Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (1,450)

Search Parameters:
Keywords = false negative results

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
13 pages, 625 KB  
Article
Revisiting High-Sensitivity Cardiac Troponin Abnormal Baseline Cutoffs: Implications for AMI Diagnosis in the Emergency Department
by Kavithalakshmi Sataranatarajan, Madhusudhanan Narasimhan, Ishwar Daniel Chuckaree, Jyoti Balani, Ray Zhang, Rebecca Vigen and Alagarraju Muthukumar
J. Clin. Med. 2025, 14(20), 7308; https://doi.org/10.3390/jcm14207308 (registering DOI) - 16 Oct 2025
Abstract
Background: Current clinical guidelines recommend 52 ng/L as the abnormal baseline cutoff in high-sensitivity cardiac troponin (hs-cTn) algorithms for the rapid diagnosis of acute myocardial infarction (AMI). Though abnormal, this threshold is not AMI-specific, leading to extensive workups for many non-AMI chest [...] Read more.
Background: Current clinical guidelines recommend 52 ng/L as the abnormal baseline cutoff in high-sensitivity cardiac troponin (hs-cTn) algorithms for the rapid diagnosis of acute myocardial infarction (AMI). Though abnormal, this threshold is not AMI-specific, leading to extensive workups for many non-AMI chest pain patients, overutilization of resources, and emergency department (ED) overcrowding. Hence, the performance of this baseline abnormal cutoff was compared against the refined new thresholds for rapid AMI diagnosis in ED chest pain patients. Methods: We included ED chest pain patients with hs-cTnT and hs-cTnI levels simultaneously measured and clinical outcomes adjudicated by cardiologists. We performed receiver operating characteristics (ROC) analyses across various thresholds for diagnostic performance, including sensitivity, specificity, negative and positive likelihood ratios, and predictive values. Statistical analysis was carried out using Graphpad Prism 10, with p < 0.05 considered as significant. Results: In our study, 17 patients were adjudicated as AMI, and 682 patients were ruled out for AMI. In 15/17 AMI cases, baseline hs-cTn values far exceeded 52 ng/L. Notably, among non-AMI individuals, 140 (hs-cTnT) and 91 (hs-cTnI) also exceeded this cutoff. ROC analyses identified optimal abnormal cutoffs of 82 ng/L for hs-cTnT and 122 ng/L for hs-cTnI, which improved specificity without compromising sensitivity. Post-discharge follow-up at 1, 3, and 12 months for cardiovascular events supported these revised thresholds. Conclusions: Increasing the baseline abnormal value from 52 ng/L to 82 ng/L for hs-cTnT and to 122 ng/L for hs-cTnI in care pathways could reduce false positives with the potential to decrease unnecessary testing and alleviate long stays in the ED and resource management. Larger, diverse cohort studies are warranted to validate these findings. Full article
(This article belongs to the Special Issue The Role of Biomarkers in Cardiovascular Diseases)
Show Figures

Figure 1

20 pages, 3219 KB  
Article
Development of an Efficient Algorithm for Sea Surface Enteromorpha Object Detection
by Yan Liu, Xianghui Su, Ran Ma, Hailin Liu, Xiangfeng Kong, Fengqing Liu, Yang Gao and Qian Shi
Water 2025, 17(20), 2973; https://doi.org/10.3390/w17202973 - 15 Oct 2025
Abstract
In recent years, frequent outbreaks of Enteromorpha disasters in the Yellow Sea have caused substantial economic losses to coastal cities. In order to tackle the challenges of the low detection accuracy and high false negative rate of Enteromorpha detection in complex marine environments, [...] Read more.
In recent years, frequent outbreaks of Enteromorpha disasters in the Yellow Sea have caused substantial economic losses to coastal cities. In order to tackle the challenges of the low detection accuracy and high false negative rate of Enteromorpha detection in complex marine environments, this study proposes an object detection algorithm CEE-YOLOv8, improved from YOLOv8n, and establishes the Enteromorpha dataset. Firstly, this study integrates a C2f-ConvNeXtv2 module into the YOLOv8n Backbone network to augment multi-scale feature extraction capabilities. Secondly, an ECA attention mechanism is incorporated into the Neck network to enhance the perception ability of the model to different sizes of Enteromorpha. Finally, the CIoU loss function is replaced with EIoU to optimize bounding box localization precision. Experiment results on the self-made Enteromorpha dataset show that the improved CEE-YOLOv8 model achieves a 3.2% increase in precision, a 3.3% improvement in recall, and a 4.1% gain in mAP50-95 compared to the benchmark model YOLOv8n. Consequently, the proposed model provides robust technical support for future Enteromorpha monitoring initiatives. Full article
Show Figures

Figure 1

36 pages, 2393 KB  
Perspective
Voxel-Based Dose–Toxicity Modeling for Predicting Post-Radiotherapy Toxicity: A Critical Perspective
by Tanuj Puri
J. Clin. Med. 2025, 14(20), 7248; https://doi.org/10.3390/jcm14207248 - 14 Oct 2025
Abstract
This perspective paper critically examines the emerging role of voxel-based analysis (VBA), also referred to as image-based data mining (IBDM), in dose–toxicity modeling for post-radiotherapy toxicity assessment. These techniques offer promising insights into localized organ subregions associated with toxicity, yet their current application [...] Read more.
This perspective paper critically examines the emerging role of voxel-based analysis (VBA), also referred to as image-based data mining (IBDM), in dose–toxicity modeling for post-radiotherapy toxicity assessment. These techniques offer promising insights into localized organ subregions associated with toxicity, yet their current application faces substantial methodological and validation challenges. Based on prior studies and practical experience, we highlight seven key limitations: (i) lack of clinical validation for dose–toxicity models, (ii) strong dependence of results on statistical method selection (parametric vs. nonparametric), (iii) insensitivity of commonly used tests to uniform dose scaling, (iv) influence of tail selection (one- vs. two-tailed tests) on statistical power, (v) frequent misapplication of permutation testing, (vi) reliance on dose as the sole predictor while neglecting patient-, treatment-, and genomic-level covariates, and (vii) misinterpretation of voxel-wise associations as causal in the absence of appropriate causal inference frameworks. Collectively, these limitations can obscure clinically relevant dose differences, inflate false-positive or false-negative findings, obscure effect direction, introduce confounded associations, and ultimately yield inconsistent identification of high-risk subregions in organs at risk and poor reproducibility across studies. Notably, current univariable VBA/IBDM approaches should be regarded as hypothesis-generating rather than clinical decision-making tools, as unvalidated findings risk premature translation into clinical practice. Advancing personalized radiotherapy requires rigorous outcome validation, integration of multivariable and causal modeling strategies, and incorporation of clinical and genomic data. By moving beyond dose-only predictor models, VBA/IBDM can achieve greater biological relevance, reliability, and clinical utility, supporting more precise and individualized radiotherapy strategies. Full article
(This article belongs to the Special Issue Recent Developments of Radiotherapy in Oncology)
Show Figures

Figure 1

13 pages, 666 KB  
Article
Early Sepsis Detection in Adult Patients with Suspected Sepsis in an Emergency Setting: A Sequential Strategy of Monocyte Distribution Width and Presepsin
by Hanah Kim, Mina Hur, Hyejung Lee, Gun-Hyuk Lee, Kyeong Ryong Lee and Ferdinando Mannello
Diagnostics 2025, 15(20), 2574; https://doi.org/10.3390/diagnostics15202574 - 13 Oct 2025
Viewed by 159
Abstract
Background/Objectives: Monocyte distribution width (MDW) is a US FDA-cleared early sepsis indicator for adult patients presenting to the emergency department (ED). Presepsin, a soluble CD14 subtype, is another sepsis biomarker reflecting innate immune activation. We explored the clinical utility of sequential MDW [...] Read more.
Background/Objectives: Monocyte distribution width (MDW) is a US FDA-cleared early sepsis indicator for adult patients presenting to the emergency department (ED). Presepsin, a soluble CD14 subtype, is another sepsis biomarker reflecting innate immune activation. We explored the clinical utility of sequential MDW and presepsin testing for early sepsis detection in the ED. Methods: In a total of 281 adult ED patients with suspected sepsis (including 128 patients with confirmed sepsis), MDW was measured on a DxH 900 analyzer (Beckman Coulter, USA), and presepsin level was measured using the HISCL Presepsin assay (Sysmex, Japan). Diagnostic performances of MDW, presepsin, and their combination (MDW followed by presepsin) were compared using sensitivity, specificity, and area under the curves (AUC) of receiver operating characteristic (ROC) curve analyses. Results: MDW, presepsin, and their combination were comparable for diagnosing sepsis (AUC ranges: 0.52–0.65). Compared with MDW and presepsin, their combination increased diagnostic sensitivity (90.6%, 89.8%, and 98.4%, respectively). Moreover, the sequential strategy significantly reduced false-negative results compared to each biomarker (2 [1.6%] for the sequential strategy vs. 12 [9.4%] for MDW vs. 13 [10.2%] for presepsin, p < 0.001). Conclusions: Compared with individual measurement of MDW and presepsin, the sequential strategy of MDW followed by presepsin would improve early sepsis detection in ED patients by significantly reducing false negatives. This approach would ensure timely and effective triage for ruling in septic patients, potentially leading to improved patient outcomes. Full article
(This article belongs to the Special Issue Recent Advances in Sepsis)
Show Figures

Figure 1

21 pages, 2900 KB  
Article
Optimizing Detection Reliability in Safety-Critical Computer Vision: Transfer Learning and Hyperparameter Tuning with Multi-Task Learning
by Waun Broderick and Sabine McConnell
Sensors 2025, 25(20), 6306; https://doi.org/10.3390/s25206306 - 12 Oct 2025
Viewed by 221
Abstract
This paper presents a methodological framework for selectively optimizing computer vision models for safety-critical applications. Through systematic processes of hyperparameter tuning alongside multitask learning, we attempt to create a highly interpretable system to better assess the dangers of models intended for safety operations [...] Read more.
This paper presents a methodological framework for selectively optimizing computer vision models for safety-critical applications. Through systematic processes of hyperparameter tuning alongside multitask learning, we attempt to create a highly interpretable system to better assess the dangers of models intended for safety operations and intentionally select their trade-offs. Using thermographic images of a specific imitation explosive, we create a case study for the viability of humanitarian demining operations. We hope to demonstrate how this approach provides a developmental framework for creating humanitarian AI systems that optimize safety verification in real-world scenarios. By employing a comprehensive grid search across 64 model configurations to evaluate how loss function weights impact detection reliability, with particular focus on minimizing false negative rates due to their operational impact. The optimized configuration achieves a 37.5% reduction in false negatives while improving precision by 2.8%, resulting in 90% detection accuracy with 92% precision. However, to expand the generalizability of this model, we hope to call institutions to openly share their data to increase the breadth of imitation landmines and terrain data to train models from. Full article
(This article belongs to the Special Issue Feature Papers in Smart Sensing and Intelligent Sensors 2025)
Show Figures

Figure 1

23 pages, 2499 KB  
Review
Application of Machine Learning and Deep Learning Techniques for Enhanced Insider Threat Detection in Cybersecurity: Bibliometric Review
by Hillary Kwame Ofori, Kwame Bell-Dzide, William Leslie Brown-Acquaye, Forgor Lempogo, Samuel O. Frimpong, Israel Edem Agbehadji and Richard C. Millham
Symmetry 2025, 17(10), 1704; https://doi.org/10.3390/sym17101704 - 11 Oct 2025
Viewed by 300
Abstract
Insider threats remain a persistent challenge in cybersecurity, as malicious or negligent insiders exploit legitimate access to compromise systems and data. This study presents a bibliometric review of 325 peer-reviewed publications from 2015 to 2025 to examine how machine learning (ML) and deep [...] Read more.
Insider threats remain a persistent challenge in cybersecurity, as malicious or negligent insiders exploit legitimate access to compromise systems and data. This study presents a bibliometric review of 325 peer-reviewed publications from 2015 to 2025 to examine how machine learning (ML) and deep learning (DL) techniques for insider threat detection have evolved. The analysis investigates temporal publication trends, influential authors, international collaboration networks, thematic shifts, and algorithmic preferences. Results show a steady rise in research output and a transition from traditional ML models, such as decision trees and random forests, toward advanced DL methods, including long short-term memory (LSTM) networks, autoencoders, and hybrid ML–DL frameworks. Co-authorship mapping highlights China, India, and the United States as leading contributors, while keyword analysis underscores the increasing focus on behavior-based and eXplainable AI models. Symmetry emerges as a central theme, reflected in balancing detection accuracy with computational efficiency, and minimizing false positives while avoiding false negatives. The study recommends adaptive hybrid architectures, particularly Bidirectional LSTM–Variational Auto-Encoder (BiLSTM-VAE) models with eXplainable AI, as promising solutions that restore symmetry between detection accuracy and transparency, strengthening both technical performance and organizational trust. Full article
(This article belongs to the Special Issue Symmetry and Asymmetry in Artificial Intelligence for Cybersecurity)
Show Figures

Figure 1

38 pages, 2958 KB  
Review
Multiplexed Optical Nanobiosensing Technologies for Disease Biomarker Detection
by Pureum Kim, Min Yu Choi, Yubeen Lee, Ki-Bum Lee and Jin-Ha Choi
Biosensors 2025, 15(10), 682; https://doi.org/10.3390/bios15100682 - 9 Oct 2025
Viewed by 309
Abstract
Most biomarkers exhibit abnormal expression in more than one disease, making conventional single-biomarker detection strategies prone to false-negative results. Detecting multiple biomarkers associated with a single disease can therefore substantially improve diagnostic accuracy. Accordingly, recent research has focused on precise multiplex detection, leading [...] Read more.
Most biomarkers exhibit abnormal expression in more than one disease, making conventional single-biomarker detection strategies prone to false-negative results. Detecting multiple biomarkers associated with a single disease can therefore substantially improve diagnostic accuracy. Accordingly, recent research has focused on precise multiplex detection, leading to the development of sensors employing various readout methods, including electrochemical, fluorescence, Raman, and colorimetric approaches. This review focuses on optical sensing applications, such as fluorescence, Raman spectroscopy, and colorimetry, which offer rapid and straightforward detection and are well suited for point-of-care testing (POCT). These optical sensors exploit nanoscale phenomena derived from the intrinsic properties of nanomaterials, including metal-enhanced fluorescence (MEF), Förster resonance energy transfer (FRET), and surface-enhanced Raman scattering (SERS), which can be tailored through modifications in material type and structure. We summarize the types and properties of commonly used nanomaterials, including plasmonic and carbon-based nanoparticles, and provide a comprehensive overview of recent advances in multiplex biomarker detection. Furthermore, we address the potential of these nanosensors for clinical translation and POCT applications, highlighting their relevance for next-generation disease diagnostic platforms. Full article
(This article belongs to the Special Issue Nanomaterial-Based Biosensors for Point-of-Care Testing)
Show Figures

Figure 1

29 pages, 7823 KB  
Article
Real-Time Detection Sensor for Unmanned Aerial Vehicle Using an Improved YOLOv8s Algorithm
by Fuhao Lu, Chao Zeng, Hangkun Shi, Yanghui Xu and Song Fu
Sensors 2025, 25(19), 6246; https://doi.org/10.3390/s25196246 - 9 Oct 2025
Viewed by 596
Abstract
This study advances the unmanned aerial vehicle (UAV) localization technology within the framework of a low-altitude economy, with particular emphasis on the accurate and real-time identification and tracking of unauthorized (“black-flying”) drones. Conventional YOLOv8s-based target detection algorithms often suffer from missed detections due [...] Read more.
This study advances the unmanned aerial vehicle (UAV) localization technology within the framework of a low-altitude economy, with particular emphasis on the accurate and real-time identification and tracking of unauthorized (“black-flying”) drones. Conventional YOLOv8s-based target detection algorithms often suffer from missed detections due to their reliance on single-frame features. To address this limitation, this paper proposes an improved detection algorithm that integrates a long-short-term memory (LSTM) network into the YOLOv8s framework. By incorporating time-series modeling, the LSTM module enables the retention of historical features and dynamic prediction of UAV trajectories. The loss function combines bounding box regression loss with binary cross-entropy and is optimized using the Adam algorithm to enhance training convergence. The training data distribution is validated through Monte Carlo random sampling, which improves the model’s generalization to complex scenes. Simulation results demonstrate that the proposed method significantly enhances UAV detection performance. In addition, when deployed on the RK3588-based embedded system, the method achieves a low false negative rate and exhibits robust detection capabilities, indicating strong potential for practical applications in airspace management and counter-UAV operations. Full article
(This article belongs to the Special Issue Smart Sensing and Control for Autonomous Intelligent Unmanned Systems)
Show Figures

Figure 1

20 pages, 5378 KB  
Article
Lightweight GAN for Restoring Blurred Images to Enhance Citrus Detection
by Yuyu Huang, Hui Li, Yuheng Yang, Chengsong Li, Lihong Wang and Pei Wang
Plants 2025, 14(19), 3085; https://doi.org/10.3390/plants14193085 - 6 Oct 2025
Viewed by 281
Abstract
Image blur is a major factor that degrades object detection in agricultural applications, particularly in orchards where crop occlusion, leaf movement, and camera shake frequently reduce image quality. This study proposed a lightweight generative adversarial network, AGG-DeblurGAN, to address non-uniform motion blur in [...] Read more.
Image blur is a major factor that degrades object detection in agricultural applications, particularly in orchards where crop occlusion, leaf movement, and camera shake frequently reduce image quality. This study proposed a lightweight generative adversarial network, AGG-DeblurGAN, to address non-uniform motion blur in citrus tree images. The model integrates the GhostNet backbone, attention-enhanced Ghost modules, and a Gated Half Instance Normalization Module. A blur detection mechanism enabled dynamic routing, reducing computation on sharp images. Experiments on a citrus dataset showed that AGG-DeblurGAN maintained restoration quality while improving efficiency. For object detection, restored citrus images achieved an 86.4% improvement in mAP@0.5:0.95, a 76.9% gain in recall, and a 40.1% increase in F1 score compared to blurred images, while the false negative rate dropped by 63.9%. These results indicate that AGG-DeblurGAN can serve as a reference for improving image preprocessing and detection performance in agricultural vision systems. Full article
Show Figures

Figure 1

18 pages, 2116 KB  
Article
A Markov Chain Replacement Strategy for Surrogate Identifiers: Minimizing Re-Identification Risk While Preserving Text Reuse
by John D. Osborne, Andrew Trotter, Tobias O’Leary, Chris Coffee, Micah D. Cochran, Luis Mansilla-Gonzalez, Akhil Nadimpalli, Alex McAnnally, Abdulateef I. Almudaifer, Jeffrey R. Curtis, Salma M. Aly and Richard E. Kennedy
Electronics 2025, 14(19), 3945; https://doi.org/10.3390/electronics14193945 - 6 Oct 2025
Viewed by 637
Abstract
“Hiding in Plain Sight” (HIPS) strategies for Personal Health Information (PHI) replace PHI with surrogate values to hinder re-identification attempts. We evaluate three different HIPS strategies for PHI replacement, a standard Consistent replacement strategy, a Random replacement strategy, and a novel Markov model [...] Read more.
“Hiding in Plain Sight” (HIPS) strategies for Personal Health Information (PHI) replace PHI with surrogate values to hinder re-identification attempts. We evaluate three different HIPS strategies for PHI replacement, a standard Consistent replacement strategy, a Random replacement strategy, and a novel Markov model strategy. We evaluate the privacy-preserving benefits and relative utility for information extraction of these strategies on both a simulated PHI distribution and real clinical corpora from two different institutions using a range of false negative error rates (FNER). The Markov strategy consistently outperformed the Consistent and Random substitution strategies on both real data and in statistical simulations. Using FNER ranging from 0.1% to 5%, PHI leakage at the document level could be reduced from 27.1% to 0.1% and from 94.2% to 57.7% with the Markov strategy versus the standard Consistent substitution strategy, at 0.1% and 0.5% FNER, respectively. Additionally, we assessed the generated corpora containing synthetic PHI for reuse using a variety of information extraction methods. Results indicate that modern deep learning methods have similar performance on all strategies, but older machine learning techniques can suffer from the change in context. Overall, a Markov surrogate generation strategy substantially reduces the chance of inadvertent PHI release. Full article
Show Figures

Figure 1

16 pages, 860 KB  
Article
Exploratory Analysis on Physiological and Biomechanical Correlates of Performance in the CrossFit Benchmark Workout Fran
by Alexandra Malheiro, Pedro Forte, David Rodríguez Rosell, Diogo L. Marques and Mário C. Marques
J. Funct. Morphol. Kinesiol. 2025, 10(4), 387; https://doi.org/10.3390/jfmk10040387 - 5 Oct 2025
Viewed by 445
Abstract
Background: The multifactorial nature of CrossFit performance remains incompletely understood, particularly regarding sex- and experience-related physiological and biomechanical factors. Methods: Fifteen trained athletes (8 males, 7 females) completed assessments of anthropometry, estimated one-repetition maximums (bench press, back squat, deadlift), squat jump [...] Read more.
Background: The multifactorial nature of CrossFit performance remains incompletely understood, particularly regarding sex- and experience-related physiological and biomechanical factors. Methods: Fifteen trained athletes (8 males, 7 females) completed assessments of anthropometry, estimated one-repetition maximums (bench press, back squat, deadlift), squat jump (SJ), maximal oxygen uptake (VO2max), ventilatory responses (V˙E), and heart rate (HR). Spearman, Pearson, and partial correlations were calculated with Holm and false discovery rate (FDR) corrections. Results: Males displayed greater body mass, lean and muscle mass, maximal strength, and aerobic capacity than females (all Holm-adjusted p < 0.01). Experienced athletes completed Fran faster than beginners despite broadly similar anthropometric and aerobic profiles. In the pooled sample, WOD time showed moderate negative relationships with estimated 1RM back squat (ρ = −0.54), deadlift (ρ = −0.56), and bench press (ρ = −0.65) before correction; none remained significant after Holm/FDR adjustment, and partial correlations controlling for training years were further attenuated. Conclusions: This exploratory study provides preliminary evidence suggesting that maximal strength may contribute to Fran performance, whereas conventional aerobic measures were less influential. However, given the very small sample (n = 15, 8 males and 7 females) and the fact that no relationships remained statistically significant after correction for multiple testing, the results must be regarded as preliminary, hypothesis-generating evidence only, requiring confirmation in larger and adequately powered studies. Full article
(This article belongs to the Special Issue Biomechanical Analysis in Physical Activity and Sports—2nd Edition)
Show Figures

Figure 1

21 pages, 3489 KB  
Article
GA-YOLOv11: A Lightweight Subway Foreign Object Detection Model Based on Improved YOLOv11
by Ning Guo, Min Huang and Wensheng Wang
Sensors 2025, 25(19), 6137; https://doi.org/10.3390/s25196137 - 4 Oct 2025
Viewed by 528
Abstract
Modern subway platforms are generally equipped with platform screen door systems to enhance safety, but the gap between the platform screen doors and train doors may cause passengers or objects to become trapped, leading to accidents. Addressing the issues of excessive parameter counts [...] Read more.
Modern subway platforms are generally equipped with platform screen door systems to enhance safety, but the gap between the platform screen doors and train doors may cause passengers or objects to become trapped, leading to accidents. Addressing the issues of excessive parameter counts and computational complexity in existing foreign object intrusion detection algorithms, as well as false positives and false negatives for small objects, this article introduces a lightweight deep learning model based on YOLOv11n, named GA-YOLOv11. First, a lightweight GhostConv convolution module is introduced into the backbone network to reduce computational resource waste in irrelevant areas, thereby lowering model complexity and computational load. Additionally, the GAM attention mechanism is incorporated into the head network to enhance the model’s ability to distinguish features, enabling precise identification of object location and category, and significantly reducing the probability of false positives and false negatives. Experimental results demonstrate that in comparison to the original YOLOv11n model, the improved model achieves 3.3%, 3.2%, 1.2%, and 3.5% improvements in precision, recall, mAP@0.5, and mAP@0.5: 0.95, respectively. In contrast to the original YOLOv11n model, the number of parameters and GFLOPs were reduced by 18% and 7.9%, respectfully, while maintaining the same model size. The improved model is more lightweight while ensuring real-time performance and accuracy, designed for detecting foreign objects in subway platform gaps. Full article
(This article belongs to the Special Issue Image Processing and Analysis for Object Detection: 3rd Edition)
Show Figures

Figure 1

20 pages, 510 KB  
Article
Effect of GenAI Dependency on University Students’ Academic Achievement: The Mediating Role of Self-Efficacy and Moderating Role of Perceived Teacher Caring
by Wenxiu Jia, Li Pan and Siobhan Neary
Behav. Sci. 2025, 15(10), 1348; https://doi.org/10.3390/bs15101348 - 2 Oct 2025
Viewed by 821
Abstract
Generative artificial intelligence (GenAI) holds significant potential to enhance university students’ learning. However, over-reliance on it to complete academic tasks poses a risk to academic achievement by potentially encouraging cognitive outsourcing. Despite this growing concern and an expanding body of research on GenAI [...] Read more.
Generative artificial intelligence (GenAI) holds significant potential to enhance university students’ learning. However, over-reliance on it to complete academic tasks poses a risk to academic achievement by potentially encouraging cognitive outsourcing. Despite this growing concern and an expanding body of research on GenAI usage, the mechanisms through which GenAI dependency and perceived teacher caring affect their academic achievement and self-efficacy remain underexplored. Based on the theory of media system dependence, this study explores the mechanisms through which university students’ dependency on GenAI affects their academic outcomes, focusing on the mediating role of self-efficacy and moderating role of perceived teacher caring. A survey was conducted with 418 university students from Chinese public universities who had used GenAI for an extended period. The results revealed that GenAI dependency positively predicts false self-efficacy and negatively predicts academic achievement, exhibiting a significant Dunning–Kruger effect. Perceived teacher caring moderates the relationship between GenAI dependency and self-efficacy. High perceived teacher caring mitigates the Dunning–Kruger effect but has a weak moderating effect on academic achievement. These findings enhance the explanatory power of the media system dependency theory in educational contexts and reveal the pathways through which GenAI dependency and teacher caring affect learning processes and outcomes. This study expands the theoretical implications of teacher caring in the digital age and provides empirical evidence to aid higher education administrators in optimising AI governance and teachers in improving instructional interventions. Full article
Show Figures

Figure 1

9 pages, 421 KB  
Case Report
Possible Drug–Radiopharmaceutical Interaction in 99mTc-Sestamibi Parathyroid Imaging
by Tracia-Gay Kennedy-Dixon, Mellanie-Anne Didier, Keisha Allen-Dougan, Peter Glegg and Maxine Gossell-Williams
Pharmacy 2025, 13(5), 140; https://doi.org/10.3390/pharmacy13050140 - 1 Oct 2025
Viewed by 244
Abstract
Drug–radiopharmaceutical interactions can significantly alter radiotracer biodistribution, complicating diagnostic accuracy. This case report describes a 64-year-old male who underwent a Technetium-99m-methoxyisobutyl isonitrile (99mTc-MIBI) parathyroid scan for suspected primary hyperparathyroidism. Initially, the patient was asked to discontinue his medications for his chronic [...] Read more.
Drug–radiopharmaceutical interactions can significantly alter radiotracer biodistribution, complicating diagnostic accuracy. This case report describes a 64-year-old male who underwent a Technetium-99m-methoxyisobutyl isonitrile (99mTc-MIBI) parathyroid scan for suspected primary hyperparathyroidism. Initially, the patient was asked to discontinue his medications for his chronic illnesses for 24 h prior to the scan. However, the images revealed significantly reduced counts/tracer uptake in the thyroid, parathyroid and cardiac tissues in both the early and delayed phases. After a detailed review of his medication profile, it was postulated that there were potential interactions involving multiple P-glycoprotein (P-gp) substrates with specific emphasis on amlodipine, atorvastatin and telmisartan. The patient was advised to discontinue all medications for 72 h prior to the date of a repeat scan which was scheduled for two weeks after his initial scan. The repeat scan successfully detected a small focus of marked tracer retention in the left inferior parathyroid bed, suggestive of a small parathyroid adenoma. Post-surgery, the focus identified on the scan was removed and histologically confirmed to be a parathyroid adenoma. This is the first report of its kind among nuclear medicine patients in Jamaica. It highlights the importance of reviewing medication history prior to nuclear imaging, particularly when using radiotracers affected by P-gp mechanisms. This is crucial for mitigating against false-negative results, thus ensuring accurate diagnosis and appropriate clinical management. Full article
(This article belongs to the Section Pharmacy Practice and Practice-Based Research)
Show Figures

Figure 1

31 pages, 5551 KB  
Article
Optimized Intrusion Detection in the IoT Through Statistical Selection and Classification with CatBoost and SNN
by Brou Médard Kouassi, Abou Bakary Ballo, Kacoutchy Jean Ayikpa, Diarra Mamadou and Youssouf Diabagate
Technologies 2025, 13(10), 441; https://doi.org/10.3390/technologies13100441 - 30 Sep 2025
Viewed by 254
Abstract
With the rapid expansion of the Internet of Things (IoT), interconnected systems are becoming increasingly vulnerable to cyberattacks, making intrusion detection essential but difficult. The marked imbalance between regular traffic and attacks, as well as the redundancy of variables from multiple sensors and [...] Read more.
With the rapid expansion of the Internet of Things (IoT), interconnected systems are becoming increasingly vulnerable to cyberattacks, making intrusion detection essential but difficult. The marked imbalance between regular traffic and attacks, as well as the redundancy of variables from multiple sensors and protocols, greatly complicates this task. The study aims to improve the robustness of IoT intrusion detection systems by reducing the risks of overfitting and false negatives through appropriate rebalancing and variable selection strategies. We combine two data rebalancing techniques, Synthetic Minority Over-sampling Technique (SMOTE) and Random Undersampling (RUS), with two feature selection methods, LASSO and Mutual Information, and then evaluate their performance on two classification models: CatBoost and a Simple Neural Network (SNN). The experiments show the superiority of CatBoost, which achieves an accuracy of 82% compared to 80% for SNN, and confirm the effectiveness of SMOTE over RUS, particularly for SNN. The CatBoost + SMOTE + LASSO configuration stands out with a recall of 82.43% and an F1-score of 85.08%, offering the best compromise between detection and reliability. These results demonstrate that combining rebalancing and variable selection techniques significantly enhances the performance and reliability of intrusion detection systems in the IoT, thereby strengthening cybersecurity in connected environments. Full article
(This article belongs to the Special Issue IoT-Enabling Technologies and Applications—2nd Edition)
Show Figures

Figure 1

Back to TopTop