Search Results (4,406)

Background/Objectives: This study aims to build an interpretable and accurate predictive model for myocardial infarction (MI) using Explainable Boosting Machines (EBM), a state-of-the-art Explainable Artificial Intelligence (XAI) technique. The objective is to identify and rank clinically relevant biomarkers that contribute to MI diagnosis while maintaining transparency to support clinical decision making. Methods: The dataset comprises 1319 patient records collected in 2018 from a cardiology center in the Erbil region of Iraq. Each record includes eight routinely measured clinical and biochemical features, such as troponin, CK-MB, and glucose levels, and a binary outcome variable indicating the presence or absence of MI. After preprocessing (e.g., one-hot encoding, normalization), the EBM model was trained using 80% of the data and tested on the remaining 20%. Model performance was evaluated using standard metrics including AUC, accuracy, sensitivity, specificity, F1 score, and Matthews correlation coefficient. Feature importance was assessed to identify key predictors. Partial dependence analyses provided insights into how each variable affected model predictions. Results: The EBM model demonstrated excellent diagnostic performance, achieving an AUC of 0.980, an accuracy of 96.6%, sensitivity of 96.8%, and specificity of 96.2%. Troponin and CK-MB were identified as the top predictors, confirming their established clinical relevance in MI diagnosis. In contrast, demographic and hemodynamic variables such as age and blood pressure contributed minimally. Partial dependence plots revealed non-linear effects of key biomarkers. Local explanation plots demonstrated the model’s ability to make confident, interpretable predictions for both positive and negative cases. Conclusions: The findings highlight the potential of EBM as a clinically useful and ethical AI approach for MI diagnosis. By combining high predictive accuracy with transparency, EBM supports biomarker prioritization and clinical risk stratification, thus aligning with precision medicine and responsible AI principles. Future research should validate the model on multi-center datasets and explore additional features for broader clinical use. Full article

Topic modeling in digital news faces the dual challenge of thematic overlap and evolving semantic boundaries, especially in morphologically rich languages like Turkish. To address these obstacles, we propose a topic modeling framework enhanced with knowledge graphs that explicitly incorporates uncertainty in topic assignment. We focus on the diversity of Fuzzy Latent Semantic Analysis (FLSA) and compare the performance with Latent Dirichlet Allocation (LDA), BERTopic, and embedding-based Top2Vec on a corpus drawn from two Turkish news agencies. We evaluate each model using standard metrics for topic coherence, diversity, and interpretability. We propose Shannon entropy of node-degree distributions to measure the network complexity of knowledge graphs as topic similarity. Our results indicate that FLSA achieves perfect topic diversity, 1.000 and improved interpretability, 0.33 over LDA, 0.09 while also enhancing coherence, 0.33 vs. 0.27. Top2Vec demonstrates the strongest coherence, 0.81 and interpretability, 0.78 with high diversity, 0.97, reflecting its capacity to form semantically cohesive clusters. Entropy analysis further shows that FLSA produces the most information-rich topic networks. These findings suggest that fuzzy modeling and embedding-based approaches offer complementary strengths, uncertainty-aware flexibility, and semantic precision, thereby improving topic discovery in complex, unstructured news environments. Full article

This study systematically investigates the effects of aging treatment (AT) on the microstructure and properties of Cr/DLC coatings deposited via cathodic arc ion plating onto the surface of ECAP-7075 aluminum alloy. Utilizing a comprehensive approach combining performance tests (nanoindentation, nanoscratch testing, dynamic polarization analysis) with characterization tests (scanning electron microscopy, energy dispersive spectroscopy, X-ray diffraction, and X-ray photoelectron spectroscopy), the synergistic effects of equal channel angular pressing (ECAP) and aging treatment(AT) were elucidated. The results demonstrate that the combined ECAP and AT significantly enhance the coating’s performance. Specifically, AT promotes the precipitation of η’ phase within the 7075 aluminum alloy substrate, increases the size of Cr₇C₃ crystallites in the Cr-based interlayer, improves the crystallinity of the Cr₇C₃ phase on the (060) or (242) crystal planes, and elevates the sp³-C/sp²-C ratio in the diamond-like carbon(DLC) top layer, leading to partial healing of defects and a denser overall coating structure. These microstructural transformations, induced by AT, result in substantial improvements in the mechanical properties (hardness reaching 5.2 GPa, bond strength achieving 15.1 N) and corrosion resistance (corrosion potential increasing to -0.698 V) of the Cr/DLC-coated ECAP-7075 aluminum alloy. This enhanced combination of properties makes these coatings particularly well-suited for high-performance aerospace components requiring both wear resistance and corrosion protection in demanding environments. Full article

Ransomware attacks pose a serious threat to global cybersecurity, inflicting severe financial and operational damage on organizations, individuals, and critical infrastructure. Despite their pervasive impact, proactive measures to mitigate ransomware threats remain underdeveloped, with most efforts focused on reactive responses. Moreover, prior literature reveals a significant gap in systematic approaches for predicting such incidents. This research seeks to address this gap by employing time-series analysis to forecast ransomware attacks. Using 1880 ransomware incidents, we decompose the dataset into trend, seasonal, and residual components, fit a time-series model, and forecast future attacks. The results indicate that time-series analysis is useful for uncovering broad, structural patterns in ransomware data. To gain further insight into these results, we perform sub-analyses based on attacks targeting the top five sectors. The findings reveal reasonable predictive performance for ransomware attacks against government facilities and the healthcare and public health sector, with the latter showing an upward trend in attacks. By providing a predictive lens, our model equips organizations with actionable intelligence, enabling preemptive measures and enhanced situational awareness. Finally, this research underscores the importance of integrating time-series forecasting into cybersecurity strategies and seeks to pave the way for future advancements in predictive analytics for cyber threats. Full article

Background and Clinical Significance: Patients with a neurodegenerative condition known as posterior cortical atrophy (PCA) can present with attention impairments across a variety of cognitive contexts, but the consequences of these are little explored in example of single word reading. Case Presentation: We present a detailed single-case study of KL, a local resident of South Wales, a patient diagnosed with posterior cortical atrophy (PCA) in 2018, whose reading and letter-naming abilities are selectively disrupted under non-canonical visual presentations. In particular, KL shows significantly impaired accuracy performance when reading words presented in tilted (rotated 90°) format. By contrast, his reading under conventional horizontal (canonical) presentation is nearly flawless. Whilst other presentation formats including, mixed-case text (e.g., TaBLe) and vertical (marquee) format led to only mild performance decrements—even though mixed-case formats are generally thought to increase attentional ‘crowding’ effects. Discussion: These findings indicate that impairments of word reading can emerge in PCA when visual-attentional demands are sufficiently high, and access to ‘top down’ orthographic information is severely attenuated. Next, we explored a cardinal feature of attentional dyslexia, namely the word–letter reading dissociation in which word reading is superior to letter-in-string naming. In KL, a similar dissociative pattern could be provoked by non-canonical formats. That is, conditions that similarly disrupted his word reading led to a pronounced disparity between word and letter-in-string naming performance. Moreover, different orientation formats revealed the availability (or otherwise) of distinct compensatory strategies. KL successfully relied on an oral (letter by letter) spelling strategy when reading vertically presented words or naming letters-in-strings, whereas he had no ability to engage compensatory mental rotation processes for tilted text. Thus, the observed impact of non-canonical presentations was moderated by the success or failure of alternative compensatory strategies. Conclusions: Importantly, our results suggest that an attentional ‘dyslexia-like’ profile can be unmasked in PCA under sufficiently taxing visual-attentional conditions. This approach may prove useful in clinical assessment, highlighting subtle reading impairments that conventional testing might overlook. Full article

This study investigates the tribological behavior and wear mechanisms of Q235 steel components subjected to abrasive interaction with rice, a critical challenge in agricultural machinery performance and longevity. We employed a comprehensive multi-scale framework, integrating bench-top tribological testing, advanced Discrete Element Method (DEM) coupled with a wear model (DEM-Wear), and detailed surface characterization. Bench tests revealed a composite wear mechanism for the rice–steel tribo-pair, transitioning from mechanical polishing under mild conditions to significant soft abrasive micro-cutting driven by the silica particles inherent in rice during high-load, high-velocity interactions. This elucidated fundamental friction and wear phenomena at the micro-level. A novel, calibrated DEM-Wear model was developed and validated, accurately predicting macroscopic wear “hot spots” on full-scale combine harvester header platforms with excellent geometric similarity to real-world wear profiles. This provides a robust predictive tool for component lifespan and performance optimization. Furthermore, fractal analysis was successfully applied to quantitatively characterize worn surfaces, establishing fractal dimension (Ds) as a sensitive metric for wear severity, increasing from ~2.17 on unworn surfaces to ~2.3156 in severely worn regions, directly correlating with the dominant wear mechanisms. This study offers a valuable computational approach for understanding and mitigating wear in tribosystems involving complex particulate matter, contributing to improved machinery reliability and reduced operational costs. Full article

Dyspepsia or indigestion is known to be a symptom of several gastrointestinal issues including gastroesophageal reflux disease (GERD) and gastric cancer. With the ever-increasing popularity of traditional herbal medicines, the research selected rosemary, or Salvia rosmarinus, due to its historical ethnopharmacological applications and ease of cultivation. Potential targets of molecules from S. rosmarinus are explored for the molecular pathogenesis of functional dyspepsia. Through a network pharmacology approach, it has been shown that there is a significant interaction between the disease and the plant’s compounds. The pathways involving the target genes of S. rosmarinus that are related to functional dyspepsia were revealed to be implicated in the development of certain diseases like gastric cancer and fibrosis which are both precursors to dyspepsia. Moreover, through molecular docking, the results of the pathway analyses were computationally validated indicating that the compound luteolin has the most significant interaction against dyspepsia-related genes. It effectively promotes apoptosis in cancer pathways, reducing the chances of gastric cancer carcinogenesis. To further validate these findings, molecular dynamics simulation was performed to compare the stability and binding behavior of the top-performing compound against the reference compound. The results of this study could be a possible basis in developing pharmaceuticals against gastrointestinal diseases, specifically, dyspepsia. Full article

With the growing emphasis on healthy eating and nutrition management in modern society, food image recognition has become increasingly important. However, it faces challenges such as large intra-class differences and high inter-class similarities. To tackle these issues, we present a Food Feature Fusion Network (FFFNet), which leverages a multi-head cross-attention mechanism to integrate the local detail-capturing capability of Convolutional Neural Networks with the global modeling capacity of Vision Transformers. This enables the model to capture key discriminative features when addressing such challenging food recognition tasks. FFFNet also introduces self-supervised clustering, generating pseudo-labels from the feature space distribution and employing a clustering objective derived from Kullback–Leibler divergence to optimize the feature space distribution. By maximizing similarity between features and their corresponding cluster centers, and minimizing similarity with non-corresponding centers, it promotes intra-class compactness and inter-class separability, thereby addressing the core challenges. We evaluated FFFNet across the ISIA Food-500, ETHZ Food-101, and UEC Food256 datasets, attaining Top-1/Top-5 accuracies of 65.31%/88.94%, 89.98%/98.37%, and 80.91%/94.92%, respectively, outperforming existing approaches. Full article

Background: Histone deacetylase 6 (HDAC6) is a unique class IIb HDAC isozyme characterized by two catalytic domains and a zinc finger ubiquitin-binding domain. It plays critical roles in various cellular processes, including protein degradation, autophagy, immune regulation, and cytoskeletal dynamics. Due to its multifunctional nature and overexpression in several cancer types, HDAC6 has emerged as a promising therapeutic target. Methods: In this study, we employed a ligand-based pharmacophore modeling approach using a structurally diverse set of known HDAC6 inhibitors. This was followed by the virtual screening of over 140,000 commercially available compounds from both the MolPort and Asinex databases. The screening workflow incorporated pharmacophore filtering, molecular docking, and molecular dynamic (MD) simulations. Binding free energies were estimated using Molecular Mechanics Generalized Born Surface Area (MM-GBSA) analysis to prioritize top candidates. A fluorometric enzymatic assay was used to measure HDAC6 activity, while cell viability assay by Cell Titer Glo was used to assess the anti-tumor activity against drug-sensitive and -resistant multiple myeloma (MM) cells. Western blotting was used to evaluate the acetylation of tubulin or histone H4 after treatment with selected compounds. Results: Three promising compounds were identified based on stable binding conformations and favorable interactions within the HDAC6 catalytic pocket. Among them, Molecular Mechanics Generalized Born Surface Area (MM-GBSA) analysis identified Compound 10 (AKOS030273637) as the top theoretical binder, with a ΔG_bind value of −45.41 kcal/mol. In vitro enzymatic assays confirmed its binding to the HDAC6 catalytic domain and inhibitory activity. Functional studies on MM cell lines, including drug-resistant variants, showed that Compound 10 reduced cell viability. Increased acetylation of α-tubulin, a substrate of HDAC6, likely suggested on-target mechanism of action. Conclusion: Compound 10, featuring a benzyl 4-[4-(hydroxyamino)-4-oxobutylidene] piperidine-1-carboxylate scaffold, demonstrates potential drug-like properties and a predicted bidentate zinc ion coordination, supporting its potential as an HDAC6 inhibitor for further development in hematologic malignancies. Full article

Accurate classification of brain tumors in medical imaging is crucial to ensure reliable diagnoses and effective treatment planning. This study introduces a novel double ensemble framework that synergistically combines pre-trained Deep Learning (DL) models for feature extraction with optimized Machine Learning (ML) classifiers for robust classification. The framework incorporates comprehensive preprocessing and data augmentation of brain Magnetic Resonance Images (MRIs), followed by deep feature extraction based on transfer learning using pre-trained Vision Transformer (ViT) networks. The novelty of our approach lies in its dual-level ensemble strategy: we employ a feature-level ensemble, which integrates deep features from the top-performing ViT models, and a classifier-level ensemble, which aggregates predictions from various hyperparameter-optimized ML classifiers. Experiments on two public MRI brain tumor datasets from Kaggle demonstrate that this approach significantly surpasses state-of-the-art methods, underscoring the importance of feature and classifier fusion. The proposed methodology also highlights the critical roles that hyperparameter optimization and advanced preprocessing techniques can play in improving the diagnostic accuracy and reliability of medical image analysis, advancing the integration of DL and ML in this vital, clinically relevant task. Full article

This study concerns the evaluation of adhesive and wettability energetic signatures of a model orthodontic wire exposed to commercial mouthrinses. The surface wetting properties were evaluated from the contact angle hysteresis (CAH) approach applied to dynamic contact angle data derived from the original drop on a vertical filament method. Young, advancing, receding CA apart from adhesive film pressure, surface energy, work of adhesion, etc. were chosen as interfacial interaction indicators, allowing for the optimal concentration and placement of the key component(s) accumulation to be predicted for effective antibacterial activity to eliminate plaque formation on the prosthetic materials. Surfactant compounds when adsorb at interfaces confer rheological properties to the surfaces, leading to surface relaxation, which depends on the timescale of the deformation. The surface dilatational complex modulus E, with compression elasticity E_d and viscosity E_i parts, determined in the stress–relaxation Langmuir trough measurements, exhibited the viscoelastic surface film behavior with the relaxation times (0.41–3.13 s), pointing to the vertically segregated film structure as distinct, stratified layers with the most insoluble compound on the system top (as indicated with the 2D polymer film scaling theory exponent y = 12.9–15.5). Kinetic rheology parameters could affect the wettability, adhesion, and spreading characteristics of mouthrinse liquids. Full article

The skin, the largest organ of the body, acts as a protective shield against external stimuli. Skin lesions, which can be the result of inflammation, infection, tumors, or autoimmune conditions, can appear as rashes, spots, lumps, or scales, or remain asymptomatic until they become severe. Conventional diagnostic approaches such as visual inspection and palpation often lack accuracy. Artificial intelligence (AI) improves diagnostic precision by analyzing large volumes of skin images to detect subtle patterns that clinicians may not recognize. This study presents a multiclass skin lesion diagnostic model developed using the CSMUH dataset, which focuses on the Eastern population. The dataset was categorized into seven disease classes for model training. A total of 25 pre-trained models, including convolutional neural networks (CNNs) and vision transformers (ViTs), were fine-tuned. The top three models were combined into an ensemble using the hard and soft voting methods. To ensure reliability, the model was tested through five randomized experiments and validated using the holdout technique. The proposed ensemble model, Swin-ViT-EfficientNetB4, achieved the highest test accuracy of 98.5%, demonstrating strong potential for accurate and early skin lesion diagnosis. Full article

How can we address the rapid advancement and widespread adoption of Artificial Intelligence (AI) across various sectors of society? This paper aims to provide insights through a cybernetic-systemic approach, which is well-suited to tackle the complexities of this new landscape. We will utilize the framework of Organizational Cybernetics (OC) and the Viable System Model (VSM), along with Perez Rios’s Taxonomy of Organizational Pathologies (TOP). By examining the key risks and potential challenges posed by AI through the lens of OC, this paper seeks to contribute to the development of more effective strategies for responsible innovation and governance in AI. Full article

Prompt optimization through textual feedback has shown promising results in improving the performance of large language models (LLMs) on downstream tasks. However, existing approaches often rely on selecting prompt edits from a pool of candidate gradients using random sampling or local heuristics, requiring multiple evaluations to find effective modifications. In this work, we propose a center-aware selection method that identifies high-quality gradient candidates based on their proximity to a robust semantic center representation of the gradient pool. Rather than sampling or scoring candidates iteratively, our method embeds all textual gradients and deterministically selects the top-k closest to the semantic center, which captures the consensus of the candidate pool. Experiments on three diverse datasets demonstrate that our approach not only improves predictive performance but also reduces the number of required model queries. In addition, qualitative analyses reveal that gradients near the center tend to encode more generalizable reasoning patterns. These findings highlight the utility of semantic embedding space as a reliable signal for selecting effective prompt edits in a resource-efficient manner. Full article

Background/Objectives In this study we approach the problem of medical image segmentation by introducing a new loss function envelope that is derived from the Top-k loss strategy. We exploit the fact that, for semantic segmentation, the training loss is computed at two levels, more specifically at pixel level and at image level. Quite often, the envisaged problem has particularities that include noisy annotation at pixel level and limited data, but with accurate annotations at image level. Methods To address the mentioned issues, the Top-k strategy at image level and respectively the “Bottom all but $\sigma$” strategy at pixel level are assumed. To deal with the discontinuities of the differentials faced in the automatic learning, a derivative smoothing procedure is introduced. Results The method is thoroughly and successfully tested (in conjunction with a variety of backbone models) for several medical image segmentation tasks performed onto a variety of image acquisition types and human body regions. We present the burned skin area segmentation in standard color images, the segmentation of fetal abdominal structures in ultrasound images and ventricles and myocardium segmentation in cardiac MRI images, in all cases yielding performance improvements. Conclusions The proposed novel mechanism enhances model training by selectively emphasizing certain loss values by the use of two complementary strategies. The major benefits of the approach are clear in challenging scenarios, where the segmentation problem is inherently difficult or where the quality of pixel-level annotations is degraded by noise or inconsistencies. The proposed approach performs equally well in both convolutional neural networks (CNNs) and vision transformer (ViT) architectures. Full article