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
Reconfigurable Intelligent Surface(RIS)is regarded as a cutting-edge technology for the development of future wireless communication networks with improved frequency efficiency and reduced energy consumption.This pape...Reconfigurable Intelligent Surface(RIS)is regarded as a cutting-edge technology for the development of future wireless communication networks with improved frequency efficiency and reduced energy consumption.This paper proposes an architecture by combining RIS with Generalized Spatial Modulation(GSM)and then presents a Multi-Residual Deep Neural Network(MR-DNN)scheme,where the active antennas and their transmitted constellation symbols are detected by sub-DNNs in the detection block.Simulation results demonstrate that the proposed MR-DNN detection algorithm performs considerably better than the traditional Zero-Forcing(ZF)and the Minimum Mean Squared Error(MMSE)detection algorithms in terms of Bit Error Rate(BER).Moreover,the MR-DNN detection algorithm has less time complexity than the traditional detection algorithms.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
Hydrogen energy is a crucial support for China’s low-carbon energy transition.With the large-scale integration of renewable energy,the combination of hydrogen and integrated energy systems has become one of the most ...Hydrogen energy is a crucial support for China’s low-carbon energy transition.With the large-scale integration of renewable energy,the combination of hydrogen and integrated energy systems has become one of the most promising directions of development.This paper proposes an optimized schedulingmodel for a hydrogen-coupled electro-heat-gas integrated energy system(HCEHG-IES)using generative adversarial imitation learning(GAIL).The model aims to enhance renewable-energy absorption,reduce carbon emissions,and improve grid-regulation flexibility.First,the optimal scheduling problem of HCEHG-IES under uncertainty is modeled as a Markov decision process(MDP).To overcome the limitations of conventional deep reinforcement learning algorithms—including long optimization time,slow convergence,and subjective reward design—this study augments the PPO algorithm by incorporating a discriminator network and expert data.The newly developed algorithm,termed GAIL,enables the agent to perform imitation learning from expert data.Based on this model,dynamic scheduling decisions are made in continuous state and action spaces,generating optimal energy-allocation and management schemes.Simulation results indicate that,compared with traditional reinforcement-learning algorithms,the proposed algorithmoffers better economic performance.Guided by expert data,the agent avoids blind optimization,shortens the offline training time,and improves convergence performance.In the online phase,the algorithm enables flexible energy utilization,thereby promoting renewable-energy absorption and reducing carbon emissions.展开更多
This study explores a novel educational model of generative AI-empowered interdisciplinary project-based learning(PBL).By analyzing the current applications of generative AI technology in information technology curric...This study explores a novel educational model of generative AI-empowered interdisciplinary project-based learning(PBL).By analyzing the current applications of generative AI technology in information technology curricula,it elucidates its advantages and operational mechanisms in interdisciplinary PBL.Combining case studies and empirical research,the investigation proposes implementation pathways and strategies for the generative AI-enhanced interdisciplinary PBL model,detailing specific applications across three phases:project preparation,implementation,and evaluation.The research demonstrates that generative AI-enabled interdisciplinary project-based learning can effectively enhance students’learning motivation,interdisciplinary thinking capabilities,and innovative competencies,providing new conceptual frameworks and practical approaches for educational model innovation.展开更多
Federated Learning(FL)has recently emerged as a promising paradigm that enables medical institutions to collaboratively train robust models without centralizing sensitive patient information.Data collected from differ...Federated Learning(FL)has recently emerged as a promising paradigm that enables medical institutions to collaboratively train robust models without centralizing sensitive patient information.Data collected from different institutions represent distinct source domains.Consequently,discrepancies in feature distributions can significantly hinder a model’s generalization to unseen domains.While domain generalization(DG)methods have been proposed to address this challenge,many may compromise data privacy in FL by requiring clients to transmit their local feature representations to the server.Furthermore,existing adversarial training methods,commonly used to align marginal feature distributions,fail to ensure the consistency of conditional distributions.This consistency is often critical for accurate predictions in unseen domains.To address these limitations,we propose GPAF,a privacy-preserving federated learning(FL)framework that mitigates both domain and label shifts in healthcare applications.GPAF aligns conditional distributions across clients in the latent space and restricts communication to model parameters.This design preserves class semantics,enhances privacy,and improves communication efficiency.At the server,a global generator learns a conditional feature distribution from clients’feedback.During local training,each client minimizes an adversarial loss to align its local conditional distribution with the global distribution,enabling the FL model to learn robust,domain-invariant representations across all source domains.To evaluate the effectiveness of our approach,experiments on a medical imaging benchmark demonstrate that GPAF outperforms four FL baselines,achieving up to 17%higher classification accuracy and 25%faster convergence in non-IID scenarios.These results highlight GPAF’s capability to generalize across domains while maintaining strict privacy,offering a robust solution for decentralized healthcare challenges.展开更多
Network architectures assisted by Generative Artificial Intelligence(GAI)are envisioned as foundational elements of sixth-generation(6G)communication system.To deliver ubiquitous intelligent services and meet diverse ...Network architectures assisted by Generative Artificial Intelligence(GAI)are envisioned as foundational elements of sixth-generation(6G)communication system.To deliver ubiquitous intelligent services and meet diverse service requirements,6G network architecture should offer personalized services to various mobile devices.Federated learning(FL)with personalized local training,as a privacypreserving machine learning(ML)approach,can be applied to address these challenges.In this paper,we propose a meta-learning-based personalized FL(PFL)method that improves both communication and computation efficiency by utilizing over-the-air computations.Its“pretraining-and-fine-tuning”principle makes it particularly suitable for enabling edge nodes to access personalized GAI services while preserving local privacy.Experiment results demonstrate the outperformance and efficacy of the proposed algorithm,and notably indicate enhanced communication efficiency without compromising accuracy.展开更多
This paper addresses the performance degradation issue in a fast radio burst search pipeline based on deep learning.This issue is caused by the class imbalance of the radio frequency interference samples in the traini...This paper addresses the performance degradation issue in a fast radio burst search pipeline based on deep learning.This issue is caused by the class imbalance of the radio frequency interference samples in the training dataset,and one solution is applied to improve the distribution of the training data by augmenting minority class samples using a deep convolutional generative adversarial network.Experi.mental results demonstrate that retraining the deep learning model with the newly generated dataset leads to a new fast radio burst classifier,which effectively reduces false positives caused by periodic wide-band impulsive radio frequency interference,thereby enhancing the performance of the search pipeline.展开更多
As energy demands continue to rise in modern society,the development of high-performance lithium-ion batteries(LIBs)has become crucial.However,traditional research methods of material science face challenges such as l...As energy demands continue to rise in modern society,the development of high-performance lithium-ion batteries(LIBs)has become crucial.However,traditional research methods of material science face challenges such as lengthy timelines and complex processes.In recent years,the integration of machine learning(ML)in LIB materials,including electrolytes,solid-state electrolytes,and electrodes,has yielded remarkable achievements.This comprehensive review explores the latest applications of ML in predicting LIB material performance,covering the core principles and recent advancements in three key inverse material design strategies:high-throughput virtual screening,global optimization,and generative models.These strategies have played a pivotal role in fostering LIB material innovations.Meanwhile,the paper briefly discusses the challenges associated with applying ML to materials research and offers insights and directions for future research.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 inversion of ocean subsurface temperature and salinity(TS)is a hot topic and challenging problem in the oceanic sciences.In this study,a new method for the inversion of underwater TS in the South China Sea is prop...The inversion of ocean subsurface temperature and salinity(TS)is a hot topic and challenging problem in the oceanic sciences.In this study,a new method for the inversion of underwater TS in the South China Sea is proposed based on an improved generative adversarial network(GAN).The proposed model can derive the underwater TS from sea surface data(specifically,sea surface temperature and the sea surface height anomalies)with an eddy-resolving horizontal resolution of(1/12)°.For comparison,a robust statistics-based model,the Modular Ocean Data Assimilation System(MODAS),is also used to invert the subsurface TS in this study.Results show that the root-mean-square errors(RMSEs)of the TS inversions from the GAN-based model are significantly smaller than those from MODAS,especially in the thermocline of the South China Sea,where the RMSE of temperature can be reduced by up to 21.7%and the subsurface salinity RMSE is smaller than 0.32.In particular,the inversion results obtained using the proposed model are more accurate in either the seasonalscale or the synoptic-scale analysis.Firstly,the GAN-based model is more effective for the seasonal-scale extraction and diagnosis of the subsurface stratification,especially in the Luzon Strait and coastal shelf sea areas,in which stronger nonlinearities arise from the Kuroshio intrusion or complex coastal processes dominate the ocean subsurface dynamics.Secondly,the vertical heat pump and cold suction effects in the ocean's upper layers induced by the passage of a typhoon can be reflected more reasonably based on the synoptic-scale analysis with the proposed model.Furthermore,the underwater 3D structure of mesoscale eddies can be skillfully captured by AIGAN(Attention and Inception GAN),which can extract more refined eddy patterns with stronger recognition capability compared with the statistics-based MODAS.The present study can be extended to further explore the subsurface characteristics of the internal variability in the South China Sea.展开更多
Dear Editor,Health management is essential to ensure battery performance and safety, while data-driven learning system is a promising solution to enable efficient state of health(SoH) estimation of lithium-ion(Liion) ...Dear Editor,Health management is essential to ensure battery performance and safety, while data-driven learning system is a promising solution to enable efficient state of health(SoH) estimation of lithium-ion(Liion) batteries. However, the time-consuming signal data acquisition and the lack of interpretability of model still hinder its efficient deployment. Motivated by this, this letter proposes a novel and interpretable data-driven learning strategy through combining the benefits of explainable AI and non-destructive ultrasonic detection for battery SoH estimation. Specifically, after equipping battery with advanced ultrasonic sensor to promise fast real-time ultrasonic signal measurement, an interpretable data-driven learning strategy named generalized additive neural decision ensemble(GANDE) is designed to rapidly estimate battery SoH and explain the effects of the involved ultrasonic features of interest.展开更多
Alzheimer’s Disease(AD)is a progressive neurodegenerative disorder that significantly affects cognitive function,making early and accurate diagnosis essential.Traditional Deep Learning(DL)-based approaches often stru...Alzheimer’s Disease(AD)is a progressive neurodegenerative disorder that significantly affects cognitive function,making early and accurate diagnosis essential.Traditional Deep Learning(DL)-based approaches often struggle with low-contrast MRI images,class imbalance,and suboptimal feature extraction.This paper develops a Hybrid DL system that unites MobileNetV2 with adaptive classification methods to boost Alzheimer’s diagnosis by processing MRI scans.Image enhancement is done using Contrast-Limited Adaptive Histogram Equalization(CLAHE)and Enhanced Super-Resolution Generative Adversarial Networks(ESRGAN).A classification robustness enhancement system integrates class weighting techniques and a Matthews Correlation Coefficient(MCC)-based evaluation method into the design.The trained and validated model gives a 98.88%accuracy rate and 0.9614 MCC score.We also performed a 10-fold cross-validation experiment with an average accuracy of 96.52%(±1.51),a loss of 0.1671,and an MCC score of 0.9429 across folds.The proposed framework outperforms the state-of-the-art models with a 98%weighted F1-score while decreasing misdiagnosis results for every AD stage.The model demonstrates apparent separation abilities between AD progression stages according to the results of the confusion matrix analysis.These results validate the effectiveness of hybrid DL models with adaptive preprocessing for early and reliable Alzheimer’s diagnosis,contributing to improved computer-aided diagnosis(CAD)systems in clinical practice.展开更多
Robot calligraphy visually reflects the motion capability of robotic manipulators.While traditional researches mainly focus on image generation and the writing of simple calligraphic strokes or characters,this article...Robot calligraphy visually reflects the motion capability of robotic manipulators.While traditional researches mainly focus on image generation and the writing of simple calligraphic strokes or characters,this article presents a generative adversarial network(GAN)-based motion learning method for robotic calligraphy synthesis(Gan2CS)that can enhance the efficiency in writing complex calligraphy words and reproducing classic calligraphy works.The key technologies in the proposed approach include:(1)adopting the GAN to learn the motion parameters from the robot writing operation;(2)converting the learnt motion data into the style font and realising the transition from static calligraphy images to dynamic writing demonstration;(3)reproducing high-precision calligraphy works by synthesising the writing motion data hierarchically.In this study,the motion trajectories of sample calligraphy images are firstly extracted and converted into the robot module.The robot performs the writing with motion planning,and the writing motion parameters of calligraphy strokes are learnt with GANs.Then the motion data of basic strokes is synthesised based on the hierarchical process of‘stroke-radicalpart-character’.And the robot re-writes the synthesised characters whose similarity with the original calligraphy characters is evaluated.Regular calligraphy characters have been tested in the experiments for method validation and the results validated that the robot can actualise the robotic calligraphy synthesis of writing motion data with GAN.展开更多
Medical image analysis has become a cornerstone of modern healthcare,driven by the exponential growth of data from imaging modalities such as MRI,CT,PET,ultrasound,and X-ray.Traditional machine learning methods have m...Medical image analysis has become a cornerstone of modern healthcare,driven by the exponential growth of data from imaging modalities such as MRI,CT,PET,ultrasound,and X-ray.Traditional machine learning methods have made early contributions;however,recent advancements in deep learning(DL)have revolutionized the field,offering state-of-the-art performance in image classification,segmentation,detection,fusion,registration,and enhancement.This comprehensive review presents an in-depth analysis of deep learning methodologies applied across medical image analysis tasks,highlighting both foundational models and recent innovations.The article begins by introducing conventional techniques and their limitations,setting the stage for DL-based solutions.Core DL architectures,including Convolutional Neural Networks(CNNs),Recurrent Neural Networks(RNNs),Generative Adversarial Networks(GANs),Vision Transformers(ViTs),and hybrid models,are discussed in detail,including their advantages and domain-specific adaptations.Advanced learning paradigms such as semi-supervised learning,selfsupervised learning,and few-shot learning are explored for their potential to mitigate data annotation challenges in clinical datasets.This review further categorizes major tasks in medical image analysis,elaborating on how DL techniques have enabled precise tumor segmentation,lesion detection,modality fusion,super-resolution,and robust classification across diverse clinical settings.Emphasis is placed on applications in oncology,cardiology,neurology,and infectious diseases,including COVID-19.Challenges such as data scarcity,label imbalance,model generalizability,interpretability,and integration into clinical workflows are critically examined.Ethical considerations,explainable AI(XAI),federated learning,and regulatory compliance are discussed as essential components of real-world deployment.Benchmark datasets,evaluation metrics,and comparative performance analyses are presented to support future research.The article concludes with a forward-looking perspective on the role of foundation models,multimodal learning,edge AI,and bio-inspired computing in the future of medical imaging.Overall,this review serves as a valuable resource for researchers,clinicians,and developers aiming to harness deep learning for intelligent,efficient,and clinically viable medical image analysis.展开更多
In this paper, a learning control approach is applied to the generalized projective synchronisation （GPS） of different chaotic systems with unknown periodically time-varying parameters. Using the Lyapunov--Krasovski...In this paper, a learning control approach is applied to the generalized projective synchronisation （GPS） of different chaotic systems with unknown periodically time-varying parameters. Using the Lyapunov--Krasovskii functional stability theory, a differential-difference mixed parametric learning law and an adaptive learning control law are constructed to make the states of two different chaotic systems asymptotically synchronised. The scheme is successfully applied to the generalized projective synchronisation between the Lorenz system and Chen system. Moreover, numerical simulations results are used to verify the effectiveness of the proposed scheme.展开更多
Efficiently tracking and imaging interested moving targets is crucial across various applications,from autonomous systems to surveillance.However,persistent challenges remain in various fields,including environmental ...Efficiently tracking and imaging interested moving targets is crucial across various applications,from autonomous systems to surveillance.However,persistent challenges remain in various fields,including environmental intricacies,limitations in perceptual technologies,and privacy considerations.We present a teacher-student learning model,the generative adversarial network(GAN)-guided diffractive neural network(DNN),which performs visual tracking and imaging of the interested moving target.The GAN,as a teacher model,empowers efficient acquisition of the skill to differentiate the specific target of interest in the domains of visual tracking and imaging.The DNN-based student model learns to master the skill to differentiate the interested target from the GAN.The process of obtaining a GAN-guided DNN starts with capturing moving objects effectively using an event camera with high temporal resolution and low latency.Then,the generative power of GAN is utilized to generate data with position-tracking capability for the interested moving target,subsequently serving as labels to the training of the DNN.The DNN learns to image the target during training while retaining the target’s positional information.Our experimental demonstration highlights the efficacy of the GAN-guided DNN in visual tracking and imaging of the interested moving target.We expect the GAN-guided DNN can significantly enhance autonomous systems and surveillance.展开更多
In this paper,based on physics-informed neural networks(PINNs),a good deep learning neural network framework that can be used to effectively solve the nonlinear evolution partial differential equations(PDEs)and other ...In this paper,based on physics-informed neural networks(PINNs),a good deep learning neural network framework that can be used to effectively solve the nonlinear evolution partial differential equations(PDEs)and other types of nonlinear physical models,we study the nonlinear Schrodinger equation(NLSE)with the generalized PT-symmetric Scarf-Ⅱpotential,which is an important physical model in many fields of nonlinear physics.Firstly,we choose three different initial values and the same Dinchlet boundaiy conditions to solve the NLSE with the generalized PT-symmetric Scarf-Ⅱpotential via the PINN deep learning method,and the obtained results are compared with ttose denved by the toditional numencal methods.Then,we mvestigate effect of two factors(optimization steps and activation functions)on the performance of the PINN deep learning method in the NLSE with the generalized PT-symmetric Scarf-Ⅱpotential.Ultimately,the data-driven coefficient discovery of the generalized PT-symmetric Scarf-Ⅱpotential or the dispersion and nonlinear items of the NLSE with the generalized PT-symmetric Scarf-Ⅱpotential can be approximately ascertained by using the PINN deep learning method.Our results may be meaningful for further investigation of the nonlinear Schrodmger equation with the generalized PT-symmetric Scarf-Ⅱpotential in the deep learning.展开更多
A new algorithm is proposed, which immolates the optimality of control policies potentially to obtain the robnsticity of solutions. The robnsticity of solutions maybe becomes a very important property for a learning s...A new algorithm is proposed, which immolates the optimality of control policies potentially to obtain the robnsticity of solutions. The robnsticity of solutions maybe becomes a very important property for a learning system when there exists non-matching between theory models and practical physical system, or the practical system is not static, or the availability of a control action changes along with the variety of time. The main contribution is that a set of approximation algorithms and their convergence results are given. A generalized average operator instead of the general optimal operator max （or rain） is applied to study a class of important learning algorithms, dynamic prOgramming algorithms, and discuss their convergences from theoretic point of view. The purpose for this research is to improve the robnsticity of reinforcement learning algorithms theoretically.展开更多
This paper describes the self—adjustment of some tuning-knobs of the generalized predictive controller(GPC).A three feedforward neural network was utilized to on line learn two key tuning-knobs of GPC,and BP algorith...This paper describes the self—adjustment of some tuning-knobs of the generalized predictive controller(GPC).A three feedforward neural network was utilized to on line learn two key tuning-knobs of GPC,and BP algorithm was used for the training of the linking-weights of the neural network.Hence it gets rid of the difficulty of choosing these tuning-knobs manually and provides easier condition for the wide applications of GPC on industrial plants.Simulation results illustrated the effectiveness of the method.展开更多
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 Shenzhen Basic Research Program under Grant JCYJ20220531103008018,20231120142345001 and 20231127144045001the Guangdong Basic Research Program under Grant 2024ZDZX1016the Natural Science Foundation of China under Grant U20A20156.
文摘Reconfigurable Intelligent Surface(RIS)is regarded as a cutting-edge technology for the development of future wireless communication networks with improved frequency efficiency and reduced energy consumption.This paper proposes an architecture by combining RIS with Generalized Spatial Modulation(GSM)and then presents a Multi-Residual Deep Neural Network(MR-DNN)scheme,where the active antennas and their transmitted constellation symbols are detected by sub-DNNs in the detection block.Simulation results demonstrate that the proposed MR-DNN detection algorithm performs considerably better than the traditional Zero-Forcing(ZF)and the Minimum Mean Squared Error(MMSE)detection algorithms in terms of Bit Error Rate(BER).Moreover,the MR-DNN detection algorithm has less time complexity than the traditional detection algorithms.
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supported by State Grid Corporation Technology Project(No.522437250003).
文摘Hydrogen energy is a crucial support for China’s low-carbon energy transition.With the large-scale integration of renewable energy,the combination of hydrogen and integrated energy systems has become one of the most promising directions of development.This paper proposes an optimized schedulingmodel for a hydrogen-coupled electro-heat-gas integrated energy system(HCEHG-IES)using generative adversarial imitation learning(GAIL).The model aims to enhance renewable-energy absorption,reduce carbon emissions,and improve grid-regulation flexibility.First,the optimal scheduling problem of HCEHG-IES under uncertainty is modeled as a Markov decision process(MDP).To overcome the limitations of conventional deep reinforcement learning algorithms—including long optimization time,slow convergence,and subjective reward design—this study augments the PPO algorithm by incorporating a discriminator network and expert data.The newly developed algorithm,termed GAIL,enables the agent to perform imitation learning from expert data.Based on this model,dynamic scheduling decisions are made in continuous state and action spaces,generating optimal energy-allocation and management schemes.Simulation results indicate that,compared with traditional reinforcement-learning algorithms,the proposed algorithmoffers better economic performance.Guided by expert data,the agent avoids blind optimization,shortens the offline training time,and improves convergence performance.In the online phase,the algorithm enables flexible energy utilization,thereby promoting renewable-energy absorption and reducing carbon emissions.
文摘This study explores a novel educational model of generative AI-empowered interdisciplinary project-based learning(PBL).By analyzing the current applications of generative AI technology in information technology curricula,it elucidates its advantages and operational mechanisms in interdisciplinary PBL.Combining case studies and empirical research,the investigation proposes implementation pathways and strategies for the generative AI-enhanced interdisciplinary PBL model,detailing specific applications across three phases:project preparation,implementation,and evaluation.The research demonstrates that generative AI-enabled interdisciplinary project-based learning can effectively enhance students’learning motivation,interdisciplinary thinking capabilities,and innovative competencies,providing new conceptual frameworks and practical approaches for educational model innovation.
文摘Federated Learning(FL)has recently emerged as a promising paradigm that enables medical institutions to collaboratively train robust models without centralizing sensitive patient information.Data collected from different institutions represent distinct source domains.Consequently,discrepancies in feature distributions can significantly hinder a model’s generalization to unseen domains.While domain generalization(DG)methods have been proposed to address this challenge,many may compromise data privacy in FL by requiring clients to transmit their local feature representations to the server.Furthermore,existing adversarial training methods,commonly used to align marginal feature distributions,fail to ensure the consistency of conditional distributions.This consistency is often critical for accurate predictions in unseen domains.To address these limitations,we propose GPAF,a privacy-preserving federated learning(FL)framework that mitigates both domain and label shifts in healthcare applications.GPAF aligns conditional distributions across clients in the latent space and restricts communication to model parameters.This design preserves class semantics,enhances privacy,and improves communication efficiency.At the server,a global generator learns a conditional feature distribution from clients’feedback.During local training,each client minimizes an adversarial loss to align its local conditional distribution with the global distribution,enabling the FL model to learn robust,domain-invariant representations across all source domains.To evaluate the effectiveness of our approach,experiments on a medical imaging benchmark demonstrate that GPAF outperforms four FL baselines,achieving up to 17%higher classification accuracy and 25%faster convergence in non-IID scenarios.These results highlight GPAF’s capability to generalize across domains while maintaining strict privacy,offering a robust solution for decentralized healthcare challenges.
基金supported in part by the National Key R&D Program of China under Grant 2024YFE0200700in part by the National Natural Science Foundation of China under Grant 62201504.
文摘Network architectures assisted by Generative Artificial Intelligence(GAI)are envisioned as foundational elements of sixth-generation(6G)communication system.To deliver ubiquitous intelligent services and meet diverse service requirements,6G network architecture should offer personalized services to various mobile devices.Federated learning(FL)with personalized local training,as a privacypreserving machine learning(ML)approach,can be applied to address these challenges.In this paper,we propose a meta-learning-based personalized FL(PFL)method that improves both communication and computation efficiency by utilizing over-the-air computations.Its“pretraining-and-fine-tuning”principle makes it particularly suitable for enabling edge nodes to access personalized GAI services while preserving local privacy.Experiment results demonstrate the outperformance and efficacy of the proposed algorithm,and notably indicate enhanced communication efficiency without compromising accuracy.
基金supported by the Chinese Academy of Science"Light of West China"Program(2022-XBQNXZ-015)the National Natural Science Foundation of China(11903071)the Operation,Maintenance and Upgrading Fund for Astronomical Telescopes and Facility Instruments,budgeted from the Ministry of Finance of China and administered by the Chinese Academy of Sciences。
文摘This paper addresses the performance degradation issue in a fast radio burst search pipeline based on deep learning.This issue is caused by the class imbalance of the radio frequency interference samples in the training dataset,and one solution is applied to improve the distribution of the training data by augmenting minority class samples using a deep convolutional generative adversarial network.Experi.mental results demonstrate that retraining the deep learning model with the newly generated dataset leads to a new fast radio burst classifier,which effectively reduces false positives caused by periodic wide-band impulsive radio frequency interference,thereby enhancing the performance of the search pipeline.
基金supported by the National Natural Science Foundation of China(Grant Nos.22225801,W2441009,22408228)。
文摘As energy demands continue to rise in modern society,the development of high-performance lithium-ion batteries(LIBs)has become crucial.However,traditional research methods of material science face challenges such as lengthy timelines and complex processes.In recent years,the integration of machine learning(ML)in LIB materials,including electrolytes,solid-state electrolytes,and electrodes,has yielded remarkable achievements.This comprehensive review explores the latest applications of ML in predicting LIB material performance,covering the core principles and recent advancements in three key inverse material design strategies:high-throughput virtual screening,global optimization,and generative models.These strategies have played a pivotal role in fostering LIB material innovations.Meanwhile,the paper briefly discusses the challenges associated with applying ML to materials research and offers insights and directions for future research.
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.
基金supported by the National Research and Development Program of China(Grant No.2021YFC2803003)the National Natural Science Foundation of China(Grant No.42375143)。
文摘The inversion of ocean subsurface temperature and salinity(TS)is a hot topic and challenging problem in the oceanic sciences.In this study,a new method for the inversion of underwater TS in the South China Sea is proposed based on an improved generative adversarial network(GAN).The proposed model can derive the underwater TS from sea surface data(specifically,sea surface temperature and the sea surface height anomalies)with an eddy-resolving horizontal resolution of(1/12)°.For comparison,a robust statistics-based model,the Modular Ocean Data Assimilation System(MODAS),is also used to invert the subsurface TS in this study.Results show that the root-mean-square errors(RMSEs)of the TS inversions from the GAN-based model are significantly smaller than those from MODAS,especially in the thermocline of the South China Sea,where the RMSE of temperature can be reduced by up to 21.7%and the subsurface salinity RMSE is smaller than 0.32.In particular,the inversion results obtained using the proposed model are more accurate in either the seasonalscale or the synoptic-scale analysis.Firstly,the GAN-based model is more effective for the seasonal-scale extraction and diagnosis of the subsurface stratification,especially in the Luzon Strait and coastal shelf sea areas,in which stronger nonlinearities arise from the Kuroshio intrusion or complex coastal processes dominate the ocean subsurface dynamics.Secondly,the vertical heat pump and cold suction effects in the ocean's upper layers induced by the passage of a typhoon can be reflected more reasonably based on the synoptic-scale analysis with the proposed model.Furthermore,the underwater 3D structure of mesoscale eddies can be skillfully captured by AIGAN(Attention and Inception GAN),which can extract more refined eddy patterns with stronger recognition capability compared with the statistics-based MODAS.The present study can be extended to further explore the subsurface characteristics of the internal variability in the South China Sea.
基金supported by the National Natural Science Foundation of China(62373224,62333013,U23A20327)the Natural Science Foundation of Shandong Province(ZR2024JQ021)
文摘Dear Editor,Health management is essential to ensure battery performance and safety, while data-driven learning system is a promising solution to enable efficient state of health(SoH) estimation of lithium-ion(Liion) batteries. However, the time-consuming signal data acquisition and the lack of interpretability of model still hinder its efficient deployment. Motivated by this, this letter proposes a novel and interpretable data-driven learning strategy through combining the benefits of explainable AI and non-destructive ultrasonic detection for battery SoH estimation. Specifically, after equipping battery with advanced ultrasonic sensor to promise fast real-time ultrasonic signal measurement, an interpretable data-driven learning strategy named generalized additive neural decision ensemble(GANDE) is designed to rapidly estimate battery SoH and explain the effects of the involved ultrasonic features of interest.
基金funded by the Deanship of Graduate Studies and Scientific Research at Jouf University under grant No.(DGSSR-2025-02-01295).
文摘Alzheimer’s Disease(AD)is a progressive neurodegenerative disorder that significantly affects cognitive function,making early and accurate diagnosis essential.Traditional Deep Learning(DL)-based approaches often struggle with low-contrast MRI images,class imbalance,and suboptimal feature extraction.This paper develops a Hybrid DL system that unites MobileNetV2 with adaptive classification methods to boost Alzheimer’s diagnosis by processing MRI scans.Image enhancement is done using Contrast-Limited Adaptive Histogram Equalization(CLAHE)and Enhanced Super-Resolution Generative Adversarial Networks(ESRGAN).A classification robustness enhancement system integrates class weighting techniques and a Matthews Correlation Coefficient(MCC)-based evaluation method into the design.The trained and validated model gives a 98.88%accuracy rate and 0.9614 MCC score.We also performed a 10-fold cross-validation experiment with an average accuracy of 96.52%(±1.51),a loss of 0.1671,and an MCC score of 0.9429 across folds.The proposed framework outperforms the state-of-the-art models with a 98%weighted F1-score while decreasing misdiagnosis results for every AD stage.The model demonstrates apparent separation abilities between AD progression stages according to the results of the confusion matrix analysis.These results validate the effectiveness of hybrid DL models with adaptive preprocessing for early and reliable Alzheimer’s diagnosis,contributing to improved computer-aided diagnosis(CAD)systems in clinical practice.
基金National Key Research and Development Program of China,Grant/Award Numbers:2021YFB2501301,2019YFB1600704The Science and Technology Development Fund,Grant/Award Numbers:0068/2020/AGJ,SKL‐IOTSC(UM)‐2021‐2023GDST,Grant/Award Numbers:2020B1212030003,MYRG2022‐00192‐FST。
文摘Robot calligraphy visually reflects the motion capability of robotic manipulators.While traditional researches mainly focus on image generation and the writing of simple calligraphic strokes or characters,this article presents a generative adversarial network(GAN)-based motion learning method for robotic calligraphy synthesis(Gan2CS)that can enhance the efficiency in writing complex calligraphy words and reproducing classic calligraphy works.The key technologies in the proposed approach include:(1)adopting the GAN to learn the motion parameters from the robot writing operation;(2)converting the learnt motion data into the style font and realising the transition from static calligraphy images to dynamic writing demonstration;(3)reproducing high-precision calligraphy works by synthesising the writing motion data hierarchically.In this study,the motion trajectories of sample calligraphy images are firstly extracted and converted into the robot module.The robot performs the writing with motion planning,and the writing motion parameters of calligraphy strokes are learnt with GANs.Then the motion data of basic strokes is synthesised based on the hierarchical process of‘stroke-radicalpart-character’.And the robot re-writes the synthesised characters whose similarity with the original calligraphy characters is evaluated.Regular calligraphy characters have been tested in the experiments for method validation and the results validated that the robot can actualise the robotic calligraphy synthesis of writing motion data with GAN.
文摘Medical image analysis has become a cornerstone of modern healthcare,driven by the exponential growth of data from imaging modalities such as MRI,CT,PET,ultrasound,and X-ray.Traditional machine learning methods have made early contributions;however,recent advancements in deep learning(DL)have revolutionized the field,offering state-of-the-art performance in image classification,segmentation,detection,fusion,registration,and enhancement.This comprehensive review presents an in-depth analysis of deep learning methodologies applied across medical image analysis tasks,highlighting both foundational models and recent innovations.The article begins by introducing conventional techniques and their limitations,setting the stage for DL-based solutions.Core DL architectures,including Convolutional Neural Networks(CNNs),Recurrent Neural Networks(RNNs),Generative Adversarial Networks(GANs),Vision Transformers(ViTs),and hybrid models,are discussed in detail,including their advantages and domain-specific adaptations.Advanced learning paradigms such as semi-supervised learning,selfsupervised learning,and few-shot learning are explored for their potential to mitigate data annotation challenges in clinical datasets.This review further categorizes major tasks in medical image analysis,elaborating on how DL techniques have enabled precise tumor segmentation,lesion detection,modality fusion,super-resolution,and robust classification across diverse clinical settings.Emphasis is placed on applications in oncology,cardiology,neurology,and infectious diseases,including COVID-19.Challenges such as data scarcity,label imbalance,model generalizability,interpretability,and integration into clinical workflows are critically examined.Ethical considerations,explainable AI(XAI),federated learning,and regulatory compliance are discussed as essential components of real-world deployment.Benchmark datasets,evaluation metrics,and comparative performance analyses are presented to support future research.The article concludes with a forward-looking perspective on the role of foundation models,multimodal learning,edge AI,and bio-inspired computing in the future of medical imaging.Overall,this review serves as a valuable resource for researchers,clinicians,and developers aiming to harness deep learning for intelligent,efficient,and clinically viable medical image analysis.
基金supported by the National Natural Science Foundation of China (Grant No. 60374015)
文摘In this paper, a learning control approach is applied to the generalized projective synchronisation （GPS） of different chaotic systems with unknown periodically time-varying parameters. Using the Lyapunov--Krasovskii functional stability theory, a differential-difference mixed parametric learning law and an adaptive learning control law are constructed to make the states of two different chaotic systems asymptotically synchronised. The scheme is successfully applied to the generalized projective synchronisation between the Lorenz system and Chen system. Moreover, numerical simulations results are used to verify the effectiveness of the proposed scheme.
基金supported by the National Natural Science Foundation of China(Grant Nos.62422509 and 62405188)the Shanghai Natural Science Foundation(Grant No.23ZR1443700)+3 种基金the Shuguang Program of Shanghai Education Development Foundation and Shanghai Municipal Education Commission(Grant No.23SG41)the Young Elite Scientist Sponsorship Program by CAST(Grant No.20220042)the Science and Technology Commission of Shanghai Municipality(Grant No.21DZ1100500)the Shanghai Municipal Science and Technology Major Project,and the Shanghai Frontiers Science Center Program(2021-2025 No.20).
文摘Efficiently tracking and imaging interested moving targets is crucial across various applications,from autonomous systems to surveillance.However,persistent challenges remain in various fields,including environmental intricacies,limitations in perceptual technologies,and privacy considerations.We present a teacher-student learning model,the generative adversarial network(GAN)-guided diffractive neural network(DNN),which performs visual tracking and imaging of the interested moving target.The GAN,as a teacher model,empowers efficient acquisition of the skill to differentiate the specific target of interest in the domains of visual tracking and imaging.The DNN-based student model learns to master the skill to differentiate the interested target from the GAN.The process of obtaining a GAN-guided DNN starts with capturing moving objects effectively using an event camera with high temporal resolution and low latency.Then,the generative power of GAN is utilized to generate data with position-tracking capability for the interested moving target,subsequently serving as labels to the training of the DNN.The DNN learns to image the target during training while retaining the target’s positional information.Our experimental demonstration highlights the efficacy of the GAN-guided DNN in visual tracking and imaging of the interested moving target.We expect the GAN-guided DNN can significantly enhance autonomous systems and surveillance.
基金supported by the National Natural Science Foundation of China under Grant Nos.11775121,11435005the K.C.Wong Magna Fund of Ningbo University。
文摘In this paper,based on physics-informed neural networks(PINNs),a good deep learning neural network framework that can be used to effectively solve the nonlinear evolution partial differential equations(PDEs)and other types of nonlinear physical models,we study the nonlinear Schrodinger equation(NLSE)with the generalized PT-symmetric Scarf-Ⅱpotential,which is an important physical model in many fields of nonlinear physics.Firstly,we choose three different initial values and the same Dinchlet boundaiy conditions to solve the NLSE with the generalized PT-symmetric Scarf-Ⅱpotential via the PINN deep learning method,and the obtained results are compared with ttose denved by the toditional numencal methods.Then,we mvestigate effect of two factors(optimization steps and activation functions)on the performance of the PINN deep learning method in the NLSE with the generalized PT-symmetric Scarf-Ⅱpotential.Ultimately,the data-driven coefficient discovery of the generalized PT-symmetric Scarf-Ⅱpotential or the dispersion and nonlinear items of the NLSE with the generalized PT-symmetric Scarf-Ⅱpotential can be approximately ascertained by using the PINN deep learning method.Our results may be meaningful for further investigation of the nonlinear Schrodmger equation with the generalized PT-symmetric Scarf-Ⅱpotential in the deep learning.
基金Project supported by the National Natural Science Foundation of China (Nos. 10471088 and 60572126)
文摘A new algorithm is proposed, which immolates the optimality of control policies potentially to obtain the robnsticity of solutions. The robnsticity of solutions maybe becomes a very important property for a learning system when there exists non-matching between theory models and practical physical system, or the practical system is not static, or the availability of a control action changes along with the variety of time. The main contribution is that a set of approximation algorithms and their convergence results are given. A generalized average operator instead of the general optimal operator max （or rain） is applied to study a class of important learning algorithms, dynamic prOgramming algorithms, and discuss their convergences from theoretic point of view. The purpose for this research is to improve the robnsticity of reinforcement learning algorithms theoretically.
基金Supported by the National 863 CIMS Project Foundation(863-511-010)Tianjin Natural Science Foundation(983602011)Backbone Young Teacher Project Foundation of Ministry of Education
文摘This paper describes the self—adjustment of some tuning-knobs of the generalized predictive controller(GPC).A three feedforward neural network was utilized to on line learn two key tuning-knobs of GPC,and BP algorithm was used for the training of the linking-weights of the neural network.Hence it gets rid of the difficulty of choosing these tuning-knobs manually and provides easier condition for the wide applications of GPC on industrial plants.Simulation results illustrated the effectiveness of the method.
