Search Results (5,705)

An integrated nonlinear dynamic model was developed to investigate resonance in a four-cylinder engine mounted on a viscoelastic foundation. A coupled lumped-parameter formulation captures vertical and torsional responses under unbalanced inertial forces, combustion torque, and stochastic base excitation. Time-domain simulations show that at low rotational speeds the vertical displacement reaches transient amplitudes before converging to periodic oscillations, whereas higher excitation speeds reduce steady-state amplitudes. Torsional motion exhibits initial angles near 0.05 rad that decay below 0.01 rad in steady state, with further reduction at higher speeds. Frequency-domain analysis indicates that vibration energy is concentrated in engine-order harmonics between approximately 8 and 50 Hz, while components above 60 Hz are strongly attenuated, yielding a dynamic range exceeding 50 dB. Finite element modal analysis identifies the first four structural modes between 18 Hz and 666 Hz, revealing an increasingly dominant overall translational mode and a localized directional behavior at higher frequencies. A high-dimensional kernel density spectrogram integrates modal and spectral features to map resonance regions. Results indicate that increasing rotational excitation enhances inertial stiffening, systematically reduces displacement amplitudes, and preserves bounded periodic dynamics without instability. Full article

Automated and comprehensive processing of hyperspectral image data is increasingly important in academic research and medical technology. This study presents an automated processing pipeline that integrates hyperspectral image acquisition, analysis, multimodal fusion, and centralized data management to improve the interpretability of spectral information for biological tissue analysis. The pipeline supports modular hyperspectral data processing, fusion of complementary wavelength ranges, and scalable data storage, and was implemented in Python 3.13.3. The pipeline was evaluated using hyperspectral imaging data acquired from a coronal mouse brain section. Clustering-based analysis and spectral correlation metrics were applied to assess the impact of multimodal data fusion on spectral representation. Clustering of individual modalities yielded silhouette coefficients of 0.5879 for near-infrared data, 0.6020 for mid-infrared data, and 0.6715 for RGB data. Multimodal fusion reduced the silhouette coefficient to 0.5420 and enabled the identification of anatomical structures that were not distinguishable in any single modality. High spectral correlation coefficients exceeding 0.98 confirmed that spectral fidelity was preserved during fusion. These results demonstrate that automated multimodal hyperspectral data fusion can enhance the interpretability of biological tissue despite reduced clustering compactness. The proposed pipeline provides a structured framework for preclinical hyperspectral imaging workflows and supports exploratory biological analysis in medical imaging contexts. Full article

Accurate identification of Alzheimer’s disease (AD)-related cellular characteristics from microscopy images is essential for understanding neurodegenerative mechanisms at the cellular level. While most computational approaches focus on macroscopic neuroimaging modalities, cell type classification from microscopy remains relatively underexplored. In this study, we propose a hybrid vision transformer–convolutional neural network (ViT–CNN) framework that integrates DeiT-Small and EfficientNet-B7 to classify three AD-related cell types—astrocytes, cortical neurons, and SH-SY5Y neuroblastoma cells—from phase-contrast microscopy images. We perform a comparative evaluation against conventional CNN architectures (DenseNet, ResNet, InceptionNet, and MobileNet) and prompt-based multimodal vision–language models (GPT-5, GPT-4o, and Gemini 2.5-Flash) using zero-shot, few-shot, and chain-of-thought prompting. Experiments conducted with stratified fivefold cross-validation show that the proposed hybrid model achieves a test accuracy of 61.03% and a macro F1 score of 61.85, outperforming standalone CNN baselines and prompt-only LLM approaches under data-limited conditions. These results suggest that combining convolutional inductive biases with transformer-based global context modeling can improve generalization for cellular microscopy classification. While constrained by dataset size and scope, this work serves as a proof of concept and highlights promising directions for future research in domain-specific pretraining, multimodal data integration, and explainable AI for AD-related cellular analysis. Full article

Background: Imaging-transcriptomic analysis, through the integration of multimodal magnetic resonance imaging (MRI) and transcriptomic data, provides complementary structural, functional, and molecular information that is crucial for the early detection and mechanistic exploration of Alzheimer’s disease (AD). However, effectively extracting features from heterogeneous multimodal data and capturing the associations between microscopic molecular variations and macroscopic brain alterations remain key challenges. Recent advances in deep learning and multimodal integration have enhanced the ability to model nonlinear cross-modal relationships, enabling more accurate identification of imaging-transcriptomic biomarkers and subtypes. Developing robust multimodal frameworks is therefore essential for early AD detection, subtype identification, and advancing precision medicine in neurodegenerative diseases. Methods: In this study, a two-stage method of multimodal Feature Extraction based on Association Analysis and Graph Convolutional Network with Self-Attention and Self-Expression framework (MFEAA-GCNSASE) for early diagnosis of AD and effective identification of subtypes of MCI with different progression to AD is proposed. In the first stage, the MFEAA model is applied to integrate multiple association analysis methods on sMRI, PET, and transcriptomic data to identify key multimodal biomarkers for AD and mild cognitive impairment (MCI). In the second stage, the GCNSASE model enhances classification accuracy between AD and MCI patients through self-attention and self-expression layers. Additionally, unsupervised clustering was performed on MCI samples using top multimodal biomarkers to explore subtype heterogeneity and conversion risk. Reliable MCI subtypes were also identified through a consensus clustering approach. Results: The proposed algorithm integrates sMRI, PET, and transcriptomic data, identifying robust biomarkers including the Left Hippocampus, Left Angular Gyrus, and key genes such as SLC25A5 and GABARAP. To ensure statistical robustness given the extreme class imbalance, we employed a rigorous repeated stratified cross-validation (RSCV) framework. GCNSASE achieved state-of-the-art discrimination performance with mean AUC values ranging from 0.946 to 0.961 across feature subsets (10–50%), significantly outperforming MOGONET (mean AUC: 0.844–0.875, p < 0.001) and conventional machine learning models with tighter 95% confidence intervals, indicating superior stability despite the limited AD sample size. Clustering analysis revealed two distinct MCI subtypes with divergent molecular landscapes: Subtype A was enriched in energy metabolism and cellular maintenance pathways, whereas Subtype B was enriched in neuroinflammatory and aberrant signaling pathways. Notably, the majority of MCI patients who subsequently converted to AD were concentrated in the immune-inflammatory Subtype B. These findings highlight that neuroinflammation coupled with bioenergetic failure constitutes a critical mechanism driving the conversion from MCI to AD. Conclusions: The proposed methods not only provide the key multimodal biomarkers and enhance the accuracy of the classification model for early AD diagnosis but also identify biologically and clinically meaningful MCI subtypes with distinct molecular signatures and conversion risks. Exploring these associated multimodal biomarkers and MCI subtypes is of great significance, as they help elucidate the heterogeneous mechanisms underlying AD onset and progression, enable the identification of high-risk individuals likely to convert to AD, and provide a foundation for targeted therapeutic strategies and individualized clinical management. These findings have important implications for understanding disease heterogeneity, discovering potential intervention targets, and advancing precision medicine in neurodegenerative diseases. Full article

Accurate and early detection of bone cancer is critical for improving patient outcomes, yet conventional radiographic interpretation remains limited by subjectivity and variability. Conventional AI models often struggle with complex multi-modal noise distributions, non-convex and topologically entangled latent manifolds, extreme class imbalance in rare oncological conditions, and heterogeneous data fusion constraints. To address these challenges, we present a Quantum-Inspired Classical Convolutional Neural Network (QC-CNN) inspired by quantum analogies for automated bone cancer detection in radiographic images. The proposed architecture integrates classical convolutional layers for hierarchical feature extraction with a classical variational layer motivated by high-dimensional Hilbert space analogies for enhanced pattern discrimination. A curated and annotated dataset of bone X-ray images was utilized, partitioned into training, validation, and independent test cohorts. The QC-CNN was optimized using stochastic gradient descent (SGD) with adaptive learning rate scheduling, and regularization strategies were applied to mitigate overfitting. Quantitative evaluation demonstrated superior diagnostic performance, achieving high accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). Results highlight the ability of classical CNN with quantum-inspired design to capture non-linear correlations and subtle radiographic biomarkers that classical CNNs may overlook. This study establishes QC-CNN as a promising framework for quantum-analogy motivated medical image analysis, providing evidence of its utility in oncology and underscoring its potential for translation into clinical decision-support systems for early bone cancer diagnosis. All computations in the present study are performed using classical algorithms, with quantum-inspired concepts serving as a conceptual framework for model design and motivating future extensions. Full article

The study focuses on the results of the analysis of data recorded during Ambient Vibration Tests (AVT) conducted on a portion of the Medieval Walls of Verona (Northern Italy). Seismometric stations were installed both at the top and at the base of the walls, recording the free vibrations of the structure. Spectral analyses provide information about the principal modal frequencies, which are compared with the results obtained through Operational Modal Analysis (OMA) techniques. Numerical models were developed to describe the elastic behavior of the walls and to support the interpretation of the experimentally identified modes. Seismic noise measurements were also performed on the ground to characterize the spectral response of the soil and to estimate the soil–structure interaction. The combined use of AVT data, OMA procedures, and numerical modeling allowed for a robust identification of the fundamental dynamic properties of the walls, highlighting the predominance of out-of-plane modes and the limited dynamic coupling with the underlying soil. The study demonstrates the effectiveness of this non-invasive approach for improving the knowledge of structural assessment, reducing uncertainties in mechanical parameter calibration, and supporting informed conservation, maintenance, and risk-mitigation strategies for historic defensive masonry structures. Full article

Multimodal Learning Analytics (MMLA) is an extension of Learning Analytics that combines multiple data streams such as audio, video, physiological signals, logs, and spatial trails to analyze learning processes that cannot be easily captured through any single modality. This review synthesizes research on sensing and instrumentation, feature extraction, multimodal fusion, modeling approaches, and end-to-end systems that provide feedback and support reflection. We also discuss how generative AI and Large Language Models (LLMs) increasingly improve MMLA pipelines by enabling scalable semantic and pragmatic analysis of learner discourse and interaction. In addition, we review robustness issues that arise when working with real-world data (e.g., noise, missing data, and scalability) and responsible deployment issues such as privacy and student-focused views of fairness, accountability, transparency, and ethics (FATE). Full article

Background/Objectives: Analysis of histopathological images is the absolute standard of breast cancer diagnosis. However, modern deep learning- and ViT-based architecture still struggle to capture effective local and global discriminatory patterns that tend to make architecture more complex, increasing the risk of overfitting and optimization problems. Methods: To address these problems, this paper proposes a four-phase hybrid framework that aims to enhance the feature fusion, improving the model’s strength, robustness, and generalization ability. In Phase 1, the BreakHis dataset was split patient-wise into a 70-15-15 manner to avoid data leakage, while extensive data augmentation, comprehensive normalization, and a five-fold cross-validation protocol were implemented to make the dataset more varied and reliably evaluated without bias. Phase 2 entailed the training of three CNNs (VGG16, ResNet50, and DenseNet121) and four ViTs (DeiT, CaiT, T2T-ViT, and Swin Transformer) independently to establish the strict baseline performance standards. In Phase 3, the CNN-based features were fused and classified with a soft voting mechanism to allow more stable and representative learning. Phase 4 depicts the Proposed Framework, which combines the two best-performing CNN and ViT models. Feature refinements were performed randomly by using Global Average Pooling and feature scaling, while a self-attention mechanism enabled the accurate cross-modal feature fusion. The generalization capability of the fused representation was further enhanced by the subsequent of dense layers followed by dropout. Results: XGBoost exhibited the highest performance among the evaluated ML classifiers, achieving 98.7% accuracy and 98.7% F1-score on BreakHis, while achieving 95.8% accuracy on external BACH dataset backed by Grad-CAM- and Grad-CAM++-based interpretability. Conclusions: By integrating CNNs and ViTs through self-attention, the proposed framework offers a robust and interpretable solution for automated breast cancer diagnosis. Full article

Modal superposition enables efficient estimation of full-field structural displacements from sparse measurements, forming a keystone of structural health monitoring (SHM) in linear elastic systems. Accurate reconstruction critically depends on selection of the most relevant vibration modes, traditionally guided by the Internal Strain Potential Energy Criterion (ISPEC), which identifies modes contributing most to internal strain energy. However, the purely analytical formulation of ISPEC requires full knowledge of the deformation field, limiting its applicability in real-time monitoring. This study extends ISPEC using supervised machine learning to enable adaptive mode selection for previously unseen deformation states. A Random Forest classifier is trained on synthetic deformation data generated from a finite element model of a square steel plate. Measurement signals are obtained from a transient analysis in which harmonic displacements are applied to four nodes at the plate plane. Reconstruction performance is evaluated numerically by comparing predicted displacements against reference finite element solutions, using instantaneous residuals, normalised root-mean-square error (NRMSE) and normalised cross-correlation. Results demonstrate that the hybrid ISPEC–machine learning approach accurately reconstructs full-field deflections from eight measurement nodes, with NRMSE typically below 5% and cross-correlation above 0.75. Minor overestimation at peak deflections indicates conservative predictions, while computational efficiency allows real-time implementation. Full article

Background: Relative apical sparing of longitudinal strain is widely used as a diagnostic marker of cardiac amyloidosis. However, similar deformation patterns have been reported in other cardiac diseases, raising concerns regarding disease specificity. A comprehensive multimodality synthesis of the relative apical sparing pattern (RASP) across disease entities is lacking. Methods: A systematic review and meta-analysis were conducted according to PRISMA guidelines. PubMed, Scopus, and EMBASE were searched through December 2025 for studies reporting RASP or regional longitudinal strain values allowing standardized RASP calculation. Cardiac amyloidosis and major phenocopies—including aortic stenosis, hypertrophic cardiomyopathy, hypertensive heart disease, Fabry disease, mitral valve prolapse, and other cardiomyopathies—were included. Random-effects models were used to compare cardiac amyloidosis with non-amyloid conditions using standardized mean differences (SMDs), with subgroup analyses according to imaging modality (two-dimensional speckle-tracking echocardiography [2D-STE] versus cardiac magnetic resonance feature tracking [CMR-FT]). Results: Fourteen studies (nine 2D-STE and five CMR-FT) were included in the quantitative synthesis. Overall, cardiac amyloidosis was associated with significantly higher RASP compared with non-amyloid conditions (SMD 0.676, 95% CI 0.493–0.860; p < 0.001), with substantial heterogeneity (I² = 96.9%). Modality-stratified analyses showed a very large pooled effect for 2D-STE (SMD 2.152, 95% CI 1.354–2.950; I² = 97.6%) and a moderate, homogeneous effect for CMR-FT (SMD 0.594, 95% CI 0.405–0.782; I² = 0%). Sensitivity analyses confirmed robustness. No significant publication bias was detected by Egger’s test. Conclusions: Relative apical sparing is not specific to cardiac amyloidosis but is most pronounced in this condition. Its diagnostic magnitude varies across modalities and clinical contexts, supporting a multiparametric, modality-specific interpretation. Full article

Background: Temporomandibular disorders (TMDs) are common musculoskeletal conditions associated with pain, functional limitation, and reduced quality of life (QoL). Despite the widespread use of conservative and minimally invasive treatments, the available evidence remains fragmented across heterogeneous interventions, diagnostic criteria, and outcome measures, limiting comparative interpretation and clinical applicability. Objectives: The primary objective of this systematic review is to evaluate the effectiveness of conservative and minimally invasive interventions for pain reduction in adult patients with temporomandibular disorders. Secondary objectives include assessing effects on mandibular function and QoL and exploring differences across intervention categories, TMD subtypes, diagnostic criteria, and follow-up durations. Methods: This protocol is registered in the International Prospective Register of Systematic Reviews (PROSPERO; CRD420251250251) and adheres to the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols (PRISMA-P) guidelines. A systematic search will be conducted in PubMed/MEDLINE, Web of Science, Scopus, Embase, and Cochrane Central Register of Controlled Trials (CENTRAL) for randomized controlled trials (RCTs) published from 1 January 2015, up to the date of study initiation, using controlled vocabulary terms and free-text keywords combined with Boolean operators. Eligible studies will include adult patients (≥18 years) diagnosed with temporomandibular disorders using validated diagnostic criteria and treated with conservative or minimally invasive interventions, compared with placebo/sham, no treatment or usual care, or active comparators, in accordance with the PICOS framework. Two reviewers will independently screen studies and extract data, with disagreements resolved by consensus or consultation with a third reviewer; the study selection process will be documented using a PRISMA 2020 flow diagram. Interventions will be synthesized within predefined clusters (e.g., physical and manual therapies, occlusal splint therapy, physical agent modalities, and minimally invasive joint procedures). Risk of bias will be assessed using the revised Cochrane Risk of Bias tool (RoB 2). The primary outcome will be pain intensity, while secondary outcomes will include mandibular function and QoL. Where appropriate, meta-analysis using a random-effects model will be performed; otherwise, a structured narrative synthesis will be provided. Expected Impact: The systematic review is expected to deliver an updated and methodologically rigorous synthesis of evidence on conservative and minimally invasive interventions for TMDs. By addressing existing research gaps such as the fragmentation of evidence across intervention types, heterogeneity in diagnostic criteria, and variability in outcome measures, this review will support evidence-based clinical decision-making and identify priorities for future research. Full article

Diabetes mellitus is a multifactorial metabolic disorder associated with a number of chronic complications, including neuropathy, impaired wound healing, vascular dysfunction, and metabolic dysregulation. Despite advances in pharmacological treatments and lifestyle interventions, current therapies often fail to prevent or reverse these complications entirely. This narrative review examines the therapeutic potential of laser-based modalities, particularly low-level laser therapy (LLLT) and photobiomodulation therapy (PBMT), as complementary strategies in diabetes management. Analysis of experimental and clinical studies shows that laser therapy can enhance wound healing, alleviate neuropathic pain, improve glycaemic control and insulin sensitivity, modulate inflammatory and oxidative stress pathways, and support vascular function. These effects are primarily mediated through mitochondrial activation, nitric oxide release, angiogenesis, modulation of redox-sensitive transcription factors, and preservation of pancreatic β-cell function. Furthermore, laser therapy exhibits a favourable safety profile with minimal side effects. The review highlights the current challenges, such as the lack of standardised treatment parameters (e.g., wavelength, dosage, and duration) and the limited number of large-scale clinical trials. It emphasises the need for personalised protocols and integration of laser therapy with pharmacological and physiotherapeutic interventions. Continued research and interdisciplinary collaboration are needed to realise the potential of laser therapy as an integral component of comprehensive, evidence-based diabetes care. Full article

Decarbonization has emerged as a crucial objective in the optimization of port collection and distribution networks. To investigate the synergistic effects of carbon trading mechanisms and the implementation of electric autonomous container trucks (EACTs), this study develops a multi-objective bi-level programming model that simultaneously minimizes transportation cost, carbon trading cost, and transportation time. The model is solved using the Non-dominated Sorting Genetic Algorithm II (NSGA-II), generating a Pareto-optimal solution set, from which the optimal solution is selected using a normalized ideal point method. Simulation-based case studies validate the feasibility and practical applicability of the proposed model. The results show that the optimized network significantly outperforms the traditional road-dominant mode. Under the baseline carbon price of 70 CNY/ton, the optimal deployment rate of EACTs reaches 25.03% and 33.87%. Sensitivity analysis reveals a distinct non-linear threshold effect: increasing the carbon price to 90 CNY/ton drives the EACT adoption rate to 32.76% and 45.38%, resulting in a 6.98% reduction in carbon emissions and a 12.75% decrease in total operational costs compared to the baseline scenario. Additionally, strict carbon quotas (e.g., 3000 tons) are found to further compel a modal shift, peaking EACT usage at 35.08% and 46.71%. These quantitative findings offer actionable insights for optimizing multimodal transport structures and refining carbon trading policies. Full article

Regional epidemic risk prediction requires holistic modeling of heterogeneous data sources such as demographic structure, health capacity, geographical features and human mobility. In this study, a unique and multi-modal epidemiological data set integrating demographic, health, geographic and mobility indicators of Türkiye and its neighboring countries was collected. Türkiye’s neighboring countries are Greece, Bulgaria, Georgia, Armenia, Iran, and Iraq. This dataset, created by combining raw data from these neighboring countries, provides a comprehensive regional representation that allows for both quantitative classification and spatial mapping of epidemiological risk. To address the class imbalance problem, Conditional GAN (CGAN), a class-conditional synthetic example generation approach that enhances high-risk category representation was used. In this study, we proposed a multi-view deep learning model named MV-RiskNet, which effectively models the multi-dimensional data structure by processing each view into independent subnetworks and integrating the representations with an attention-based fusion mechanism for regional epidemic risk prediction. Experimental studies were compared using Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Autoencoder classifier, and Graph Convolutional Network (GCN) models. The proposed MV-RiskNet with CGAN model achieved better results compared to other models, with 97.22% accuracy and 97.40% F1-score. The generated risk maps reveal regional clustering patterns in a spatially consistent manner, while attention analyses show that demographic and geographic features are the dominant determinants, while mobility plays a complementary role, especially in high-risk regions. Full article

Phase unwrapping is a critical step in interferometric imaging modalities such as holography and synthetic aperture radar, yet conventional analytical algorithms struggle in low signal-to-noise and high-speckle environments. This study presents an artificial intelligence (AI)-based phase-unwrapping framework using a Pix2Pix conditional generative adversarial network (cGAN). A model was designed for robustness under Rayleigh-distributed speckle noise and phase decorrelation, conditions representative of realistic interferometric measurements. Trained on synthetically generated wrapped–unwrapped phase pairs, the AI approach was compared against established analytical phase-unwrapping methods, a quality-guided unwrapping algorithm (Herraez)and a minimum-norm network-flow optimization method (Costantini). Quantitative evaluation using the root mean square error (RMSE), structural similarity index measure (SSIM), and a composite performance index demonstrated that the cGAN was superior under noisy conditions, successfully recovering phase information beyond its training noise range at $\sigma =10$, and accurately unwrapping phases up to $\sigma =20$. This was under a pure unwrapping performance analysis, utility performance was also tested comparing all images to clean noiseless phase. The Pix2Pix model also proved resilient to detector artifacts, despite not being explicitly trained on them, and its worst performance yielded RMSE and SSIM values of 0.089 and 0.927, respectively, with perfect values being 0 and 1. The proposed framework simultaneously unwraps and denoises the phase, offering a simple, open-source, and highly adaptable alternative for phase unwrapping in noisy interferometric systems. Future work will focus on extending the framework to experimental datasets. Full article