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
Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion Encoder-Decode...Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion Encoder-Decoder (ACSF-ED) network to predict the action and locate the object efficiently. In the Adaptive Cross-Scale Fusion Spatio-Temporal Encoder (ACSF ST-Encoder), the Asymptotic Cross-scale Feature-fusion Module (ACCFM) is designed to address the issue of information degradation caused by the propagation of high-level semantic information, thereby extracting high-quality multi-scale features to provide superior features for subsequent spatio-temporal information modeling. Within the Shared-Head Decoder structure, a shared classification and regression detection head is constructed. A multi-constraint loss function composed of one-to-one, one-to-many, and contrastive denoising losses is designed to address the problem of insufficient constraint force in predicting results with traditional methods. This loss function enhances the accuracy of model classification predictions and improves the proximity of regression position predictions to ground truth objects. The proposed method model is evaluated on the popular dataset UCF101-24 and JHMDB-21. Experimental results demonstrate that the proposed method achieves an accuracy of 81.52% on the Frame-mAP metric, surpassing current existing methods.展开更多
In tissue engineering(TE),tissue-inducing scaffolds are a promising solution for organ and tissue repair owing to their ability to attract stem cells in vivo,thereby inducing endogenous tissue regeneration through top...In tissue engineering(TE),tissue-inducing scaffolds are a promising solution for organ and tissue repair owing to their ability to attract stem cells in vivo,thereby inducing endogenous tissue regeneration through topological cues.An ideal TE scaffold should possess biomimetic cross-scale structures,similar to that of natural extracellular matrices,at the nano-to macro-scale level.Although freeform fabrication of TE scaffolds can be achieved through 3D printing,this method is limited in simultaneously building multiscale structures.To address this challenge,low-temperature fields were adopted in the traditional fabrication processes,such as casting and 3D printing.Ice crystals grow during scaffold fabrication and act as a template to control the nano-and micro-structures.These microstructures can be optimized by adjusting various parameters,such as the direction and magnitude of the low-temperature field.By preserving the macro-features fabricated using traditional methods,additional micro-structures with smaller scales can be incorporated simultaneously,realizing cross-scale structures that provide a better mimic of natural organs and tissues.In this paper,we present a state-of-the-art review of three low-temperature-field-assisted fabrication methods—freeze casting,cryogenic3D printing,and freeze spinning.Fundamental working principles,fabrication setups,processes,and examples of biomedical applications are introduced.The challenges and outlook for low-temperature-assisted fabrication are also discussed.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
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
Global and local modeling is essential for image super-resolution tasks.However,current efforts often lack explicit consideration of the cross-scale knowledge in large-scale earth observation scenarios,resulting in su...Global and local modeling is essential for image super-resolution tasks.However,current efforts often lack explicit consideration of the cross-scale knowledge in large-scale earth observation scenarios,resulting in suboptimal single-scale representations in global and local modeling.The key motivation of this work is inspired by two observations:1)There exists hierarchical features at the local and global regions in remote sensing images,and 2)they exhibit scale variation of similar ground objects(e.g.cross-scale similarity).In light of these,this paper presents an effective method to grasp the global and local image hierarchies by systematically exploring the cross-scale correlation.Specifically,we developed a Cross-scale Self-Attention(CSA)to model the global features,which introduces an auxiliary token space to calculate cross-scale self-attention matrices,thus exploring global dependency from diverse token scales.To extract the cross-scale localities,a Cross-scale Channel Attention(CCA)is devised,where multi-scale features are explored and progressively incorporated into an enriched feature.Moreover,by hierarchically deploying CSA and CCA into transformer groups,the proposed Cross-scale Hierarchical Transformer(CHT)can effectively explore cross-scale representations in remote sensing images,leading to a favorable reconstruction performance.Comprehensive experiments and analysis on four remote sensing datasets have demonstrated the superiority of CHT in both simulated and real-world remote sensing scenes.In particular,our CHT outperforms the state-of-the-art approach(TransENet)in terms of PSNR by 0.11 dB on average,but only accounts for 54.8%of its parameters.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
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
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
The paper is devoted to the study of the gravitational collapse within the framework of the spherically symmetric problem in the Newton theory and general relativity on the basis of the pressure-free model of the cont...The paper is devoted to the study of the gravitational collapse within the framework of the spherically symmetric problem in the Newton theory and general relativity on the basis of the pressure-free model of the continuum. In application to the Newton gravitation theory, the analysis consists of three stages. First, we assume that the gravitational force is determined by the initial sphere radius and constant density and does not change in the process of the sphere collapse. The obtained analytical solution allows us to find the collapse time in the first approximation. Second, we construct the step-by-step process in which the gravitational force at a given time moment depends on the current sphere radius and density. The obtained numerical solution specifies the collapse time depending on the number of steps. Third, we find the exact value of the collapse time which is the limit of the step-by-step solutions and study the collapse and the expansion processes in the Newton theory. In application to general relativity, we use the space model corresponding to the special four-dimensional space which is Euclidean with respect to space coordinates and Riemannian with respect to the time coordinate only. The obtained solution specifies two possible scenarios. First, sphere contraction results in the infinitely high density with the finite collapse time, which does not coincide with the conventional result corresponding to the Schwarzschild geometry. Second, sphere expansion with the velocity which increases with a distance from the sphere center and decreases with time.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support for this work was supported by Key Lab of Intelligent and Green Flexographic Printing under Grant ZBKT202301.
文摘Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion Encoder-Decoder (ACSF-ED) network to predict the action and locate the object efficiently. In the Adaptive Cross-Scale Fusion Spatio-Temporal Encoder (ACSF ST-Encoder), the Asymptotic Cross-scale Feature-fusion Module (ACCFM) is designed to address the issue of information degradation caused by the propagation of high-level semantic information, thereby extracting high-quality multi-scale features to provide superior features for subsequent spatio-temporal information modeling. Within the Shared-Head Decoder structure, a shared classification and regression detection head is constructed. A multi-constraint loss function composed of one-to-one, one-to-many, and contrastive denoising losses is designed to address the problem of insufficient constraint force in predicting results with traditional methods. This loss function enhances the accuracy of model classification predictions and improves the proximity of regression position predictions to ground truth objects. The proposed method model is evaluated on the popular dataset UCF101-24 and JHMDB-21. Experimental results demonstrate that the proposed method achieves an accuracy of 81.52% on the Frame-mAP metric, surpassing current existing methods.
基金National Natural Science Foundation Council of China(Grant No.52305359)Hubei Provincial Natural Science Foundation of China(Grant No.2023AFB141)National Medical Products Administration Key Laboratory for Dental Materials(PKUSS20240401)。
文摘In tissue engineering(TE),tissue-inducing scaffolds are a promising solution for organ and tissue repair owing to their ability to attract stem cells in vivo,thereby inducing endogenous tissue regeneration through topological cues.An ideal TE scaffold should possess biomimetic cross-scale structures,similar to that of natural extracellular matrices,at the nano-to macro-scale level.Although freeform fabrication of TE scaffolds can be achieved through 3D printing,this method is limited in simultaneously building multiscale structures.To address this challenge,low-temperature fields were adopted in the traditional fabrication processes,such as casting and 3D printing.Ice crystals grow during scaffold fabrication and act as a template to control the nano-and micro-structures.These microstructures can be optimized by adjusting various parameters,such as the direction and magnitude of the low-temperature field.By preserving the macro-features fabricated using traditional methods,additional micro-structures with smaller scales can be incorporated simultaneously,realizing cross-scale structures that provide a better mimic of natural organs and tissues.In this paper,we present a state-of-the-art review of three low-temperature-field-assisted fabrication methods—freeze casting,cryogenic3D printing,and freeze spinning.Fundamental working principles,fabrication setups,processes,and examples of biomedical applications are introduced.The challenges and outlook for low-temperature-assisted fabrication are also discussed.
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.
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.
基金supported in part by the National Natural Science Foundation of China[grant numbers 42230108,and 61971319].
文摘Global and local modeling is essential for image super-resolution tasks.However,current efforts often lack explicit consideration of the cross-scale knowledge in large-scale earth observation scenarios,resulting in suboptimal single-scale representations in global and local modeling.The key motivation of this work is inspired by two observations:1)There exists hierarchical features at the local and global regions in remote sensing images,and 2)they exhibit scale variation of similar ground objects(e.g.cross-scale similarity).In light of these,this paper presents an effective method to grasp the global and local image hierarchies by systematically exploring the cross-scale correlation.Specifically,we developed a Cross-scale Self-Attention(CSA)to model the global features,which introduces an auxiliary token space to calculate cross-scale self-attention matrices,thus exploring global dependency from diverse token scales.To extract the cross-scale localities,a Cross-scale Channel Attention(CCA)is devised,where multi-scale features are explored and progressively incorporated into an enriched feature.Moreover,by hierarchically deploying CSA and CCA into transformer groups,the proposed Cross-scale Hierarchical Transformer(CHT)can effectively explore cross-scale representations in remote sensing images,leading to a favorable reconstruction performance.Comprehensive experiments and analysis on four remote sensing datasets have demonstrated the superiority of CHT in both simulated and real-world remote sensing scenes.In particular,our CHT outperforms the state-of-the-art approach(TransENet)in terms of PSNR by 0.11 dB on average,but only accounts for 54.8%of its parameters.
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.
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.
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.
文摘The paper is devoted to the study of the gravitational collapse within the framework of the spherically symmetric problem in the Newton theory and general relativity on the basis of the pressure-free model of the continuum. In application to the Newton gravitation theory, the analysis consists of three stages. First, we assume that the gravitational force is determined by the initial sphere radius and constant density and does not change in the process of the sphere collapse. The obtained analytical solution allows us to find the collapse time in the first approximation. Second, we construct the step-by-step process in which the gravitational force at a given time moment depends on the current sphere radius and density. The obtained numerical solution specifies the collapse time depending on the number of steps. Third, we find the exact value of the collapse time which is the limit of the step-by-step solutions and study the collapse and the expansion processes in the Newton theory. In application to general relativity, we use the space model corresponding to the special four-dimensional space which is Euclidean with respect to space coordinates and Riemannian with respect to the time coordinate only. The obtained solution specifies two possible scenarios. First, sphere contraction results in the infinitely high density with the finite collapse time, which does not coincide with the conventional result corresponding to the Schwarzschild geometry. Second, sphere expansion with the velocity which increases with a distance from the sphere center and decreases with time.
