Three long-term field trials in humid regions of Canada and the USA were used to evaluate the influence of soil depth and sample numbers on soil organic carbon (SOC) sequestration in no-tillage (NT) and moldboard plow...Three long-term field trials in humid regions of Canada and the USA were used to evaluate the influence of soil depth and sample numbers on soil organic carbon (SOC) sequestration in no-tillage (NT) and moldboard plow (MP) corn (Zea mays L.) and soybean (Glycine max L.) production systems. The first trial was conducted on a Maryhill silt loam (Typic Hapludalf) at Elora, Ontario, Canada, the second on a Brookston clay loam (Typic Argiaquoll) at Woodslee, Ontario, Canada, and the third on a Thorp silt loam (Argiaquic Argialboll) at Urbana, Illinois, USA. No-tillage led to significantly higher SOC concentrations in the top 5 cm compared to MP at all 3 sites. However, NT resulted in significantly lower SOC in sub-surface soils as compared to MP at Woodslee (10-20 cm, P = 0.01) and Urbana (20-30 cm, P < 0.10). No-tillage had significantly more SOC storage than MP at the Elora site (3.3 Mg C ha-1) and at the Woodslee site (6.2 Mg C ha-1) on an equivalent mass basis (1350 Mg ha-1 soil equivalent mass). Similarly, NT had greater SOC storage than MP at the Urbana site (2.7 Mg C ha-1) on an equivalent mass basis of 675 Mg ha-1 soil. However, these differences disappeared when the entire plow layer was evaluated for both the Woodslee and Urbana sites as a result of the higher SOC concentrations in MP than in NT at depth. Using the minimum detectable difference technique, we observed that up to 1500 soil sample per tillage treatment comparison will have to be collected and analyzed for the Elora and Woodslee sites and over 40 soil samples per tillage treatment comparison for the Urbana to statistically separate significant differences in the SOC contents of sub-plow depth soils. Therefore, it is impracticable, and at the least prohibitively expensive, to detect tillage-induced differences in soil C beyond the plow layer in various soils.展开更多
To utilizing the characteristic of radar cross section （RCS） of the low detectable aircraft, a special path planning algorithm to eluding radars by the variable RCS is presented. The algorithm first gives the RCS ch...To utilizing the characteristic of radar cross section （RCS） of the low detectable aircraft, a special path planning algorithm to eluding radars by the variable RCS is presented. The algorithm first gives the RCS changing model of low detectable aircraft, then establishes a threat model of a ground-based air defense system according to the relations between RCS and the radar range coverage. By the new cost functions of the flight path, which consider both factors of the survival probability and the distance of total route, this path planning method is simulated based on the Dijkstra algorithm, and the planned route meets the flight capacity constraints. Simulation results show that using the effective path planning algorithm, the low detectable aircraft can give full play to its own advantage of stealth to achieve the purpose of silent penetration.展开更多
In this study,the theory of minimum detectable activity concentration(MDAC)for airborne gamma-ray spectrometry(AGS)was derived,and the relationship between the MDAC and the intrinsic effi-ciency of a scintillation cou...In this study,the theory of minimum detectable activity concentration(MDAC)for airborne gamma-ray spectrometry(AGS)was derived,and the relationship between the MDAC and the intrinsic effi-ciency of a scintillation counter,volume,and energy res-olution of scintillation crystals,and flight altitude of an aircraft was investigated.To verify this theory,experi-mental devices based on NaI and CeBr 3 scintillation counters were prepared,and the potassium,uranium,and thorium contents in calibration pads obtained via the stripping ratio method and theory were compared.The MDACs of AGS under different conditions were calculated and analyzed using the proposed theory and the Monte Carlo method.The relative errors found via a comparison of the experimental and theoretical results were less than 4%.The theory of MDAC can guide the work of AGS in probing areas with low radioactivity.展开更多
We present a new quantum protocol for solving detectable Byzantine agreement problem between threeparties by employing one quantum key distribution protocol.The protocol is suggested by a special four-qubit entangleds...We present a new quantum protocol for solving detectable Byzantine agreement problem between threeparties by employing one quantum key distribution protocol.The protocol is suggested by a special four-qubit entangledstate instead of singlet states,which shows that singlet states are not necessary to achieve detectable Byzantine agreement.展开更多
Background:Myxomas are the most common primary cardiac tumors.Angiographically detectable neovascularity(ADN)of myxoma is increasingly being reported as a result of the use of coronary angiography(CAG)to detect corona...Background:Myxomas are the most common primary cardiac tumors.Angiographically detectable neovascularity(ADN)of myxoma is increasingly being reported as a result of the use of coronary angiography(CAG)to detect coronary artery disease.However,the clinical signifi cance of these fi ndings is not fully understood.Methods:We enrolled 59 patients with cardiac myxoma who also underwent CAG between January 2013 and October 2018.Patients were followed up for a mean of 28.9 months(range 1-69 months).The clinical features,echocardiography measurements,pathological examination fi ndings,CAG results,and outcomes during follow-up were compared between patients with ADN and patients without ADN.Results:ADN was found in 25 patients(42.4%).The arteries feeding the ADN included the right coronary artery(n=15),the left circumfl ex coronary artery(n=7),and both arteries(n=3).The patients with ADN had a higher proportion of eosinophils(3.2%vs.2.2%,P=0.03)and higher low-density lipoprotein cholesterol level(2.7 mmol/L vs.2.2 mmol/L,P=0.02).Myxoma pedicles were more likely to be located in the interatrial septum in patients with ADN(96%vs.73.5%,P=0.02).No signifi cant correlation was observed between the groups in clinical manifestations,atrial arrhythmia,myxoma size,cardiac chamber size,left ventricular ejection fraction,and the prevalence of complication with coronary artery disease[16%in the ADN group(n=4)vs.20.6%in the non-ADN group(n=7),P=0.66].However,patients with ADN tended to have a lower incidence of major adverse cardiac and cerebrovascular events on long-term follow-up(0%vs.14.7%,P=0.07).Conclusion:CAG-detected ADN in patients with cardiac myxoma is associated with a borderline lower rate of major adverse cardiac and cerebrovascular events.展开更多
The determination of the effective minimum detectable activity （MDA） of radionuclides by a detection system plays an im- portant role in environmental radiation monitoring. In this study, the responses of an NaI（TI...The determination of the effective minimum detectable activity （MDA） of radionuclides by a detection system plays an im- portant role in environmental radiation monitoring. In this study, the responses of an NaI（TI） airborne γ ray spectrometry （AGRS） system to different radionuclides （137Cs and 131I） were investigated using the Monte Carlo technique. The MDA values were determined under different conditions according to the counting spectra obtained from the Monte Carlo simulation. The equivalent mass thickness method was applied to the Monte Carlo modeling for monitoring ground radiation to reduce sta- tistical uncertainty. The secondary source method was used to monitor both air and ground radiation. A quadratic relationship was found between the MDA and activity concentration. An exponential relationship was found between the MDA and altitude The MDA of a specific radionuclide from external detectors was found to be superior to that obtained from internal detectors under the same conditions. The MDA values in an NaI（Tl） AGRS system under different conditions can be estimated based on the results of this study.展开更多
Single orbit bistatic space-based radar （SBR） is composed of two radars in the same orbit. The characteristics of the clutter Doppler-angle spectrum of a single orbit bistatic SBR show that the slope of the mainbeam...Single orbit bistatic space-based radar （SBR） is composed of two radars in the same orbit. The characteristics of the clutter Doppler-angle spectrum of a single orbit bistatic SBR show that the slope of the mainbeam clutter spectrum is highly sensitive to the cone angles. Therefore, the minimum detectable velocity of the bistatic system is dependent on the cone angle. Then a new combined working mode of singleorbit bistatic SBR system was developed in which one radar will act as the transmitter and another as the receiver to improve detection performance for all angles. Simulation results by space-time adaptive processing verify the improved detection performance. The new design also reduces the average power of each radar system and the size and weight of the on-board solar array-battery system.展开更多
The rapid proliferation of Internet of Things(IoT)devices in critical healthcare infrastructure has introduced significant security and privacy challenges that demand innovative,distributed architectural solutions.Thi...The rapid proliferation of Internet of Things(IoT)devices in critical healthcare infrastructure has introduced significant security and privacy challenges that demand innovative,distributed architectural solutions.This paper proposes FE-ACS(Fog-Edge Adaptive Cybersecurity System),a novel hierarchical security framework that intelligently distributes AI-powered anomaly detection algorithms across edge,fog,and cloud layers to optimize security efficacy,latency,and privacy.Our comprehensive evaluation demonstrates that FE-ACS achieves superior detection performance with an AUC-ROC of 0.985 and an F1-score of 0.923,while maintaining significantly lower end-to-end latency(18.7 ms)compared to cloud-centric(152.3 ms)and fog-only(34.5 ms)architectures.The system exhibits exceptional scalability,supporting up to 38,000 devices with logarithmic performance degradation—a 67×improvement over conventional cloud-based approaches.By incorporating differential privacy mechanisms with balanced privacy-utility tradeoffs(ε=1.0–1.5),FE-ACS maintains 90%–93%detection accuracy while ensuring strong privacy guarantees for sensitive healthcare data.Computational efficiency analysis reveals that our architecture achieves a detection rate of 12,400 events per second with only 12.3 mJ energy consumption per inference.In healthcare risk assessment,FE-ACS demonstrates robust operational viability with low patient safety risk(14.7%)and high system reliability(94.0%).The proposed framework represents a significant advancement in distributed security architectures,offering a scalable,privacy-preserving,and real-time solution for protecting healthcare IoT ecosystems against evolving cyber threats.展开更多
Breast cancer screening programs rely heavily on mammography for early detection;however,diagnostic performance is strongly affected by inter-reader variability,breast density,and the limitations of conven-tional comp...Breast cancer screening programs rely heavily on mammography for early detection;however,diagnostic performance is strongly affected by inter-reader variability,breast density,and the limitations of conven-tional computer-aided detection systems.Recent advances in deep learning have enabled more robust and scalable solutions for large-scale screening,yet a systematic comparison of modern object detection architectures on nationally representative datasets remains limited.This study presents a comprehensive quantitative comparison of prominent deep learning–based object detection architectures for Artificial Intelligence-assisted mammography analysis using the MammosighTR dataset,developed within the Turkish National Breast Cancer Screening Program.The dataset comprises 12,740 patient cases collected between 2016 and 2022,annotated with BI-RADS categories,breast density levels,and lesion localization labels.A total of 31 models were evaluated,including One-Stage,Two-Stage,and Transformer-based architectures,under a unified experimental framework at both patient and breast levels.The results demonstrate that Two-Stage architectures consistently outperform One-Stage models,achieving approximately 2%–4%higher Macro F1-Scores and more balanced precision–recall trade-offs,with Double-Head R-CNN and Dynamic R-CNN yielding the highest overall performance(Macro F1≈0.84–0.86).This advantage is primarily attributed to the region proposal mechanism and improved class balance inherent to Two-Stage designs.One-Stage detectors exhibited higher sensitivity and faster inference,reaching Recall values above 0.88,but experienced minor reductions in Precision and overall accuracy(≈1%–2%)compared with Two-Stage models.Among Transformer-based architectures,Deformable DEtection TRansformer demonstrated strong robustness and consistency across datasets,achieving Macro F1-Scores comparable to CNN-based detectors(≈0.83–0.85)while exhibiting minimal performance degradation under distributional shifts.Breast density–based analysis revealed increased misclassification rates in medium-density categories(types B and C),whereas Transformer-based architectures maintained more stable performance in high-density type D tissue.These findings quantitatively confirm that both architectural design and tissue characteristics play a decisive role in diagnostic accuracy.Overall,the study provides a reproducible benchmark and highlights the potential of hybrid approaches that combine the accuracy of Two-Stage detectors with the contextual modeling capability of Transformer architectures for clinically reliable breast cancer screening systems.展开更多
With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comp...With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comprise heterogeneous networks where outdated systems coexist with the latest devices,spanning a range of devices from non-encrypted ones to fully encrypted ones.Given the limited visibility into payloads in this context,this study investigates AI-based attack detection methods that leverage encrypted traffic metadata,eliminating the need for decryption and minimizing system performance degradation—especially in light of these heterogeneous devices.Using the UNSW-NB15 and CICIoT-2023 dataset,encrypted and unencrypted traffic were categorized according to security protocol,and AI-based intrusion detection experiments were conducted for each traffic type based on metadata.To mitigate the problem of class imbalance,eight different data sampling techniques were applied.The effectiveness of these sampling techniques was then comparatively analyzed using two ensemble models and three Deep Learning(DL)models from various perspectives.The experimental results confirmed that metadata-based attack detection is feasible using only encrypted traffic.In the UNSW-NB15 dataset,the f1-score of encrypted traffic was approximately 0.98,which is 4.3%higher than that of unencrypted traffic(approximately 0.94).In addition,analysis of the encrypted traffic in the CICIoT-2023 dataset using the same method showed a significantly lower f1-score of roughly 0.43,indicating that the quality of the dataset and the preprocessing approach have a substantial impact on detection performance.Furthermore,when data sampling techniques were applied to encrypted traffic,the recall in the UNSWNB15(Encrypted)dataset improved by up to 23.0%,and in the CICIoT-2023(Encrypted)dataset by 20.26%,showing a similar level of improvement.Notably,in CICIoT-2023,f1-score and Receiver Operation Characteristic-Area Under the Curve(ROC-AUC)increased by 59.0%and 55.94%,respectively.These results suggest that data sampling can have a positive effect even in encrypted environments.However,the extent of the improvement may vary depending on data quality,model architecture,and sampling strategy.展开更多
Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone t...Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.展开更多
Traffic sign detection is an important part of autonomous driving,and its recognition accuracy and speed are directly related to road traffic safety.Although convolutional neural networks(CNNs)have made certain breakt...Traffic sign detection is an important part of autonomous driving,and its recognition accuracy and speed are directly related to road traffic safety.Although convolutional neural networks(CNNs)have made certain breakthroughs in this field,in the face of complex scenes,such as image blur and target occlusion,the traffic sign detection continues to exhibit limited accuracy,accompanied by false positives and missed detections.To address the above problems,a traffic sign detection algorithm,You Only Look Once-based Skip Dynamic Way(YOLO-SDW)based on You Only Look Once version 8 small(YOLOv8s),is proposed.Firstly,a Skip Connection Reconstruction(SCR)module is introduced to efficiently integrate fine-grained feature information and enhance the detection accuracy of the algorithm in complex scenes.Secondly,a C2f module based on Dynamic Snake Convolution(C2f-DySnake)is proposed to dynamically adjust the receptive field information,improve the algorithm’s feature extraction ability for blurred or occluded targets,and reduce the occurrence of false detections and missed detections.Finally,the Wise Powerful IoU v2(WPIoUv2)loss function is proposed to further improve the detection accuracy of the algorithm.Experimental results show that the average precision mAP@0.5 of YOLO-SDW on the TT100K dataset is 89.2%,and mAP@0.5:0.95 is 68.5%,which is 4%and 3.3%higher than the YOLOv8s baseline,respectively.YOLO-SDW ensures real-time performance while having higher accuracy.展开更多
This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagno...This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagnostic performance and computational efficiency.To this end,a total of 3234 high-resolution images(2400×1080)were collected from three major rice diseases Rice Blast,Bacterial Blight,and Brown Spot—frequently found in actual rice cultivation fields.These images served as the training dataset.The proposed YOLOv5-V2 model removes the Focus layer from the original YOLOv5s and integrates ShuffleNet V2 into the backbone,thereby resulting in both model compression and improved inference speed.Additionally,YOLOv5-P,based on PP-PicoDet,was configured as a comparative model to quantitatively evaluate performance.Experimental results demonstrated that YOLOv5-V2 achieved excellent detection performance,with an mAP 0.5 of 89.6%,mAP 0.5–0.95 of 66.7%,precision of 91.3%,and recall of 85.6%,while maintaining a lightweight model size of 6.45 MB.In contrast,YOLOv5-P exhibited a smaller model size of 4.03 MB,but showed lower performance with an mAP 0.5 of 70.3%,mAP 0.5–0.95 of 35.2%,precision of 62.3%,and recall of 74.1%.This study lays a technical foundation for the implementation of smart agriculture and real-time disease diagnosis systems by proposing a model that satisfies both accuracy and lightweight requirements.展开更多
The global population is rapidly expanding,driving an increasing demand for intelligent healthcare systems.Artificial intelligence(AI)applications in remote patient monitoring and diagnosis have achieved remarkable pr...The global population is rapidly expanding,driving an increasing demand for intelligent healthcare systems.Artificial intelligence(AI)applications in remote patient monitoring and diagnosis have achieved remarkable progress and are emerging as a major development trend.Among these applications,mouth motion tracking and mouth-state detection represent an important direction,providing valuable support for diagnosing neuromuscular disorders such as dysphagia,Bell’s palsy,and Parkinson’s disease.In this study,we focus on developing a real-time system capable of monitoring and detecting mouth state that can be efficiently deployed on edge devices.The proposed system integrates the Facial Landmark Detection technique with an optimized model combining a Bidirectional Gated Recurrent Unit(BiGRU)and Comprehensive Learning Particle Swarm Optimization(CLPSO).We conducted a comprehensive comparison and evaluation of the proposed model against several traditional models using multiple performance metrics,including accuracy,precision,recall,F1-score,cosine similarity,ROC–AUC,and the precision–recall curve.The proposed method achieved an impressive accuracy of 96.57%with an excellent precision of 98.25%on our self-collected dataset,outperforming traditional models and related works in the same field.These findings highlight the potential of the proposed approach for implementation in real-time patient monitoring systems,contributing to improved diagnostic accuracy and supporting healthcare professionals in patient treatment and care.展开更多
In printed circuit board(PCB)manufacturing,surface defects can significantly affect product quality.To address the performance degradation,high false detection rates,and missed detections caused by complex backgrounds...In printed circuit board(PCB)manufacturing,surface defects can significantly affect product quality.To address the performance degradation,high false detection rates,and missed detections caused by complex backgrounds in current intelligent inspection algorithms,this paper proposes CG-YOLOv8,a lightweight and improved model based on YOLOv8n for PCB surface defect detection.The proposed method optimizes the network architecture and compresses parameters to reduce model complexity while maintaining high detection accuracy,thereby enhancing the capability of identifying diverse defects under complex conditions.Specifically,a cascaded multi-receptive field(CMRF)module is adopted to replace the SPPF module in the backbone to improve feature perception,and an inverted residual mobile block(IRMB)is integrated into the C2f module to further enhance performance.Additionally,conventional convolution layers are replaced with GSConv to reduce computational cost,and a lightweight Convolutional Block Attention Module based Convolution(CBAMConv)module is introduced after Grouped Spatial Convolution(GSConv)to preserve accuracy through attention mechanisms.The detection head is also optimized by removing medium and large-scale detection layers,thereby enhancing the model’s ability to detect small-scale defects and further reducing complexity.Experimental results show that,compared to the original YOLOv8n,the proposed CG-YOLOv8 reduces parameter count by 53.9%,improves mAP@0.5 by 2.2%,and increases precision and recall by 2.0%and 1.8%,respectively.These improvements demonstrate that CG-YOLOv8 offers an efficient and lightweight solution for PCB surface defect detection.展开更多
The Financial Technology(FinTech)sector has witnessed rapid growth,resulting in increasingly complex and high-volume digital transactions.Although this expansion improves efficiency and accessibility,it also introduce...The Financial Technology(FinTech)sector has witnessed rapid growth,resulting in increasingly complex and high-volume digital transactions.Although this expansion improves efficiency and accessibility,it also introduces significant vulnerabilities,including fraud,money laundering,and market manipulation.Traditional anomaly detection techniques often fail to capture the relational and dynamic characteristics of financial data.Graph Neural Networks(GNNs),capable of modeling intricate interdependencies among entities,have emerged as a powerful framework for detecting subtle and sophisticated anomalies.However,the high-dimensionality and inherent noise of FinTech datasets demand robust feature selection strategies to improve model scalability,performance,and interpretability.This paper presents a comprehensive survey of GNN-based approaches for anomaly detection in FinTech,with an emphasis on the synergistic role of feature selection.We examine the theoretical foundations of GNNs,review state-of-the-art feature selection techniques,analyze their integration with GNNs,and categorize prevalent anomaly types in FinTech applications.In addition,we discuss practical implementation challenges,highlight representative case studies,and propose future research directions to advance the field of graph-based anomaly detection in financial systems.展开更多
Halide perovskites have emerged as promising materials for X-ray detection with exceptional properties and reasonable costs.Among them,heterostructures between 3D perovskites and low-dimensional perovskites attract in...Halide perovskites have emerged as promising materials for X-ray detection with exceptional properties and reasonable costs.Among them,heterostructures between 3D perovskites and low-dimensional perovskites attract intensive studies of their advantages due to low-level ion migration and decent stability.However,there is still a lack of methods to precisely construct heterostructures and a fundamental understanding of their structure-dependent optoelectronic properties.Herein,a gas-phase method was developed to grow 2D perovskites directly on 3D perovskites with nanoscale accuracy.In addition,the larger steric hindrance of organic layers of 2D perovskites was proved to enable slower ion migration,which resulted in reduced trap states and better stability.Based on MAPbBr_(3)single crystals with the(PA)_(2)PbBr_(4)capping layer,the X-ray detector achieved a sensitivity of 22,245μC Gy_(air)^(−1)cm^(−2),a response speed of 240μs,and a dark current drift of 1.17.10^(–4)nA cm^(−1)s^(−1)V^(−1),which were among the highest reported for state-of-the-art perovskite-based X-ray detectors.This study presents a precise synthesis method to construct perovskite-based heterostructures.It also brings an in-depth understanding of the relationship between lattice structures and properties,which are beneficial for advancing high-performance and cost-effective X-ray detectors.展开更多
Community detection is one of the most fundamental applications in understanding the structure of complicated networks.Furthermore,it is an important approach to identifying closely linked clusters of nodes that may r...Community detection is one of the most fundamental applications in understanding the structure of complicated networks.Furthermore,it is an important approach to identifying closely linked clusters of nodes that may represent underlying patterns and relationships.Networking structures are highly sensitive in social networks,requiring advanced techniques to accurately identify the structure of these communities.Most conventional algorithms for detecting communities perform inadequately with complicated networks.In addition,they miss out on accurately identifying clusters.Since single-objective optimization cannot always generate accurate and comprehensive results,as multi-objective optimization can.Therefore,we utilized two objective functions that enable strong connections between communities and weak connections between them.In this study,we utilized the intra function,which has proven effective in state-of-the-art research studies.We proposed a new inter-function that has demonstrated its effectiveness by making the objective of detecting external connections between communities is to make them more distinct and sparse.Furthermore,we proposed a Multi-Objective community strength enhancement algorithm(MOCSE).The proposed algorithm is based on the framework of the Multi-Objective Evolutionary Algorithm with Decomposition(MOEA/D),integrated with a new heuristic mutation strategy,community strength enhancement(CSE).The results demonstrate that the model is effective in accurately identifying community structures while also being computationally efficient.The performance measures used to evaluate the MOEA/D algorithm in our work are normalized mutual information(NMI)and modularity(Q).It was tested using five state-of-the-art algorithms on social networks,comprising real datasets(Zachary,Dolphin,Football,Krebs,SFI,Jazz,and Netscience),as well as twenty synthetic datasets.These results provide the robustness and practical value of the proposed algorithm in multi-objective community identification.展开更多
Synthetic speech detection is an essential task in the field of voice security,aimed at identifying deceptive voice attacks generated by text-to-speech(TTS)systems or voice conversion(VC)systems.In this paper,we propo...Synthetic speech detection is an essential task in the field of voice security,aimed at identifying deceptive voice attacks generated by text-to-speech(TTS)systems or voice conversion(VC)systems.In this paper,we propose a synthetic speech detection model called TFTransformer,which integrates both local and global features to enhance detection capabilities by effectively modeling local and global dependencies.Structurally,the model is divided into two main components:a front-end and a back-end.The front-end of the model uses a combination of SincLayer and two-dimensional(2D)convolution to extract high-level feature maps(HFM)containing local dependency of the input speech signals.The back-end uses time-frequency Transformer module to process these feature maps and further capture global dependency.Furthermore,we propose TFTransformer-SE,which incorporates a channel attention mechanism within the 2D convolutional blocks.This enhancement aims to more effectively capture local dependencies,thereby improving the model’s performance.The experiments were conducted on the ASVspoof 2021 LA dataset,and the results showed that the model achieved an equal error rate(EER)of 3.37%without data augmentation.Additionally,we evaluated the model using the ASVspoof 2019 LA dataset,achieving an EER of 0.84%,also without data augmentation.This demonstrates that combining local and global dependencies in the time-frequency domain can significantly improve detection accuracy.展开更多
Modern intrusion detection systems(MIDS)face persistent challenges in coping with the rapid evolution of cyber threats,high-volume network traffic,and imbalanced datasets.Traditional models often lack the robustness a...Modern intrusion detection systems(MIDS)face persistent challenges in coping with the rapid evolution of cyber threats,high-volume network traffic,and imbalanced datasets.Traditional models often lack the robustness and explainability required to detect novel and sophisticated attacks effectively.This study introduces an advanced,explainable machine learning framework for multi-class IDS using the KDD99 and IDS datasets,which reflects real-world network behavior through a blend of normal and diverse attack classes.The methodology begins with sophisticated data preprocessing,incorporating both RobustScaler and QuantileTransformer to address outliers and skewed feature distributions,ensuring standardized and model-ready inputs.Critical dimensionality reduction is achieved via the Harris Hawks Optimization(HHO)algorithm—a nature-inspired metaheuristic modeled on hawks’hunting strategies.HHO efficiently identifies the most informative features by optimizing a fitness function based on classification performance.Following feature selection,the SMOTE is applied to the training data to resolve class imbalance by synthetically augmenting underrepresented attack types.The stacked architecture is then employed,combining the strengths of XGBoost,SVM,and RF as base learners.This layered approach improves prediction robustness and generalization by balancing bias and variance across diverse classifiers.The model was evaluated using standard classification metrics:precision,recall,F1-score,and overall accuracy.The best overall performance was recorded with an accuracy of 99.44%for UNSW-NB15,demonstrating the model’s effectiveness.After balancing,the model demonstrated a clear improvement in detecting the attacks.We tested the model on four datasets to show the effectiveness of the proposed approach and performed the ablation study to check the effect of each parameter.Also,the proposed model is computationaly efficient.To support transparency and trust in decision-making,explainable AI(XAI)techniques are incorporated that provides both global and local insight into feature contributions,and offers intuitive visualizations for individual predictions.This makes it suitable for practical deployment in cybersecurity environments that demand both precision and accountability.展开更多
文摘Three long-term field trials in humid regions of Canada and the USA were used to evaluate the influence of soil depth and sample numbers on soil organic carbon (SOC) sequestration in no-tillage (NT) and moldboard plow (MP) corn (Zea mays L.) and soybean (Glycine max L.) production systems. The first trial was conducted on a Maryhill silt loam (Typic Hapludalf) at Elora, Ontario, Canada, the second on a Brookston clay loam (Typic Argiaquoll) at Woodslee, Ontario, Canada, and the third on a Thorp silt loam (Argiaquic Argialboll) at Urbana, Illinois, USA. No-tillage led to significantly higher SOC concentrations in the top 5 cm compared to MP at all 3 sites. However, NT resulted in significantly lower SOC in sub-surface soils as compared to MP at Woodslee (10-20 cm, P = 0.01) and Urbana (20-30 cm, P < 0.10). No-tillage had significantly more SOC storage than MP at the Elora site (3.3 Mg C ha-1) and at the Woodslee site (6.2 Mg C ha-1) on an equivalent mass basis (1350 Mg ha-1 soil equivalent mass). Similarly, NT had greater SOC storage than MP at the Urbana site (2.7 Mg C ha-1) on an equivalent mass basis of 675 Mg ha-1 soil. However, these differences disappeared when the entire plow layer was evaluated for both the Woodslee and Urbana sites as a result of the higher SOC concentrations in MP than in NT at depth. Using the minimum detectable difference technique, we observed that up to 1500 soil sample per tillage treatment comparison will have to be collected and analyzed for the Elora and Woodslee sites and over 40 soil samples per tillage treatment comparison for the Urbana to statistically separate significant differences in the SOC contents of sub-plow depth soils. Therefore, it is impracticable, and at the least prohibitively expensive, to detect tillage-induced differences in soil C beyond the plow layer in various soils.
文摘To utilizing the characteristic of radar cross section （RCS） of the low detectable aircraft, a special path planning algorithm to eluding radars by the variable RCS is presented. The algorithm first gives the RCS changing model of low detectable aircraft, then establishes a threat model of a ground-based air defense system according to the relations between RCS and the radar range coverage. By the new cost functions of the flight path, which consider both factors of the survival probability and the distance of total route, this path planning method is simulated based on the Dijkstra algorithm, and the planned route meets the flight capacity constraints. Simulation results show that using the effective path planning algorithm, the low detectable aircraft can give full play to its own advantage of stealth to achieve the purpose of silent penetration.
基金This work was supported by the Sichuan Science and Technology Program(No.2020JDRC0108)the National Science Foundation of China(Nos.41774147 and 41774190).
文摘In this study,the theory of minimum detectable activity concentration(MDAC)for airborne gamma-ray spectrometry(AGS)was derived,and the relationship between the MDAC and the intrinsic effi-ciency of a scintillation counter,volume,and energy res-olution of scintillation crystals,and flight altitude of an aircraft was investigated.To verify this theory,experi-mental devices based on NaI and CeBr 3 scintillation counters were prepared,and the potassium,uranium,and thorium contents in calibration pads obtained via the stripping ratio method and theory were compared.The MDACs of AGS under different conditions were calculated and analyzed using the proposed theory and the Monte Carlo method.The relative errors found via a comparison of the experimental and theoretical results were less than 4%.The theory of MDAC can guide the work of AGS in probing areas with low radioactivity.
基金Supported by National Natural Science Foundation of China under Grant Nos.60873191,60903152,and 60821001SRFDP under Grant No.200800131016+5 种基金Beijing Nova Program under Grant No.2008B51Key Project of Chinese Ministry of Education under Grant No.109014Beijing Natural Science Foundation under Grant No.4072020China Postdoctoral Science Foundation under Grant No.20090450018National Laboratory for Modern Communications Science Foundation of China under Grant No.9140C1101010601ISN Open Foundation
文摘We present a new quantum protocol for solving detectable Byzantine agreement problem between threeparties by employing one quantum key distribution protocol.The protocol is suggested by a special four-qubit entangledstate instead of singlet states,which shows that singlet states are not necessary to achieve detectable Byzantine agreement.
文摘Background:Myxomas are the most common primary cardiac tumors.Angiographically detectable neovascularity(ADN)of myxoma is increasingly being reported as a result of the use of coronary angiography(CAG)to detect coronary artery disease.However,the clinical signifi cance of these fi ndings is not fully understood.Methods:We enrolled 59 patients with cardiac myxoma who also underwent CAG between January 2013 and October 2018.Patients were followed up for a mean of 28.9 months(range 1-69 months).The clinical features,echocardiography measurements,pathological examination fi ndings,CAG results,and outcomes during follow-up were compared between patients with ADN and patients without ADN.Results:ADN was found in 25 patients(42.4%).The arteries feeding the ADN included the right coronary artery(n=15),the left circumfl ex coronary artery(n=7),and both arteries(n=3).The patients with ADN had a higher proportion of eosinophils(3.2%vs.2.2%,P=0.03)and higher low-density lipoprotein cholesterol level(2.7 mmol/L vs.2.2 mmol/L,P=0.02).Myxoma pedicles were more likely to be located in the interatrial septum in patients with ADN(96%vs.73.5%,P=0.02).No signifi cant correlation was observed between the groups in clinical manifestations,atrial arrhythmia,myxoma size,cardiac chamber size,left ventricular ejection fraction,and the prevalence of complication with coronary artery disease[16%in the ADN group(n=4)vs.20.6%in the non-ADN group(n=7),P=0.66].However,patients with ADN tended to have a lower incidence of major adverse cardiac and cerebrovascular events on long-term follow-up(0%vs.14.7%,P=0.07).Conclusion:CAG-detected ADN in patients with cardiac myxoma is associated with a borderline lower rate of major adverse cardiac and cerebrovascular events.
基金supported by the National Defense Basic Scientific Research Project(Grant No.B2520133077)National High-tech R&D Program of China("863"Program)(Grant No.2012AA061803)
文摘The determination of the effective minimum detectable activity （MDA） of radionuclides by a detection system plays an im- portant role in environmental radiation monitoring. In this study, the responses of an NaI（TI） airborne γ ray spectrometry （AGRS） system to different radionuclides （137Cs and 131I） were investigated using the Monte Carlo technique. The MDA values were determined under different conditions according to the counting spectra obtained from the Monte Carlo simulation. The equivalent mass thickness method was applied to the Monte Carlo modeling for monitoring ground radiation to reduce sta- tistical uncertainty. The secondary source method was used to monitor both air and ground radiation. A quadratic relationship was found between the MDA and activity concentration. An exponential relationship was found between the MDA and altitude The MDA of a specific radionuclide from external detectors was found to be superior to that obtained from internal detectors under the same conditions. The MDA values in an NaI（Tl） AGRS system under different conditions can be estimated based on the results of this study.
文摘Single orbit bistatic space-based radar （SBR） is composed of two radars in the same orbit. The characteristics of the clutter Doppler-angle spectrum of a single orbit bistatic SBR show that the slope of the mainbeam clutter spectrum is highly sensitive to the cone angles. Therefore, the minimum detectable velocity of the bistatic system is dependent on the cone angle. Then a new combined working mode of singleorbit bistatic SBR system was developed in which one radar will act as the transmitter and another as the receiver to improve detection performance for all angles. Simulation results by space-time adaptive processing verify the improved detection performance. The new design also reduces the average power of each radar system and the size and weight of the on-board solar array-battery system.
基金supported by the Deanship of Graduate Studies and Scientific Research at Jouf University under grant No.(DGSSR-2025-02-01276).
文摘The rapid proliferation of Internet of Things(IoT)devices in critical healthcare infrastructure has introduced significant security and privacy challenges that demand innovative,distributed architectural solutions.This paper proposes FE-ACS(Fog-Edge Adaptive Cybersecurity System),a novel hierarchical security framework that intelligently distributes AI-powered anomaly detection algorithms across edge,fog,and cloud layers to optimize security efficacy,latency,and privacy.Our comprehensive evaluation demonstrates that FE-ACS achieves superior detection performance with an AUC-ROC of 0.985 and an F1-score of 0.923,while maintaining significantly lower end-to-end latency(18.7 ms)compared to cloud-centric(152.3 ms)and fog-only(34.5 ms)architectures.The system exhibits exceptional scalability,supporting up to 38,000 devices with logarithmic performance degradation—a 67×improvement over conventional cloud-based approaches.By incorporating differential privacy mechanisms with balanced privacy-utility tradeoffs(ε=1.0–1.5),FE-ACS maintains 90%–93%detection accuracy while ensuring strong privacy guarantees for sensitive healthcare data.Computational efficiency analysis reveals that our architecture achieves a detection rate of 12,400 events per second with only 12.3 mJ energy consumption per inference.In healthcare risk assessment,FE-ACS demonstrates robust operational viability with low patient safety risk(14.7%)and high system reliability(94.0%).The proposed framework represents a significant advancement in distributed security architectures,offering a scalable,privacy-preserving,and real-time solution for protecting healthcare IoT ecosystems against evolving cyber threats.
文摘Breast cancer screening programs rely heavily on mammography for early detection;however,diagnostic performance is strongly affected by inter-reader variability,breast density,and the limitations of conven-tional computer-aided detection systems.Recent advances in deep learning have enabled more robust and scalable solutions for large-scale screening,yet a systematic comparison of modern object detection architectures on nationally representative datasets remains limited.This study presents a comprehensive quantitative comparison of prominent deep learning–based object detection architectures for Artificial Intelligence-assisted mammography analysis using the MammosighTR dataset,developed within the Turkish National Breast Cancer Screening Program.The dataset comprises 12,740 patient cases collected between 2016 and 2022,annotated with BI-RADS categories,breast density levels,and lesion localization labels.A total of 31 models were evaluated,including One-Stage,Two-Stage,and Transformer-based architectures,under a unified experimental framework at both patient and breast levels.The results demonstrate that Two-Stage architectures consistently outperform One-Stage models,achieving approximately 2%–4%higher Macro F1-Scores and more balanced precision–recall trade-offs,with Double-Head R-CNN and Dynamic R-CNN yielding the highest overall performance(Macro F1≈0.84–0.86).This advantage is primarily attributed to the region proposal mechanism and improved class balance inherent to Two-Stage designs.One-Stage detectors exhibited higher sensitivity and faster inference,reaching Recall values above 0.88,but experienced minor reductions in Precision and overall accuracy(≈1%–2%)compared with Two-Stage models.Among Transformer-based architectures,Deformable DEtection TRansformer demonstrated strong robustness and consistency across datasets,achieving Macro F1-Scores comparable to CNN-based detectors(≈0.83–0.85)while exhibiting minimal performance degradation under distributional shifts.Breast density–based analysis revealed increased misclassification rates in medium-density categories(types B and C),whereas Transformer-based architectures maintained more stable performance in high-density type D tissue.These findings quantitatively confirm that both architectural design and tissue characteristics play a decisive role in diagnostic accuracy.Overall,the study provides a reproducible benchmark and highlights the potential of hybrid approaches that combine the accuracy of Two-Stage detectors with the contextual modeling capability of Transformer architectures for clinically reliable breast cancer screening systems.
基金supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.RS-2023-00235509Development of security monitoring technology based network behavior against encrypted cyber threats in ICT convergence environment).
文摘With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comprise heterogeneous networks where outdated systems coexist with the latest devices,spanning a range of devices from non-encrypted ones to fully encrypted ones.Given the limited visibility into payloads in this context,this study investigates AI-based attack detection methods that leverage encrypted traffic metadata,eliminating the need for decryption and minimizing system performance degradation—especially in light of these heterogeneous devices.Using the UNSW-NB15 and CICIoT-2023 dataset,encrypted and unencrypted traffic were categorized according to security protocol,and AI-based intrusion detection experiments were conducted for each traffic type based on metadata.To mitigate the problem of class imbalance,eight different data sampling techniques were applied.The effectiveness of these sampling techniques was then comparatively analyzed using two ensemble models and three Deep Learning(DL)models from various perspectives.The experimental results confirmed that metadata-based attack detection is feasible using only encrypted traffic.In the UNSW-NB15 dataset,the f1-score of encrypted traffic was approximately 0.98,which is 4.3%higher than that of unencrypted traffic(approximately 0.94).In addition,analysis of the encrypted traffic in the CICIoT-2023 dataset using the same method showed a significantly lower f1-score of roughly 0.43,indicating that the quality of the dataset and the preprocessing approach have a substantial impact on detection performance.Furthermore,when data sampling techniques were applied to encrypted traffic,the recall in the UNSWNB15(Encrypted)dataset improved by up to 23.0%,and in the CICIoT-2023(Encrypted)dataset by 20.26%,showing a similar level of improvement.Notably,in CICIoT-2023,f1-score and Receiver Operation Characteristic-Area Under the Curve(ROC-AUC)increased by 59.0%and 55.94%,respectively.These results suggest that data sampling can have a positive effect even in encrypted environments.However,the extent of the improvement may vary depending on data quality,model architecture,and sampling strategy.
文摘Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.
基金funded by Key research and development Program of Henan Province(No.251111211200)National Natural Science Foundation of China(Grant No.U2004163).
文摘Traffic sign detection is an important part of autonomous driving,and its recognition accuracy and speed are directly related to road traffic safety.Although convolutional neural networks(CNNs)have made certain breakthroughs in this field,in the face of complex scenes,such as image blur and target occlusion,the traffic sign detection continues to exhibit limited accuracy,accompanied by false positives and missed detections.To address the above problems,a traffic sign detection algorithm,You Only Look Once-based Skip Dynamic Way(YOLO-SDW)based on You Only Look Once version 8 small(YOLOv8s),is proposed.Firstly,a Skip Connection Reconstruction(SCR)module is introduced to efficiently integrate fine-grained feature information and enhance the detection accuracy of the algorithm in complex scenes.Secondly,a C2f module based on Dynamic Snake Convolution(C2f-DySnake)is proposed to dynamically adjust the receptive field information,improve the algorithm’s feature extraction ability for blurred or occluded targets,and reduce the occurrence of false detections and missed detections.Finally,the Wise Powerful IoU v2(WPIoUv2)loss function is proposed to further improve the detection accuracy of the algorithm.Experimental results show that the average precision mAP@0.5 of YOLO-SDW on the TT100K dataset is 89.2%,and mAP@0.5:0.95 is 68.5%,which is 4%and 3.3%higher than the YOLOv8s baseline,respectively.YOLO-SDW ensures real-time performance while having higher accuracy.
文摘This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagnostic performance and computational efficiency.To this end,a total of 3234 high-resolution images(2400×1080)were collected from three major rice diseases Rice Blast,Bacterial Blight,and Brown Spot—frequently found in actual rice cultivation fields.These images served as the training dataset.The proposed YOLOv5-V2 model removes the Focus layer from the original YOLOv5s and integrates ShuffleNet V2 into the backbone,thereby resulting in both model compression and improved inference speed.Additionally,YOLOv5-P,based on PP-PicoDet,was configured as a comparative model to quantitatively evaluate performance.Experimental results demonstrated that YOLOv5-V2 achieved excellent detection performance,with an mAP 0.5 of 89.6%,mAP 0.5–0.95 of 66.7%,precision of 91.3%,and recall of 85.6%,while maintaining a lightweight model size of 6.45 MB.In contrast,YOLOv5-P exhibited a smaller model size of 4.03 MB,but showed lower performance with an mAP 0.5 of 70.3%,mAP 0.5–0.95 of 35.2%,precision of 62.3%,and recall of 74.1%.This study lays a technical foundation for the implementation of smart agriculture and real-time disease diagnosis systems by proposing a model that satisfies both accuracy and lightweight requirements.
基金supported by the National Science and Technology Council,Taiwan,with grant numbers NSTC 114-2622-8-992-007-TD1 and 112-2811-E-992-003-MY3.
文摘The global population is rapidly expanding,driving an increasing demand for intelligent healthcare systems.Artificial intelligence(AI)applications in remote patient monitoring and diagnosis have achieved remarkable progress and are emerging as a major development trend.Among these applications,mouth motion tracking and mouth-state detection represent an important direction,providing valuable support for diagnosing neuromuscular disorders such as dysphagia,Bell’s palsy,and Parkinson’s disease.In this study,we focus on developing a real-time system capable of monitoring and detecting mouth state that can be efficiently deployed on edge devices.The proposed system integrates the Facial Landmark Detection technique with an optimized model combining a Bidirectional Gated Recurrent Unit(BiGRU)and Comprehensive Learning Particle Swarm Optimization(CLPSO).We conducted a comprehensive comparison and evaluation of the proposed model against several traditional models using multiple performance metrics,including accuracy,precision,recall,F1-score,cosine similarity,ROC–AUC,and the precision–recall curve.The proposed method achieved an impressive accuracy of 96.57%with an excellent precision of 98.25%on our self-collected dataset,outperforming traditional models and related works in the same field.These findings highlight the potential of the proposed approach for implementation in real-time patient monitoring systems,contributing to improved diagnostic accuracy and supporting healthcare professionals in patient treatment and care.
基金funded by the Joint Funds of the National Natural Science Foundation of China(U2341223)the Beijing Municipal Natural Science Foundation(No.4232067).
文摘In printed circuit board(PCB)manufacturing,surface defects can significantly affect product quality.To address the performance degradation,high false detection rates,and missed detections caused by complex backgrounds in current intelligent inspection algorithms,this paper proposes CG-YOLOv8,a lightweight and improved model based on YOLOv8n for PCB surface defect detection.The proposed method optimizes the network architecture and compresses parameters to reduce model complexity while maintaining high detection accuracy,thereby enhancing the capability of identifying diverse defects under complex conditions.Specifically,a cascaded multi-receptive field(CMRF)module is adopted to replace the SPPF module in the backbone to improve feature perception,and an inverted residual mobile block(IRMB)is integrated into the C2f module to further enhance performance.Additionally,conventional convolution layers are replaced with GSConv to reduce computational cost,and a lightweight Convolutional Block Attention Module based Convolution(CBAMConv)module is introduced after Grouped Spatial Convolution(GSConv)to preserve accuracy through attention mechanisms.The detection head is also optimized by removing medium and large-scale detection layers,thereby enhancing the model’s ability to detect small-scale defects and further reducing complexity.Experimental results show that,compared to the original YOLOv8n,the proposed CG-YOLOv8 reduces parameter count by 53.9%,improves mAP@0.5 by 2.2%,and increases precision and recall by 2.0%and 1.8%,respectively.These improvements demonstrate that CG-YOLOv8 offers an efficient and lightweight solution for PCB surface defect detection.
基金supported by Ho Chi Minh City Open University,Vietnam under grant number E2024.02.1CD and Suan Sunandha Rajabhat University,Thailand.
文摘The Financial Technology(FinTech)sector has witnessed rapid growth,resulting in increasingly complex and high-volume digital transactions.Although this expansion improves efficiency and accessibility,it also introduces significant vulnerabilities,including fraud,money laundering,and market manipulation.Traditional anomaly detection techniques often fail to capture the relational and dynamic characteristics of financial data.Graph Neural Networks(GNNs),capable of modeling intricate interdependencies among entities,have emerged as a powerful framework for detecting subtle and sophisticated anomalies.However,the high-dimensionality and inherent noise of FinTech datasets demand robust feature selection strategies to improve model scalability,performance,and interpretability.This paper presents a comprehensive survey of GNN-based approaches for anomaly detection in FinTech,with an emphasis on the synergistic role of feature selection.We examine the theoretical foundations of GNNs,review state-of-the-art feature selection techniques,analyze their integration with GNNs,and categorize prevalent anomaly types in FinTech applications.In addition,we discuss practical implementation challenges,highlight representative case studies,and propose future research directions to advance the field of graph-based anomaly detection in financial systems.
基金support from National Key Research and Development Program of China(2024YFE0217100)the National Natural Science Foundation of China(21905006,22261160370,and 62105075)+7 种基金the Guangdong Provincial Science and Technology Plan(2021A0505110003)the Natural Science Foundation of Hunan Province,China(2023JJ50132)Guangxi Department of Science and Technology(2020GXNSFBA159049 and AD19110030)the Shenzhen Science and Technology Program(SGDX20230116093205009,JCYJ20220818100211025 and 2022378670)the Natural Science Foundation of Top Talent of SZTU(GDRC202343)financial support of Innovation and Technology Fund(#GHP/245/22SZ)The University Grant Council of the University of Hong Kong(grant No.2302101786)General Research Fund(grant Nos.17200823 and 17310624)from the Research Grants Council.
文摘Halide perovskites have emerged as promising materials for X-ray detection with exceptional properties and reasonable costs.Among them,heterostructures between 3D perovskites and low-dimensional perovskites attract intensive studies of their advantages due to low-level ion migration and decent stability.However,there is still a lack of methods to precisely construct heterostructures and a fundamental understanding of their structure-dependent optoelectronic properties.Herein,a gas-phase method was developed to grow 2D perovskites directly on 3D perovskites with nanoscale accuracy.In addition,the larger steric hindrance of organic layers of 2D perovskites was proved to enable slower ion migration,which resulted in reduced trap states and better stability.Based on MAPbBr_(3)single crystals with the(PA)_(2)PbBr_(4)capping layer,the X-ray detector achieved a sensitivity of 22,245μC Gy_(air)^(−1)cm^(−2),a response speed of 240μs,and a dark current drift of 1.17.10^(–4)nA cm^(−1)s^(−1)V^(−1),which were among the highest reported for state-of-the-art perovskite-based X-ray detectors.This study presents a precise synthesis method to construct perovskite-based heterostructures.It also brings an in-depth understanding of the relationship between lattice structures and properties,which are beneficial for advancing high-performance and cost-effective X-ray detectors.
文摘Community detection is one of the most fundamental applications in understanding the structure of complicated networks.Furthermore,it is an important approach to identifying closely linked clusters of nodes that may represent underlying patterns and relationships.Networking structures are highly sensitive in social networks,requiring advanced techniques to accurately identify the structure of these communities.Most conventional algorithms for detecting communities perform inadequately with complicated networks.In addition,they miss out on accurately identifying clusters.Since single-objective optimization cannot always generate accurate and comprehensive results,as multi-objective optimization can.Therefore,we utilized two objective functions that enable strong connections between communities and weak connections between them.In this study,we utilized the intra function,which has proven effective in state-of-the-art research studies.We proposed a new inter-function that has demonstrated its effectiveness by making the objective of detecting external connections between communities is to make them more distinct and sparse.Furthermore,we proposed a Multi-Objective community strength enhancement algorithm(MOCSE).The proposed algorithm is based on the framework of the Multi-Objective Evolutionary Algorithm with Decomposition(MOEA/D),integrated with a new heuristic mutation strategy,community strength enhancement(CSE).The results demonstrate that the model is effective in accurately identifying community structures while also being computationally efficient.The performance measures used to evaluate the MOEA/D algorithm in our work are normalized mutual information(NMI)and modularity(Q).It was tested using five state-of-the-art algorithms on social networks,comprising real datasets(Zachary,Dolphin,Football,Krebs,SFI,Jazz,and Netscience),as well as twenty synthetic datasets.These results provide the robustness and practical value of the proposed algorithm in multi-objective community identification.
基金supported by project ZR2022MF330 supported by Shandong Provincial Natural Science Foundationthe National Natural Science Foundation of China under Grant No.61701286.
文摘Synthetic speech detection is an essential task in the field of voice security,aimed at identifying deceptive voice attacks generated by text-to-speech(TTS)systems or voice conversion(VC)systems.In this paper,we propose a synthetic speech detection model called TFTransformer,which integrates both local and global features to enhance detection capabilities by effectively modeling local and global dependencies.Structurally,the model is divided into two main components:a front-end and a back-end.The front-end of the model uses a combination of SincLayer and two-dimensional(2D)convolution to extract high-level feature maps(HFM)containing local dependency of the input speech signals.The back-end uses time-frequency Transformer module to process these feature maps and further capture global dependency.Furthermore,we propose TFTransformer-SE,which incorporates a channel attention mechanism within the 2D convolutional blocks.This enhancement aims to more effectively capture local dependencies,thereby improving the model’s performance.The experiments were conducted on the ASVspoof 2021 LA dataset,and the results showed that the model achieved an equal error rate(EER)of 3.37%without data augmentation.Additionally,we evaluated the model using the ASVspoof 2019 LA dataset,achieving an EER of 0.84%,also without data augmentation.This demonstrates that combining local and global dependencies in the time-frequency domain can significantly improve detection accuracy.
基金funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R104)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Modern intrusion detection systems(MIDS)face persistent challenges in coping with the rapid evolution of cyber threats,high-volume network traffic,and imbalanced datasets.Traditional models often lack the robustness and explainability required to detect novel and sophisticated attacks effectively.This study introduces an advanced,explainable machine learning framework for multi-class IDS using the KDD99 and IDS datasets,which reflects real-world network behavior through a blend of normal and diverse attack classes.The methodology begins with sophisticated data preprocessing,incorporating both RobustScaler and QuantileTransformer to address outliers and skewed feature distributions,ensuring standardized and model-ready inputs.Critical dimensionality reduction is achieved via the Harris Hawks Optimization(HHO)algorithm—a nature-inspired metaheuristic modeled on hawks’hunting strategies.HHO efficiently identifies the most informative features by optimizing a fitness function based on classification performance.Following feature selection,the SMOTE is applied to the training data to resolve class imbalance by synthetically augmenting underrepresented attack types.The stacked architecture is then employed,combining the strengths of XGBoost,SVM,and RF as base learners.This layered approach improves prediction robustness and generalization by balancing bias and variance across diverse classifiers.The model was evaluated using standard classification metrics:precision,recall,F1-score,and overall accuracy.The best overall performance was recorded with an accuracy of 99.44%for UNSW-NB15,demonstrating the model’s effectiveness.After balancing,the model demonstrated a clear improvement in detecting the attacks.We tested the model on four datasets to show the effectiveness of the proposed approach and performed the ablation study to check the effect of each parameter.Also,the proposed model is computationaly efficient.To support transparency and trust in decision-making,explainable AI(XAI)techniques are incorporated that provides both global and local insight into feature contributions,and offers intuitive visualizations for individual predictions.This makes it suitable for practical deployment in cybersecurity environments that demand both precision and accountability.
