Graph Federated Learning(GFL)has shown great potential in privacy protection and distributed intelligence through distributed collaborative training of graph-structured data without sharing raw information.However,exi...Graph Federated Learning(GFL)has shown great potential in privacy protection and distributed intelligence through distributed collaborative training of graph-structured data without sharing raw information.However,existing GFL approaches often lack the capability for comprehensive feature extraction and adaptive optimization,particularly in non-independent and identically distributed(NON-IID)scenarios where balancing global structural understanding and local node-level detail remains a challenge.To this end,this paper proposes a novel framework called GFL-SAR(Graph Federated Collaborative Learning Framework Based on Structural Amplification and Attention Refinement),which enhances the representation learning capability of graph data through a dual-branch collaborative design.Specifically,we propose the Structural Insight Amplifier(SIA),which utilizes an improved Graph Convolutional Network(GCN)to strengthen structural awareness and improve modeling of topological patterns.In parallel,we propose the Attentive Relational Refiner(ARR),which employs an enhanced Graph Attention Network(GAT)to perform fine-grained modeling of node relationships and neighborhood features,thereby improving the expressiveness of local interactions and preserving critical contextual information.GFL-SAR effectively integrates multi-scale features from every branch via feature fusion and federated optimization,thereby addressing existing GFL limitations in structural modeling and feature representation.Experiments on standard benchmark datasets including Cora,Citeseer,Polblogs,and Cora_ML demonstrate that GFL-SAR achieves superior performance in classification accuracy,convergence speed,and robustness compared to existing methods,confirming its effectiveness and generalizability in GFL tasks.展开更多
Internet of Things(IoTs)devices are bringing about a revolutionary change our society by enabling connectivity regardless of time and location.However,The extensive deployment of these devices also makes them attracti...Internet of Things(IoTs)devices are bringing about a revolutionary change our society by enabling connectivity regardless of time and location.However,The extensive deployment of these devices also makes them attractive victims for themalicious actions of adversaries.Within the spectrumof existing threats,Side-ChannelAttacks(SCAs)have established themselves as an effective way to compromise cryptographic implementations.These attacks exploit unintended,unintended physical leakage that occurs during the cryptographic execution of devices,bypassing the theoretical strength of the crypto design.In recent times,the advancement of deep learning has provided SCAs with a powerful ally.Well-trained deep-learningmodels demonstrate an exceptional capacity to identify correlations between side-channel measurements and sensitive data,thereby significantly enhancing such attacks.To further understand the security threats posed by deep-learning SCAs and to aid in formulating robust countermeasures in the future,this paper undertakes an exhaustive investigation of leading-edge SCAs targeting Advanced Encryption Standard(AES)implementations.The study specifically focuses on attacks that exploit power consumption and electromagnetic(EM)emissions as primary leakage sources,systematically evaluating the extent to which diverse deep learning techniques enhance SCAs acrossmultiple critical dimensions.These dimensions include:(i)the characteristics of publicly available datasets derived from various hardware and software platforms;(ii)the formalization of leakage models tailored to different attack scenarios;(iii)the architectural suitability and performance of state-of-the-art deep learning models.Furthermore,the survey provides a systematic synthesis of current research findings,identifies significant unresolved issues in the existing literature and suggests promising directions for future work,including cross-device attack transferability and the impact of quantum-classical hybrid computing on side-channel security.展开更多
Unmanned Aerial Vehicle(UAV)plays a prominent role in various fields,and autonomous navigation is a crucial component of UAV intelligence.Deep Reinforcement Learning(DRL)has expanded the research avenues for addressin...Unmanned Aerial Vehicle(UAV)plays a prominent role in various fields,and autonomous navigation is a crucial component of UAV intelligence.Deep Reinforcement Learning(DRL)has expanded the research avenues for addressing challenges in autonomous navigation.Nonetheless,challenges persist,including getting stuck in local optima,consuming excessive computations during action space exploration,and neglecting deterministic experience.This paper proposes a noise-driven enhancement strategy.In accordance with the overall learning phases,a global noise control method is designed,while a differentiated local noise control method is developed by analyzing the exploration demands of four typical situations encountered by UAV during navigation.Both methods are integrated into a dual-model for noise control to regulate action space exploration.Furthermore,noise dual experience replay buffers are designed to optimize the rational utilization of both deterministic and noisy experience.In uncertain environments,based on the Twin Delay Deep Deterministic Policy Gradient(TD3)algorithm with Long Short-Term Memory(LSTM)network and Priority Experience Replay(PER),a Noise-Driven Enhancement Priority Memory TD3(NDE-PMTD3)is developed.We established a simulation environment to compare different algorithms,and the performance of the algorithms is analyzed in various scenarios.The training results indicate that the proposed algorithm accelerates the convergence speed and enhances the convergence stability.In test experiments,the proposed algorithm successfully and efficiently performs autonomous navigation tasks in diverse environments,demonstrating superior generalization results.展开更多
To better understand the migration behavior of plastic fragments in the environment,development of rapid non-destructive methods for in-situ identification and characterization of plastic fragments is necessary.Howeve...To better understand the migration behavior of plastic fragments in the environment,development of rapid non-destructive methods for in-situ identification and characterization of plastic fragments is necessary.However,most of the studies had focused only on colored plastic fragments,ignoring colorless plastic fragments and the effects of different environmental media(backgrounds),thus underestimating their abundance.To address this issue,the present study used near-infrared spectroscopy to compare the identification of colored and colorless plastic fragments based on partial least squares-discriminant analysis(PLS-DA),extreme gradient boost,support vector machine and random forest classifier.The effects of polymer color,type,thickness,and background on the plastic fragments classification were evaluated.PLS-DA presented the best and most stable outcome,with higher robustness and lower misclassification rate.All models frequently misinterpreted colorless plastic fragments and its background when the fragment thickness was less than 0.1mm.A two-stage modeling method,which first distinguishes the plastic types and then identifies colorless plastic fragments that had been misclassified as background,was proposed.The method presented an accuracy higher than 99%in different backgrounds.In summary,this study developed a novel method for rapid and synchronous identification of colored and colorless plastic fragments under complex environmental backgrounds.展开更多
Solar cell defects exhibit significant variations and multiple types,with some defect data being difficult to acquire or having small scales,posing challenges in terms of small sample and small target in defect detect...Solar cell defects exhibit significant variations and multiple types,with some defect data being difficult to acquire or having small scales,posing challenges in terms of small sample and small target in defect detection for solar cells.In order to address this issue,this paper proposes a multi-step approach for detecting the complex defects of solar cells.First,individual cell plates are extracted from electroluminescence images for block-by-block detection.Then,StyleGAN2-Ada is utilized for generative adversarial networks data augmentation to expand the number of defect samples in small sample defects.Finally,the fake dataset is combined with real dataset,and the improved YOLOv5 model is trained on this mixed dataset.Experimental results demonstrate that the proposed method achieves a superior performance in detecting the defects with small sample and small target,with the final recall rate reaching 99.7%,an increase of 3.9% compared with the unimproved model.Additionally,the precision and mean average precision are increased by 3.4% and 3.5%,respectively.Moreover,the experiments demonstrate that the improved network training on the mixed dataset can effectively enhance the detection performance of the model.The combination of these approaches significantly improves the network’s ability to detect solar cell defects.展开更多
Although conventional object detection methods achieve high accuracy through extensively annotated datasets,acquiring such large-scale labeled data remains challenging and cost-prohibitive in numerous real-world appli...Although conventional object detection methods achieve high accuracy through extensively annotated datasets,acquiring such large-scale labeled data remains challenging and cost-prohibitive in numerous real-world applications.Few-shot object detection presents a new research idea that aims to localize and classify objects in images using only limited annotated examples.However,the inherent challenge in few-shot object detection lies in the insufficient sample diversity to fully characterize the sample feature distribution,which consequently impacts model performance.Inspired by contrastive learning principles,we propose an Implicit Feature Contrastive Learning(IFCL)module to address this limitation and augment feature diversity for more robust representational learning.This module generates augmented support sample features in a mixed feature space and implicitly contrasts them with query Region of Interest(RoI)features.This approach facilitates more comprehensive learning of both intra-class feature similarity and inter-class feature diversity,thereby enhancing the model’s object classification and localization capabilities.Extensive experiments on PASCAL VOC show that our method achieves a respective improvement of 3.2%,1.8%,and 2.3%on 10-shot of three Novel Sets compared to the baseline model FPD.展开更多
This study utilized a sequential mediating model to examine the role of motivation to learn and transfer selfefficacy in the relationships between perceived content validity,mentoring function,continuous learning work...This study utilized a sequential mediating model to examine the role of motivation to learn and transfer selfefficacy in the relationships between perceived content validity,mentoring function,continuous learning work culture and intention to transfer learning.The sample comprized 429 final-year apprentices in Guangdong province,China(females=69.9%,Engineering&Medicine=69%,mean age=20.99,SD=1.60).The apprentices completed standardized measures of motivation to learn,transfer self-efficacy perceived content validity,mentoring function,and continuous learning work culture.Structural equation modeling was used to analyze the data.Results showed perceived content validity,mentoring function,continuous learning culture to predict intention to transfer learning.Of these factors,perceived content validity was the strongest predictor of intention to transfer learning.Of these factors,perceived content validity was the most influential predictor of intention to transfer learning.The motivation to learn and transfer self-efficacy sequentially mediated the relationship between mentoring function and intention to learning transfer to be stronger than by either alone.Although perceived content validity and continuous learning culture exhibited no significant direct effects on intention to transfer learning,they demonstrated positive indirect associations with intention to transfer via motivation to learn and transfer self-efficacy.These study findings extend the applications of the learning transfer framework to individuals undergoing apprenticeship training which also would apply to other a long-term work-based learning programs.展开更多
Hepatocellular carcinoma(HCC)remains a leading cause of cancer-related mortality globally,necessitating advanced diagnostic tools to improve early detection and personalized targeted therapy.This review synthesizes ev...Hepatocellular carcinoma(HCC)remains a leading cause of cancer-related mortality globally,necessitating advanced diagnostic tools to improve early detection and personalized targeted therapy.This review synthesizes evidence on explainable ensemble learning approaches for HCC classification,emphasizing their integration with clinical workflows and multi-omics data.A systematic analysis[including datasets such as The Cancer Genome Atlas,Gene Expression Omnibus,and the Surveillance,Epidemiology,and End Results(SEER)datasets]revealed that explainable ensemble learning models achieve high diagnostic accuracy by combining clinical features,serum biomarkers such as alpha-fetoprotein,imaging features such as computed tomography and magnetic resonance imaging,and genomic data.For instance,SHapley Additive exPlanations(SHAP)-based random forests trained on NCBI GSE14520 microarray data(n=445)achieved 96.53%accuracy,while stacking ensembles applied to the SEER program data(n=1897)demonstrated an area under the receiver operating characteristic curve of 0.779 for mortality prediction.Despite promising results,challenges persist,including the computational costs of SHAP and local interpretable model-agnostic explanations analyses(e.g.,TreeSHAP requiring distributed computing for metabolomics datasets)and dataset biases(e.g.,SEER’s Western population dominance limiting generalizability).Future research must address inter-cohort heterogeneity,standardize explainability metrics,and prioritize lightweight surrogate models for resource-limited settings.This review presents the potential of explainable ensemble learning frameworks to bridge the gap between predictive accuracy and clinical interpretability,though rigorous validation in independent,multi-center cohorts is critical for real-world deployment.展开更多
Indoor scene semantic segmentation is essential for enabling robots to understand and interact with their environments effectively.However,numerous challenges remain unresolved,particularly in single-robot systems,whi...Indoor scene semantic segmentation is essential for enabling robots to understand and interact with their environments effectively.However,numerous challenges remain unresolved,particularly in single-robot systems,which often struggle with the complexity and variability of indoor scenes.To address these limitations,we introduce a novel multi-robot collaborative framework based on multiplex interactive learning(MPIL)in which each robot specialises in a distinct visual task within a unified multitask architecture.During training,the framework employs task-specific decoders and cross-task feature sharing to enhance collaborative optimisation.At inference time,robots operate independently with optimised models,enabling scalable,asynchronous and efficient deployment in real-world scenarios.Specifically,MPIL employs specially designed modules that integrate RGB and depth data,refine feature representations and facilitate the simultaneous execution of multiple tasks,such as instance segmentation,scene classification and semantic segmentation.By leveraging these modules,distinct agents within multi-robot systems can effectively handle specialised tasks,thereby enhancing the overall system's flexibility and adaptability.This collaborative effort maximises the strengths of each robot,resulting in a more comprehensive understanding of environments.Extensive experiments on two public benchmark datasets demonstrate MPIL's competitive performance compared to state-of-the-art approaches,highlighting the effectiveness and robustness of our multi-robot system in complex indoor environments.展开更多
With the rapid urbanization and exponential population growth in China,two-wheeled vehicles have become a popular mode of transportation,particularly for short-distance travel.However,due to a lack of safety awareness...With the rapid urbanization and exponential population growth in China,two-wheeled vehicles have become a popular mode of transportation,particularly for short-distance travel.However,due to a lack of safety awareness,traffic violations by two-wheeled vehicle riders have become a widespread concern,contributing to urban traffic risks.Currently,significant human and material resources are being allocated to monitor and intercept non-compliant riders to ensure safe driving behavior.To enhance the safety,efficiency,and cost-effectiveness of traffic monitoring,automated detection systems based on image processing algorithms can be employed to identify traffic violations from eye-level video footage.In this study,we propose a robust detection algorithm specifically designed for two-wheeled vehicles,which serves as a fundamental step toward intelligent traffic monitoring.Our approach integrates a novel convolutional and attention mechanism to improve detection accuracy and efficiency.Additionally,we introduce a semi-supervised training strategy that leverages a large number of unlabeled images to enhance the model’s learning capability by extracting valuable background information.This method enables the model to generalize effectively to diverse urban environments and varying lighting conditions.We evaluate our proposed algorithm on a custom-built dataset,and experimental results demonstrate its superior performance,achieving an average precision(AP)of 95%and a recall(R)of 90.6%.Furthermore,the model maintains a computational efficiency of only 25.7 GFLOPs while achieving a high processing speed of 249 FPS,making it highly suitable for deployment on edge devices.Compared to existing detection methods,our approach significantly enhances the accuracy and robustness of two-wheeled vehicle identification while ensuring real-time performance.展开更多
Hepatitis is an infection that affects the liver through contaminated foods or blood transfusions,and it has many types,from normal to serious.Hepatitis is diagnosed through many blood tests and factors;Artificial Int...Hepatitis is an infection that affects the liver through contaminated foods or blood transfusions,and it has many types,from normal to serious.Hepatitis is diagnosed through many blood tests and factors;Artificial Intelligence(AI)techniques have played an important role in early diagnosis and help physicians make decisions.This study evaluated the performance of Machine Learning(ML)algorithms on the hepatitis data set.The dataset contains missing values that have been processed and outliers removed.The dataset was counterbalanced by the Synthetic Minority Over-sampling Technique(SMOTE).The features of the data set were processed in two ways:first,the application of the Recursive Feature Elimination(RFE)algorithm to arrange the percentage of contribution of each feature to the diagnosis of hepatitis,then selection of important features using the t-distributed Stochastic Neighbor Embedding(t-SNE)and Principal Component Analysis(PCA)algorithms.Second,the SelectKBest function was applied to give scores for each attribute,followed by the t-SNE and PCA algorithms.Finally,the classification algorithms K-Nearest Neighbors(KNN),Support Vector Machine(SVM),Artificial Neural Network(ANN),Decision Tree(DT),and Random Forest(RF)were fed by the dataset after processing the features in different methods are RFE with t-SNE and PCA and SelectKBest with t-SNE and PCA).All algorithms yielded promising results for diagnosing hepatitis data sets.The RF with RFE and PCA methods achieved accuracy,Precision,Recall,and AUC of 97.18%,96.72%,97.29%,and 94.2%,respectively,during the training phase.During the testing phase,it reached accuracy,Precision,Recall,and AUC by 96.31%,95.23%,97.11%,and 92.67%,respectively.展开更多
Nonlinear science is a fundamental area of physics research that investigates complex dynamical systems which are often characterized by high sensitivity and nonlinear behaviors.Numerical simulations play a pivotal ro...Nonlinear science is a fundamental area of physics research that investigates complex dynamical systems which are often characterized by high sensitivity and nonlinear behaviors.Numerical simulations play a pivotal role in nonlinear science,serving as a critical tool for revealing the underlying principles governing these systems.In addition,they play a crucial role in accelerating progress across various fields,such as climate modeling,weather forecasting,and fluid dynamics.However,their high computational cost limits their application in high-precision or long-duration simulations.In this study,we propose a novel data-driven approach for simulating complex physical systems,particularly turbulent phenomena.Specifically,we develop an efficient surrogate model based on the wavelet neural operator(WNO).Experimental results demonstrate that the enhanced WNO model can accurately simulate small-scale turbulent flows while using lower computational costs.In simulations of complex physical fields,the improved WNO model outperforms established deep learning models,such as U-Net,Res Net,and the Fourier neural operator(FNO),in terms of accuracy.Notably,the improved WNO model exhibits exceptional generalization capabilities,maintaining stable performance across a wide range of initial conditions and high-resolution scenarios without retraining.This study highlights the significant potential of the enhanced WNO model for simulating complex physical systems,providing strong evidence to support the development of more efficient,scalable,and high-precision simulation techniques.展开更多
Speech-face association aims to achieve identity matching between facial images and voice segments by aligning cross-modal features.Existing research primarily focuses on learning shared-space representations and comp...Speech-face association aims to achieve identity matching between facial images and voice segments by aligning cross-modal features.Existing research primarily focuses on learning shared-space representations and computing one-to-one similarities between cross-modal sample pairs to establish their correlation.However,these approaches do not fully account for intra-class variations between the modalities or the many-to-many relationships among cross-modal samples,which are crucial for robust association modeling.To address these challenges,we propose a novel framework that leverages global information to align voice and face embeddings while effectively correlating identity information embedded in both modalities.First,we jointly pre-train face recognition and speaker recognition networks to encode discriminative features from facial images and voice segments.This shared pre-training step ensures the extraction of complementary identity information across modalities.Subsequently,we introduce a cross-modal simplex center loss,which aligns samples with identity centers located at the vertices of a regular simplex inscribed on a hypersphere.This design enforces an equidistant and balanced distribution of identity embeddings,reducing intra-class variations.Furthermore,we employ an improved triplet center loss that emphasizes hard sample mining and optimizes inter-class separability,enhancing the model’s ability to generalize across challenging scenarios.Extensive experiments validate the effectiveness of our framework,demonstrating superior performance across various speech-face association tasks,including matching,verification,and retrieval.Notably,in the challenging gender-constrained matching task,our method achieves a remarkable accuracy of 79.22%,significantly outperforming existing approaches.These results highlight the potential of the proposed framework to advance the state of the art in cross-modal identity association.展开更多
Objective:This study aimed to develop and validate a predictive model for postoperative complications in gastrointestinal cancer patients using a large multicenter database,based on machine learning algorithms.Methods...Objective:This study aimed to develop and validate a predictive model for postoperative complications in gastrointestinal cancer patients using a large multicenter database,based on machine learning algorithms.Methods:We analyzed the clinicopathological data of 3,926 gastrointestinal cancer patients from the Prevalence of Abdominal Complications After GastroEnterological surgery(PACAGE)database,covering 20 medical centers from December 2018 to December 2020.The predictive performance was evaluated using receiver operating characteristic(ROC)curves and Brier Score.Results:The patients were divided into gastric(2,271 cases)and colorectal cancer(1,655 cases)groups and further divided into training and external validation sets.The overall postoperative complication rates for gastric and colorectal cancer groups were 18.1%and 14.8%,respectively.The most common complication was the intraabdominal infection in both gastric and colorectal cancer groups.In the training set,the Random Forest(RF)model predicted the highest mean area under the curve(AUC)values for overall complications and different types of complications,in both the gastric cancer group and the colorectal cancer group,with similar results obtained in the external validation set.ROC curve analysis showed good predictive performance of the RF model for overall and infectious complications.An application-based clinical tool was developed for easy application in clinical practice.Conclusions:This model demonstrated good predictive performance for overall and infectious complications based on the multi-center database,supporting clinical decision-making and personalized treatment strategies.展开更多
To capture the nonlinear dynamics and gain evolution in chirped pulse amplification(CPA)systems,the split-step Fourier method and the fourth-order Runge–Kutta method are integrated to iteratively address the generali...To capture the nonlinear dynamics and gain evolution in chirped pulse amplification(CPA)systems,the split-step Fourier method and the fourth-order Runge–Kutta method are integrated to iteratively address the generalized nonlinear Schrödinger equation and the rate equations.However,this approach is burdened by substantial computational demands,resulting in significant time expenditures.In the context of intelligent laser optimization and inverse design,the necessity for numerous simulations further exacerbates this issue,highlighting the need for fast and accurate simulation methodologies.Here,we introduce an end-to-end model augmented with active learning(E2E-AL)with decent generalization through different dedicated embedding methods over various parameters.On an identical computational platform,the artificial intelligence–driven model is 2000 times faster than the conventional simulation method.Benefiting from the active learning strategy,the E2E-AL model achieves decent precision with only two-thirds of the training samples compared with the case without such a strategy.Furthermore,we demonstrate a multi-objective inverse design of the CPA systems enabled by the E2E-AL model.The E2E-AL framework manifests the potential of becoming a standard approach for the rapid and accurate modeling of ultrafast lasers and is readily extended to simulate other complex systems.展开更多
The manufacturing processes of casing rings are prone to multi-type defects such as holes,cracks,and porosity,so ultrasonic testing is vital for the quality of aeroengine.Conventional ultrasonic testing requires manua...The manufacturing processes of casing rings are prone to multi-type defects such as holes,cracks,and porosity,so ultrasonic testing is vital for the quality of aeroengine.Conventional ultrasonic testing requires manual analysis,which is susceptible to human omission,inconsistent results,and time-consumption.In this paper,a method for automated detection of defects is proposed for the ultrasonic Total Focusing Method(TFM)inspection of casing rings based on deep learning.First,the original datasets of defect images are established,and the Mask R-CNN is used to increase the number of defects in a single image.Then,the YOLOX-S-improved lightweight model is proposed,and the feature extraction network is replaced by Faster Net to reduce redundant computations.The Super-Resolution Generative Adversarial Network(SRGAN)and Convolutional Block Attention Module(CBAM)are integrated to improve the identification precision.Finally,a new test dataset is created by ultrasonic TFM inspection of an aeroengine casing ring.The results show that the mean of Average Precision(m AP)of the YOLOX-S-improved model reaches 99.17%,and the corresponding speed reaches 77.6 FPS.This study indicates that the YOLOX-S-improved model performs better than conventional object detection models.And the generalization ability of the proposed model is verified by ultrasonic B-scan images.展开更多
Landslide susceptibility evaluation plays an important role in disaster prevention and reduction.Feature-based transfer learning(TL)is an effective method for solving landslide susceptibility mapping(LSM)in target reg...Landslide susceptibility evaluation plays an important role in disaster prevention and reduction.Feature-based transfer learning(TL)is an effective method for solving landslide susceptibility mapping(LSM)in target regions with no available samples.However,as the study area expands,the distribution of land-slide types and triggering mechanisms becomes more diverse,leading to performance degradation in models relying on landslide evaluation knowledge from a single source domain due to domain feature shift.To address this,this study proposes a Multi-source Domain Adaptation Convolutional Neural Network(MDACNN),which combines the landslide prediction knowledge learned from two source domains to perform cross-regional LSM in complex large-scale areas.The method is validated through case studies in three regions located in southeastern coastal China and compared with single-source domain TL models(TCA-based models).The results demonstrate that MDACNN effectively integrates transfer knowledge from multiple source domains to learn diverse landslide-triggering mechanisms,thereby significantly reducing prediction bias inherent to single-source domain TL models,achieving an average improvement of 16.58%across all metrics.Moreover,the landslide susceptibility maps gener-ated by MDACNN accurately quantify the spatial distribution of landslide risks in the target area,provid-ing a powerful scientific and technological tool for landslide disaster management and prevention.展开更多
BACKGROUND Neoadjuvant therapy prior to surgery plays a critical role in improving the prognosis of patients with unresectable or locally advanced gastric cancer(GC).Postoperative complications,particularly those clas...BACKGROUND Neoadjuvant therapy prior to surgery plays a critical role in improving the prognosis of patients with unresectable or locally advanced gastric cancer(GC).Postoperative complications,particularly those classified as Clavien-Dindo grade≥II,remain a major concern for surgeons.In recent years machine learning(ML)has emerged as a prominent approach for disease diagnosis and prediction.However,studies on both postoperative complications and ML in patients with GC receiving neoadjuvant therapy remain limited.AIM To develop an ML model to predict Clavien-Dindo grade≥II complications in patients with GC after neoadjuvant therapy and laparoscopic gastrectomy.METHODS Clinical data were collected from 455 patients with GC who underwent neoadjuvant therapy followed by laparoscopic gastrectomy at Peking Union Medical College Hospital(2014-2024).Potential predictors were identified through univariate analysis and least absolute shrinkage and selection operator regression.Six ML algorithms including XGBoost,random forest,neural network ensemble(NNE),logistic regression,GLMnet,and decision tree were trained and optimized using nested cross-validation.Model performance was evaluated using the area under the receiver operating characteristic curve,decision curve analysis,and calibration curves.RESULTS A total of 455 patients were included of whom 69(15.16%)developed Clavien-Dindo grade≥II complications.The predictive model was constructed using seven variables,including smoking status,Nutritional Risk Screening-2002 score,American Society of Anesthesiologists classification,neoadjuvant therapy,surgical approach,operating time,and intraoperative blood loss.Among the six models the NNE model outperformed the others,achieving the highest area under the receiver operating characteristic curve(0.789,0.739-0.840)and demonstrating superior discrimination,clinical utility,and calibration.CONCLUSION The NNE-based prediction model effectively identified patients with GC at high risk of Clavien-Dindo grade≥II complications after neoadjuvant therapy and laparoscopic gastrectomy.展开更多
The continuous emergence of new pollutants poses significant threats to both human health and ecological environments.Nontarget analysis based on mass spectrometry has become prevalent for detecting new pollutants due...The continuous emergence of new pollutants poses significant threats to both human health and ecological environments.Nontarget analysis based on mass spectrometry has become prevalent for detecting new pollutants due to its high throughput capabilities.However,structural elucidation remains a major challenge in nontarget analysis.Here,we review the implementation of machine learning techniques to accelerate nontarget structural elucidation,with particular focus on spectral library matching,structural database retrieval,and de novo structure generation.We investigated the design principles,technical characteristics,and comparative evaluation of these computational approaches.In addition,we show their applications in environmental nontarget analysis for new pollutant identification.Finally,we discuss the challenges of current approaches and the future development trends.This review aims to deepen the understanding of existing computational approaches,promote the application of machine learning techniques in nontarget identification,and facilitate the integration of artificial intelligence with environmental pollutant analysis.展开更多
基金supported by National Natural Science Foundation of China(62466045)Inner Mongolia Natural Science Foundation Project(2021LHMS06003)Inner Mongolia University Basic Research Business Fee Project(114).
文摘Graph Federated Learning(GFL)has shown great potential in privacy protection and distributed intelligence through distributed collaborative training of graph-structured data without sharing raw information.However,existing GFL approaches often lack the capability for comprehensive feature extraction and adaptive optimization,particularly in non-independent and identically distributed(NON-IID)scenarios where balancing global structural understanding and local node-level detail remains a challenge.To this end,this paper proposes a novel framework called GFL-SAR(Graph Federated Collaborative Learning Framework Based on Structural Amplification and Attention Refinement),which enhances the representation learning capability of graph data through a dual-branch collaborative design.Specifically,we propose the Structural Insight Amplifier(SIA),which utilizes an improved Graph Convolutional Network(GCN)to strengthen structural awareness and improve modeling of topological patterns.In parallel,we propose the Attentive Relational Refiner(ARR),which employs an enhanced Graph Attention Network(GAT)to perform fine-grained modeling of node relationships and neighborhood features,thereby improving the expressiveness of local interactions and preserving critical contextual information.GFL-SAR effectively integrates multi-scale features from every branch via feature fusion and federated optimization,thereby addressing existing GFL limitations in structural modeling and feature representation.Experiments on standard benchmark datasets including Cora,Citeseer,Polblogs,and Cora_ML demonstrate that GFL-SAR achieves superior performance in classification accuracy,convergence speed,and robustness compared to existing methods,confirming its effectiveness and generalizability in GFL tasks.
基金The Key R&D Program of Hunan Province(Grant No.2025AQ2024)of the Department of Science and Technology of Hunan Province.Distinguished Young Scientists Fund(Grant No.24B0446)of Hunan Education Department.
文摘Internet of Things(IoTs)devices are bringing about a revolutionary change our society by enabling connectivity regardless of time and location.However,The extensive deployment of these devices also makes them attractive victims for themalicious actions of adversaries.Within the spectrumof existing threats,Side-ChannelAttacks(SCAs)have established themselves as an effective way to compromise cryptographic implementations.These attacks exploit unintended,unintended physical leakage that occurs during the cryptographic execution of devices,bypassing the theoretical strength of the crypto design.In recent times,the advancement of deep learning has provided SCAs with a powerful ally.Well-trained deep-learningmodels demonstrate an exceptional capacity to identify correlations between side-channel measurements and sensitive data,thereby significantly enhancing such attacks.To further understand the security threats posed by deep-learning SCAs and to aid in formulating robust countermeasures in the future,this paper undertakes an exhaustive investigation of leading-edge SCAs targeting Advanced Encryption Standard(AES)implementations.The study specifically focuses on attacks that exploit power consumption and electromagnetic(EM)emissions as primary leakage sources,systematically evaluating the extent to which diverse deep learning techniques enhance SCAs acrossmultiple critical dimensions.These dimensions include:(i)the characteristics of publicly available datasets derived from various hardware and software platforms;(ii)the formalization of leakage models tailored to different attack scenarios;(iii)the architectural suitability and performance of state-of-the-art deep learning models.Furthermore,the survey provides a systematic synthesis of current research findings,identifies significant unresolved issues in the existing literature and suggests promising directions for future work,including cross-device attack transferability and the impact of quantum-classical hybrid computing on side-channel security.
基金the Collaborative Innovation Project of Shanghai,China for the financial support。
文摘Unmanned Aerial Vehicle(UAV)plays a prominent role in various fields,and autonomous navigation is a crucial component of UAV intelligence.Deep Reinforcement Learning(DRL)has expanded the research avenues for addressing challenges in autonomous navigation.Nonetheless,challenges persist,including getting stuck in local optima,consuming excessive computations during action space exploration,and neglecting deterministic experience.This paper proposes a noise-driven enhancement strategy.In accordance with the overall learning phases,a global noise control method is designed,while a differentiated local noise control method is developed by analyzing the exploration demands of four typical situations encountered by UAV during navigation.Both methods are integrated into a dual-model for noise control to regulate action space exploration.Furthermore,noise dual experience replay buffers are designed to optimize the rational utilization of both deterministic and noisy experience.In uncertain environments,based on the Twin Delay Deep Deterministic Policy Gradient(TD3)algorithm with Long Short-Term Memory(LSTM)network and Priority Experience Replay(PER),a Noise-Driven Enhancement Priority Memory TD3(NDE-PMTD3)is developed.We established a simulation environment to compare different algorithms,and the performance of the algorithms is analyzed in various scenarios.The training results indicate that the proposed algorithm accelerates the convergence speed and enhances the convergence stability.In test experiments,the proposed algorithm successfully and efficiently performs autonomous navigation tasks in diverse environments,demonstrating superior generalization results.
基金supported by the National Natural Science Foundation of China(No.22276139)the Shanghai’s Municipal State-owned Assets Supervision and Administration Commission(No.2022028).
文摘To better understand the migration behavior of plastic fragments in the environment,development of rapid non-destructive methods for in-situ identification and characterization of plastic fragments is necessary.However,most of the studies had focused only on colored plastic fragments,ignoring colorless plastic fragments and the effects of different environmental media(backgrounds),thus underestimating their abundance.To address this issue,the present study used near-infrared spectroscopy to compare the identification of colored and colorless plastic fragments based on partial least squares-discriminant analysis(PLS-DA),extreme gradient boost,support vector machine and random forest classifier.The effects of polymer color,type,thickness,and background on the plastic fragments classification were evaluated.PLS-DA presented the best and most stable outcome,with higher robustness and lower misclassification rate.All models frequently misinterpreted colorless plastic fragments and its background when the fragment thickness was less than 0.1mm.A two-stage modeling method,which first distinguishes the plastic types and then identifies colorless plastic fragments that had been misclassified as background,was proposed.The method presented an accuracy higher than 99%in different backgrounds.In summary,this study developed a novel method for rapid and synchronous identification of colored and colorless plastic fragments under complex environmental backgrounds.
文摘Solar cell defects exhibit significant variations and multiple types,with some defect data being difficult to acquire or having small scales,posing challenges in terms of small sample and small target in defect detection for solar cells.In order to address this issue,this paper proposes a multi-step approach for detecting the complex defects of solar cells.First,individual cell plates are extracted from electroluminescence images for block-by-block detection.Then,StyleGAN2-Ada is utilized for generative adversarial networks data augmentation to expand the number of defect samples in small sample defects.Finally,the fake dataset is combined with real dataset,and the improved YOLOv5 model is trained on this mixed dataset.Experimental results demonstrate that the proposed method achieves a superior performance in detecting the defects with small sample and small target,with the final recall rate reaching 99.7%,an increase of 3.9% compared with the unimproved model.Additionally,the precision and mean average precision are increased by 3.4% and 3.5%,respectively.Moreover,the experiments demonstrate that the improved network training on the mixed dataset can effectively enhance the detection performance of the model.The combination of these approaches significantly improves the network’s ability to detect solar cell defects.
基金funded by the China Chongqing Municipal Science and Technology Bureau,grant numbers CSTB2024TIAD-CYKJCXX0009,CSTB2024NSCQ-LZX0043,CSTB2022NSCQ-MSX0288Chongqing Municipal Commission of Housing and Urban-Rural Development,grant number CKZ2024-87+3 种基金the Chongqing University of Technology Graduate Education High-Quality Development Project,grant number gzlsz202401the Chongqing University of Technology—Chongqing LINGLUE Technology Co.,Ltd.Electronic Information(Artificial Intelligence)Graduate Joint Training Basethe Postgraduate Education and Teaching Reform Research Project in Chongqing,grant number yjg213116the Chongqing University of Technology-CISDI Chongqing Information Technology Co.,Ltd.Computer Technology Graduate Joint Training Base.
文摘Although conventional object detection methods achieve high accuracy through extensively annotated datasets,acquiring such large-scale labeled data remains challenging and cost-prohibitive in numerous real-world applications.Few-shot object detection presents a new research idea that aims to localize and classify objects in images using only limited annotated examples.However,the inherent challenge in few-shot object detection lies in the insufficient sample diversity to fully characterize the sample feature distribution,which consequently impacts model performance.Inspired by contrastive learning principles,we propose an Implicit Feature Contrastive Learning(IFCL)module to address this limitation and augment feature diversity for more robust representational learning.This module generates augmented support sample features in a mixed feature space and implicitly contrasts them with query Region of Interest(RoI)features.This approach facilitates more comprehensive learning of both intra-class feature similarity and inter-class feature diversity,thereby enhancing the model’s object classification and localization capabilities.Extensive experiments on PASCAL VOC show that our method achieves a respective improvement of 3.2%,1.8%,and 2.3%on 10-shot of three Novel Sets compared to the baseline model FPD.
基金funded by Hanshan Normal University School-Level Research Initiation Program(grant numbers QD202244QD2024207)+3 种基金the Guangdong Higher Education Society’s“Fourteenth Five-Year”Plan 2024 Higher Education Research(grant number 24GYB43)the 2024 Guangdong Provincial Undergraduate Teaching Quality and Teaching Reform Engineering Project:Excellence Program for Cultivating Publicly-Funded Pre-service Teachers for Primary Education in the Context of Rural Revitalizationthe Hanshan Normal University Guangdong East Regional Education Collaborative Innovation Research Centerfunded by these sources.
文摘This study utilized a sequential mediating model to examine the role of motivation to learn and transfer selfefficacy in the relationships between perceived content validity,mentoring function,continuous learning work culture and intention to transfer learning.The sample comprized 429 final-year apprentices in Guangdong province,China(females=69.9%,Engineering&Medicine=69%,mean age=20.99,SD=1.60).The apprentices completed standardized measures of motivation to learn,transfer self-efficacy perceived content validity,mentoring function,and continuous learning work culture.Structural equation modeling was used to analyze the data.Results showed perceived content validity,mentoring function,continuous learning culture to predict intention to transfer learning.Of these factors,perceived content validity was the strongest predictor of intention to transfer learning.Of these factors,perceived content validity was the most influential predictor of intention to transfer learning.The motivation to learn and transfer self-efficacy sequentially mediated the relationship between mentoring function and intention to learning transfer to be stronger than by either alone.Although perceived content validity and continuous learning culture exhibited no significant direct effects on intention to transfer learning,they demonstrated positive indirect associations with intention to transfer via motivation to learn and transfer self-efficacy.These study findings extend the applications of the learning transfer framework to individuals undergoing apprenticeship training which also would apply to other a long-term work-based learning programs.
文摘Hepatocellular carcinoma(HCC)remains a leading cause of cancer-related mortality globally,necessitating advanced diagnostic tools to improve early detection and personalized targeted therapy.This review synthesizes evidence on explainable ensemble learning approaches for HCC classification,emphasizing their integration with clinical workflows and multi-omics data.A systematic analysis[including datasets such as The Cancer Genome Atlas,Gene Expression Omnibus,and the Surveillance,Epidemiology,and End Results(SEER)datasets]revealed that explainable ensemble learning models achieve high diagnostic accuracy by combining clinical features,serum biomarkers such as alpha-fetoprotein,imaging features such as computed tomography and magnetic resonance imaging,and genomic data.For instance,SHapley Additive exPlanations(SHAP)-based random forests trained on NCBI GSE14520 microarray data(n=445)achieved 96.53%accuracy,while stacking ensembles applied to the SEER program data(n=1897)demonstrated an area under the receiver operating characteristic curve of 0.779 for mortality prediction.Despite promising results,challenges persist,including the computational costs of SHAP and local interpretable model-agnostic explanations analyses(e.g.,TreeSHAP requiring distributed computing for metabolomics datasets)and dataset biases(e.g.,SEER’s Western population dominance limiting generalizability).Future research must address inter-cohort heterogeneity,standardize explainability metrics,and prioritize lightweight surrogate models for resource-limited settings.This review presents the potential of explainable ensemble learning frameworks to bridge the gap between predictive accuracy and clinical interpretability,though rigorous validation in independent,multi-center cohorts is critical for real-world deployment.
基金supported by the National Natural Science Foundation of China under Grant 62373009.
文摘Indoor scene semantic segmentation is essential for enabling robots to understand and interact with their environments effectively.However,numerous challenges remain unresolved,particularly in single-robot systems,which often struggle with the complexity and variability of indoor scenes.To address these limitations,we introduce a novel multi-robot collaborative framework based on multiplex interactive learning(MPIL)in which each robot specialises in a distinct visual task within a unified multitask architecture.During training,the framework employs task-specific decoders and cross-task feature sharing to enhance collaborative optimisation.At inference time,robots operate independently with optimised models,enabling scalable,asynchronous and efficient deployment in real-world scenarios.Specifically,MPIL employs specially designed modules that integrate RGB and depth data,refine feature representations and facilitate the simultaneous execution of multiple tasks,such as instance segmentation,scene classification and semantic segmentation.By leveraging these modules,distinct agents within multi-robot systems can effectively handle specialised tasks,thereby enhancing the overall system's flexibility and adaptability.This collaborative effort maximises the strengths of each robot,resulting in a more comprehensive understanding of environments.Extensive experiments on two public benchmark datasets demonstrate MPIL's competitive performance compared to state-of-the-art approaches,highlighting the effectiveness and robustness of our multi-robot system in complex indoor environments.
基金supported by the Natural Science Foundation Project of Fujian Province,China(Grant No.2023J011439 and No.2019J01859).
文摘With the rapid urbanization and exponential population growth in China,two-wheeled vehicles have become a popular mode of transportation,particularly for short-distance travel.However,due to a lack of safety awareness,traffic violations by two-wheeled vehicle riders have become a widespread concern,contributing to urban traffic risks.Currently,significant human and material resources are being allocated to monitor and intercept non-compliant riders to ensure safe driving behavior.To enhance the safety,efficiency,and cost-effectiveness of traffic monitoring,automated detection systems based on image processing algorithms can be employed to identify traffic violations from eye-level video footage.In this study,we propose a robust detection algorithm specifically designed for two-wheeled vehicles,which serves as a fundamental step toward intelligent traffic monitoring.Our approach integrates a novel convolutional and attention mechanism to improve detection accuracy and efficiency.Additionally,we introduce a semi-supervised training strategy that leverages a large number of unlabeled images to enhance the model’s learning capability by extracting valuable background information.This method enables the model to generalize effectively to diverse urban environments and varying lighting conditions.We evaluate our proposed algorithm on a custom-built dataset,and experimental results demonstrate its superior performance,achieving an average precision(AP)of 95%and a recall(R)of 90.6%.Furthermore,the model maintains a computational efficiency of only 25.7 GFLOPs while achieving a high processing speed of 249 FPS,making it highly suitable for deployment on edge devices.Compared to existing detection methods,our approach significantly enhances the accuracy and robustness of two-wheeled vehicle identification while ensuring real-time performance.
基金funded by Scientific Research Deanship at University of Ha’il,Saudi Arabia,through project number GR-24009.
文摘Hepatitis is an infection that affects the liver through contaminated foods or blood transfusions,and it has many types,from normal to serious.Hepatitis is diagnosed through many blood tests and factors;Artificial Intelligence(AI)techniques have played an important role in early diagnosis and help physicians make decisions.This study evaluated the performance of Machine Learning(ML)algorithms on the hepatitis data set.The dataset contains missing values that have been processed and outliers removed.The dataset was counterbalanced by the Synthetic Minority Over-sampling Technique(SMOTE).The features of the data set were processed in two ways:first,the application of the Recursive Feature Elimination(RFE)algorithm to arrange the percentage of contribution of each feature to the diagnosis of hepatitis,then selection of important features using the t-distributed Stochastic Neighbor Embedding(t-SNE)and Principal Component Analysis(PCA)algorithms.Second,the SelectKBest function was applied to give scores for each attribute,followed by the t-SNE and PCA algorithms.Finally,the classification algorithms K-Nearest Neighbors(KNN),Support Vector Machine(SVM),Artificial Neural Network(ANN),Decision Tree(DT),and Random Forest(RF)were fed by the dataset after processing the features in different methods are RFE with t-SNE and PCA and SelectKBest with t-SNE and PCA).All algorithms yielded promising results for diagnosing hepatitis data sets.The RF with RFE and PCA methods achieved accuracy,Precision,Recall,and AUC of 97.18%,96.72%,97.29%,and 94.2%,respectively,during the training phase.During the testing phase,it reached accuracy,Precision,Recall,and AUC by 96.31%,95.23%,97.11%,and 92.67%,respectively.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.42005003 and 41475094)。
文摘Nonlinear science is a fundamental area of physics research that investigates complex dynamical systems which are often characterized by high sensitivity and nonlinear behaviors.Numerical simulations play a pivotal role in nonlinear science,serving as a critical tool for revealing the underlying principles governing these systems.In addition,they play a crucial role in accelerating progress across various fields,such as climate modeling,weather forecasting,and fluid dynamics.However,their high computational cost limits their application in high-precision or long-duration simulations.In this study,we propose a novel data-driven approach for simulating complex physical systems,particularly turbulent phenomena.Specifically,we develop an efficient surrogate model based on the wavelet neural operator(WNO).Experimental results demonstrate that the enhanced WNO model can accurately simulate small-scale turbulent flows while using lower computational costs.In simulations of complex physical fields,the improved WNO model outperforms established deep learning models,such as U-Net,Res Net,and the Fourier neural operator(FNO),in terms of accuracy.Notably,the improved WNO model exhibits exceptional generalization capabilities,maintaining stable performance across a wide range of initial conditions and high-resolution scenarios without retraining.This study highlights the significant potential of the enhanced WNO model for simulating complex physical systems,providing strong evidence to support the development of more efficient,scalable,and high-precision simulation techniques.
基金funded by the Scientific Funding for China Academy of Railway Sciences Corporation Limited,China(No.2023YJ125).
文摘Speech-face association aims to achieve identity matching between facial images and voice segments by aligning cross-modal features.Existing research primarily focuses on learning shared-space representations and computing one-to-one similarities between cross-modal sample pairs to establish their correlation.However,these approaches do not fully account for intra-class variations between the modalities or the many-to-many relationships among cross-modal samples,which are crucial for robust association modeling.To address these challenges,we propose a novel framework that leverages global information to align voice and face embeddings while effectively correlating identity information embedded in both modalities.First,we jointly pre-train face recognition and speaker recognition networks to encode discriminative features from facial images and voice segments.This shared pre-training step ensures the extraction of complementary identity information across modalities.Subsequently,we introduce a cross-modal simplex center loss,which aligns samples with identity centers located at the vertices of a regular simplex inscribed on a hypersphere.This design enforces an equidistant and balanced distribution of identity embeddings,reducing intra-class variations.Furthermore,we employ an improved triplet center loss that emphasizes hard sample mining and optimizes inter-class separability,enhancing the model’s ability to generalize across challenging scenarios.Extensive experiments validate the effectiveness of our framework,demonstrating superior performance across various speech-face association tasks,including matching,verification,and retrieval.Notably,in the challenging gender-constrained matching task,our method achieves a remarkable accuracy of 79.22%,significantly outperforming existing approaches.These results highlight the potential of the proposed framework to advance the state of the art in cross-modal identity association.
基金supported by the Natural Science Foundation of Fujian Province(No.2022J01755)。
文摘Objective:This study aimed to develop and validate a predictive model for postoperative complications in gastrointestinal cancer patients using a large multicenter database,based on machine learning algorithms.Methods:We analyzed the clinicopathological data of 3,926 gastrointestinal cancer patients from the Prevalence of Abdominal Complications After GastroEnterological surgery(PACAGE)database,covering 20 medical centers from December 2018 to December 2020.The predictive performance was evaluated using receiver operating characteristic(ROC)curves and Brier Score.Results:The patients were divided into gastric(2,271 cases)and colorectal cancer(1,655 cases)groups and further divided into training and external validation sets.The overall postoperative complication rates for gastric and colorectal cancer groups were 18.1%and 14.8%,respectively.The most common complication was the intraabdominal infection in both gastric and colorectal cancer groups.In the training set,the Random Forest(RF)model predicted the highest mean area under the curve(AUC)values for overall complications and different types of complications,in both the gastric cancer group and the colorectal cancer group,with similar results obtained in the external validation set.ROC curve analysis showed good predictive performance of the RF model for overall and infectious complications.An application-based clinical tool was developed for easy application in clinical practice.Conclusions:This model demonstrated good predictive performance for overall and infectious complications based on the multi-center database,supporting clinical decision-making and personalized treatment strategies.
基金supported by the National Natural Science Foundation of China(Grant Nos.62227821,62025503,and 62205199).
文摘To capture the nonlinear dynamics and gain evolution in chirped pulse amplification(CPA)systems,the split-step Fourier method and the fourth-order Runge–Kutta method are integrated to iteratively address the generalized nonlinear Schrödinger equation and the rate equations.However,this approach is burdened by substantial computational demands,resulting in significant time expenditures.In the context of intelligent laser optimization and inverse design,the necessity for numerous simulations further exacerbates this issue,highlighting the need for fast and accurate simulation methodologies.Here,we introduce an end-to-end model augmented with active learning(E2E-AL)with decent generalization through different dedicated embedding methods over various parameters.On an identical computational platform,the artificial intelligence–driven model is 2000 times faster than the conventional simulation method.Benefiting from the active learning strategy,the E2E-AL model achieves decent precision with only two-thirds of the training samples compared with the case without such a strategy.Furthermore,we demonstrate a multi-objective inverse design of the CPA systems enabled by the E2E-AL model.The E2E-AL framework manifests the potential of becoming a standard approach for the rapid and accurate modeling of ultrafast lasers and is readily extended to simulate other complex systems.
基金supported by the Postdoctoral Fellowship Program of CPSF,China(No.GZC20232015)the China Postdoctoral Science Foundation(No.2024M752499)+3 种基金the Postdoctoral Project of Hubei Province,China(No.2024HBBHCXA076)the Wuhan East Lake New Technology Development Zone Open List Project,China(No.2022KJB128)the National Natural Science Foundation of China(No.51875428)the Fundamental Research Funds for the Central Universities,China(No.104972024RSCbs0013)。
文摘The manufacturing processes of casing rings are prone to multi-type defects such as holes,cracks,and porosity,so ultrasonic testing is vital for the quality of aeroengine.Conventional ultrasonic testing requires manual analysis,which is susceptible to human omission,inconsistent results,and time-consumption.In this paper,a method for automated detection of defects is proposed for the ultrasonic Total Focusing Method(TFM)inspection of casing rings based on deep learning.First,the original datasets of defect images are established,and the Mask R-CNN is used to increase the number of defects in a single image.Then,the YOLOX-S-improved lightweight model is proposed,and the feature extraction network is replaced by Faster Net to reduce redundant computations.The Super-Resolution Generative Adversarial Network(SRGAN)and Convolutional Block Attention Module(CBAM)are integrated to improve the identification precision.Finally,a new test dataset is created by ultrasonic TFM inspection of an aeroengine casing ring.The results show that the mean of Average Precision(m AP)of the YOLOX-S-improved model reaches 99.17%,and the corresponding speed reaches 77.6 FPS.This study indicates that the YOLOX-S-improved model performs better than conventional object detection models.And the generalization ability of the proposed model is verified by ultrasonic B-scan images.
基金the National Natural Science Foundation of China(Grant No.42301002,and 52109118)Fujian Provincial Water Resources Science and Technology Project(Grant No.MSK202524)Guidance fund for Science and Technology Program,Fujian province(Grant No.2024Y0002).
文摘Landslide susceptibility evaluation plays an important role in disaster prevention and reduction.Feature-based transfer learning(TL)is an effective method for solving landslide susceptibility mapping(LSM)in target regions with no available samples.However,as the study area expands,the distribution of land-slide types and triggering mechanisms becomes more diverse,leading to performance degradation in models relying on landslide evaluation knowledge from a single source domain due to domain feature shift.To address this,this study proposes a Multi-source Domain Adaptation Convolutional Neural Network(MDACNN),which combines the landslide prediction knowledge learned from two source domains to perform cross-regional LSM in complex large-scale areas.The method is validated through case studies in three regions located in southeastern coastal China and compared with single-source domain TL models(TCA-based models).The results demonstrate that MDACNN effectively integrates transfer knowledge from multiple source domains to learn diverse landslide-triggering mechanisms,thereby significantly reducing prediction bias inherent to single-source domain TL models,achieving an average improvement of 16.58%across all metrics.Moreover,the landslide susceptibility maps gener-ated by MDACNN accurately quantify the spatial distribution of landslide risks in the target area,provid-ing a powerful scientific and technological tool for landslide disaster management and prevention.
基金Supported by the National Key Research and Development Program of China,No.2022YFF1100404the National High Level Hospital Clinical Research Funding of China,No.2022-PUMCH-B-005.
文摘BACKGROUND Neoadjuvant therapy prior to surgery plays a critical role in improving the prognosis of patients with unresectable or locally advanced gastric cancer(GC).Postoperative complications,particularly those classified as Clavien-Dindo grade≥II,remain a major concern for surgeons.In recent years machine learning(ML)has emerged as a prominent approach for disease diagnosis and prediction.However,studies on both postoperative complications and ML in patients with GC receiving neoadjuvant therapy remain limited.AIM To develop an ML model to predict Clavien-Dindo grade≥II complications in patients with GC after neoadjuvant therapy and laparoscopic gastrectomy.METHODS Clinical data were collected from 455 patients with GC who underwent neoadjuvant therapy followed by laparoscopic gastrectomy at Peking Union Medical College Hospital(2014-2024).Potential predictors were identified through univariate analysis and least absolute shrinkage and selection operator regression.Six ML algorithms including XGBoost,random forest,neural network ensemble(NNE),logistic regression,GLMnet,and decision tree were trained and optimized using nested cross-validation.Model performance was evaluated using the area under the receiver operating characteristic curve,decision curve analysis,and calibration curves.RESULTS A total of 455 patients were included of whom 69(15.16%)developed Clavien-Dindo grade≥II complications.The predictive model was constructed using seven variables,including smoking status,Nutritional Risk Screening-2002 score,American Society of Anesthesiologists classification,neoadjuvant therapy,surgical approach,operating time,and intraoperative blood loss.Among the six models the NNE model outperformed the others,achieving the highest area under the receiver operating characteristic curve(0.789,0.739-0.840)and demonstrating superior discrimination,clinical utility,and calibration.CONCLUSION The NNE-based prediction model effectively identified patients with GC at high risk of Clavien-Dindo grade≥II complications after neoadjuvant therapy and laparoscopic gastrectomy.
基金supported by the Key Research and Development Program of Zhejiang Province(2023C02037)the Strategic Priority Research Program of the Chinese Academy of Sciences(XDB0750100)+3 种基金the National Natural Science Foundation of China(22376092,U24A20512,22276090,and 22206075)Anhui Provincial Key Research and Development Project(2023t07020004)State Environmental Protection Key Laboratory of Dioxin Pollution Control Open Fund(2023)Jiangsu Provincial Administration for Market Regulation Science and Technology Program(KJ2024011)。
文摘The continuous emergence of new pollutants poses significant threats to both human health and ecological environments.Nontarget analysis based on mass spectrometry has become prevalent for detecting new pollutants due to its high throughput capabilities.However,structural elucidation remains a major challenge in nontarget analysis.Here,we review the implementation of machine learning techniques to accelerate nontarget structural elucidation,with particular focus on spectral library matching,structural database retrieval,and de novo structure generation.We investigated the design principles,technical characteristics,and comparative evaluation of these computational approaches.In addition,we show their applications in environmental nontarget analysis for new pollutant identification.Finally,we discuss the challenges of current approaches and the future development trends.This review aims to deepen the understanding of existing computational approaches,promote the application of machine learning techniques in nontarget identification,and facilitate the integration of artificial intelligence with environmental pollutant analysis.
