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
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 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
Zero-shot learning enables the recognition of new class samples by migrating models learned from semanticfeatures and existing sample features to things that have never been seen before. The problems of consistencyof ...Zero-shot learning enables the recognition of new class samples by migrating models learned from semanticfeatures and existing sample features to things that have never been seen before. The problems of consistencyof different types of features and domain shift problems are two of the critical issues in zero-shot learning. Toaddress both of these issues, this paper proposes a new modeling structure. The traditional approach mappedsemantic features and visual features into the same feature space;based on this, a dual discriminator approachis used in the proposed model. This dual discriminator approach can further enhance the consistency betweensemantic and visual features. At the same time, this approach can also align unseen class semantic features andtraining set samples, providing a portion of information about the unseen classes. In addition, a new feature fusionmethod is proposed in the model. This method is equivalent to adding perturbation to the seen class features,which can reduce the degree to which the classification results in the model are biased towards the seen classes.At the same time, this feature fusion method can provide part of the information of the unseen classes, improvingits classification accuracy in generalized zero-shot learning and reducing domain bias. The proposed method isvalidated and compared with othermethods on four datasets, and fromthe experimental results, it can be seen thatthe method proposed in this paper achieves promising results.展开更多
The interpretation of representations and generalization powers has been a long-standing challenge in the fields of machine learning(ML)and artificial intelligence.This study contributes to understanding the emergence...The interpretation of representations and generalization powers has been a long-standing challenge in the fields of machine learning(ML)and artificial intelligence.This study contributes to understanding the emergence of universal scaling laws in quantum-probabilistic ML.We consider the generative tensor network(GTN)in the form of a matrix-product state as an example and show that with an untrained GTN(such as a random TN state),the negative logarithmic likelihood(NLL)L generally increases linearly with the number of features M,that is,L≃kM+const.This is a consequence of the so-called“catastrophe of orthogonality,”which states that quantum many-body states tend to become exponentially orthogonal to each other as M increases.This study reveals that,while gaining information through training,the linear-scaling law is suppressed by a negative quadratic correction,leading to L≃βM−αM^(2)+const.The scaling coefficients exhibit logarithmic relationships with the number of training samples and quantum channelsχ.The emergence of a quadratic correction term in the NLL for the testing(training)set can be regarded as evidence of the generalization(representation)power of the GTN.Over-parameterization can be identified by the deviation in the values ofαbetween the training and testing sets while increasingχ.We further investigate how orthogonality in the quantum-feature map relates to the satisfaction of quantum-probabilistic interpretation and the representation and generalization powers of the GTN.Unveiling universal scaling laws in quantum-probabilistic ML would be a valuable step toward establishing a white-box ML scheme interpreted within the quantum-probabilistic framework.展开更多
BACKGROUND Currently,very few studies have examined the analgesic effectiveness and safety of dexmedetomidine-assisted intravenous-inhalation combined general anesthesia in laparoscopic minimally invasive surgery for ...BACKGROUND Currently,very few studies have examined the analgesic effectiveness and safety of dexmedetomidine-assisted intravenous-inhalation combined general anesthesia in laparoscopic minimally invasive surgery for inguinal hernia.AIM To investigate the analgesic effect and safety of dexmedetomidine-assisted intravenous-inhalation combined general anesthesia in laparoscopic minimally invasive surgery for inguinal hernia.METHODS In this retrospective study,94 patients scheduled for laparoscopic minimally invasive surgery for inguinal hernia,admitted to Yiwu Central Hospital between May 2022 and May 2023,were divided into a control group(inhalation combined general anesthesia)and a treatment group(dexmedetomidine-assisted intrave-nous-inhalation combined general anesthesia).Perioperative indicators,analgesic effect,preoperative and postoperative 24-hours blood pressure(BP)and heart rate(HR),stress indicators,immune function levels,and adverse reactions were com-pared between the two groups.RESULTS Baseline data,including age,hernia location,place of residence,weight,monthly income,education level,and underlying diseases,were not significantly different between the two groups,indicating comparability(P>0.05).No significant difference was found in operation time and anesthesia time between the two groups(P>0.05).However,the treatment group exhibited a shorter postoperative urinary catheter removal time and hospital stay than the control group(P<0.05).Preoperatively,no significant differences were found in the visual analog scale(VAS)scores between the two groups(P>0.05).However,at 12,18,and 24 hours postoper-atively,the treatment group had significantly lower VAS scores than the control group(P<0.05).Although no significant differences in preoperative hemodynamic indicators were found between the two groups(P>0.05),both groups experienced some extent of changes in postoperative HR,diastolic BP(DBP),and systolic BP(SBP).Nevertheless,the treatment group showed smaller changes in HR,DBP,and SBP than the control group(P<0.05).Preoperative immune function indicators showed no significant differences between the two groups(P>0.05).However,postoperatively,the treatment group demonstrated higher levels of CD3+,CD4+,and CD4+/CD8+and lower levels of CD8+than the control group(P<0.05).The rates of adverse reactions were 6.38%and 23.40%in the treatment and control groups,respectively,revealing a significant difference(χ2=5.371,P=0.020).CONCLUSION Dexmedetomidine-assisted intravenous-inhalation combined general anesthesia can promote early recovery of patients undergoing laparoscopic minimally invasive surgery for inguinal hernia.It ensures stable blood flow,improves postoperative analgesic effects,reduces postoperative pain intensity,alleviates stress response,improves immune function,facilitates anesthesia recovery,and enhances safety.展开更多
Neural Networks (NN) are the functional unit of Deep Learning and are known to mimic the behavior of the human brain to solve complex data-driven problems. Whenever we train our own neural networks, we need to take ca...Neural Networks (NN) are the functional unit of Deep Learning and are known to mimic the behavior of the human brain to solve complex data-driven problems. Whenever we train our own neural networks, we need to take care of something called the generalization of the neural network. The performance of Artificial Neural Networks (ANN) mostly depends upon its generalization capability. In this paper, we propose an innovative approach to enhance the generalization capability of artificial neural networks (ANN) using structural redundancy. A novel perspective on handling input data prototypes and their impact on the development of generalization, which could improve to ANN architectures accuracy and reliability is described.展开更多
Retinal blood vessel segmentation is crucial for diagnosing ocular and cardiovascular diseases.Although the introduction of U-Net in 2015 by Olaf Ronneberger significantly advanced this field,yet issues like limited t...Retinal blood vessel segmentation is crucial for diagnosing ocular and cardiovascular diseases.Although the introduction of U-Net in 2015 by Olaf Ronneberger significantly advanced this field,yet issues like limited training data,imbalance data distribution,and inadequate feature extraction persist,hindering both the segmentation performance and optimal model generalization.Addressing these critical issues,the DEFFA-Unet is proposed featuring an additional encoder to process domain-invariant pre-processed inputs,thereby improving both richer feature encoding and enhanced model generalization.A feature filtering fusion module is developed to ensure the precise feature filtering and robust hybrid feature fusion.In response to the task-specific need for higher precision where false positives are very costly,traditional skip connections are replaced with the attention-guided feature reconstructing fusion module.Additionally,innovative data augmentation and balancing methods are proposed to counter data scarcity and distribution imbalance,further boosting the robustness and generalization of the model.With a comprehensive suite of evaluation metrics,extensive validations on four benchmark datasets(DRIVE,CHASEDB1,STARE,and HRF)and an SLO dataset(IOSTAR),demonstrate the proposed method’s superiority over both baseline and state-of-the-art models.Particularly the proposed method significantly outperforms the compared methods in cross-validation model generalization.展开更多
This paper proposes a zero-shot based spatial recognition AI algorithm by fusing and developing multidimensional vision identification technology adapted to the situation in large indoor and underground spaces.With th...This paper proposes a zero-shot based spatial recognition AI algorithm by fusing and developing multidimensional vision identification technology adapted to the situation in large indoor and underground spaces.With the expansion of large shopping malls and underground urban spaces(UUS),there is an increasing need for new technologies that can quickly identify complex indoor structures and changes such as relocation,remodeling,and construction for the safety and management of citizens through the provision of the up-to-date indoor 3D site maps.The proposed algorithm utilizes data collected by an unmanned robot to create a 3D site map of the up-to-date indoor site and recognizes complex indoor spaces based on zero-shot learning.This research specifically addresses two major challenges:the difficulty of detecting walls and floors due to complex patterns and the difficulty of spatial perception due to unknown obstacles.The proposed algorithm addresses the limitations of the existing foundation model,detects floors and obstacles without expensive sensors,and improves the accuracy of spatial recognition by combining floor detection,vanishing point detection,and fusion obstacle detection algorithms.The experimental results show that the algorithm effectively detects the floor and obstacles in various indoor environments,with F1 scores of 0.96 and 0.93 in the floor detection and obstacle detection experiments,respectively.展开更多
The US 2024 general election ended with the Republican Party winning the presidential, House and Senate elections at the same time. In the presidential election, the Republican Party not only won more popular votes in...The US 2024 general election ended with the Republican Party winning the presidential, House and Senate elections at the same time. In the presidential election, the Republican Party not only won more popular votes in over 90% counties than in the 2020 general election, but also won seven highly contested swing States with greater edges. This also marks the first time since 2004 that the Republican Party has won a relative majority of popular votes in the presidential election.展开更多
With the availability of high-performance computing technology and the development of advanced numerical simulation methods, Computational Fluid Dynamics (CFD) is becoming more and more practical and efficient in engi...With the availability of high-performance computing technology and the development of advanced numerical simulation methods, Computational Fluid Dynamics (CFD) is becoming more and more practical and efficient in engineering. As one of the high-precision representative algorithms, the high-order Discontinuous Galerkin Method (DGM) has not only attracted widespread attention from scholars in the CFD research community, but also received strong development. However, when DGM is extended to high-speed aerodynamic flow field calculations, non-physical numerical Gibbs oscillations near shock waves often significantly affect the numerical accuracy and even cause calculation failure. Data driven approaches based on machine learning techniques can be used to learn the characteristics of Gibbs noise, which motivates us to use it in high-speed DG applications. To achieve this goal, labeled data need to be generated in order to train the machine learning models. This paper proposes a new method for denoising modeling of Gibbs phenomenon using a machine learning technique, the zero-shot learning strategy, to eliminate acquiring large amounts of CFD data. The model adopts a graph convolutional network combined with graph attention mechanism to learn the denoising paradigm from synthetic Gibbs noise data and generalize to DGM numerical simulation data. Numerical simulation results show that the Gibbs denoising model proposed in this paper can suppress the numerical oscillation near shock waves in the high-order DGM. Our work automates the extension of DGM to high-speed aerodynamic flow field calculations with higher generalization and lower cost.展开更多
Large language models(LLMs)have demonstrated remarkable generalization abilities across multiple tasks in natural language processing(NLP).For multi-step reasoning tasks,chain-of-thought(CoT)prompting facilitates step...Large language models(LLMs)have demonstrated remarkable generalization abilities across multiple tasks in natural language processing(NLP).For multi-step reasoning tasks,chain-of-thought(CoT)prompting facilitates step-by-step thinking,leading to improved performance.However,despite significant advancements in LLMs,current CoT prompting performs suboptimally on smaller-scale models that have fewer parameters.Additionally,the common paradigm of few-shot CoT prompting relies on a set of manual demonstrations,with performance contingent on the quality of these annotations and varying with task-specific requirements.To address these limitations,we propose a select-and-answer prompting method(SAP)to enhance language model performance on reasoning tasks without the need for manual demonstrations.This method comprises two primary steps:guiding the model to conduct preliminary analysis and generate several candidate answers based on the prompting;allowing the model to provide final answers derived from these candidate answers.The proposed prompting strategy is evaluated across two language models of varying sizes and six datasets.On ChatGLM-6B,SAP consistently outperforms few-shot CoT across all datasets.For GPT-3.5,SAP achieves comparable performance to few-shot CoT and outperforms zero-shot CoT in most cases.These experimental results indicate that SAP can significantly improve the accuracy of language models in reasoning tasks.展开更多
Digital twin shows broad application prospects in the aerospace field.This paper introduces a generalized satellite digital twin system in detail.With the innovative design concepts of modularization,generalization an...Digital twin shows broad application prospects in the aerospace field.This paper introduces a generalized satellite digital twin system in detail.With the innovative design concepts of modularization,generalization and modeling,on the one hand,the system has successfully achieved the reuse of software modules among different satellite models;on the other hand,it has achieved the reuse of software modules between the digital twin and the testing system,significantly improving the development efficiency of the digital twin system.The paper elaborates on the technical architecture and application fields of this digital twin system,and further prospects its future development.At the same time,through a real inorbit case,the engineering value of the digital twin system is strongly demonstrated.展开更多
Mingalarpar!On behalf of the Consulate-General of the Republic of the Union of Myanmar in Nanning,I would like to express my sincerest congratulations to CAEXPO on reaching the remarkable milestone of over 20 years—a...Mingalarpar!On behalf of the Consulate-General of the Republic of the Union of Myanmar in Nanning,I would like to express my sincerest congratulations to CAEXPO on reaching the remarkable milestone of over 20 years—an incredible journey filled with numerous achievements.展开更多
BACKGROUND The coronavirus disease 2019(COVID-19)outbreak lasted several months,having started in December 2019.This study aimed to report the impacts of various factors on the depression levels of the general public ...BACKGROUND The coronavirus disease 2019(COVID-19)outbreak lasted several months,having started in December 2019.This study aimed to report the impacts of various factors on the depression levels of the general public and ascertain how emotional measures could be affected by psychosocial factors during the COVID-19 pandemic.AIM To investigate the depression levels of the general public in China during the COVID-19 pandemic.METHODS A total of 2001 self-reported questionnaires about Beck Depression Inventory(BDI)were collected on August 22,2022 via the website.Each questionnaire included four levels of depression and other demographic information.The BDI scores and incidences of different depression levels were compared between various groups of respondents.χ2 analysis and the two-tailed t-test were used to assess categorical and continuous data,respectively.Multiple linear regressions and logistic regressions were employed for correlation analysis.RESULTS The averaged BDI score in this study was higher than that for the non-epidemic periods,as reported in previous studies.Even higher BDI scores and incidences of moderate and severe depression were recorded for people who were quarantined for suspected COVID-19 infection,compared to the respondents who were not quarantined.The participants who did not take protective measures were associated with higher BDI scores than those who made efforts to keep themselves relatively safer.Similarly,the people who did not return to work had higher BDI scores compared to those managed to.A significant association existed between the depression levels of the subgroups and each of the factors,except gender and location of residence.However,quarantine was the most relative predictor for depression levels,followed by failure to take preventive measures and losing a partner,either through divorce or death.CONCLUSION Based on these data,psychological interventions for the various subpopulations in the general public can be implemented during and after the COVID-19 pandemic.Other countries can also use the data as a reference.展开更多
Primary healthcare service is the first line of defense to guard the health of the nation,and traditional Chinese medicine(TCM),with its characteristics of“simplicity,testing and inexpensiveness,”holistic outlook,an...Primary healthcare service is the first line of defense to guard the health of the nation,and traditional Chinese medicine(TCM),with its characteristics of“simplicity,testing and inexpensiveness,”holistic outlook,and the concept of treating the disease before it occurs,has a unique advantage in primary healthcare and a great demand for it.This paper analyzes the core challenges facing the cultivation of general medicine talents in TCM colleges and universities,such as the disconnection between cultivation goals and grassroots,the misalignment between practical ability and grassroots demand,and the lack of career attraction.On this basis,it puts forward a systematic reform path with the core concept of“rooting at the grassroots,highlighting characteristics,and strengthening competence”to cultivate talents that meet grassroots needs,aiming to provide theoretical references for TCM colleges and universities to cultivate excellent TCM talents who are“able to go down to the grassroots,be useful,stay in the field,and have development”,and to provide theoretical reference for the training of excellent TCM talents.The aim is to provide a theoretical reference for Chinese medicine colleges to cultivate excellent Chinese medicine talents who can“get down,use,stay and develop,”and to help the construction of a healthy China.展开更多
The construction of new medicine is a strategic plan proposed by the Party and the state for the development of medical education in the new era,which brings new opportunities and challenges to the cultivation of gene...The construction of new medicine is a strategic plan proposed by the Party and the state for the development of medical education in the new era,which brings new opportunities and challenges to the cultivation of general medical talents.Based on the connotation of the new medical construction,we will promote the construction of a comprehensive medical talent training system.By creating a characteristic general education curriculum system,building a high-level clinical practice teaching base,creating an innovation and entrepreneurship education platform for the First Affiliated Hospital of Xi’an Medical University,and reforming and improving the internal incentive mechanism for teachers,we aim to cultivate comprehensive medical talents who are“useful,competent,capable,and able to stay,”and contribute to the construction of a healthy China.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(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Zero-shot learning enables the recognition of new class samples by migrating models learned from semanticfeatures and existing sample features to things that have never been seen before. The problems of consistencyof different types of features and domain shift problems are two of the critical issues in zero-shot learning. Toaddress both of these issues, this paper proposes a new modeling structure. The traditional approach mappedsemantic features and visual features into the same feature space;based on this, a dual discriminator approachis used in the proposed model. This dual discriminator approach can further enhance the consistency betweensemantic and visual features. At the same time, this approach can also align unseen class semantic features andtraining set samples, providing a portion of information about the unseen classes. In addition, a new feature fusionmethod is proposed in the model. This method is equivalent to adding perturbation to the seen class features,which can reduce the degree to which the classification results in the model are biased towards the seen classes.At the same time, this feature fusion method can provide part of the information of the unseen classes, improvingits classification accuracy in generalized zero-shot learning and reducing domain bias. The proposed method isvalidated and compared with othermethods on four datasets, and fromthe experimental results, it can be seen thatthe method proposed in this paper achieves promising results.
基金supported in part by the Beijing Natural Science Foundation (Grant No. 1232025)the Ministry of Education Key Laboratory of Quantum Physics and Photonic Quantum Information (Grant No. ZYGX2024K020)Academy for Multidisciplinary Studies, Capital Normal University.
文摘The interpretation of representations and generalization powers has been a long-standing challenge in the fields of machine learning(ML)and artificial intelligence.This study contributes to understanding the emergence of universal scaling laws in quantum-probabilistic ML.We consider the generative tensor network(GTN)in the form of a matrix-product state as an example and show that with an untrained GTN(such as a random TN state),the negative logarithmic likelihood(NLL)L generally increases linearly with the number of features M,that is,L≃kM+const.This is a consequence of the so-called“catastrophe of orthogonality,”which states that quantum many-body states tend to become exponentially orthogonal to each other as M increases.This study reveals that,while gaining information through training,the linear-scaling law is suppressed by a negative quadratic correction,leading to L≃βM−αM^(2)+const.The scaling coefficients exhibit logarithmic relationships with the number of training samples and quantum channelsχ.The emergence of a quadratic correction term in the NLL for the testing(training)set can be regarded as evidence of the generalization(representation)power of the GTN.Over-parameterization can be identified by the deviation in the values ofαbetween the training and testing sets while increasingχ.We further investigate how orthogonality in the quantum-feature map relates to the satisfaction of quantum-probabilistic interpretation and the representation and generalization powers of the GTN.Unveiling universal scaling laws in quantum-probabilistic ML would be a valuable step toward establishing a white-box ML scheme interpreted within the quantum-probabilistic framework.
文摘BACKGROUND Currently,very few studies have examined the analgesic effectiveness and safety of dexmedetomidine-assisted intravenous-inhalation combined general anesthesia in laparoscopic minimally invasive surgery for inguinal hernia.AIM To investigate the analgesic effect and safety of dexmedetomidine-assisted intravenous-inhalation combined general anesthesia in laparoscopic minimally invasive surgery for inguinal hernia.METHODS In this retrospective study,94 patients scheduled for laparoscopic minimally invasive surgery for inguinal hernia,admitted to Yiwu Central Hospital between May 2022 and May 2023,were divided into a control group(inhalation combined general anesthesia)and a treatment group(dexmedetomidine-assisted intrave-nous-inhalation combined general anesthesia).Perioperative indicators,analgesic effect,preoperative and postoperative 24-hours blood pressure(BP)and heart rate(HR),stress indicators,immune function levels,and adverse reactions were com-pared between the two groups.RESULTS Baseline data,including age,hernia location,place of residence,weight,monthly income,education level,and underlying diseases,were not significantly different between the two groups,indicating comparability(P>0.05).No significant difference was found in operation time and anesthesia time between the two groups(P>0.05).However,the treatment group exhibited a shorter postoperative urinary catheter removal time and hospital stay than the control group(P<0.05).Preoperatively,no significant differences were found in the visual analog scale(VAS)scores between the two groups(P>0.05).However,at 12,18,and 24 hours postoper-atively,the treatment group had significantly lower VAS scores than the control group(P<0.05).Although no significant differences in preoperative hemodynamic indicators were found between the two groups(P>0.05),both groups experienced some extent of changes in postoperative HR,diastolic BP(DBP),and systolic BP(SBP).Nevertheless,the treatment group showed smaller changes in HR,DBP,and SBP than the control group(P<0.05).Preoperative immune function indicators showed no significant differences between the two groups(P>0.05).However,postoperatively,the treatment group demonstrated higher levels of CD3+,CD4+,and CD4+/CD8+and lower levels of CD8+than the control group(P<0.05).The rates of adverse reactions were 6.38%and 23.40%in the treatment and control groups,respectively,revealing a significant difference(χ2=5.371,P=0.020).CONCLUSION Dexmedetomidine-assisted intravenous-inhalation combined general anesthesia can promote early recovery of patients undergoing laparoscopic minimally invasive surgery for inguinal hernia.It ensures stable blood flow,improves postoperative analgesic effects,reduces postoperative pain intensity,alleviates stress response,improves immune function,facilitates anesthesia recovery,and enhances safety.
文摘Neural Networks (NN) are the functional unit of Deep Learning and are known to mimic the behavior of the human brain to solve complex data-driven problems. Whenever we train our own neural networks, we need to take care of something called the generalization of the neural network. The performance of Artificial Neural Networks (ANN) mostly depends upon its generalization capability. In this paper, we propose an innovative approach to enhance the generalization capability of artificial neural networks (ANN) using structural redundancy. A novel perspective on handling input data prototypes and their impact on the development of generalization, which could improve to ANN architectures accuracy and reliability is described.
文摘Retinal blood vessel segmentation is crucial for diagnosing ocular and cardiovascular diseases.Although the introduction of U-Net in 2015 by Olaf Ronneberger significantly advanced this field,yet issues like limited training data,imbalance data distribution,and inadequate feature extraction persist,hindering both the segmentation performance and optimal model generalization.Addressing these critical issues,the DEFFA-Unet is proposed featuring an additional encoder to process domain-invariant pre-processed inputs,thereby improving both richer feature encoding and enhanced model generalization.A feature filtering fusion module is developed to ensure the precise feature filtering and robust hybrid feature fusion.In response to the task-specific need for higher precision where false positives are very costly,traditional skip connections are replaced with the attention-guided feature reconstructing fusion module.Additionally,innovative data augmentation and balancing methods are proposed to counter data scarcity and distribution imbalance,further boosting the robustness and generalization of the model.With a comprehensive suite of evaluation metrics,extensive validations on four benchmark datasets(DRIVE,CHASEDB1,STARE,and HRF)and an SLO dataset(IOSTAR),demonstrate the proposed method’s superiority over both baseline and state-of-the-art models.Particularly the proposed method significantly outperforms the compared methods in cross-validation model generalization.
基金supported by Kyonggi University Research Grant 2024.
文摘This paper proposes a zero-shot based spatial recognition AI algorithm by fusing and developing multidimensional vision identification technology adapted to the situation in large indoor and underground spaces.With the expansion of large shopping malls and underground urban spaces(UUS),there is an increasing need for new technologies that can quickly identify complex indoor structures and changes such as relocation,remodeling,and construction for the safety and management of citizens through the provision of the up-to-date indoor 3D site maps.The proposed algorithm utilizes data collected by an unmanned robot to create a 3D site map of the up-to-date indoor site and recognizes complex indoor spaces based on zero-shot learning.This research specifically addresses two major challenges:the difficulty of detecting walls and floors due to complex patterns and the difficulty of spatial perception due to unknown obstacles.The proposed algorithm addresses the limitations of the existing foundation model,detects floors and obstacles without expensive sensors,and improves the accuracy of spatial recognition by combining floor detection,vanishing point detection,and fusion obstacle detection algorithms.The experimental results show that the algorithm effectively detects the floor and obstacles in various indoor environments,with F1 scores of 0.96 and 0.93 in the floor detection and obstacle detection experiments,respectively.
文摘The US 2024 general election ended with the Republican Party winning the presidential, House and Senate elections at the same time. In the presidential election, the Republican Party not only won more popular votes in over 90% counties than in the 2020 general election, but also won seven highly contested swing States with greater edges. This also marks the first time since 2004 that the Republican Party has won a relative majority of popular votes in the presidential election.
基金co-supported by the Aeronautical Science Foundation of China(Nos.2018ZA52002,2019ZA052011).
文摘With the availability of high-performance computing technology and the development of advanced numerical simulation methods, Computational Fluid Dynamics (CFD) is becoming more and more practical and efficient in engineering. As one of the high-precision representative algorithms, the high-order Discontinuous Galerkin Method (DGM) has not only attracted widespread attention from scholars in the CFD research community, but also received strong development. However, when DGM is extended to high-speed aerodynamic flow field calculations, non-physical numerical Gibbs oscillations near shock waves often significantly affect the numerical accuracy and even cause calculation failure. Data driven approaches based on machine learning techniques can be used to learn the characteristics of Gibbs noise, which motivates us to use it in high-speed DG applications. To achieve this goal, labeled data need to be generated in order to train the machine learning models. This paper proposes a new method for denoising modeling of Gibbs phenomenon using a machine learning technique, the zero-shot learning strategy, to eliminate acquiring large amounts of CFD data. The model adopts a graph convolutional network combined with graph attention mechanism to learn the denoising paradigm from synthetic Gibbs noise data and generalize to DGM numerical simulation data. Numerical simulation results show that the Gibbs denoising model proposed in this paper can suppress the numerical oscillation near shock waves in the high-order DGM. Our work automates the extension of DGM to high-speed aerodynamic flow field calculations with higher generalization and lower cost.
基金National Natural Science Foundation of China(No.62176052)。
文摘Large language models(LLMs)have demonstrated remarkable generalization abilities across multiple tasks in natural language processing(NLP).For multi-step reasoning tasks,chain-of-thought(CoT)prompting facilitates step-by-step thinking,leading to improved performance.However,despite significant advancements in LLMs,current CoT prompting performs suboptimally on smaller-scale models that have fewer parameters.Additionally,the common paradigm of few-shot CoT prompting relies on a set of manual demonstrations,with performance contingent on the quality of these annotations and varying with task-specific requirements.To address these limitations,we propose a select-and-answer prompting method(SAP)to enhance language model performance on reasoning tasks without the need for manual demonstrations.This method comprises two primary steps:guiding the model to conduct preliminary analysis and generate several candidate answers based on the prompting;allowing the model to provide final answers derived from these candidate answers.The proposed prompting strategy is evaluated across two language models of varying sizes and six datasets.On ChatGLM-6B,SAP consistently outperforms few-shot CoT across all datasets.For GPT-3.5,SAP achieves comparable performance to few-shot CoT and outperforms zero-shot CoT in most cases.These experimental results indicate that SAP can significantly improve the accuracy of language models in reasoning tasks.
文摘Digital twin shows broad application prospects in the aerospace field.This paper introduces a generalized satellite digital twin system in detail.With the innovative design concepts of modularization,generalization and modeling,on the one hand,the system has successfully achieved the reuse of software modules among different satellite models;on the other hand,it has achieved the reuse of software modules between the digital twin and the testing system,significantly improving the development efficiency of the digital twin system.The paper elaborates on the technical architecture and application fields of this digital twin system,and further prospects its future development.At the same time,through a real inorbit case,the engineering value of the digital twin system is strongly demonstrated.
文摘Mingalarpar!On behalf of the Consulate-General of the Republic of the Union of Myanmar in Nanning,I would like to express my sincerest congratulations to CAEXPO on reaching the remarkable milestone of over 20 years—an incredible journey filled with numerous achievements.
文摘BACKGROUND The coronavirus disease 2019(COVID-19)outbreak lasted several months,having started in December 2019.This study aimed to report the impacts of various factors on the depression levels of the general public and ascertain how emotional measures could be affected by psychosocial factors during the COVID-19 pandemic.AIM To investigate the depression levels of the general public in China during the COVID-19 pandemic.METHODS A total of 2001 self-reported questionnaires about Beck Depression Inventory(BDI)were collected on August 22,2022 via the website.Each questionnaire included four levels of depression and other demographic information.The BDI scores and incidences of different depression levels were compared between various groups of respondents.χ2 analysis and the two-tailed t-test were used to assess categorical and continuous data,respectively.Multiple linear regressions and logistic regressions were employed for correlation analysis.RESULTS The averaged BDI score in this study was higher than that for the non-epidemic periods,as reported in previous studies.Even higher BDI scores and incidences of moderate and severe depression were recorded for people who were quarantined for suspected COVID-19 infection,compared to the respondents who were not quarantined.The participants who did not take protective measures were associated with higher BDI scores than those who made efforts to keep themselves relatively safer.Similarly,the people who did not return to work had higher BDI scores compared to those managed to.A significant association existed between the depression levels of the subgroups and each of the factors,except gender and location of residence.However,quarantine was the most relative predictor for depression levels,followed by failure to take preventive measures and losing a partner,either through divorce or death.CONCLUSION Based on these data,psychological interventions for the various subpopulations in the general public can be implemented during and after the COVID-19 pandemic.Other countries can also use the data as a reference.
文摘Primary healthcare service is the first line of defense to guard the health of the nation,and traditional Chinese medicine(TCM),with its characteristics of“simplicity,testing and inexpensiveness,”holistic outlook,and the concept of treating the disease before it occurs,has a unique advantage in primary healthcare and a great demand for it.This paper analyzes the core challenges facing the cultivation of general medicine talents in TCM colleges and universities,such as the disconnection between cultivation goals and grassroots,the misalignment between practical ability and grassroots demand,and the lack of career attraction.On this basis,it puts forward a systematic reform path with the core concept of“rooting at the grassroots,highlighting characteristics,and strengthening competence”to cultivate talents that meet grassroots needs,aiming to provide theoretical references for TCM colleges and universities to cultivate excellent TCM talents who are“able to go down to the grassroots,be useful,stay in the field,and have development”,and to provide theoretical reference for the training of excellent TCM talents.The aim is to provide a theoretical reference for Chinese medicine colleges to cultivate excellent Chinese medicine talents who can“get down,use,stay and develop,”and to help the construction of a healthy China.
基金2024 Education and Teaching Reform Research Project of Xi’an Medical University(JG2024-04):Research on the Training System of Applied,Compound,and Innovative Talents in General Practice under the Background of New Medicine2024 Innovation and Entrepreneurship Education Reform Special Project of Xi’an Medical University(2024CCJG-01):Research on the Construction of Innovation and Entrepreneurship Talent Training Model Based on the“Innovation and Entrepreneurship Education Platform”。
文摘The construction of new medicine is a strategic plan proposed by the Party and the state for the development of medical education in the new era,which brings new opportunities and challenges to the cultivation of general medical talents.Based on the connotation of the new medical construction,we will promote the construction of a comprehensive medical talent training system.By creating a characteristic general education curriculum system,building a high-level clinical practice teaching base,creating an innovation and entrepreneurship education platform for the First Affiliated Hospital of Xi’an Medical University,and reforming and improving the internal incentive mechanism for teachers,we aim to cultivate comprehensive medical talents who are“useful,competent,capable,and able to stay,”and contribute to the construction of a healthy China.
