Face liveness detection is essential for securing biometric authentication systems against spoofing attacks,including printed photos,replay videos,and 3D masks.This study systematically evaluates pre-trained CNN model...Face liveness detection is essential for securing biometric authentication systems against spoofing attacks,including printed photos,replay videos,and 3D masks.This study systematically evaluates pre-trained CNN models—DenseNet201,VGG16,InceptionV3,ResNet50,VGG19,MobileNetV2,Xception,and InceptionResNetV2—leveraging transfer learning and fine-tuning to enhance liveness detection performance.The models were trained and tested on NUAA and Replay-Attack datasets,with cross-dataset generalization validated on SiW-MV2 to assess real-world adaptability.Performance was evaluated using accuracy,precision,recall,FAR,FRR,HTER,and specialized spoof detection metrics(APCER,NPCER,ACER).Fine-tuning significantly improved detection accuracy,with DenseNet201 achieving the highest performance(98.5%on NUAA,97.71%on Replay-Attack),while MobileNetV2 proved the most efficient model for real-time applications(latency:15 ms,memory usage:45 MB,energy consumption:30 mJ).A statistical significance analysis(paired t-tests,confidence intervals)validated these improvements.Cross-dataset experiments identified DenseNet201 and MobileNetV2 as the most generalizable architectures,with DenseNet201 achieving 86.4%accuracy on Replay-Attack when trained on NUAA,demonstrating robust feature extraction and adaptability.In contrast,ResNet50 showed lower generalization capabilities,struggling with dataset variability and complex spoofing attacks.These findings suggest that MobileNetV2 is well-suited for low-power applications,while DenseNet201 is ideal for high-security environments requiring superior accuracy.This research provides a framework for improving real-time face liveness detection,enhancing biometric security,and guiding future advancements in AI-driven anti-spoofing techniques.展开更多
The phenomenon of fear memory generalization can be defined as the expansion of an individual's originally specific fear responses to a similar yet genuinely harmless stimulus or situation subsequent to the occurr...The phenomenon of fear memory generalization can be defined as the expansion of an individual's originally specific fear responses to a similar yet genuinely harmless stimulus or situation subsequent to the occurrence of a traumatic event[1].Fear generalization within the normal range represents an adaptive evolutionary mechanism to facilitate prompt reactions to potential threats and to enhance the likelihood of survival.展开更多
The challenge of enhancing the generalization capacity of reinforcement learning(RL)agents remains a formidable obstacle.Existing RL methods,despite achieving superhuman performance on certain benchmarks,often struggl...The challenge of enhancing the generalization capacity of reinforcement learning(RL)agents remains a formidable obstacle.Existing RL methods,despite achieving superhuman performance on certain benchmarks,often struggle with this aspect.A potential reason is that the benchmarks used for training and evaluation may not adequately offer a diverse set of transferable tasks.Although recent studies have developed bench-marking environments to address this shortcoming,they typically fall short in providing tasks that both ensure a solid foundation for generalization and exhibit significant variability.To overcome these limitations,this work introduces the concept that‘objects are composed of more fundamental components’in environment design,as implemented in the proposed environment called summon the magic(StM).This environment generates tasks where objects are derived from extensible and shareable basic components,facilitating strategy reuse and enhancing generalization.Furthermore,two new metrics,adaptation sensitivity range(ASR)and parameter correlation coefficient(PCC),are proposed to better capture and evaluate the generalization process of RL agents.Experimental results show that increasing the number of basic components of the object reduces the proximal policy optimization(PPO)agent’s training-testing gap by 60.9%(in episode reward),significantly alleviating overfitting.Additionally,linear variations in other environmental factors,such as the training monster set proportion and the total number of basic components,uniformly decrease the gap by at least 32.1%.These results highlight StM’s effectiveness in benchmarking and probing the generalization capabilities of RL algorithms.展开更多
Using in-situ microstructure observations from 2010 to 2018,this study investigates the performance and generalization of machine learning models in parameterizing turbulent mixing in the northwestern South China Sea....Using in-situ microstructure observations from 2010 to 2018,this study investigates the performance and generalization of machine learning models in parameterizing turbulent mixing in the northwestern South China Sea.The results show that the data-driven extreme gradient boosting(XGBoost)performs better than the other four models,i.e.,random forest,neural network,linear regression and support vector machine regression.In order to further improve the generalization of machine learning-based parameterization method,we propose a physics-informed machine learning(PIML)that couples the MacKinnon-Gregg model(known as the MG model)and Osborn’s formula to the XGBoost model.The correlation coefficient(r)and root mean square error(RMSE)between the estimated and observed 1g(ε)(whereεdenotes the turbulent kinetic energy dissipation rate)from the PIML are improved by 14%and 16%,respectively.The results also show that PIML effectively improves the generalization of the XGBoost-based parameterization method,enhancing r and RMSE by 35%and 75%,respectively.展开更多
Automatically recognizing radar emitters from com-plex electromagnetic environments is important but non-trivial.Moreover,the changing electromagnetic environment results in inconsistent signal distribution in the rea...Automatically recognizing radar emitters from com-plex electromagnetic environments is important but non-trivial.Moreover,the changing electromagnetic environment results in inconsistent signal distribution in the real world,which makes the existing approaches perform poorly for recognition tasks in different scenes.In this paper,we propose a domain generaliza-tion framework is proposed to improve the adaptability of radar emitter signal recognition in changing environments.Specifically,we propose an end-to-end denoising based domain-invariant radar emitter recognition network(DDIRNet)consisting of a denoising model and a domain invariant representation learning model(IRLM),which mutually benefit from each other.For the signal denoising model,a loss function is proposed to match the feature of the radar signals and guarantee the effectiveness of the model.For the domain invariant representation learning model,contrastive learning is introduced to learn the cross-domain feature by aligning the source and unseen domain distri-bution.Moreover,we design a data augmentation method that improves the diversity of signal data for training.Extensive experiments on classification have shown that DDIRNet achieves up to 6.4%improvement compared with the state-of-the-art radar emitter recognition methods.The proposed method pro-vides a promising direction to solve the radar emitter signal recognition problem.展开更多
In actual industrial scenarios,the variation of operating conditions,the existence of data noise,and failure of measurement equipment will inevitably affect the distribution of perceptive data.Deep learning-based faul...In actual industrial scenarios,the variation of operating conditions,the existence of data noise,and failure of measurement equipment will inevitably affect the distribution of perceptive data.Deep learning-based fault diagnosis algorithms strongly rely on the assumption that source and target data are independent and identically distributed,and the learned diagnosis knowledge is difficult to generalize to out-of-distribution data.Domain generalization(DG)aims to achieve the generalization of arbitrary target domain data by using only limited source domain data for diagnosis model training.The research of DG for fault diagnosis has made remarkable progress in recent years and lots of achievements have been obtained.In this article,for the first time a comprehensive literature review on DG for fault diagnosis from a learning mechanism-oriented perspective is provided to summarize the development in recent years.Specifically,we first conduct a comprehensive review on existing methods based on the similarity of basic principles and design motivations.Then,the recent trend of DG for fault diagnosis is also analyzed.Finally,the existing problems and future prospect is performed.展开更多
In the realm of medical image segmentation,particularly in cardiac magnetic resonance imaging(MRI),achieving robust performance with limited annotated data is a significant challenge.Performance often degrades when fa...In the realm of medical image segmentation,particularly in cardiac magnetic resonance imaging(MRI),achieving robust performance with limited annotated data is a significant challenge.Performance often degrades when faced with testing scenarios from unknown domains.To address this problem,this paper proposes a novel semi-supervised approach for cardiac magnetic resonance image segmentation,aiming to enhance predictive capabilities and domain generalization(DG).This paper establishes an MT-like model utilizing pseudo-labeling and consistency regularization from semi-supervised learning,and integrates uncertainty estimation to improve the accuracy of pseudo-labels.Additionally,to tackle the challenge of domain generalization,a data manipulation strategy is introduced,extracting spatial and content-related information from images across different domains,enriching the dataset with a multi-domain perspective.This papers method is meticulously evaluated on the publicly available cardiac magnetic resonance imaging dataset M&Ms,validating its effectiveness.Comparative analyses against various methods highlight the out-standing performance of this papers approach,demonstrating its capability to segment cardiac magnetic resonance images in previously unseen domains even with limited annotated data.展开更多
This paper analyzes the generalization of minimax regret optimization(MRO)under distribution shift.A new learning framework is proposed by injecting the measure of con-ditional value at risk(CVaR)into MRO,and its gene...This paper analyzes the generalization of minimax regret optimization(MRO)under distribution shift.A new learning framework is proposed by injecting the measure of con-ditional value at risk(CVaR)into MRO,and its generalization error bound is established through the lens of uniform convergence analysis.The CVaR-based MRO can achieve the polynomial decay rate on the excess risk,which extends the generalization analysis associated with the expected risk to the risk-averse case.展开更多
This paper puts forword 11 cartographic generalization operator models and introduces their mathematical definitions,and thus a precise mathematical form and quantitative description has been given to these formerly l...This paper puts forword 11 cartographic generalization operator models and introduces their mathematical definitions,and thus a precise mathematical form and quantitative description has been given to these formerly limited qualitative concepts.The meaning of mathematical definition of operators for cartographic generalization and the application prospect in computer_aided cartography (CAC) is stated.ract The Jurassic strata in Jingyan of Sichuan containing the Mamenchinsaurus fauna are dealt with and divided in this paper. The Mamenchisaurus fossils contained there are compared in morphological features and stratigraphically with other types of the genus on by one. The comprehensive analysis show that the Mamenchisaurus fauna of Jingyan appeared in the early Late Jurassic and is primitive in morphology. The results of the morphological identification and stratigraphical study agree with each other. Their evolutionary processes in different apoches of the Late Jurassic also made clear. Key words Jingyan, Sichuan, Mamenchisaurus Fauna, stratigraphy, evolution展开更多
Generalization ability is a major problem encountered when using neural networks to find the structures in noisy data sets. Controlling the network complexity is a common method to solve this problem. In this paper, h...Generalization ability is a major problem encountered when using neural networks to find the structures in noisy data sets. Controlling the network complexity is a common method to solve this problem. In this paper, however, a novel additive penalty term which represents the features extracted by hidden units is introduced to eliminate the overtraining of multilayer feedfoward networks. Computer simulations demonstrate that by using this unsupervised fashion penalty term, the generalization ability is greatly improved.展开更多
This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that th...This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that the outputs of the output layer in the FNNs for classification correspond to the estimates of posteriori probability of the input pattern samples with desired outputs 1 or 0. The theorem for the generalized kernel function in the radial basis function networks (RBFN) is given. For an 2-layer perceptron network (2-LPN). an idea of using extended samples to improve generalization capability is proposed. Finally. the experimental results of radar target classification are given to verify the generaliztion capability of the RBFNs.展开更多
Accurate state of health(SOH)estimation is essential for the safe and reliable operation of lithium-ion batteries.However,existing methods face significant challenges,primarily because they rely on complete charge–di...Accurate state of health(SOH)estimation is essential for the safe and reliable operation of lithium-ion batteries.However,existing methods face significant challenges,primarily because they rely on complete charge–discharge cycles and fixed-form physical constraints,which limit adaptability to different chemistries and real-world conditions.To address these issues,this study proposes an approach that extracts features from segmented state of charge(SOC)intervals and integrates them into an enhanced physics-informed neural network(PINN).Specifically,voltage data within the 25%–75%SOC range during charging are used to derive statistical,time–frequency,and mechanism-based features that capture degradation trends.A hybrid PINN-Lasso-Transformer-BiLSTM architecture is developed,where Lasso regression enables sparse feature selection,and a nonlinear empirical degradation model is embedded as a learnable physical term within a dynamically scaled composite loss.This design adaptively balances data-driven accuracy with physical consistency,thereby enhancing estimation precision,robustness,and generalization.The results show that the proposed method outperforms conventional neural networks across four battery chemistries,achieving root mean square error and mean absolute error below 1%.Notably,features from partial charging segments exhibit higher robustness than those from full cycles.Furthermore,the model maintains strong performance under high temperatures and demonstrates excellent generalization capacity in transfer learning across chemistries,temperatures,and C-rates.This work establishes a scalable and interpretable solution for accurate SOH estimation under diverse practical operating conditions.展开更多
Clouds play an important role in global atmospheric energy and water vapor budgets, and the low cloud simulations suffer from large biases in many atmospheric general circulation models. In this study, cloud microphys...Clouds play an important role in global atmospheric energy and water vapor budgets, and the low cloud simulations suffer from large biases in many atmospheric general circulation models. In this study, cloud microphysical processes such as raindrop evaporation and cloud water accretion in a double-moment six-class cloud microphysics scheme were revised to enhance the simulation of low clouds using the Global-Regional Integrated Forecast System(GRIST)model. The validation of the revised scheme using a single-column version of the GRIST demonstrated a reasonable reduction in liquid water biases. The revised parameterization simulated medium-and low-level cloud fractions that were in better agreement with the observations than the original scheme. Long-term global simulations indicate the mitigation of the originally overestimated low-level cloud fraction and cloud-water mixing ratio in mid-to high-latitude regions,primarily owing to enhanced accretion processes and weakened raindrop evaporation. The reduced low clouds with the revised scheme showed better consistency with satellite observations, particularly at mid-and high-latitudes. Further improvements can be observed in the simulated cloud shortwave radiative forcing and vertical distribution of total cloud cover. Annual precipitation in mid-latitude regions has also improved, particularly over the oceans, with significantly increased large-scale and decreased convective precipitation.展开更多
Heterogeneous catalysis is a complex,multiscale phenomenon in which reactions occur at dynamically evolving surfaces.A longstanding goal is to probe these processes to distill design rules for novel catalytic material...Heterogeneous catalysis is a complex,multiscale phenomenon in which reactions occur at dynamically evolving surfaces.A longstanding goal is to probe these processes to distill design rules for novel catalytic materials,a capability that is essential to the transition toward a sustainable future[1–3].展开更多
Objective:Deep learning is employed increasingly in Gastroenterology(GI)endoscopy computer-aided diagnostics for polyp segmentation and multi-class disease detection.In the real world,implementation requires high accu...Objective:Deep learning is employed increasingly in Gastroenterology(GI)endoscopy computer-aided diagnostics for polyp segmentation and multi-class disease detection.In the real world,implementation requires high accuracy,therapeutically relevant explanations,strong calibration,domain generalization,and efficiency.Current Convolutional Neural Network(CNN)and transformer models compromise border precision and global context,generate attention maps that fail to align with expert reasoning,deteriorate during cross-center changes,and exhibit inadequate calibration,hence diminishing clinical trust.Methods:HMA-DER is a hierarchical multi-attention architecture that uses dilation-enhanced residual blocks and an explainability-aware Cognitive Alignment Score(CAS)regularizer to directly align attribution maps with reasoning signals from experts.The framework has additions that make it more resilient and a way to test for accuracy,macro-averaged F1 score,Area Under the Receiver Operating Characteristic Curve(AUROC),calibration(Expected Calibration Error(ECE),Brier Score),explainability(CAS,insertion/deletion AUC),cross-dataset transfer,and throughput.Results:HMA-DER gets Dice Similarity Coefficient scores of 89.5%and 86.0%on Kvasir-SEG and CVC-ClinicDB,beating the strongest baseline by+1.9 and+1.7 points.It gets 86.4%and 85.3%macro-F1 and 94.0%and 93.4%AUROC on HyperKvasir and GastroVision,which is better than the baseline by+1.4/+1.6macro-F1 and+1.2/+1.1AUROC.Ablation study shows that hierarchical attention gives the highest(+3.0),followed by CAS regularization(+2–3),dilatation(+1.5–2.0),and residual connections(+2–3).Cross-dataset validation demonstrates competitive zero-shot transfer(e.g.,KS→CVC Dice 82.7%),whereas multi-dataset training diminishes the domain gap,yielding an 88.1%primary-metric average.HMA-DER’s mixed-precision inference can handle 155 pictures per second,which helps with calibration.Conclusion:HMA-DER strikes a compromise between accuracy,explainability,robustness,and efficiency for the use of reliable GI computer-aided diagnosis in real-world clinical settings.展开更多
Making full use of the operator ordering method and the integration within ordered products,we obtain the analytical evolution law of a general quadratic state in the amplitude decay channel,and find that it is determ...Making full use of the operator ordering method and the integration within ordered products,we obtain the analytical evolution law of a general quadratic state in the amplitude decay channel,and find that it is determined not only by the decay rate of the amplitude decay channel but also by the coefficients of the initial quadratic state.Further,the quantum statistical properties of the initial quadratic state for amplitude decay are investigated via its average photon number and photon-counting distribution,and its Wigner distribution function evolution is discussed in detail.展开更多
BEIJING,Feb.22(Xinhua)-The second volume of a book about the interactions between Xi Jinping,General Secretary of the Communist Party of China Central Committee,and the people during his domestic inspection tours has ...BEIJING,Feb.22(Xinhua)-The second volume of a book about the interactions between Xi Jinping,General Secretary of the Communist Party of China Central Committee,and the people during his domestic inspection tours has been published by the China Women Publishing House.展开更多
Debates regarding the specific effects of general anesthesia on developing brains have persisted for over 30 years.A consensus has been reached that prolonged,repeated,high-dose exposure to anesthetics is associated w...Debates regarding the specific effects of general anesthesia on developing brains have persisted for over 30 years.A consensus has been reached that prolonged,repeated,high-dose exposure to anesthetics is associated with a higher incidence of deficits in behavior and executive function,while single exposure has a relatively minor effect on long-term neurological function.In this review,we summarize the dose-dependent neuroprotective or neurotoxic effects of gamma-aminobutyric acid type A receptor agonists,a representative group of sedatives,on developing brains or central nervous system diseases.Most preclinical research indicates that anesthetics have neurotoxic effects on the developing brain through various signal pathways.However,recent studies on low-dose anesthetics suggest that they may promote neurodevelopment during this critical period.These findings are incomprehensible for the general“dose-effect”principles of pharmacological research,which has attracted researchers'interest and led to the following questions:What is the threshold for the dual effects exerted by anesthetics such as propofol and sevoflurane on the developing brain?To what extent can their protective effects be maximized?What are the underlying mechanisms involved in these effects?Consequently,this issue has essentially become a“mathematical problem.”After summarizing the dose-dependent effects of gamma-aminobutyric acid type A receptor agonist sedatives in both the developing brain and the brains of patients with central nervous system diseases,we believe that all such anesthetics exhibit specific threshold effects unique to each drug.These effects range from neuroprotection to neurotoxicity,depending on different brain functional states.However,the exact values of the specific thresholds for different drugs in various brain states,as well as the underlying mechanisms explaining why these thresholds exist,remain unclear.Further in-depth exploration of these issues could significantly enhance the therapeutic translational value of these anesthetics.展开更多
基金funded by Centre for Advanced Modelling and Geospatial Information Systems(CAMGIS),Faculty of Engineering and IT,University of Technology Sydney.Moreover,Ongoing Research Funding Program(ORF-2025-14)King Saud University,Riyadh,Saudi Arabia,under Project ORF-2025-。
文摘Face liveness detection is essential for securing biometric authentication systems against spoofing attacks,including printed photos,replay videos,and 3D masks.This study systematically evaluates pre-trained CNN models—DenseNet201,VGG16,InceptionV3,ResNet50,VGG19,MobileNetV2,Xception,and InceptionResNetV2—leveraging transfer learning and fine-tuning to enhance liveness detection performance.The models were trained and tested on NUAA and Replay-Attack datasets,with cross-dataset generalization validated on SiW-MV2 to assess real-world adaptability.Performance was evaluated using accuracy,precision,recall,FAR,FRR,HTER,and specialized spoof detection metrics(APCER,NPCER,ACER).Fine-tuning significantly improved detection accuracy,with DenseNet201 achieving the highest performance(98.5%on NUAA,97.71%on Replay-Attack),while MobileNetV2 proved the most efficient model for real-time applications(latency:15 ms,memory usage:45 MB,energy consumption:30 mJ).A statistical significance analysis(paired t-tests,confidence intervals)validated these improvements.Cross-dataset experiments identified DenseNet201 and MobileNetV2 as the most generalizable architectures,with DenseNet201 achieving 86.4%accuracy on Replay-Attack when trained on NUAA,demonstrating robust feature extraction and adaptability.In contrast,ResNet50 showed lower generalization capabilities,struggling with dataset variability and complex spoofing attacks.These findings suggest that MobileNetV2 is well-suited for low-power applications,while DenseNet201 is ideal for high-security environments requiring superior accuracy.This research provides a framework for improving real-time face liveness detection,enhancing biometric security,and guiding future advancements in AI-driven anti-spoofing techniques.
基金supported by the Shandong Provincial Natural Science Foundation(ZR2022QH144).
文摘The phenomenon of fear memory generalization can be defined as the expansion of an individual's originally specific fear responses to a similar yet genuinely harmless stimulus or situation subsequent to the occurrence of a traumatic event[1].Fear generalization within the normal range represents an adaptive evolutionary mechanism to facilitate prompt reactions to potential threats and to enhance the likelihood of survival.
基金Supported by the National Key R&D Program of China(No.2023YFB4502200)the National Natural Science Foundation of China(No.U22A2028,61925208,62222214,62341411,62102398,62102399,U20A20227,62302478,62302482,62302483,62302480,62302481)+2 种基金the Strategic Priority Research Program of the Chinese Academy of Sciences(No.XDB0660300,XDB0660301,XDB0660302)the Chinese Academy of Sciences Project for Young Scientists in Basic Research(No.YSBR-029)the Youth Innovation Promotion Association of Chinese Academy of Sciences and Xplore Prize.
文摘The challenge of enhancing the generalization capacity of reinforcement learning(RL)agents remains a formidable obstacle.Existing RL methods,despite achieving superhuman performance on certain benchmarks,often struggle with this aspect.A potential reason is that the benchmarks used for training and evaluation may not adequately offer a diverse set of transferable tasks.Although recent studies have developed bench-marking environments to address this shortcoming,they typically fall short in providing tasks that both ensure a solid foundation for generalization and exhibit significant variability.To overcome these limitations,this work introduces the concept that‘objects are composed of more fundamental components’in environment design,as implemented in the proposed environment called summon the magic(StM).This environment generates tasks where objects are derived from extensible and shareable basic components,facilitating strategy reuse and enhancing generalization.Furthermore,two new metrics,adaptation sensitivity range(ASR)and parameter correlation coefficient(PCC),are proposed to better capture and evaluate the generalization process of RL agents.Experimental results show that increasing the number of basic components of the object reduces the proximal policy optimization(PPO)agent’s training-testing gap by 60.9%(in episode reward),significantly alleviating overfitting.Additionally,linear variations in other environmental factors,such as the training monster set proportion and the total number of basic components,uniformly decrease the gap by at least 32.1%.These results highlight StM’s effectiveness in benchmarking and probing the generalization capabilities of RL algorithms.
基金The National Science and Technology Major Project under contract No.2024YFC2817003the National Natural Science Foundation of China under contract Nos 42276019 and 42249911the Guangdong Ordinary University Innovation Team Project under contract No.2023KCXTD015.
文摘Using in-situ microstructure observations from 2010 to 2018,this study investigates the performance and generalization of machine learning models in parameterizing turbulent mixing in the northwestern South China Sea.The results show that the data-driven extreme gradient boosting(XGBoost)performs better than the other four models,i.e.,random forest,neural network,linear regression and support vector machine regression.In order to further improve the generalization of machine learning-based parameterization method,we propose a physics-informed machine learning(PIML)that couples the MacKinnon-Gregg model(known as the MG model)and Osborn’s formula to the XGBoost model.The correlation coefficient(r)and root mean square error(RMSE)between the estimated and observed 1g(ε)(whereεdenotes the turbulent kinetic energy dissipation rate)from the PIML are improved by 14%and 16%,respectively.The results also show that PIML effectively improves the generalization of the XGBoost-based parameterization method,enhancing r and RMSE by 35%and 75%,respectively.
基金supported by the National Natural Science Foundation of China(62101575)the Research Project of NUDT(ZK22-57)the Self-directed Project of State Key Laboratory of High Performance Computing(202101-16).
文摘Automatically recognizing radar emitters from com-plex electromagnetic environments is important but non-trivial.Moreover,the changing electromagnetic environment results in inconsistent signal distribution in the real world,which makes the existing approaches perform poorly for recognition tasks in different scenes.In this paper,we propose a domain generaliza-tion framework is proposed to improve the adaptability of radar emitter signal recognition in changing environments.Specifically,we propose an end-to-end denoising based domain-invariant radar emitter recognition network(DDIRNet)consisting of a denoising model and a domain invariant representation learning model(IRLM),which mutually benefit from each other.For the signal denoising model,a loss function is proposed to match the feature of the radar signals and guarantee the effectiveness of the model.For the domain invariant representation learning model,contrastive learning is introduced to learn the cross-domain feature by aligning the source and unseen domain distri-bution.Moreover,we design a data augmentation method that improves the diversity of signal data for training.Extensive experiments on classification have shown that DDIRNet achieves up to 6.4%improvement compared with the state-of-the-art radar emitter recognition methods.The proposed method pro-vides a promising direction to solve the radar emitter signal recognition problem.
基金supported by the National Natural Science Foundation of China(62322315,61873237)the Zhejiang Provincial Natural Science Foundation of China(LR22F030003)+1 种基金supported by Research Grant Council of Hong Kong(11201023,11202224)Hong Kong Innovation and Technology Commission(InnoHK Project CIMDA).
文摘In actual industrial scenarios,the variation of operating conditions,the existence of data noise,and failure of measurement equipment will inevitably affect the distribution of perceptive data.Deep learning-based fault diagnosis algorithms strongly rely on the assumption that source and target data are independent and identically distributed,and the learned diagnosis knowledge is difficult to generalize to out-of-distribution data.Domain generalization(DG)aims to achieve the generalization of arbitrary target domain data by using only limited source domain data for diagnosis model training.The research of DG for fault diagnosis has made remarkable progress in recent years and lots of achievements have been obtained.In this article,for the first time a comprehensive literature review on DG for fault diagnosis from a learning mechanism-oriented perspective is provided to summarize the development in recent years.Specifically,we first conduct a comprehensive review on existing methods based on the similarity of basic principles and design motivations.Then,the recent trend of DG for fault diagnosis is also analyzed.Finally,the existing problems and future prospect is performed.
基金Supported by the National Natural Science Foundation of China(No.62001313)the Key Project of Liaoning Provincial Department of Science and Technology(No.2021JH2/10300134,2022JH1/10500004)。
文摘In the realm of medical image segmentation,particularly in cardiac magnetic resonance imaging(MRI),achieving robust performance with limited annotated data is a significant challenge.Performance often degrades when faced with testing scenarios from unknown domains.To address this problem,this paper proposes a novel semi-supervised approach for cardiac magnetic resonance image segmentation,aiming to enhance predictive capabilities and domain generalization(DG).This paper establishes an MT-like model utilizing pseudo-labeling and consistency regularization from semi-supervised learning,and integrates uncertainty estimation to improve the accuracy of pseudo-labels.Additionally,to tackle the challenge of domain generalization,a data manipulation strategy is introduced,extracting spatial and content-related information from images across different domains,enriching the dataset with a multi-domain perspective.This papers method is meticulously evaluated on the publicly available cardiac magnetic resonance imaging dataset M&Ms,validating its effectiveness.Comparative analyses against various methods highlight the out-standing performance of this papers approach,demonstrating its capability to segment cardiac magnetic resonance images in previously unseen domains even with limited annotated data.
基金Supported by Education Science Planning Project of Hubei Province(2020GB198)Natural Science Foundation of Hubei Province(2023AFB523).
文摘This paper analyzes the generalization of minimax regret optimization(MRO)under distribution shift.A new learning framework is proposed by injecting the measure of con-ditional value at risk(CVaR)into MRO,and its generalization error bound is established through the lens of uniform convergence analysis.The CVaR-based MRO can achieve the polynomial decay rate on the excess risk,which extends the generalization analysis associated with the expected risk to the risk-averse case.
文摘This paper puts forword 11 cartographic generalization operator models and introduces their mathematical definitions,and thus a precise mathematical form and quantitative description has been given to these formerly limited qualitative concepts.The meaning of mathematical definition of operators for cartographic generalization and the application prospect in computer_aided cartography (CAC) is stated.ract The Jurassic strata in Jingyan of Sichuan containing the Mamenchinsaurus fauna are dealt with and divided in this paper. The Mamenchisaurus fossils contained there are compared in morphological features and stratigraphically with other types of the genus on by one. The comprehensive analysis show that the Mamenchisaurus fauna of Jingyan appeared in the early Late Jurassic and is primitive in morphology. The results of the morphological identification and stratigraphical study agree with each other. Their evolutionary processes in different apoches of the Late Jurassic also made clear. Key words Jingyan, Sichuan, Mamenchisaurus Fauna, stratigraphy, evolution
文摘Generalization ability is a major problem encountered when using neural networks to find the structures in noisy data sets. Controlling the network complexity is a common method to solve this problem. In this paper, however, a novel additive penalty term which represents the features extracted by hidden units is introduced to eliminate the overtraining of multilayer feedfoward networks. Computer simulations demonstrate that by using this unsupervised fashion penalty term, the generalization ability is greatly improved.
文摘This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that the outputs of the output layer in the FNNs for classification correspond to the estimates of posteriori probability of the input pattern samples with desired outputs 1 or 0. The theorem for the generalized kernel function in the radial basis function networks (RBFN) is given. For an 2-layer perceptron network (2-LPN). an idea of using extended samples to improve generalization capability is proposed. Finally. the experimental results of radar target classification are given to verify the generaliztion capability of the RBFNs.
基金supported by the Shanghai Pilot Program for Basic Research(22T01400100-18)the National Natural Science Foundation of China(22278127 and 12447149)+1 种基金the Fundamental Research Funds for the Central Universities(2022ZFJH004)the Postdoctoral Fellowship Program of CPSF(GZB20250159).
文摘Accurate state of health(SOH)estimation is essential for the safe and reliable operation of lithium-ion batteries.However,existing methods face significant challenges,primarily because they rely on complete charge–discharge cycles and fixed-form physical constraints,which limit adaptability to different chemistries and real-world conditions.To address these issues,this study proposes an approach that extracts features from segmented state of charge(SOC)intervals and integrates them into an enhanced physics-informed neural network(PINN).Specifically,voltage data within the 25%–75%SOC range during charging are used to derive statistical,time–frequency,and mechanism-based features that capture degradation trends.A hybrid PINN-Lasso-Transformer-BiLSTM architecture is developed,where Lasso regression enables sparse feature selection,and a nonlinear empirical degradation model is embedded as a learnable physical term within a dynamically scaled composite loss.This design adaptively balances data-driven accuracy with physical consistency,thereby enhancing estimation precision,robustness,and generalization.The results show that the proposed method outperforms conventional neural networks across four battery chemistries,achieving root mean square error and mean absolute error below 1%.Notably,features from partial charging segments exhibit higher robustness than those from full cycles.Furthermore,the model maintains strong performance under high temperatures and demonstrates excellent generalization capacity in transfer learning across chemistries,temperatures,and C-rates.This work establishes a scalable and interpretable solution for accurate SOH estimation under diverse practical operating conditions.
基金National Natural Science Foundation of China(42375153,42105153,42205157)Development of Science and Technology at Chinese Academy of Meteorological Sciences(2023KJ038)。
文摘Clouds play an important role in global atmospheric energy and water vapor budgets, and the low cloud simulations suffer from large biases in many atmospheric general circulation models. In this study, cloud microphysical processes such as raindrop evaporation and cloud water accretion in a double-moment six-class cloud microphysics scheme were revised to enhance the simulation of low clouds using the Global-Regional Integrated Forecast System(GRIST)model. The validation of the revised scheme using a single-column version of the GRIST demonstrated a reasonable reduction in liquid water biases. The revised parameterization simulated medium-and low-level cloud fractions that were in better agreement with the observations than the original scheme. Long-term global simulations indicate the mitigation of the originally overestimated low-level cloud fraction and cloud-water mixing ratio in mid-to high-latitude regions,primarily owing to enhanced accretion processes and weakened raindrop evaporation. The reduced low clouds with the revised scheme showed better consistency with satellite observations, particularly at mid-and high-latitudes. Further improvements can be observed in the simulated cloud shortwave radiative forcing and vertical distribution of total cloud cover. Annual precipitation in mid-latitude regions has also improved, particularly over the oceans, with significantly increased large-scale and decreased convective precipitation.
文摘Heterogeneous catalysis is a complex,multiscale phenomenon in which reactions occur at dynamically evolving surfaces.A longstanding goal is to probe these processes to distill design rules for novel catalytic materials,a capability that is essential to the transition toward a sustainable future[1–3].
文摘Objective:Deep learning is employed increasingly in Gastroenterology(GI)endoscopy computer-aided diagnostics for polyp segmentation and multi-class disease detection.In the real world,implementation requires high accuracy,therapeutically relevant explanations,strong calibration,domain generalization,and efficiency.Current Convolutional Neural Network(CNN)and transformer models compromise border precision and global context,generate attention maps that fail to align with expert reasoning,deteriorate during cross-center changes,and exhibit inadequate calibration,hence diminishing clinical trust.Methods:HMA-DER is a hierarchical multi-attention architecture that uses dilation-enhanced residual blocks and an explainability-aware Cognitive Alignment Score(CAS)regularizer to directly align attribution maps with reasoning signals from experts.The framework has additions that make it more resilient and a way to test for accuracy,macro-averaged F1 score,Area Under the Receiver Operating Characteristic Curve(AUROC),calibration(Expected Calibration Error(ECE),Brier Score),explainability(CAS,insertion/deletion AUC),cross-dataset transfer,and throughput.Results:HMA-DER gets Dice Similarity Coefficient scores of 89.5%and 86.0%on Kvasir-SEG and CVC-ClinicDB,beating the strongest baseline by+1.9 and+1.7 points.It gets 86.4%and 85.3%macro-F1 and 94.0%and 93.4%AUROC on HyperKvasir and GastroVision,which is better than the baseline by+1.4/+1.6macro-F1 and+1.2/+1.1AUROC.Ablation study shows that hierarchical attention gives the highest(+3.0),followed by CAS regularization(+2–3),dilatation(+1.5–2.0),and residual connections(+2–3).Cross-dataset validation demonstrates competitive zero-shot transfer(e.g.,KS→CVC Dice 82.7%),whereas multi-dataset training diminishes the domain gap,yielding an 88.1%primary-metric average.HMA-DER’s mixed-precision inference can handle 155 pictures per second,which helps with calibration.Conclusion:HMA-DER strikes a compromise between accuracy,explainability,robustness,and efficiency for the use of reliable GI computer-aided diagnosis in real-world clinical settings.
文摘Making full use of the operator ordering method and the integration within ordered products,we obtain the analytical evolution law of a general quadratic state in the amplitude decay channel,and find that it is determined not only by the decay rate of the amplitude decay channel but also by the coefficients of the initial quadratic state.Further,the quantum statistical properties of the initial quadratic state for amplitude decay are investigated via its average photon number and photon-counting distribution,and its Wigner distribution function evolution is discussed in detail.
文摘BEIJING,Feb.22(Xinhua)-The second volume of a book about the interactions between Xi Jinping,General Secretary of the Communist Party of China Central Committee,and the people during his domestic inspection tours has been published by the China Women Publishing House.
文摘Debates regarding the specific effects of general anesthesia on developing brains have persisted for over 30 years.A consensus has been reached that prolonged,repeated,high-dose exposure to anesthetics is associated with a higher incidence of deficits in behavior and executive function,while single exposure has a relatively minor effect on long-term neurological function.In this review,we summarize the dose-dependent neuroprotective or neurotoxic effects of gamma-aminobutyric acid type A receptor agonists,a representative group of sedatives,on developing brains or central nervous system diseases.Most preclinical research indicates that anesthetics have neurotoxic effects on the developing brain through various signal pathways.However,recent studies on low-dose anesthetics suggest that they may promote neurodevelopment during this critical period.These findings are incomprehensible for the general“dose-effect”principles of pharmacological research,which has attracted researchers'interest and led to the following questions:What is the threshold for the dual effects exerted by anesthetics such as propofol and sevoflurane on the developing brain?To what extent can their protective effects be maximized?What are the underlying mechanisms involved in these effects?Consequently,this issue has essentially become a“mathematical problem.”After summarizing the dose-dependent effects of gamma-aminobutyric acid type A receptor agonist sedatives in both the developing brain and the brains of patients with central nervous system diseases,we believe that all such anesthetics exhibit specific threshold effects unique to each drug.These effects range from neuroprotection to neurotoxicity,depending on different brain functional states.However,the exact values of the specific thresholds for different drugs in various brain states,as well as the underlying mechanisms explaining why these thresholds exist,remain unclear.Further in-depth exploration of these issues could significantly enhance the therapeutic translational value of these anesthetics.
