Search Results (59)

Parkinson’s disease (PD) is the second most prevalent neurodegenerative disorder worldwide, and its early diagnosis remains a major challenge due to reliance on subjective clinical assessments. This study proposes a bio-inspired computational framework for automatic PD detection that draws explicit architectural inspiration from two biological systems: the hierarchical tonotopic organization of the human auditory cortex, which motivates the design of a 1D Convolutional Neural Network (CNN) for vocal biomarker analysis, and the basal ganglia–cerebellar motor control circuit, which motivates the selection and design of features extracted from Archimedean spiral drawing tasks. Unlike previous studies that apply standard machine learning techniques without grounding architectural choices in biological mechanisms, the proposed framework establishes a direct mapping between neural processing pathways and model design decisions. A Support Vector Machine (SVM) classifier evaluated on the Kaggle vocal dataset achieved 87% test accuracy with no overfitting, outperforming AdaBoost, Random Forest, KNN, XGBoost, and Decision Trees in terms of generalization. The 1D CNN applied to UCI spiral drawing data achieved 85% test accuracy, with overfitting behavior addressed through architectural regularization strategies including early stopping. A conceptual multimodal fusion architecture integrating both modalities is proposed as a direction for future experimental validation; it was not implemented or experimentally validated within the present study. The primary novelty of the framework resides in this explicit biomimetic grounding, which distinguishes it from existing performance-driven approaches. Results confirm that biologically grounded computational models constitute promising objective decision-support tools for early PD diagnosis. Full article

We study the planar dynamics of a charged particle subjected to a radially repulsive inverted harmonic potential and a perpendicular uniform magnetic field, a configuration that is relevant to nanoscale-charged transport and confinement in low-dimensional systems. The competition between the destabilizing central repulsion and magnetic field-induced rotational motion gives rise to rich trajectory behavior, including spiraling, unbounded escape, and parameter-dependent quasi-confined motion. The governing coupled differential equations of motion are solved analytically. The resulting trajectories are classified as functions of system parameters. The proposed framework provides insight into charge carrier dynamics in nanostructured environments such as quantum wells, 2D materials, and plasma-like nanosystems, where effective repulsive potentials may arise from external gating or collective interactions. In addition, the model offers a classical analogue for interpreting features associated with magnetic confinement in non-equilibrium or unstable regimes. These results contribute to the theoretical foundation for designing and controlling charged particle motion in emerging nanomaterials and devices. Full article

This study involves the design of an integrated machine dedicated to the core processes of classifying, shelling, and cleaning to address the critical drawbacks of existing Camellia oleifera fruit processing equipment, including the high manual labor requirement, low operating efficiency, unsatisfactory shelling and cleaning performance, and severe camellia seed damage. The classifying system employed a slat drum structure, and response surface methodology (RSM) was utilized to determine and optimize its operating parameters: spiral blade speed: 20 rpm; drum speed: 10 rpm; and rise angle: 9.6°. The shelling system employed a horizontal flexible structure, and polyurethane was the core material. We determined through single-factor experiments that the shelling drum rotation speed was 200 rpm. For the cleaning system, a composite mode integrating drum screening and friction separation was adopted, and single-factor experiments further determined the optimal operating parameters: cleaning drum rotation speed: 20 rpm; friction conveyor shaft rotation speed: 150 rpm; and cleaning inclination angle: 25°. The performance test verified that the integrated machine achieved outstanding results: the shelling rate reached 97.52%, the camellia seed breakage rate did not exceed 2.42%, the impurity content rate did not exceed 1.99%, the loss rate was less than 3.66%, and the processing capacity reached 2614 kg/h. Full article

The effective recognition of risky driving behaviors holds technical potential for supporting accident prevention and sustainable transportation. However, existing intelligent algorithms for optimizing deep learning models in this field often suffer from slow convergence and high errors. This study proposes a novel hybrid model (ICPO-XGBoost) for risky driving behavior classification. The improved crested porcupine optimizer (ICPO) was developed using logistic-tent composite mapping for population initialization, a hybrid mechanism combining refraction opposition-based learning and Cauchy mutation to avoid local optima, and an adaptive variable spiral search with inertia weight to balance global and local search. The ICPO was then employed to optimize the hyperparameters of the XGBoost classifier. The ICPO demonstrated superior optimization accuracy and convergence speed compared to benchmark algorithms. The ICPO-XGBoost model achieved accuracy, precision, recall, and F1 scores of 96.2%, 95.4%, 95.8%, and 95.6%, respectively, for classifying and identifying risky driving behaviors. Compared to various benchmark models, these results represent increases of 12.7–24.8%, 14.8–31.8%, 14.9–31.0%, and 15.0–32.4%, respectively. For specific driving behavior categories (normal driving, slow driving, short-distance tailgating, sudden acceleration/deceleration, frequent lane changing, and forced lane changing), the precision, recall, and F1 scores of the ICPO-XGBoost model fell within the ranges of 84.8–99.2%, 87.5–100.0%, and 86.2–99.2%, respectively. Compared to benchmark models, these metrics show increases of 1.5–75.8%, 5.8–68.1%, and 3.3–72.6%, respectively. Notably, the model significantly improved accuracy in identifying sudden acceleration/deceleration behaviors. The results of this model facilitate the classification and early warning of risky driving behaviors, thereby reducing the frequency of such behaviors, lowering the risk of traffic accidents, and enhancing road traffic safety. Full article

Nearest-neighbor classifiers are accurate and easy to deploy, but their memory footprint and inference time grow with the size of the reference set. This paper studies an evolutionary prototype selection strategy for k-nearest neighbor (K-NN) classification aimed at extreme, class-balancedreduction. A compact genetic algorithm (GA) evolves a fixed number of prototype indices per class drawn from a disjoint design partition; the selected prototypes are then used by a 1-NN classifier, with fitness defined as the number of correctly classified test instances. To address concerns about generality and baseline strength, we evaluate an experimental suite including synthetic 2D Gaussians ($\sigma =0.5$ and $\sigma =1.0$) and a 3D three-moons geometry, as well as public benchmarks spanning binary and multi-class settings and higher-dimensional data (Breast Cancer Wisconsin, Wine, Reduced MNIST/Digits 8 × 8, Forest CoverType with seven classes, and a 10D five-class spiral benchmark). We compare against K-NN baselines with $k\in \{1,3,5,7\}$ using all design samples, and include GA operator ablations (GA1/GA2/GA3). Each scenario is repeated over 30 independent runs, reporting mean ± std, min/max, per-run distributions, win/tie/loss counts, and non-parametric significance tests (paired Wilcoxon with Holm correction; Friedman where applicable). Across datasets, the GA-selected prototype banks—often orders of magnitude smaller than the full design set—match or improve accuracy, with frequent statistically supported wins against strong K-NN baselines, and in the hardest cases provide substantial compression with no loss relative to the best baseline. These results establish a reproducible baseline for extreme, class-balanced prototype reduction suitable for memory- and latency-constrained deployments and for fair comparison against more elaborate prototype selection methods. Full article

Background: Essential tremor (ET) is among the most common neurological disorders, requiring precise diagnosis and severity assessment for personalized and effective management. Methods: This study explores an innovative approach to evaluate ET severity using the gold-standard Archimedes spiral test. The family-based dataset covers the entire range of tremor severity, from very mild (level 1) to advanced stages, offering a valuable resource for studying early diagnosis and tracking disease progression. The proposed method introduces a machine learning pipeline that combines Principal Component Analysis (PCA), linear discriminant analysis (LDA), and support vector machines (SVMs) to classify ET severity based on Archimedean spiral radius data. Results: By incorporating the Fahn–Tolosa–Marin Tremor Rating Scale (FMT-TRS), the pipeline effectively distinguishes between tremor presence and severity. Its robustness was demonstrated through rigorous cross-validation and tests involving Gaussian noise perturbations. Conclusions: These results underscore the machine learning-based pipeline’s potential as a non-invasive and trustworthy diagnostic tool for clinical use and telemedicine applications. Moreover, the combination of geometric features, FMT-TRS scores, clinically oriented evaluation metrics, and classical statistical and machine learning models offers a robust, interpretable, explainable, and clinically meaningful analytical framework. Full article

The processes occurring inside a spiral jet mill are significantly influenced by the flow conditions within the grinding chamber. As part of this work, an experimental 3D model of the grinding gas flow is successfully developed for the first time based on the results of PIV measurements. This model demonstrates the typical spiral vortex flow superimposed by the nozzle jets, as well as the characteristic comminution and classifying zones. In addition, the three-dimensional analysis of the nozzle jet enables the first experimental validation of the theoretical assumption proposed in the literature that the flow dynamics in this region can be described by Abramovich’s nozzle jet model. The vortex pair located on the back of the nozzle jet essentially contributes to the formation of the kidney-shaped flow cross-section of the nozzle jet. The two vortices are verified both by the flow dynamics based on the unloaded grinding gas flow and by observing the abrasion on the inner wall of the grinding chamber caused by the particle-loaded flow. Consequently, the experimental findings can be utilized to create a model of the deflected and deformed nozzle jet, thereby providing a profound understanding of the flow processes within a spiral jet mill, particularly in the region of the nozzle jets. Full article

Preeclampsia (PE) is a complex hypertensive disorder of pregnancy characterized by new-onset hypertension and proteinuria after 20 weeks of gestation. It is classified into early-onset (EOPE, <34 weeks) and late-onset (LOPE, ≥34 weeks) subtypes, which differ in their pathophysiology, clinical course, and maternal and neonatal outcomes. EOPE arises from abnormal placentation with inadequate spiral artery remodeling and impaired uteroplacental perfusion, whereas LOPE is mainly related to maternal cardiovascular and metabolic predisposition. This review integrates current molecular, immunological, and hemodynamic evidence distinguishing EOPE from LOPE, emphasizing recent insights into angiogenic imbalance (VEGF, PlGF, sFlt-1), oxidative stress, and immune modulation. It also summarizes evolving diagnostic and prognostic biomarkers and evaluates emerging therapeutic approaches, including gene therapy targeting placental dysfunction. By comparing mechanistic pathways and clinical implications, this review highlights how gestational age–specific pathogenesis may inform risk stratification, early detection, and precision-based management of PE. Full article

Background/Objectives: Classified as a hypertensive disorder of pregnancy, preeclampsia is one of the leading causes of maternal and fetal morbidity and mortality. The abnormal trophoblast invasion that leads to a failed transformation of the uterine spiral arteries during placentation remains the most probable cause for preeclampsia. It is known that adiponectin acts on the placenta, playing a regulatory role in placentation processes. Therefore, the aim of this systematic review is to compile scientific evidence to evaluate the role of adiponectin as a biomarker for preeclampsia. Methods: The protocol for this systematic review was registered on the PROSPERO database (ID CRD42024542403) and follows the PRISMA 2020 guidelines. Overall, twenty-nine studies were selected from the PubMed and Scopus databases, including case–control, prospective and retrospective cohort, cross-sectional, and bidirectional Mendelian randomization studies. Results: From the articles analyzed, nine studies indicated an increase in adiponectin levels in preeclampsia, eleven reported a decrease, eight detected no significant changes, and in two studies, it was not possible to determine the glycoprotein levels. Analysis of the evidence quality revealed that moderate and low evidence levels predominate, with stronger evidence for decreased adiponectin levels. Conclusions: Promoting the advancement of scientific research is crucial, particularly exploring the association between adiponectin and other biomarkers. This approach could facilitate the development of screening and diagnostic methods, enabling the implementation of specific preventive and therapeutic strategies. Full article

We study unconventional multipole moments arising from noncollinear magnetic structures within an augmented framework encompassing electric, magnetic, magnetic toroidal, and electric toroidal multipoles. Employing a tight-binding model for an s-p hybridized orbital system, we analyze two spiral magnetic textures and classify the resulting multipoles according to magnetic point group symmetry. Different spiral wave types, such as cycloidal and proper-screw forms, activate distinct multipole components, with odd-parity multipoles emerging from local s-p parity mixing induced by magnetically driven inversion-symmetry breaking. Calculated multipole structure factors reveal finite-q peaks originating from higher-order magnetic-dipole-scattering processes and their characteristic couplings between Fourier components of the magnetic dipole texture. Our results demonstrate that magnetic ordering can generate parity-mixed states without intrinsic structural inversion asymmetry, offering new pathways to realize cross-correlation phenomena in functional magnetic materials. Full article

Helicobacter pylori (H. pylori) is a Gram-negative, spiral-shaped bacterium that colonizes the human stomach and is linked to various gastroduodenal diseases. The severity of different clinical outcomes may be determined by the combination of virulence genes. The aim of this study was to assess the combinations of the cytotoxin-associated gene A (cagA), the vacuolating cytotoxin A gene (vacA), the outer inflammatory protein A gene (oipA), and the blood group antigen-binding adhesin gene (babA2) genotypes in H. pylori and their associations with the clinical outcomes of infection in patients from Central Brazil. This cross-sectional study included 106 patients who underwent endoscopy or gastrectomy. The presence and genotypes of H. pylori were confirmed using Polymerase Chain Reaction (PCR). Gastropathies were classified according to established severity criteria. Multivariate logistic regression and Venn diagrams were used to evaluate gene combinations. In this study, the infection prevalence was 65.1%. The cagA/vacA/oipA/babA2 combination showed a protective effect against erosive esophagitis (p = 0.002), erosive duodenitis (p = 0.003), and general duodenitis (p < 0.001). No significant association was observed between this gene combination and severe gastric diseases, although a trend toward protection against gastric atrophy was noted (p = 0.049). These findings suggest that the coexistence of cagA/vacA/oipA/babA2 may play a protective role against inflammatory lesions. Further studies should explore the functional role of these gene combinations, also considering the immunogenetic profile of the host. Full article

Parkinson’s disease (PD) is a progressive neurodegenerative disorder that impairs motor function, often causing tremors and difficulty with movement control. A promising diagnostic method involves analyzing hand-drawn patterns, such as spirals and waves, which show characteristic distortions in individuals with PD. This study compares three computational approaches for classifying individuals as Parkinsonian or healthy based on drawing-derived features: (1) Large Language Models (LLMs), (2) traditional machine learning (ML) algorithms, and (3) a fuzzy ontology-based method using fuzzy sets and Fuzzy-OWL2. Each method offers unique strengths: LLMs leverage pre-trained knowledge for subtle pattern detection, ML algorithms excel in feature extraction and predictive accuracy, and fuzzy ontologies provide interpretable, logic-based reasoning under uncertainty. Using three structured handwriting datasets of varying complexity, we assessed performance in terms of accuracy, interpretability, and generalization. Among the approaches, the fuzzy ontology-based method showed the strongest performance on complex tasks, achieving a high F1-score, while ML models demonstrated strong generalization and LLMs offered a reliable, interpretable baseline. These findings suggest that combining symbolic and statistical AI may improve drawing-based PD diagnosis. Full article

Reinforced concrete (RC) columns play a vital role in structural integrity, and accurately predicting their failure modes is essential for enhancing seismic safety and performance. This study explores the use of a supervised machine learning approach—specifically, an artificial neural network (ANN) model—to classify failure modes of RC columns. The model is trained using data from the well-established Pacific Earthquake Engineering Research Center (PEER) structural performance database, which contains results from over 400 cyclic lateral-load tests on RC columns. These tests encompass a wide range of column types, including those with spiral or circular hoop confinement, rectangular ties, and varying configurations of longitudinal reinforcement with or without lap splices at critical sections. The ANNs were evaluated using a randomly selected subset from the PEER database, achieving classification accuracies of 94% for rectangular columns and 95% for circular columns. Notably, in certain cases, the model’s predictions aligned with or exceeded the accuracy of traditional building code-based methods. These findings underscore the strong potential of machine learning—particularly ANNs—for reliably postdicting failure modes (even the brittle ones) in RC columns, signaling a promising advancement in the field of earthquake engineering. Full article

The presence of Active Galaxy Nuclei (AGN) can affect the morphological classification of galaxies. This work aims to determine how the contribution of AGN affects the most-used morphological parameters down to the redshift of z ∼ 2 in COSMOS-like conditions. We use a sample of >2000 local non-active galaxies, with a well-known visual morphological classification, and add an AGN as an unresolved component that contributes to the total galaxy flux with 5–75%. We moved all the galaxies to lower magnitudes (higher redshifts) to map the conditions in the COSMOS field, and we measured six morphological parameters. The greatest impact on morphology occurs when considering the combined effect of magnitude, redshift, and AGN, with spiral galaxies being the most affected. In general, all the concentration parameters change significantly if the AGN contribution is >25% and the magnitude > 23. We find that the GINI coefficient is the most stable in terms of AGN and magnitude/redshift, followed by the moment of light (M20), Conselice–Bershady (CCON), and finally the Abraham (CABR) concentration indexes. We find that, when using morphological parameters, the combination of CABR, CCON, and asymmetry is the most effective in classifying active galaxies at high-redshift, followed by a combination of CABR and GINI. Full article

Galaxies moving through the gas of the intracluster medium (ICM) experience ram pressure stripping, which can leave behind a gas tail. When a disk galaxy receives the wind edge-on, however, the characteristic signature is not a typical jellyfish tail, but rather an unwinding of the spiral arms. We aim to quantify such asymmetries both in the gas and in the stellar component of a simulated galaxy. To this end, we simulate a gas-rich star-forming spiral galaxy moving through a self-consistent ICM gas. The amplitude and location of the asymmetries were measured via Fourier decomposition. We found that the asymmetry is much more evident in the gas component, but it is also measurable in the stars. The amplitude tends to increase with time and the asymmetry radius migrates inwards. We found that, when considering the gas, the spiral arms extend much further and are more unwound than the corresponding stellar arms. Characterizing the unwinding via simulations should help inform the observational criteria used to classify ram pressure stripped galaxies, as opposed to asymmetries induced by other mechanisms. Full article