Search Results (1,579)

We present FingerType, a one-handed text input method based on thumb-to-finger gestures. FingerType detects tap events from 3D hand data using a Temporal Convolutional Network (TCN) and decodes the tap sequence into words with an n-gram language model. To inform the design, we examined thumb-to-finger interactions and collected comfort ratings of finger regions. We used these results to design an improved T9-style key layout. Our system runs at 72 frames per second and reaches 94.97% accuracy for tap detection. We conducted a six-block user study with 24 participants and compared FingerType with controller input and touch input. Entry speed increased from 5.88 WPM in the first practice block to 10.63 WPM in the final block. FingerType also supported more eyes-free typing: attention on the display panel within ±15° of head-gaze was 84.41%, higher than touch input (69.47%). Finally, we report error patterns and WPM learning curves, and a model-based analysis suggests improving gesture recognition accuracy could further increase speed and narrow the gap to traditional VR input methods. Full article

Title block compliance checking requires interpreting irregular tabular layouts and reporting structural inconsistencies, not only extracting metadata. This paper introduces a user-in-the-loop, template-based method that leverages a graphical annotation workflow to encode title block structure as a hierarchical annotation graph combining detected primitives (cells/text) with user-defined semantic entities (key–value pairs, tables, headers). The resulting template is matched onto target title blocks using relative positional constraints and category-specific rules that distinguish acceptable variability from non-compliance (e.g., variable-size tables versus missing fields). The system outputs extracted key–value information and localized warning logs for end-user correction. On a real industrial example from the nuclear domain, the approach achieves 98–99% compliant annotation matching and 84% accuracy in flagging structural/content deviations, while remaining tolerant to moderate layout changes. Limitations and extensions are discussed, including support for additional fields, improved key similarity metrics, operational deployment with integrated feedback and broader benchmarking. Full article

The identification and monitoring of pavement pathologies are critical for maintaining road infrastructure and ensuring transportation safety. As traditional inspection methods are often time-consuming, labor-intensive, and prone to human error, in recent years, Unmanned Aerial Vehicles (UAVs) have emerged as a promising tool for pavement condition assessment due to their mobility, efficiency, and ability to capture high-resolution imagery and multi-sensor data. This Systematic Literature Review aims to synthesize and evaluate existing research on the use of UAV for identifying pavement pathologies, such as cracks, potholes, rutting, and surface degradation. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) methodology, publications were screened and selected across major academic databases such as Scopus and Web of Science. A total of 361 relevant articles published from 2020 to July 2025 were identified and analyzed using bibliometric overview. And a full-text synthesis and qualitative analysis was performed on a subset of 108 studies, which met the quality assessment criteria. The review categorizes the UAV systems, computer vision approaches, pathology types, and pavement materials examined in the studies. The findings indicate a growing trend in the use of UAV and computer vision techniques for pavement pathology detection, along with evolving preferences for UAV platforms, analytical approaches, and targeted pathology categories over time. This review highlights current gaps and outlines future research directions to advance UAV-based pavement pathology identification as a viable and reliable alternative to conventional inspection methods. Full article

Social organizations increasingly rely on Natural Language Processing (NLP) to analyze large-scale textual data for high-stakes decisions, including university admissions, financial aid allocation, and job hiring. Current methods primarily employ topic modeling and sentiment analysis, but they fail to capture the complex ways emotions and cultural contexts shape meaning in text, potentially perpetuating bias and undermining equitable decision-making. To address this gap, we introduce the Behavioral and Emotional Theme Detection (BET) framework, a novel approach that integrates emotional, cultural, and sociological dimensions into topic detection and emotion analysis. By applying BET to English and Hebrew datasets, we showcase its multilingual adaptability and its potential to reveal rich thematic content and emotional resonance in biographical texts. Our results demonstrate that BET not only enhances the granularity and diversity of detected themes but also tracks shifts in emotional framing over time, offering deeper insights into how individuals deploy linguistic resources to position their identities, enabling more equitable assessment practices. Full article

Background/Objectives: HPV vaccination is safe, effective, and recommended at ages 11–12, yet uptake remains suboptimal. Serious video games may offer an innovative strategy to deliver brief, engaging education during clinic visits. This qualitative paper, embedded within a mixed-methods study, examined adolescents’, parents’, and healthcare providers’ (HCPs’) perceptions of the acceptability, usability, and perceived clinical applicability of HPV Detective, a tablet-based digital game designed to provide HPV-related education to parent–child dyads during pediatric clinic wait times. Methods: Eight adolescent–parent dyads (N = 16) and three HCPs from university-affiliated pediatric clinics participated in 30–60-min semi-structured Zoom interviews. Interviews were audio-recorded, transcribed, and thematically analyzed by two coders, with discrepancies resolved by consensus and reviewed by a third researcher. Results: Participants identified five key dyadic themes and four HCP themes. Adolescents described the gameplay as intuitive and enjoyable, highlighting interactive challenges and realistic avatars. Parents valued the clarity of HPV information and noted that the game helped initiate health-related conversations. Both adolescents and parents suggested enhancements including voice narration and greater customization and agreed that the game was well suited for 10–15-min clinic wait times, with text messaging preferred for follow-up. HCPs emphasized challenges such as parental hesitancy and competing clinical demands and viewed the game as a feasible adjunct to support vaccine-related discussions. Conclusions: Findings suggest the acceptability, usability, and perceived clinical applicability of a brief, clinic-based digital game for HPV-related education and engagement among adolescents and their parents. Full article

Background: Depression remains a major global mental health concern, significantly intensified during the COVID-19 pandemic. As social media usage surged during this period, it emerged as a valuable source for identifying early signs of depression. Artificial intelligence (AI) offers powerful tools to analyze large volumes of user-generated content, enabling timely and effective detection of depressive symptoms. This review aims to preliminarily explore and compare evidence on the use of AI models for detecting depression in social content across the pre-, during, and post-pandemic phases, assessing their effectiveness and limitations. Methods: A narrative literature review was conducted using PubMed and Scopus, following the SANRA guidelines to ensure methodological quality and reproducibility. The study was pre-registered in the OSF database and employed the PICOS framework for the strategy. Inclusion criteria comprised studies in English from the past 10 years that analyzed depression detection via AI, machine learning (ML), and deep learning (DL) applied to textual data, images, and social metadata. This review addresses the following four research questions: (1) whether AI models improved effectiveness in detecting depression during/after the pandemic vs. pre-pandemic; (2) whether textual, visual, or multimodal data approaches became more effective during the pandemic; (3) whether AI models better addressed technical challenges (data quality/diversity) post-pandemic; and (4) whether strategies for responsible AI implementation improved during/after the pandemic. Results: Out of 349 identified records, nine primary studies were included, as most excluded articles had a predominantly technical focus and did not meet the clinical relevance criteria. AI models demonstrated strong potential in detecting depression, particularly through text-based classification and social content analysis. Several studies reported high predictive performance, with notable improvements in accuracy and sensitivity during and after the pandemic, although evidence remains limited. Conclusions: Our preliminary analysis suggests that AI-based depression detection on social media shows potential for clinical use, highlighting interdisciplinary collaboration, ethical considerations, and patient-centered approaches. These findings require confirmation and validation through larger, well-designed systematic reviews. Full article

Background: Hip joint disorders exhibit diverse and overlapping radiological features, complicating early diagnosis and limiting the diagnostic value of single-modality imaging. Isolated imaging or clinical data may therefore inadequately represent disease-specific pathological characteristics. Methods: This retrospective study included 605 hip joints from Center A (2018–2024), comprising normal hips, osteoarthritis, osteonecrosis of the femoral head (ONFH), and femoroacetabular impingement (FAI). An independent cohort of 24 hips from Center B (2024–2025) was used for external validation. A multimodal deep learning framework was developed to jointly analyze radiographs, CT volumes, and clinical texts. Features were extracted using ResNet50, 3D-ResNet50, and a pretrained BERT model, followed by attention-based fusion for four-class classification. Results: The combined Clinical+X-ray+CT model achieved an AUC of 0.949 on the internal test set, outperforming all single-modality models. Improvements were consistently observed in accuracy, sensitivity, specificity, and decision curve analysis. Grad-CAM visualizations confirmed that the model attended to clinically relevant anatomical regions. Conclusions: Attention-based multimodal feature fusion substantially improves diagnostic performance for hip joint diseases, providing an interpretable and clinically applicable framework for early detection and precise classification in orthopedic imaging. Full article

Background/Objectives: Interpretation of chest X-rays (CXRs) requires accurate identification of lesion presence, diagnosis, location, size, and number to be considered complete. However, the effectiveness of large language models with vision capabilities (LLMs) in performing these tasks remains uncertain. This study aimed to evaluate the image-only interpretation performance of LLMs in the absence of clinical information. Methods: A total of 247 CXRs covering 13 diagnostic categories, including pulmonary edema, cardiomegaly, lobar pneumonia, and other conditions, were evaluated using Gemini 1.0, Gemini 1.5 Pro, GPT-4 Turbo, and GPT-4o. The text outputs generated by the LLMs were evaluated at two levels: (1) primary diagnosis accuracy across the 13 predefined diagnostic categories, and (2) identification of key imaging features described in the generated text. Primary diagnosis accuracy was assessed based on whether the model correctly identified the target diagnostic category and was classified as fully correct, partially correct, or incorrect according to predefined clinical criteria. Non-diagnostic imaging features, such as posteroanterior and anteroposterior (PA/AP) views, side markers, foreign bodies, and devices, were recorded and analyzed separately rather than being incorporated into the primary diagnostic scoring. Results: When fully and partially correct responses were treated as successful detections, vLLMs showed higher sensitivity for large, bilateral, multiple lesions and prominent devices, including acute pulmonary edema, lobar pneumonia, multiple malignancies, massive pleural effusions, and pacemakers, all of which demonstrated statistically significant differences across categories in chi-square analyses. Feature descriptions varied among models, especially in PA/AP views and side markers, though central lines were partially recognized. Across the entire dataset, Gemini 1.5 Pro achieved the highest overall detection rate, followed by Gemini 1.0, GPT-4o, and GPT-4 Turbo. Conclusions: Although LLMs were able to identify certain diagnoses and key imaging features, their limitations in detecting small lesions, recognizing laterality, reasoning through differential diagnoses, and using domain-specific expressions indicate that CXR interpretation without textual cues still requires further improvement. Full article

The article presents the current state of knowledge on genetic modifiers of ovarian cancer risk in women carrying pathogenic variants (PVs) in the BRCA1 and BRCA2 genes, which are major contributors to hereditary susceptibility to this malignancy. Although PV carriers have high disease penetrance (BRCA1: ~40% and BRCA2: 11–27%), substantial variability in individual risk is observed, suggesting the influence of additional genetic variants. Background: Ovarian cancer is characterized by late detection and high mortality, and a significant portion of risk among BRCA1/2 carriers is shaped by reproductive and environmental factors as well as genetic modifiers. The article emphasizes that carriers of the same BRCA PV can exhibit markedly different risk levels depending on additional variants that modulate key biological processes, such as DNA repair, cell cycle regulation, and apoptosis. Methods: A systematic literature search covering the years 1996–2025 was conducted in the PubMed database. Initially, 734 publications were identified; after removing duplicates, thematically irrelevant articles, non-full-text papers, and studies not meeting the inclusion criteria, 47 articles were included in the review. These studies covered candidate gene analyses, GWAS, and data from the CIMBA consortium, which enables the examination of large cohorts of PV carriers. Results: The review identified numerous variants associated with increased or decreased ovarian cancer risk in BRCA1 carriers, including the following: OGG1, DR4, MDM2, CYP2A7, CASP8, ITGB3, HRAS1, TRIM61, and MTHFR. The reviewed studies also identified both protective and risk-increasing variants among BRCA2 PV carriers: UNG, TDG, and PARP2, and haplotypes in ATM, BRIP1, BARD1, MRE11, RAD51, and 9p22.2. The analysis identified 11 variants affecting both BRCA1 and BRCA2 carriers, most of which increase risk, including the following: IRS1, RSPO1, SYNPO2, BABAM1, MRPL34, PLEKHM1, and TIPARP. Protective variants include BNC2 and LINC00824. The only SNP reaching genome-wide significance (p < 5 × 10⁻⁸) was in BNC2. Conclusions: The article summarizes the growing number of genetic modifiers of ovarian cancer risk among BRCA1/2 carriers and highlights their potential to improve individualized risk assessment, enhance patient stratification, support personalized prevention and surveillance strategies, deepen the understanding of disease biology, and identify potential therapeutic targets. Full article

NFT prices are shaped by heterogeneous signals including visual appearance, textual narratives, transaction trajectories, and on-chain interactions, yet existing studies often model these factors in isolation and rarely unify multimodal alignment, temporal non-stationarity, and heterogeneous relational dependencies in a leakage-safe forecasting setting. We propose MM-Temporal-Graph, a cross-modal temporal graph transformer framework for explainable NFT valuation and information-centric risk forecasting. The model encodes image, text, transaction time series, and blockchain behavioral features, constructs a heterogeneous NFT interaction graph (co-transaction, shared creator, wallet relation, and price co-movement), and jointly performs relation-aware graph attention and global temporal–structural transformer reasoning with an adaptive fusion gate. A contrastive multimodal alignment objective improves robustness under market drift, while a risk-aware regularizer and a multi-source risk index enable early warning and interpretable attribution across modalities, time segments, and relational neighborhoods. On MultiNFT-T, MM-Temporal-Graph improves MAE from 0.162 to 0.153 and R² from 0.823 to 0.841 over the strongest multimodal graph baseline, and achieves 87.4% early risk detection accuracy. These results support accurate, robust, and explainable NFT valuation and proactive risk monitoring in Web3 markets. Full article

Large Language Models (LLMs) are vulnerable to Indirect Prompt Injection Attacks (IPIAs), where malicious instructions are embedded within external content rather than direct user input. This study presents an embedding-based detection approach that analyses the semantic relationship between user intent and external content, enabling the early identification of IPIAs that conventional defences overlook. We also provide a dataset of 70,000 samples, constructed using 35,000 malicious instances from the Benchmark for Indirect Prompt Injection Attacks (BIPIA) and 35,000 benign instances generated using ChatGPT-4o-mini. Furthermore, we performed a comparative analysis of three embedding models, namely OpenAI text-embedding-3-small, GTE-large, and MiniLM-L6-v2, evaluated in combination with XGBoost, LightGBM, and Random Forest classifiers. The best-performing configuration using OpenAI embeddings with XGBoost achieved an accuracy of 97.7% and an F1-score of 0.977, matching or exceeding the performance of existing IPIA detection methods while offering practical deployment advantages. Unlike prevention-focused approaches that require modifications to the underlying LLM architecture, the proposed method operates as a model-agnostic external detection layer with an average inference time of 0.001 ms per sample. This detection-based approach complements existing prevention mechanisms by providing a lightweight, scalable solution that can be integrated into LLM pipelines without requiring architectural changes. Full article

Detecting fake news is essential in natural language processing to verify news authenticity and prevent misinformation-driven social, political, and economic disruptions targeting specific groups. A major challenge in multimodal fake news detection is effectively integrating textual and visual modalities, as semantic gaps and contextual variations between images and text complicate alignment, interpretation, and the detection of subtle or blatant inconsistencies. To enhance accuracy in fake news detection, this article introduces an ensemble-based framework that integrates textual and visual data using ViLBERT’s two-stream architecture, incorporates VADER sentiment analysis to detect emotional language, and uses Image–Text Contextual Similarity to identify mismatches between visual and textual elements. These features are processed through the Bi-GRU classifier, Transformer-XL, DistilBERT, and XLNet, combined via a stacked ensemble method with soft voting, culminating in a T5 metaclassifier that predicts the outcome for robustness. Results on the Fakeddit and Weibo benchmarking datasets show that our method outperforms state-of-the-art models, achieving up to 96% and 94% accuracy in fake news detection, respectively. This study highlights the necessity for advanced multimodal fake news detection systems to address the increasing complexity of misinformation and offers a promising solution. Full article

Metaphor is ubiquitous in daily communication and makes language expression more vivid. Identifying metaphorical words, known as metaphor detection, is crucial for capturing the real meaning of a sentence. As an important step of metaphorical understanding, the correct interpretation of metaphorical words directly affects metaphor detection. This article investigates how to use metaphor interpretation to enhance metaphor detection. Since previous approaches for metaphor interpretation are coarse-grained or constrained by ambiguous meanings of substitute words, we propose a different interpretation mechanism that explains metaphorical words by means of gloss-based interpretations. To comprehensively explore the optimal joint strategy, we go beyond previous work by designing diverse model architectures. We investigate both classification and sequence labeling paradigms, incorporating distinct component designs based on MIP and SPV theories. Furthermore, we integrate Part-of-Speech tags and external knowledge to further refine the feature representation. All methods utilize pre-trained language models to encode text and capture semantic information of the text. Since this mechanism involves both metaphor detection and metaphor interpretation but there is a lack of datasets annotated for both tasks, we have enhanced three datasets with glosses for metaphor detection: one Chinese dataset (PSUCMC) and two English datasets (TroFi and VUA). Experimental results demonstrate that the proposed joint methods are superior to or at least comparable to state-of-the-art methods on the three enhanced datasets. Results confirm that joint learning of metaphor detection and gloss-based interpretation makes metaphor detection more accurate. Full article

Background and Objectives: Acute and obstructive pyelonephritis (AOP) management, despite advancements in diagnostic imaging and antimicrobial therapy, is characterized by delayed recognition and increasing antimicrobial resistance. This review aimed to summarize current evidence regarding the clinical characteristics, microbiological spectrum, biomarkers, and imaging findings associated with AOP. Materials and Methods: A systematic review was conducted according to PRISMA guidelines and registered in PROSPERO (CRD420251162736). Literature searches were performed across the PubMed, Scopus, and Web of Science databases for articles published between January 2014 and 31 March 2025 using the term “acute obstructive pyelonephritis”. Inclusion criteria comprised original full-text English-language studies, published in the last 10 years and conducted in adults, reporting clinical, laboratory, microbiological, and imaging characteristics. Exclusion criteria are letters to the editor, expert opinions, case reports, conference or meeting abstracts, reviews, and redundant publications; having unclear or incomplete data; and being performed on cell cultures or on mammals. The quality of included studies was assessed using the Newcastle–Ottawa Scale. Results: Twenty-three studies met the inclusion criteria. AOP predominantly affected elderly patients with comorbidities, especially diabetes mellitus and urinary tract obstruction. Predictors of septic shock included thrombocytopenia, hypoalbuminemia, elevated procalcitonin (>1.12 µg/L), presepsin, and a neutrophil-to-lymphocyte ratio ≥ 8.7. Escherichia coli remained the leading pathogen (60–95%) with extended-spectrum β-lactamase (ESBL) rates between 20 and 70%, followed by Klebsiella pneumoniae. CT demonstrated 71–100% sensitivity for detecting obstructive complications, confirming its superiority over ultrasound, while MRI provided comparable diagnostic accuracy in selected cases. Source control through double-J stenting or percutaneous drainage significantly improved survival. Conclusions: AOP requires prompt recognition and early decompression to prevent sepsis-related mortality. Biomarkers such as procalcitonin, presepsin, and neutrophil to lymphocyte ratio enhance risk stratification, while CT remains the gold-standard imaging modality. The increasing prevalence of ESBL-producing pathogens underscores the need for antimicrobial stewardship and individualized therapeutic strategies guided by local resistance data. Full article

In recent years, Advanced Persistent Threat (APT) malware, with its high stealth, has made it difficult for unimodal detection methods to accurately identify its disguised malicious behaviors. To address this challenge, this paper proposes an APT Malware Detection Model based on Heterogeneous Multimodal Semantic Fusion (HMSF-ADM). By integrating the API call sequence features of APT malware in the operating system and the RGB image features of PE files, the model constructs multimodal representations with stronger discriminability, thus achieving efficient and accurate identification of APT malicious behaviors. First, the model employs two encoders, namely a Transformer encoder equipped with the DPCFTE module and a CAS-ViT encoder, to encode sequence features and image features, respectively, completing local–global collaborative context modeling. Then, the sequence encoding results and image encoding results are interactively fused via two cross-attention mechanisms to generate fused representations. Finally, a TextCNN-based classifier is utilized to perform classification prediction on the fused representations. Experimental results on two APT malware datasets demonstrate that the proposed HMSF-ADM model outperforms various mainstream multimodal comparison models in core metrics such as accuracy, precision, and F1-score. Notably, the F1-score of the model exceeds 0.95 for the vast majority of APT malware families, and its accuracy and F1-score both remain above 0.986 in the task of distinguishing between ordinary malware and APT malware. Full article