Search Results (697)

Urban scene understanding for inclusive smart cities remains challenged by the scarcity of training data capturing people with mobility impairments. We propose SYNTHUA-DT, a novel methodological framework that integrates unmanned aerial vehicle (UAV) photogrammetry, 3D digital twin modeling, and high-fidelity simulation in Unreal Engine to generate annotated synthetic datasets for urban accessibility applications. This framework produces photo-realistic images with automatic pixel-perfect segmentation labels, dramatically reducing the need for manual annotation. Focusing on the detection of individuals using mobility aids (e.g., wheelchairs) in complex urban environments, SYNTHUA-DT is designed as a generalized, replicable pipeline adaptable to different cities and scenarios. The novelty lies in combining real-city digital twins with procedurally placed virtual agents, enabling diverse viewpoints and scenarios that are impractical to capture in real life. The computational efficiency and scale of this synthetic data generation offer significant advantages over conventional datasets (such as Cityscapes or KITTI), which are limited in accessibility-related content and costly to annotate. A case study using a digital twin of Curitiba, Brazil, validates the framework’s real-world applicability: 22,412 labeled images were synthesized to train and evaluate vision models for mobility aids user detection. The results demonstrate improved recognition performance and robustness, highlighting SYNTHUA-DT’s potential to advance urban accessibility by providing abundant, bias-mitigating training data. This work paves the way for inclusive computer vision systems in smart cities through a rigorously engineered synthetic data pipeline. Full article

Background/Objectives: Olfactory impairment has been proposed as an early marker for Alzheimer’s disease (AD), yet the mechanisms linking sensory decline to genetic and environmental risk factors remain unclear. We aimed to identify early biomarkers and brain network alterations associated with AD risk by multimodal analyses in humanized APOE mice. Methods: We evaluated olfactory behavior, diffusion MRI connectomics, and brain and blood transcriptomics in mice stratified by APOE2, APOE3, and APOE4 genotypes, age, sex, high-fat diet, and immune background (HN). Behavioral assays assessed odor salience, novelty detection, and memory. Elastic Net-regularized multi-set canonical correlation analysis (MCCA) was used to link behavior to brain connectivity. Blood transcriptomics and gene ontology analyses identified peripheral molecular correlates. Results: APOE4 mice exhibited accelerated deficits in odor-guided behavior and memory, especially under high-fat diet, while APOE2 mice were more resilient (ANOVA: APOE x HN, F(2, 1669) = 77.25, p < 0.001, eta squared = 0.08). Age and diet compounded behavioral impairments (diet x age: F(1, 1669) = 16.04, p < 0.001). Long-term memory was particularly reduced in APOE4 mice (APOE x HN, F(2,395) = 5.6, p = 0.004). MCCA identified subnetworks explaining up to 24% of behavioral variance (sum of canonical correlations: 1.27, 95% CI [1.18, 1.85], p < 0.0001), with key connections involving the ventral orbital and somatosensory cortices. Blood eigengene modules correlated with imaging changes (e.g., subiculum diffusivity: r = −0.5, p < 1 × 10⁻³⁰), and enriched synaptic pathways were identified across brain and blood. Conclusions: Olfactory behavior, shaped by genetic and environmental factors, may serve as a sensitive, translatable biomarker of AD risk. Integrative systems-level approaches reveal brain and blood signatures of early sensory–cognitive vulnerability, supporting new avenues for early detection and intervention in AD. Full article

The 2021 WHO classification of brain tumours revolutionised the oncological field by emphasising the role of molecular, genetic and pathogenetic advances in classifying brain tumours. In this context, incidental gliomas have been increasingly identified due to the widespread performance of standard and advanced MRI sequences and represent a diagnostic and therapeutic challenge. The impactful decision to perform a surgical procedure deeply relies on the non-invasive identification of features or parameters that may correlate with brain tumour genetic profile and grading. Therefore, it is paramount to reach an early and proper diagnosis through neuroradiological techniques, such as MRI. Standard MRI sequences are the cornerstone of diagnosis, while consolidated and emerging roles have been awarded to advanced sequences such as Diffusion-Weighted Imaging/Apparent Diffusion Coefficient (DWI/ADC), Perfusion-Weighted Imaging (PWI), Magnetic Resonance Spectroscopy (MRS), Diffusion Tensor Imaging (DTI) and functional MRI (fMRI). The current novelty relies on the application of AI in brain neuro-oncology, mainly based on radiomics and radiogenomics models, which enhance standard and advanced MRI sequences in predicting glioma genetic status by identifying the mutation of multiple key biomarkers deeply impacting patients’ diagnosis, prognosis and treatment, such as IDH, EGFR, TERT, MGMT promoter, p53, H3-K27M, ATRX, Ki67 and 1p19. AI-driven models demonstrated high accuracy in glioma detection, grading, prognostication, and pre-surgical planning and appear to be a promising frontier in the neuroradiological field. On the other hand, standardisation challenges in image acquisition, segmentation and feature extraction variability, data scarcity and single-omics analysis, model reproducibility and generalizability, the black box nature and interpretability concerns, as well as ethical and privacy challenges remain key issues to address. Future directions, rooted in enhanced standardisation and multi-institutional validation, advancements in multi-omics integration, and explainable AI and federated learning, may effectively overcome these challenges and promote efficient AI-based models in glioma management. The aims of our multidisciplinary review are to: (1) extensively present the role of standard and advanced MRI sequences in the differential diagnosis of iLGGs as compared to HGGs (High-Grade Gliomas); (2) give an overview of the current and main applications of AI tools in the differential diagnosis of iLGGs as compared to HGGs (High-Grade Gliomas); (3) show the role of MRI, radiomics and radiogenomics in unravelling glioma genetic profiles. Standard and advanced MRI, radiomics and radiogenomics are key to unveiling the grading and genetic profile of gliomas and supporting the pre-operative planning, with significant impact on patients’ differential diagnosis, prognosis prediction and treatment strategies. Today, neuroradiologists are called to efficiently use AI tools for the in vivo, non-invasive, and comprehensive assessment of gliomas in the path towards patients’ personalised medicine. Full article

This study investigates the performance of Distributed Acoustic Sensing (DAS) for detecting gas pipeline leaks under controlled experimental conditions, using multiple fiber cable types deployed both internally and externally. A 21 m steel pipeline with a 1 m test section was configured to simulate leakage scenarios with varying leak sizes (¼”, ½”, ¾”, and 1”), orientations (top, side, bottom), and flow velocities (2–18 m/s). Experiments were conducted under two installation conditions: a supported pipeline mounted on tripods, and a buried pipeline laid on the ground and covered with sand. Four fiber deployment methods were tested: three internal cables of varying geometries and one externally mounted straight cable. DAS data were analyzed using both time-domain vibration intensity and frequency-domain spectral methods. The results demonstrate that leak detectability is influenced by multiple interacting factors, including flow rate, leak size and orientation, pipeline installation method, and fiber cable type and deployment approach. Internally deployed black and flat cables exhibited higher sensitivity to leak-induced vibrations, particularly at higher flow velocities, larger leak sizes, and for bottom-positioned leaks. The thick internal cable showed limited response due to its wireline-like construction. In contrast, the external straight cable responded selectively, with performance dependent on mechanical coupling. Overall, leakage detectability was reduced in the buried configuration due to damping effects. The novelty of this work lies in the successful detection of gas leaks using internally deployed fiber optic cables, which has not been demonstrated in previous studies. This deployment approach is practical for field applications, particularly for pipelines that cannot be inspected using conventional methods, such as unpiggable pipelines. Full article

The release of ChatGPT and similar applications in 2022 prompted wide-ranging discussions concerning the impact of AI technologies on writing, creativity, and authorship. This article explores the question of artificial writing, taking into consideration both critical theories and creative experiments. In the first section, I review current scholarly discussions about authorship in the age of generative AI. In the second and third sections, I turn to experiments in literary co-creation that combine the affordances of technology with the human art of prompting and editing or curating. My argument has three prongs: (1) experiments that frame artificial writing as literature (memoir, poetry, autobiography, fiction) are accompanied by enlarged paratexts, which merit more attention than they have hitherto received; (2) paratexts provide salient clues on the process of co-creation, the reconfiguration of authorship, and the production of value; and (3) in the folds of paratextual explanations, one can detect the profile of the author as clever prompter, navigating a new terrain by relying at times on the certainties of conventional authorship. My analyses show that while AI-generated literature is a novel phenomenon worthy of closer scrutiny, the novelty tends to be cloaked in a familiar garb. Full article

Rust’s growing popularity in high-integrity systems requires automated vulnerability detection in order to maintain its strong safety guarantees. Although Rust’s ownership model and compile-time checks prevent many errors, sometimes unexpected bugs may occasionally pass analysis, underlining the necessity for automated safe and unsafe code detection. This paper presents Rust-IR-BERT, a machine learning approach to detect security vulnerabilities in Rust code by analyzing its compiled LLVM intermediate representation (IR) instead of the raw source code. This approach offers novelty by employing LLVM IR’s language-neutral, semantically rich representation of the program, facilitating robust detection by capturing core data and control-flow semantics and reducing language-specific syntactic noise. Our method leverages a graph-based transformer model, GraphCodeBERT, which is a transformer architecture pretrained model to encode structural code semantics via data-flow information, followed by a gradient boosting classifier, CatBoost, that is capable of handling complex feature interactions—to classify code as vulnerable or safe. The model was evaluated using a carefully curated dataset of over 2300 real-world Rust code samples (vulnerable and non-vulnerable Rust code snippets) from RustSec and OSV advisory databases, compiled to LLVM IR and labeled with corresponding Common Vulnerabilities and Exposures (CVEs) identifiers to ensure comprehensive and realistic coverage. Rust-IR-BERT achieved an overall accuracy of 98.11%, with a recall of 99.31% for safe code and 93.67% for vulnerable code. Despite these promising results, this study acknowledges potential limitations such as focusing primarily on known CVEs. Built on a representative dataset spanning over 2300 real-world Rust samples from diverse crates, Rust-IR-BERT delivers consistently strong performance. Looking ahead, practical deployment could take the form of a Cargo plugin or pre-commit hook that automatically generates and scans LLVM IR artifacts during the development cycle, enabling developers to catch vulnerabilities at an early stage in the development cycle. Full article

Cutaneous and oral mucosal adverse events (AEs) are among the most common non-hematologic toxicities observed during breast cancer treatment. These complications arise across various therapeutic modalities including chemotherapy, targeted therapy, hormonal therapy, radiotherapy, and immunotherapy. Although often underrecognized compared with systemic side effects, dermatologic and mucosal toxicities can severely impact the patients’ quality of life, leading to psychosocial distress, pain, and reduced treatment adherence. In severe cases, these toxicities may necessitate dose reductions, treatment delays, or discontinuation, thereby compromising oncologic outcomes. The growing use of precision medicine and novel targeted agents has broadened the spectrum of AEs, with some therapies linked to distinct dermatologic syndromes and mucosal complications such as mucositis, xerostomia, and lichenoid reactions. Early detection, accurate classification, and timely multidisciplinary management are essential for mitigating these effects. This review provides a comprehensive synthesis of current knowledge on cutaneous and oral mucosal toxicities associated with modern breast cancer therapies. Particular attention is given to clinical presentation, underlying pathophysiology, incidence, and evidence-based prevention and management strategies. We also explore emerging approaches, including nanoparticle-based delivery systems and personalized interventions, which may reduce toxicity without compromising therapeutic efficacy. By emphasizing the integration of dermatologic and mucosal care, this review aims to support clinicians in preserving treatment adherence and enhancing the overall therapeutic experience in breast cancer patients. The novelty of this review lies in its dual focus on cutaneous and oral complications across all major therapeutic classes, including recent biologic and immunotherapeutic agents, and its emphasis on multidisciplinary, patient-centered strategies. Full article

Pile foundations are critical structural elements, and their integrity is essential for ensuring the stability and safety of construction projects. Low-strain pile integrity testing (LSPIT) is widely used for defect detection; however, conventional manual interpretation of reflectograms is both time-consuming and susceptible to human error. This study presents a deep learning-driven approach utilizing transfer learning with convolutional neural networks (CNNs) to automate pile defect detection. A dataset of 328 reflectograms collected from real construction sites, including 246 intact and 82 defective samples, was used to train and evaluate the model. To address class imbalance, oversampling techniques were applied. Several state-of-the-art pretrained CNN architectures were compared, with ConvNeXtLarge achieving the highest accuracy of 98.2%. The accuracy reported was achieved on a dedicated test set using real reflectogram data from actual construction sites, distinguishing this study from prior work relying primarily on synthetic data. The proposed novelty includes adapting pre-trained CNN architectures specifically for real-world pile integrity testing, addressing practical challenges such as data imbalance and limited dataset size through targeted oversampling techniques. The proposed approach demonstrates significant improvements in accuracy and efficiency compared to manual interpretation methods, making it a promising solution for practical applications in the construction industry. The proposed method demonstrates potential for generalization across varying pile lengths and geological conditions, though further validation with broader datasets is recommended. Full article

This paper presents a comprehensive model for detecting and addressing concept drift in network security data using the Isolation Forest algorithm. The approach leverages Isolation Forest’s inherent ability to efficiently isolate anomalies in high-dimensional data, making it suitable for adapting to shifting data distributions in dynamic environments.Anomalies in network attack data may not occur in large numbers, so it is important to be able to detect anomalies even with small batch sizes. The novelty of this work lies in successfully detecting anomalies even with small batch sizes and identifying the point at which incremental retraining needs to be started. Triggering retraining early also keeps the model in sync with the latest data, reducing the chance for attacks to be successfully conducted. Our methodology implements an end-to-end workflow that continuously monitors incoming data and detects distribution changes using Isolation Forest, then manages model retraining using Random Forest to maintain optimal performance. We evaluate our approach using UWF-ZeekDataFall22, a newly created dataset that analyzes Zeek’s Connection Logs collected through Security Onion 2 network security monitor and labeled using the MITRE ATT&CK framework. Incremental as well as full retraining are analyzed using Random Forest. There was a steady increase in the model’s performance with incremental retraining and a positive impact on the model’s performance with full model retraining. Full article

Background/Objectives: This paper presents a medical image analysis application designed to facilitate advanced edge detection and fuzzy processing techniques within an intuitive, modular graphical user interface. Methods: Key functionalities include classical edge detection, Ant Colony Optimization (ACO)-based edge extraction, and fuzzy edge generation, which offer improved boundary representation in images where uncertainty and soft transitions are prevalent. Results: One of the main novelties in contrast to the initial innovative Medical Image Analyzer, iMIA, is the fact that the system includes fuzzy C-means clustering to support tissue classification and unsupervised segmentation based on pixel intensity distribution. The application also features an interactive zooming and panning module with the option to overlay edge detection results. As another novelty, fuzzy performance metrics were added, including fuzzy false negatives, fuzzy false positives, fuzzy true positives, and the fuzzy index, offering a more comprehensive and uncertainty-aware evaluation of edge detection accuracy. Conclusions: The application executable file is provided at no cost for the purposes of evaluation and testing. Full article

Among the existing challenges in the field of hyperspectral imaging, the need to optimize memory usage and computational capacity in material detection methods stands out, given the vast amount of data associated with the hundreds of reflectance bands. In line with this, this article proposes a comparative study on the effectiveness and efficiency of five computational methods for detecting composite material asbestos cement (AC) in hyperspectral images: correlation, spectral differential similarity (SDS), Fourier phase similarity (FPS), area under the curve (AUC), and decision trees (DT). The novelty lies in the comparison between the first four methods, which represent the spectral proximity method and a machine learning method, such as DT. Furthermore, SDS and FPS are novel methods proposed in the present document. Given the accuracy that detection methods based on supervised learning have demonstrated in material identification, the results obtained from the DT model were compared with the percentage of AC detected in a hyperspectral image of the Manga neighborhood in the city of Cartagena by the other four methods. Similarly, in terms of computational efficiency, a 20 × 20 pixel region with 380 bands was selected for the execution of multiple repetitions of each of the five computational methods considered, in order to obtain the average processing time of each method and the relative efficiency of the methods with respect to the method with the best effectiveness. The decision tree (DT) model achieved the highest classification accuracy at 99.4%, identifying 11.44% of asbestos cement (AC) pixels in the reference image. However, the correlation method, while detecting a lower percentage of AC pixels (9.72%), showed the most accurate visual performance and had no spectral overlap, with a 1.4% separation between AC and non-AC pixels. The SDS method was the most computationally efficient, running 23.85 times faster than the DT model. The proposed methods and results can be applied to other hyperspectral imaging tasks involving material identification in urban environments, especially when balancing accuracy and computational efficiency is essential. Full article

Substation equipment defect detection is a critical aspect of ensuring the reliability and stability of modern power grids. However, existing deep-learning-based detection methods often face significant challenges in real-world deployment, primarily due to low detection accuracy and inconsistent anomaly definitions across different substation environments. To address these limitations, this paper proposes the Language-Guided Enhanced Anomaly Power Equipment Detection Network (LEAD-Net), a novel framework that leverages text-guided learning during training to significantly improve defect detection performance. Unlike traditional methods, LEAD-Net integrates textual descriptions of defects, such as historical maintenance records or inspection reports, as auxiliary guidance during training. A key innovation is the Language-Guided Anomaly Feature Enhancement Module (LAFEM), which refines channel attention using these text features. Crucially, LEAD-Net operates solely on image data during inference, ensuring practical applicability. Experiments on a real-world substation dataset, comprising 8307 image–text pairs and encompassing a diverse range of defect categories encountered in operational substation environments, demonstrate that LEAD-Net significantly outperforms state-of-the-art object detection methods (Faster R-CNN, YOLOv9, DETR, and Deformable DETR), achieving a mean Average Precision (mAP) of 79.51%. Ablation studies confirm the contributions of both LAFEM and the training-time text guidance. The results highlight the effectiveness and novelty of using training-time defect descriptions to enhance visual anomaly detection without requiring text input at inference. Full article

Background/Objectives: Schizophrenia has been associated with increased inflammatory and metabolic disturbances. Perceived family support potentially affects inflammatory and metabolic biomarkers. The aim of this study was to determine the interrelations between family support, C-reactive protein (CRP) and Body Mass Index (BMI) in a sample of outpatients with schizophrenia. Importantly, this study sought to elucidate the effect of perceived family support on inflammatory processes among patients with schizophrenia. Methods: In this cross-sectional correlation study, 206 outpatients with schizophrenia in clinical remission completed a standardized self-report questionnaire that assessed family support (Family Support Scale—FSS). Sociodemographic, clinical and laboratory data were also recorded. Results: Among the participants, 49.5% had detectable CRP values (≥0.11 mg/dL), whereas 14.6% had positive CRP levels (>0.6 mg/dL). There was a significant difference in CRP levels among the different BMI groups (normal weight/overweight vs. obese). For obese patients, the crude odds ratios (ORs) for detectable and positive CRP values were 1.980 (95% confidence interval (CI) [1.056, 3.713]) and 27.818 (95% CI [6.300, 122.838]), respectively. Significant positive correlations were observed among CRP, BMI and illness duration, while scores on the FSS were negatively associated with these variables. The results of binary logistic regression analysis indicated that both BMI and family support were significant factors in determining the likelihood of having positive CRP levels, with each unit increase in the BMI associated with a 17% (95% CI [0.025, 0.337]) increase in the odds, and with each unit increase in family support leading to an 8.6% (95% CI [0.018, 0.15]) decrease. A moderation analysis revealed that the association between family support and the probability of having positive CRP levels depends on the BMI value, but only for obese patients did the protective effect of family support significantly decrease the magnitude of the risk of having positive CRP (b = −0.1972, SE = 0.053, OR = 0.821, p = 0.000, 95% CI [−0.3010, −0.0934]). Conclusions: The effect of perceived family support on inflammatory responses becomes evident in cases where beyond metabolic complications, inflammatory processes have already been established. Increased perceived family support seems to protect against inflammation and, notably, the association between low perceived family support and increased inflammation is even stronger. Establishing the role of family involvement during the treatment of patients with schizophrenia through inflammatory processes is a novelty of this study, emphasizing the need to incorporate family therapy into psychiatric treatment plans. However, primary interventions are considered necessary for patients with schizophrenia in order to maintain their BMI within normal limits and avoid the subsequent nosological sequelae. Full article

This paper focuses on the complex dynamics that concern assembly line balance in the context of mass customization within manufacturing. In fact, the increase in demand for customized products has heightened the complexities associated with achieving optimal efficiency, productivity, product quality, and customer satisfaction. The research proposes a multi-criteria analysis of statistical methods to determine the fluctuation of parameters affecting the state of balance of an assembly line. A 3D matrix model is suggested to analyze the parameters managing the assembly line. This representation is executed using the MATLAB R2024b tool, and a methodology for finding the variability of parameters affecting balance through statistical approaches is proposed. We observed that changes in parameters such as task times, worker efficiency, or material flow led to significant changes in the line’s overall balance. As a result, static balancing becomes inadequate to deal with the complexities introduced by these highly variable parameters. The novelty of this paper consists of the innovative integration of multi-criteria statistical analysis and 3D matrix modeling to detect parameter variability and optimize assembly line balancing. Conventional static approaches are often unable to capture the process-dynamic aspect of modern manufacturing. This work presents a systematic methodology capable of identifying, quantifying, and moderating the variability of key operating parameters. This methodology, carried out using MATLAB-based simulations, is based on principal component analysis (PCA) and correlation analysis to detect critical factors influencing balancing efficiency. By structuring assembly line parameters in a 3D matrix representation, this research gives a holistic, data-based method for improving decision-making in balancing procedures. The research goes beyond theoretical modeling by applying the approach to a real automotive assembly line, validating its effectiveness and demonstrating its practical applicability in industrial conditions. Full article

Background: Protein carbonylation is an irreversible post-translational modification that is considered indicative of oxidative damage. Objective: The purpose of the study was to examine by an immunohistochemical method for the first time the extent and localization of protein carbonylation in biopsies of gingiva from periodontitis patients with or without diabetes mellitus (DM). Methods: These were processed for immunohistochemical staining of the carbonylated proteins, using the ENVISIOM FLEX Mini Kit, high pH, and anti-dinitrophenyl (DNP) antibody, a marker of oxidative damage to a given protein. The extent of protein carbonylation was semi-quantitatively estimated and evaluated by calculation of the Allred score (percentage of stained cells × intensity of staining). Results: The biopsies from periodontitis patients with diabetes mellitus (DM) exhibited higher staining scores as per the percentage of positively stained cells than the biopsies from patients with only periodontitis (means of 49.2 and 16.7, respectively), the difference being statistically significant (p = 0.036). The same trend was observed in the case of the combination of the above with the intensity of staining (score parameter) as well (means of 59.6 and 20.8, p = 0.036, respectively). Conclusions: An immunohistochemical method with the novelty of utilization for the first time of the anti-dinitrophenyl (DNP) antibody in gingival tissues was introduced and showed efficacy in detecting protein carbonylation indicative of oxidative stress and its impact in the pathogenesis of these two prevalent diseases of periodontitis and diabetes mellitus. Full article