurement, predictive modeling, and trajectory similarity analysis. Full article

Magnetic resonance imaging (MRI) remains one of the most important tests for diagnosing and monitoring various diseases. In recent years, machine learning methods have been widely applied to automate MRI analysis. It supports decision-making by predicting disease and highlighting relevant regions. However, the proper use of feature extraction methods can improve the performance of the model. This paper proposes a WaveletFusion architecture that combines a two-dimensional Haar wavelet decomposition with a convolutional neural network (CNN) for classification. The approach was demonstrated on the Brain Tumor MRI dataset and further examined on the Br35H :: Brain Tumor Detection 2020 (Br35H). The model decomposes each MRI slice into approximation and directional detail subbands and fuses multi-scale wavelet features within the convolutional pipeline. To evaluate the effect of decomposition depth, WaveletFusion variants from one to eight levels were compared with a Baseline CNN model under the same training protocol. The results showed that performance improved progressively with increasing decomposition depth up to level 7, whereas the 8-level configuration consistently declined, indicating that excessive decomposition introduces information loss and over-compression in the deepest approximation pathway. The best-performing configuration, which outperformed both the Baseline CNN and the WaveletFusion variations in five independent runs, was the 7-level WaveletFusion model, achieving a test accuracy of 0.94 ± 0.01 and test macro-F1 of 0.93 ± 0.02. A similar tendency was observed on the Br35H dataset, where the 7-level model achieved a 0.97 ± 0.01 test accuracy and 0.97 ± 0.01 test macro-F1, while the 8-level configuration remained weaker on both datasets. These results show that multi-scale wavelet fusion can improve Brain Tumor MRI classification while maintaining a compact model size and a fair comparison setting, and that the decomposition depth must be selected carefully. Full article

Multi-temporal orbital satellite imagery is an alternative for measuring behavioral patterns or trends in different physiognomies through vegetation indices (VIs) and Spectral Linear Mixture Models (SLMMs). In this study, time series of Landsat 7/8/9 and Sentinel-2 have been used to classify a considerable quantity of areas spread over the São Paulo state from 2021 to 2024. Because the large amount of samples considered in our analysis, self-organizing maps (SOMs) have been applied as a convenient method to group similar satellite image time series samples with respect to a certain vegetation index or green vegetation fraction (VEG). Since every dataset area belongs to different types of physiognomies, each cluster has been labeled according to the plurality technique. Additionally, we obtained the mean spectral behavior of the VIs and VEG in the 2021–2024 seasonal cycle of all samples. The results showed similar variations from the rainy to the dry season for most of the physiognomies. On the other hand, this research indicates that the proposed method for classification the Brazilian areas spread over the São Paulo state is consistently good, obtaining the best performance (quantization error) associated with Normalized Difference Vegetation Index (NDVI) time series samples. Full article

An experimental investigation of the Cu-As-Sb ternary system in the Cu-rich region led to the identification of a new intermetallic phase, Cu₅(As,Sb)₂. The compound crystallizes in the orthorhombic Mg₅Ga₂-type structure (oI28, Ibam), analogous to the binary parent phase Cu₅As₂, with lattice parameters a = 5.968–5.977(1) Å, b = 11.550–11.565(3) Å, c = 5.530–5.573(3) Å. Similar to the parent Cu₅As₂ phase, the ternary compound forms with slight Cu under stoichiometry and exhibits a limited compositional range, with no continuous solid solubility between the binary and ternary phases. The phase formation, compositional stability, and decomposition behavior were systematically studied using a combination of powder and single-crystal X-ray diffraction (XRD, including Rietveld refinement), metallographic analysis with optical and scanning electron microscopy with energy-dispersive X-ray spectroscopy (LOM, SEM-EDXS), electron backscatter diffraction (EBSD) and thermal analysis (DTA, DSC). The results reveal that Cu₅(As,Sb)₂ is a high-temperature phase forming peritectically at 650–635 °C and stable only within a limited temperature interval. No continuous solid solubility exists between the ternary compound and the parent binary phase Cu₅As₂. Its formation occurs in strong competition with that of two other close neighboring solid-solution compounds, [Cu_3−x(As_1−ySb_y) (Cu₃P-type; hP24, P6₃cm) and Cu_3−x(As,Sb) (Cu₉TeSb₂-type; cP32, Pm−3n)], reflecting a complex interplay between composition, solubility ranges and thermal history. No evidence for the existence of high-temperature (HT) and low-temperature (LT) polymorphic phases was found for either the binary compound Cu₅As₂ or the ternary compound Cu₅(As,Sb)₂. Electrical resistivity measurements on a quenched sample indicate metallic behavior. These findings provide new insight into phase stability and structure–property relationships in Cu-As-Sb alloys and contribute to the understanding of competing intermetallic phases in this system. Full article

Adaptive recommendation mechanisms are widely used to personalise digital learning environments; however, many existing approaches prioritise algorithmic optimisation while providing limited insight into how recommendation behaviour aligns with pedagogically structured instructional artefacts, such as worksheets. To address this gap, this paper proposes a hybrid recommendation approach for adaptive worksheet generation that integrates content-based and collaborative filtering with explicit pedagogical constraints derived from Bloom’s Revised Taxonomy. The system ranks and selects learning and evaluation objects across cognitive levels by combining learner profiles, behavioural signals, and similarity-based information within a unified scoring framework. A simulation-based evaluation was conducted to examine the internal behaviour, stability, and instructional alignment of the recommendation engine under controlled conditions, using Bloom-aligned worksheets and synthetic learner profiles. The analysis focuses on expected–actual alignment and adaptive variation across cognitive levels rather than learning outcomes. Results indicate strong alignment with the intended instructional structure at lower cognitive levels, while bounded and interpretable adaptive variation emerges at higher levels. Evaluation object recommendations showed high agreement with the instructional design, exceeding 95% across simulated conditions. Overall, the study demonstrates how hybrid recommendation mechanisms can support adaptive content selection in pedagogically structured learning scenarios, offering a transparent and robust foundation for information-driven educational systems. Full article

Background/Objectives: Coronary artery ectasia (CAE) presents challenges, specifically in the context of percutaneous coronary intervention (PCI), and has been associated with adverse events, particularly in the setting of acute myocardial infarction (AMI). The objective of the present study was to assess whether CAE is associated with increased occurrence of major adverse cardiovascular events (MACEs) in patients with AMI. Methods: A systematic review and meta-analysis of observational studies were conducted. We systematically searched MEDLINE via PubMed, Scopus, the Cochrane Library (CENTRAL), ClinicalTrials.gov, and reference lists to identify eligible studies. Baseline characteristics, comorbidities, angiographic data, and rates of MACEs and their individual components (all-cause or cardiovascular mortality, repeat AMI, repeat revascularization, stroke, and heart failure) have been extracted. The results were synthesized as odds ratios (ORs) using random-effects models. Results: Ten studies and 13,908 patients were included. CAE was found to be predictive of higher odds of MACEs [OR: 2.12, 95% CI: 1.34 to 3.36]. No difference was found regarding the odds of all-cause and cardiac death. The presence of ectasia was associated with higher odds of recurrent AMI, compared with controls [OR: 2.76, 95% CI:1.62 to 4.71]. The groups were comparable regarding the need for repeat revascularization, while the reports on stroke and heart failure were scarce. Conclusions: The results highlight the compounding effect of CAE on future MACE events in patients with AMI. Patients with AMI and CAE have higher odds of repeat AMI compared to patients without CAE, while mortality and repeat revascularization rates are similar. This might indicate the need for more aggressive treatment strategies in these patients. Full article

The AVIF (AV1 Image File Format) is a modern, royalty-free image format that leverages the AV1 video codec for superior compression efficiency, supporting both lossy and lossless modes. Its entropy encoding relies on a multi-symbol context-adaptive arithmetic coder (range coding with adaptive cumulative distribution functions (CDFs)), which is effective for general imagery but may not optimally exploit the repetitive structures common in Geographic Information System (GIS) maps/data. This paper proposes replacing AVIF’s entropy encoder with the Burrows–Wheeler Transform (BWT), a reversible preprocessing algorithm that rearranges data to create runs of similar symbols, enhancing subsequent compression. We detail the technical steps for modification, drawing from AV1’s open-source implementation, and explain why BWT is advantageous for GIS raster maps/data, which often feature large uniform areas, limited color palettes, and spatial redundancies. Empirical evidence from related studies on BWT-based image compression shows improvements in lossless scenarios, potentially considerably reducing file sizes over standard methods while preserving data integrity critical for geospatial analysis. This swap could improve storage, transmission, and processing efficiency in GIS applications, such as remote sensing and cartography. The discussion includes challenges like computational overhead and compatibility, with recommendations for implementations. The resulting BWT-AVIF hybrid produces a non-standard AV1 bit-stream that is not compliant with the AV1 or AVIF specifications and therefore requires custom decoders. It is presented here as a research prototype for GIS-specific compression rather than a compliant AVIF extension. Full article

The increasing demand for energy, the finite nature of fossil fuel resources, and the necessity to reduce greenhouse gas emissions have intensified research on renewable energy sources of plant origin. Among potential energy feedstocks, herbaceous biomass has attracted growing interest due to its high productivity, rapid growth, and widespread occurrence. The aim of this study was to evaluate the energy potential of select sedge species (Carex spp.) commonly occurring in Poland as an alternative to fossil fuels. Aboveground biomass of eight sedge species was collected from natural habitats located in the Warta River valley. Cellulose, lignin, holocellulose, hemicellulose, and ash content in the biomass was determined. In addition, key energy parameters, namely net calorific value and gross calorific value, were analyzed. Differences among species were assessed using one-way analysis of variance, while similarities were explored using hierarchical clustering methods. The results revealed significant interspecific variation in both chemical composition and energy properties. Most analyzed sedge species had favorable lignocellulosic composition and energy parameters comparable to those of woody biomass, particularly willow and poplar. In contrast, Carex riparia was distinguished by a high ash content and lower calorific values, limiting its suitability for energy applications. Overall, the findings indicate that select Carex species may represent a valuable renewable feedstock for energy production, especially in the context of local and decentralized biomass-based energy systems. Full article

Currently, the number of people who have been investigated for skin cancer has increased significantly worldwide. For prior diagnosis, dermatologists can typically visually inspect skin lesions for abnormalities. However, an expert is required, and the similarity of some skin lesions remains challenging. This study aimed to address the challenge of classifying multiple images of skin conditions, including both Benign and Malignant groups, using the hierarchical method. Instead of directly performing multi-class classification using a single model, multiple binary classification models were organized to reduce task complexity and improve overall performance. In the methodology, four convolutional neural network (CNN) models, namely MobileNetV2, EfficientNet-B0, ResNet-18, and ResNet-50, were selected as candidates for this problem. The proposed hierarchical binary classification model was evaluated against conventional multi-class classification methods. As a result, various evaluation metrics were used to assess model performance, with recall as the primary metric in this study, given the emphasis on minimizing false negatives. However, some results revealed discrepancies between the highest recall and other performance metrics. Further analysis demonstrated the potential of using recall as a selection criterion for identifying the most suitable CNN models. The single model-based classification of six classes of skin lesion images achieves the highest recall of 60.27% with MobileNetV2. Meanwhile, the proposed hierarchical model achieves a higher recall of 82.62%, representing a significant increase of 22.35%. Additionally, improvements were observed across all other evaluation metrics, including accuracy (+25.46%), precision (+17.21%), F1-score (+21.34%), balanced accuracy (+12.69%), specificity (+3.03%), and G-mean (+14.25%). These improvements indicate enhanced performance in correctly identifying both positive and negative cases, while reducing misclassification rates. This outcome demonstrates the potential to improve the model’s generalizability, thereby increasing its applicability across various clinical decision-support systems. Full article

A series of morpholine-appended 1,8-naphthalimide probes (S1–S5) was developed to investigate the influence of the morpholine moiety on H₂S detection. All probes exhibited characteristic absorption and emission features and responded to H₂S with fluorescence enhancement, although the intensity varied markedly across the series. S2 displayed the highest signal enhancement, while S5 showed minimal response, highlighting the critical role of a two-carbon spacer between the morpholine group and the fluorophore for optimal sensing. Kinetic analysis revealed that S1–S4 followed similar reaction profiles, whereas S5 reacted faster but produced a weaker signal. S2 maintained reliable performance across pH 4–9 and in DMSO-containing media and demonstrated excellent selectivity over common biothiols and other potentially interfering species. These findings provide a clear structure–activity relationship for morpholine-based fluorescent probes and inform the rational design of highly selective H₂S sensors. Full article

Background/Objectives: Fractional flow reserve (FFR) is the reference standard for assessing the functional significance of intermediate coronary stenoses and guiding revascularization. Although a universal ischemic threshold is applied to all epicardial vessels, potential physiological differences between coronary territories remain insufficiently explored. The aim of this study was to evaluate whether the functional significance of intermediate coronary stenoses differs according to coronary artery and to assess the clinical outcomes of FFR-guided deferral across coronary territories. Methods: This single-center retrospective study included patients who underwent single-vessel FFR assessment for angiographically intermediate lesions between 2019 and 2022. Patients with left main disease or multivessel physiological assessment were excluded. Clinical characteristics, FFR values, and long-term outcomes were analyzed according to the investigated coronary artery. Major adverse cardiovascular events (MACE) were defined as a composite of death, myocardial infarction, and urgent revascularization. Results: A total of 310 patients (corresponding to 310 coronary arteries) were included: 211 LAD, 68 RCA, and 31 LCX lesions. Overall, 18.7% of lesions had a positive FFR (≤0.80). The only variable identified in univariable analysis as being associated with FFR positivity was the coronary artery evaluated (p < 0.001). Positive FFR values were observed in 24.6% of LAD lesions, compared with 8.8% in the RCA and none in the LCX. Among patients with negative FFR for whom revascularization was deferred, five-year MACE-free survival was similar across coronary territories (p = 0.12). Conclusions: The functional significance of intermediate coronary stenoses varies according to the coronary territory, with LAD lesions more frequently reaching ischemic thresholds. However, deferral of revascularization based on negative FFR is associated with favorable long-term outcomes across all vessels, supporting a vessel-specific physiological interpretation of coronary stenoses. Full article

Background/Objectives: Subtalar arthroereisis (STA) is widely used for symptomatic pediatric flexible flatfoot and provides consistent radiographic correction. However, return to sport (RTS) after STA is less well defined, and the relative role of early postoperative pain versus radiographic correction remains unclear. Methods: We performed a retrospective observational cohort study of consecutive skeletally immature patients treated with STA using a non-absorbable endosinotarsal screw at a single tertiary center. Inclusion criteria were symptomatic flexible flatfoot refractory to >6 months of conservative treatment, complete pre-/postoperative weight-bearing radiographs, complete functional data, and minimum follow-up of 6 months. The primary endpoint was RTS to the pre-symptom primary sport at final follow-up. Secondary outcomes were UCLA Activity Score, FAAM Sport subscale, and postoperative VAS. Radiographic correction was quantified as delta change (Δ) in Meary, Costa–Bertani, and Kite angles. Group comparisons used nonparametric tests. A parsimonious multivariable logistic regression model (EPV-constrained) included UCLA at 3 months, VAS pain, and ΔMeary. Results: Fifty patients were included (mean follow-up 9.2 ± 2.5 months; range 6–14); 27/50 (54%) resumed their primary sport. Baseline characteristics were comparable between Returners and Non-Returners. Returners showed higher early postoperative UCLA scores than Non-Returners (8.0 [7.0–8.5] vs. 6.0 [5.0–7.0], p = 0.005). FAAM Sport and VAS pain did not differ significantly between groups (p = 0.224 and p = 0.493, respectively). Radiographic correction magnitude was similar between groups (ΔMeary p = 0.938; ΔCosta–Bertani p = 0.984; ΔKite p = 0.108). In multivariable analysis, UCLA at 3 months was the only independent correlate of RTS (OR 2.65 per point, 95% CI 1.34–6.15; p = 0.009), whereas VAS pain (OR 0.98, 95% CI 0.76–1.25; p = 0.892) and ΔMeary (OR 1.01, 95% CI 0.91–1.13; p = 0.875) were not significant. Conclusions: In this cohort, STA achieved substantial radiographic correction, but neither correction magnitude nor early postoperative pain independently correlated with RTS at short-term follow-up. Early postoperative activity level was the strongest independent correlate of sport resumption, supporting a function-centered postoperative assessment beyond radiographic alignment alone. Full article

Urban density is a central concept in sustainable urban development, yet its measurement and interpretation remain fragmented and often limited to single indicators. This paper develops a multidimensional framework for measuring urban density and linking it to selected dimensions of liveability relevant to spatial planning and sustainable urban development. The approach conceptualises urban density as the interaction between morphological, functional, and structural dimensions within a common spatial unit defined as the urban footprint. The framework is operationalised through indicators capturing built form, population and activity intensity, and land-use composition, while selected liveability components—such as accessibility, green infrastructure, and environmental conditions—are incorporated as an interpretative layer. The methodology is demonstrated through its application to three Slovenian cities (Izola, Kranj, and Gornja Radgona), representing different urban typologies. The results show that similar aggregate density values may correspond to different spatial configurations, revealing patterns not captured by conventional indicators. The analysis identifies mismatches between density dimensions and a “density dilution effect” related to the use of heterogeneous spatial units. The findings confirm that the relationship between density and liveability is context-dependent, shaped by the interaction between built form, functional structure, and green space provision. The study contributes a transferable methodological framework that supports a more nuanced interpretation of urban density and provides a tool for informed and context-sensitive spatial planning, contributing to more efficient land use, improved environmental quality, and more sustainable urban development outcomes. Full article