Search Results (464)

This case report presents a multidisciplinary forensic investigation into a cold case involving a missing person in Italy, likely linked to a homicide that occurred in 2008. The investigation applied a standardized protocol integrating satellite imagery analysis, site reconnaissance, vegetation clearance, ground-penetrating radar (GPR), and cadaver dog (K9) deployment. A dedicated decision tree guided each phase, allowing for efficient allocation of resources and minimizing investigative delays. Although no human remains were recovered, the case demonstrates the practical utility and operational robustness of a structured, evidence-based model that supports decision-making even in the absence of positive findings. The approach highlights the relevance of “negative” results, which, when derived through scientifically validated procedures, offer substantial value by excluding burial scenarios with a high degree of reliability. This case is particularly significant in the Italian forensic context, where the adoption of standardized search protocols remains limited, especially in complex outdoor environments. The integration of geophysical, remote sensing, and canine methodologies—rooted in forensic geoarchaeology—provides a replicable framework that enhances both investigative effectiveness and the evidentiary admissibility of findings in court. The protocol illustrated in this study supports the consistent evaluation of large and morphologically complex areas, reduces the risk of interpretive error, and reinforces the transparency and scientific rigor expected in judicial settings. As such, it offers a model for improving forensic search strategies in both national and international contexts, particularly in long-standing or high-profile missing persons cases. Full article

Cancer metabolic reprogramming plays a critical role in tumor progression and therapeutic resistance, underscoring the need for advanced analytical strategies. Metabolomics, leveraging mass spectrometry and nuclear magnetic resonance (NMR) spectroscopy, offers a comprehensive and functional readout of tumor biochemistry. By enabling both targeted metabolite quantification and untargeted profiling, metabolomics captures the dynamic metabolic alterations associated with cancer. The integration of metabolomics with machine learning (ML) approaches further enhances the interpretation of these complex, high-dimensional datasets, providing powerful insights into cancer biology from biomarker discovery to therapeutic targeting. This review systematically examines the transformative role of ML in cancer metabolomics. We discuss how various ML methodologies—including supervised algorithms (e.g., Support Vector Machine, Random Forest), unsupervised techniques (e.g., Principal Component Analysis, t-SNE), and deep learning frameworks—are advancing cancer research. Specifically, we highlight three major applications of ML–metabolomics integration: (1) cancer subtyping, exemplified by the use of Similarity Network Fusion (SNF) and LASSO regression to classify triple-negative breast cancer into subtypes with distinct survival outcomes; (2) biomarker discovery, where Random Forest and Partial Least Squares Discriminant Analysis (PLS-DA) models have achieved >90% accuracy in detecting breast and colorectal cancers through biofluid metabolomics; and (3) prognostic modeling, demonstrated by the identification of race-specific metabolic signatures in breast cancer and the prediction of clinical outcomes in lung and ovarian cancers. Beyond these areas, we explore applications across prostate, thyroid, and pancreatic cancers, where ML-driven metabolomics is contributing to earlier detection, improved risk stratification, and personalized treatment planning. We also address critical challenges, including issues of data quality (e.g., batch effects, missing values), model interpretability, and barriers to clinical translation. Emerging solutions, such as explainable artificial intelligence (XAI) approaches and standardized multi-omics integration pipelines, are discussed as pathways to overcome these hurdles. By synthesizing recent advances, this review illustrates how ML-enhanced metabolomics bridges the gap between fundamental cancer metabolism research and clinical application, offering new avenues for precision oncology through improved diagnosis, prognosis, and tailored therapeutic strategies. Full article

Radio Frequency Identification (RFID) technology is widely applied in various scenarios, including logistics tracking, supply chain management, and target monitoring. In these contexts, the malicious cloning of legitimate tag information can lead to sensitive data leakage and disrupt the normal acquisition of tag information by readers, thereby threatening personal privacy and corporate security and incurring significant economic losses. Although some efforts have been made to detect cloning attacks, the presence of missing tags in RFID systems can obscure cloned ones, resulting in a significant reduction in identification efficiency and accuracy. To address these problems, we propose the block-based cloned tag identification (BCTI) protocol for identifying cloning attacks in the presence of missing tags. First, we introduce a block indicator to sort all tags systematically and design a block mechanism that enables tags to respond repeatedly within a block with minimal time overhead. Then, we design a superposition strategy to further reduce the number of verification times, thereby decreasing the execution overhead. Through an in-depth analysis of potential tag response patterns, we develop a precise method to identify cloning attacks and mitigate interference from missing tags in probabilistic cloning attack scenarios. Moreover, we perform parameter optimization of the BCTI protocol and validate its performance across diverse operational scenarios. Extensive simulation results demonstrate that the BCTI protocol meets the required identification reliability threshold and achieves an average improvement of $24.01\%$ in identification efficiency compared to state-of-the-art solutions. Full article

Occlusion remains a major challenge in person re-identification, as it often leads to incomplete or misleading visual cues. To address this issue, we propose a dual-branch occlusion-aware network (DOAN), which explicitly and implicitly enhances the model’s capability to perceive and handle occlusions. The proposed DOAN framework comprises two synergistic branches. In the first branch, we introduce an Occlusion-Aware Semantic Attention (OASA) module to extract semantic part features, incorporating a parallel channel and spatial attention (PCSA) block to precisely distinguish between pedestrian body regions and occlusion noise. We also generate occlusion-aware parsing labels by combining external human parsing annotations with occluder masks, providing structural supervision to guide the model in focusing on visible regions. In the second branch, we develop an occlusion-aware recovery (OAR) module that reconstructs occluded pedestrians to their original, unoccluded form, enabling the model to recover missing semantic information and enhance occlusion robustness. Extensive experiments on occluded, partial, and holistic benchmark datasets demonstrate that DOAN consistently outperforms existing state-of-the-art methods. Full article

This paper describes a novel wearable personal uroflowmeter and its use to log urine leakage episodes in women. Consisting of a miniature flow rate sensor attached under the urethral meatus, it recorded both urine flow rate and volume during activities of daily living. The sensor communicated with a determining unit incorporating a microcontroller and an inertial measurement unit worn at the waist, facilitating the post-hoc determination of which activities and changes in pose caused leakage. Six women participated in a feasibility study performed in a clinical setting. The results indicate that the uroflowmeter was 97.5% accurate in assessing micturition flow compared to gold standard uroflowmetry and leakage measurements. The system also provides subject-specific information on the relationship between physical activity and urine leakage, thereby eliminating errors due to missing data and recall bias in bladder leakage diaries and circumventing the limitations of office-based uroflowmeters. Full article

Unmanned aerial vehicles are increasingly used in civil Search and Rescue operations due to their rapid deployment and wide-area coverage capabilities. However, detecting missing persons from aerial imagery remains challenging due to small object sizes, cluttered backgrounds, and limited onboard computational resources, especially when managed by civil agencies. In this work, we present a comprehensive methodology for optimizing YOLO-based object detection models for real-time Search and Rescue scenarios. A two-stage transfer learning strategy was employed using VisDrone for general aerial object detection and Heridal for Search and Rescue-specific fine-tuning. We explored various architectural modifications, including enhanced feature fusion (FPN, BiFPN, PB-FPN), additional detection heads (P2), and modules such as CBAM, Transformers, and deconvolution, analyzing their impact on performance and computational efficiency. The best-performing configuration (YOLOv5s-PBfpn-Deconv) achieved a mAP@50 of 0.802 on the Heridal dataset while maintaining real-time inference on embedded hardware (Jetson Nano). Further tests at different flight altitudes and explainability analyses using EigenCAM confirmed the robustness and interpretability of the model in real-world conditions. The proposed solution offers a viable framework for deploying lightweight, interpretable AI systems for UAV-based Search and Rescue operations managed by civil protection authorities. Limitations and future directions include the integration of multimodal sensors and adaptation to broader environmental conditions. Full article

Parkinson’s disease (PD) is a progressive neurodegenerative disorder that impairs motor function, including the fine motor control required for handwriting. Traditional diagnostic methods often lack sensitivity and objectivity in the early stages, limiting opportunities for timely intervention. There is a growing need for non-invasive, accessible tools capable of capturing subtle motor changes that precede overt clinical symptoms. Among early PD manifestations, handwriting impairments such as micrographia have shown potential as digital biomarkers. However, conventional handwriting analysis remains subjective and limited in scope. Recent advances in artificial intelligence (AI) and machine learning (ML) enable automated analysis of handwriting dynamics, such as pressure, velocity, and fluency, collected via digital tablets and smartpens. These tools support the detection of early-stage PD, monitoring of disease progression, and assessment of therapeutic response. This paper highlights how AI-enhanced handwriting analysis provides a scalable, non-invasive method to support diagnosis, enable remote symptom tracking, and personalize treatment strategies in PD. This approach integrates clinical neurology with computer science and rehabilitation, offering practical applications in telemedicine, digital health, and personalized medicine. By capturing dynamic features often missed by traditional assessments, AI-based handwriting analysis contributes to a paradigm shift in the early detection and long-term management of PD, with broad relevance across neurology, digital diagnostics, and public health innovation. Full article

Skin cancer is one of the most prevalent forms of cancer worldwide, and early and accurate diagnosis critically impacts patient outcomes. Given the sensitive nature of medical data and its fragmented distribution across institutions (data silos), privacy-preserving collaborative learning is essential to enable knowledge-sharing without compromising patient confidentiality. While federated learning (FL) offers a promising solution, existing methods struggle with heterogeneous and missing modalities across institutions, which reduce the diagnostic accuracy. To address these challenges, we propose an effective and flexible Personalized Multimodal Federated Learning framework (PMM-FL), which enables efficient cross-client knowledge transfer while maintaining personalized performance under heterogeneous and incomplete modality conditions. Our study contains three key contributions: (1) A hierarchical aggregation strategy that decouples multi-module aggregation from local deployment via global modular-separated aggregation and local client fine-tuning. Unlike conventional FL (which synchronizes all parameters in each round), our method adopts a frequency-adaptive synchronization mechanism, updating parameters based on their stability and functional roles. (2) A multimodal fusion approach based on multitask learning, integrating learnable modality imputation and attention-based feature fusion to handle missing modalities. (3) A custom dataset combining multi-year International Skin Imaging Collaboration(ISIC) challenge data (2018–2024) to ensure comprehensive coverage of diverse skin cancer types. We evaluate PMM-FL through diverse experiment settings, demonstrating its effectiveness in heterogeneous and incomplete modality federated learning settings, achieving 92.32% diagnostic accuracy with only a 2% drop in accuracy under 30% modality missingness, with a 32.9% communication overhead decline compared with baseline FL methods. Full article

This study aimed to explore how social media usage influenced both parent and adolescent mental health and social identity during and after the COVID-19 pandemic through the theoretical foundational lens of social comparison theory. In-depth interviews with 24 mothers of adolescent children (ages 10–19) were conducted to address the research questions. Qualitative thematic analysis of the interview transcripts revealed eight emerging themes: (1) learning and entertainment, (2) maternal fears related to content binging and cyberbullying, (3) finding connection and comfort through social media during the pandemic, (4) ongoing digital care work as lasting maternal labor, (5) iterative dialogue: platform restrictions and content curation boundaries, (6) upward and downward social comparison, (7) fear of missing out (FoMO), and (8) third-person perception (TPP). The findings show that mothers perceive social media usage as either beneficial or harmful among adolescents (their children); upward and downward social comparison via social media exhibits more dynamic mechanisms. Moreover, this study enhances our theoretical understanding by linking social media usage to social identity, social comparison, and mental health during a global health crisis. Full article

This study uses a nationally representative longitudinal dataset in the US to examine the long-term association of volunteering for environmental, recycling, and conservation groups with a person’s (a) willingness to continue to volunteer later in life and (b) several measures of their mental and physical well-being including perceived social status, optimism, psychological stress, suicidal thoughts and attempts, depressive symptoms and general self-reported physical health. By using Add Health data, we match responses to an environmental volunteerism question in Wave III (2002) with subjective well-being responses in Wave V (2016–2018) to examine the long-term association between these variables. After excluding missing responses, the analysis sample consists of 9800 individuals. After using linear survey regression analyses and several techniques based on propensity scores (stratification, weighting, matching) two key results emerged: first, being involved in environmental groups and organizations early in life showed a significant positive association with more hours spent on volunteering or community service work later in life; and second, people who volunteer in early adulthood are more optimistic, more sociable, have a higher perceived social status, display less stress and depressive symptoms. Full article

Identifying when and which adolescents are at increased risk of developing problematic social media use (PSMU) is critical for effective prevention and early intervention. Previous research has examined risk and protective factors using theory-driven (confirmatory-explanatory) approaches, such as regression models. However, few studies have simultaneously considered personal, peer, and parent characteristics to assess their relative contributions, and none have explored how these factors are structurally interrelated using data-driven (inductive–exploratory) approaches. To address these gaps, this study combines logistic regression and psychological network analysis to examine which personal, parent, and peer factors are most relevant in identifying at-risk/problematic social media use among adolescents. Using three waves of data analyzed cross-sectionally from N = 2441 secondary school students, adolescents were classified as normative (0–1 symptoms) or at-risk/problematic (2+ symptoms) users based on the Social Media Disorder Scale. Logistic regression showed that fear of missing out, impulsivity, depressive symptoms, intensity of meeting with friends, and reactive parental rules uniquely predicted at-risk/problematic use. Psychological network analysis identified self-esteem, attention problems, impulsivity, depressive symptoms, and life satisfaction as central, highly interconnected nodes. These findings show that theory- and data-driven approaches illuminate different aspects of PSMU risk, and that network analysis can generate novel hypotheses about underlying processes. Full article

If artificial intelligence (AI) is to be applied in safety-critical domains, its performance needs to be evaluated reliably. The present study investigated how humans evaluate AI systems for person detection in automatic train operation. In three experiments, participants viewed image sequences of people moving in the vicinity of railway tracks. A simulated AI system highlighted all detected people—sometimes correctly and sometimes not. Participants had to provide a numerical rating of the AI’s performance and then verbally explain their rating. The experiments manipulated several factors that might influence human ratings: the types and plausibility of AI mistakes, the number of affected images, the number of people present in an image, the position of people relevant to the tracks, and the methods used to elicit human evaluations. While all these factors influenced human ratings, some effects were unexpected or deviated from normative standards. For instance, the factor with the strongest impact was people’s position relative to the tracks, although participants had explicitly been instructed that the AI could not process such information. Taken together, the results suggest that humans may sometimes evaluate more than the AI’s performance on the assigned task. Such mismatches between AI capabilities and human expectations should be taken into consideration when conducting safety audits of AI systems. Full article

Background/Objectives: Missed outpatient appointments contribute to care discontinuity and emergency department (ED) overcrowding. This study investigated the association between missed appointments and ED visits, identifying predictors such as patient characteristics, distance from the hospital, and waiting time. Methods: A retrospective analysis was conducted using a dataset of 749,450 scheduled outpatient appointments from adult patients (aged ≥ 18 years). Patients under 18 were excluded. We identified missed appointments and assessed their association with ED visits occurring in the same period. Descriptive statistics, non-parametric tests, and logistic and linear regression models were applied to examine predictors such as age, sex, distance from the hospital, waiting time, the type of service, and medical specialty. Results: The overall no-show rate was 3.85%. Among patients with missed appointments, 37.3% also visited the ED. An older age (OR = 1.007; p = 0.006) and the male gender (OR = 1.498; p < 0.001) were significant predictors of having a scheduled appointment before an ED visit. No significant associations were found for distance or specialty branch. Conclusions: Missed appointments are associated with ED utilization. Predictive factors can inform targeted interventions, such as via improved scheduling systems and personalized reminders. Distance alone may not be a barrier, but system-level solutions are needed to address no-show rates and optimize healthcare resource use. Full article

Background/Objectives: While machine learning has made substantial strides in pronunciation detection in recent years, there remains a notable gap in the literature regarding research on improvements in the acquisition of speech sounds following a training intervention, especially in the domain of perception. This study addresses this gap by developing a deep learning algorithm designed to identify perceptual gains resulting from second language (L2) phonetic training. Methods: The participants underwent multiple sessions of high-variability phonetic training, focusing on discriminating challenging L2 vowel contrasts. The deep learning model was trained on perceptual data collected before and after the intervention. Results: The results demonstrated good model performance across a range of metrics, confirming that learners’ gains in phonetic training could be effectively detected by the algorithm. Conclusions: This research underscores the potential of deep learning techniques to track improvements in phonetic training, offering a promising and practical approach for evaluating language learning outcomes and paving the way for more personalized, adaptive language learning solutions. Deep learning enables the automatic extraction of complex patterns in learner behavior that might be missed by traditional methods. This makes it especially valuable in educational contexts where subtle improvements need to be captured and assessed objectively. Full article

User churn in online games refers to players becoming inactive for an extended period. Even a small increase in churn can lead to significant revenue loss, making churn prediction crucial for sustaining long-term player engagement. Although user churn prediction has been extensively studied, most existing approaches either ignore non-login periods or treat all inactivity uniformly, overlooking key behavioral differences. This study addresses this gap by categorizing non-login periods into three types, as follows: inactivity due to new or dormant users, genuine loss of interest, and temporary inaccessibility caused by external factors. These periods are treated as either non-existent or missing data and imputed using techniques such as mean or mode substitution, linear interpolation, and multiple imputation by chained equations (MICE). MICE was selected due to its ability to impute missing values more robustly by considering multivariate relationships. A random forest (RF) classifier, chosen for its interpretability and robustness to incomplete data, serves as the primary prediction model. Additionally, classifier chains are used to capture label dependencies, and principal component analysis (PCA) is applied to reduce dimensionality and mitigate overfitting. Experiments on real-world MMORPG data show that our approach improves predictive accuracy, achieving a micro-averaged AUC of above 0.92 and a weighted F1 score exceeding 0.70. These findings suggest that our approach improves churn prediction and offers actionable insights for supporting personalized player retention strategies. Full article