The existence of absorption and reflection of light underwater leads to problems such as color distortion and blue-green bias in underwater images.In this study,a depthwise separable convolution-based generative adver...The existence of absorption and reflection of light underwater leads to problems such as color distortion and blue-green bias in underwater images.In this study,a depthwise separable convolution-based generative adversarial network(GAN)algorithm was proposed.Taking GAN as the basic framework,it combined a depthwise separable convolution module,attention mechanism,and reconstructed convolution module to realize the enhancement of underwater degraded images.Multi-scale features were captured by the depthwise separable convolution module,and the attention mechanism was utilized to enhance attention to important features.The reconstructed convolution module further extracts and fuses local and global features.Experimental results showed that the algorithm performs well in improving the color bias and blurring of underwater images,with PSNR reaching 27.835,SSIM reaching 0.883,UIQM reaching 3.205,and UCIQE reaching 0.713.The enhanced image outperforms the comparison algorithm in both subjective and objective metrics.展开更多
Generative steganography uses generative stego images to transmit secret message.It also effectively defends against statistical steganalysis.However,most existing methods focus primarily on matching the feature distr...Generative steganography uses generative stego images to transmit secret message.It also effectively defends against statistical steganalysis.However,most existing methods focus primarily on matching the feature distribution of training data,often neglecting the sequential continuity between moves in the game.This oversight can result in unnatural patterns that deviate from real user behavior,thereby reducing the security of the hidden communication.To address this issue,we design a Gomoku agent based on the AlphaZero algorithm.The model engages in self-play to generate a sequence of plausible moves.These moves formthe basis of the stego images.We then apply an attractionmatrix at each step.It guides themove selection so that themoves appearmore natural.Thismethod helps maintain logical flow between moves.It also extends the game length,which increases the embedding capacity.Next,we filter and prioritize the generated moves.The selected moves are embedded into a move pool.Secret message is mapped to thesemoves.It is then embedded step by step as the game progresses.The finalmove sequence constitutes a complete steganographic game record.The receiver can extract the secret message using this record and a predefined mapping rule.Experiments show that our method reaches a maximum embedding capacity of 223 bits per carrier.Detection accuracy is 0.500 under XuNet and 0.498 under YeNet.These results are equal to random guessing,showing strong imperceptibility.The proposed method demonstrates superior concealment,higher embedding capacity,and greater robustness against common image distortions and steganalysis attacks.展开更多
Over the years,Generative Adversarial Networks(GANs)have revolutionized the medical imaging industry for applications such as image synthesis,denoising,super resolution,data augmentation,and cross-modality translation...Over the years,Generative Adversarial Networks(GANs)have revolutionized the medical imaging industry for applications such as image synthesis,denoising,super resolution,data augmentation,and cross-modality translation.The objective of this review is to evaluate the advances,relevances,and limitations of GANs in medical imaging.An organised literature review was conducted following the guidelines of PRISMA(Preferred Reporting Items for Systematic Reviews and Meta-Analyses).The literature considered included peer-reviewed papers published between 2020 and 2025 across databases including PubMed,IEEE Xplore,and Scopus.The studies related to applications of GAN architectures in medical imaging with reported experimental outcomes and published in English in reputable journals and conferences were considered for the review.Thesis,white papers,communication letters,and non-English articles were not included for the same.CLAIM based quality assessment criteria were applied to the included studies to assess the quality.The study classifies diverse GAN architectures,summarizing their clinical applications,technical performances,and their implementation hardships.Key findings reveal the increasing applications of GANs for enhancing diagnostic accuracy,reducing data scarcity through synthetic data generation,and supporting modality translation.However,concerns such as limited generalizability,lack of clinical validation,and regulatory constraints persist.This review provides a comprehensive study of the prevailing scenario of GANs in medical imaging and highlights crucial research gaps and future directions.Though GANs hold transformative capability for medical imaging,their integration into clinical use demands further validation,interpretability,and regulatory alignment.展开更多
With the advent of the AI era,how can students effectively utilize generative AI large models to assist in course learning?At the same time,how can teachers utilize generative AI tools and the teaching concept of OBE ...With the advent of the AI era,how can students effectively utilize generative AI large models to assist in course learning?At the same time,how can teachers utilize generative AI tools and the teaching concept of OBE to stimulate students’innovative consciousness and teamwork ability,enabling students to identify some problems in a certain industry or field and creatively propose feasible solutions,and truly achieve the cultivation of new models in software engineering course teaching with the assistance of generative AI tools?This paper presents research and practice on a new model for cultivating software engineering courses that integrates generative AI and OBE,introduces the specific process of teaching reform and practice,and finally explains the achievements of teaching reform.展开更多
Tilted metasurface nanostructures,with excellent physical properties and enormous application potential,pose an urgent need for manufacturing methods.Here,electric-field-driven generative-nanoimprinting technique is p...Tilted metasurface nanostructures,with excellent physical properties and enormous application potential,pose an urgent need for manufacturing methods.Here,electric-field-driven generative-nanoimprinting technique is proposed.The electric field applied between the template and the substrate drives the contact,tilting,filling,and holding processes.By accurately controlling the introduced included angle between the flexible template and the substrate,tilted nanostructures with a controllable angle are imprinted onto the substrate,although they are vertical on the template.By flexibly adjusting the electric field intensity and the included angle,large-area uniform-tilted,gradient-tilted,and high-angle-tilted nanostructures are fabricated.In contrast to traditional replication,the morphology of the nanoimprinting structure is extended to customized control.This work provides a cost-effective,efficient,and versatile technology for the fabrication of various large-area tilted metasurface structures.As an illustration,a tilted nanograting with a high coupling efficiency is fabricated and integrated into augmented reality displays,demonstrating superior imaging quality.展开更多
High-resolution remote sensing imagery is essential for critical applications such as precision agriculture,urban management planning,and military reconnaissance.Although significant progress has been made in singleim...High-resolution remote sensing imagery is essential for critical applications such as precision agriculture,urban management planning,and military reconnaissance.Although significant progress has been made in singleimage super-resolution(SISR)using generative adversarial networks(GANs),existing approaches still face challenges in recovering high-frequency details,effectively utilizing features,maintaining structural integrity,and ensuring training stability—particularly when dealing with the complex textures characteristic of remote sensing imagery.To address these limitations,this paper proposes the Improved ResidualModule and AttentionMechanism Network(IRMANet),a novel architecture specifically designed for remote sensing image reconstruction.IRMANet builds upon the Super-Resolution Generative Adversarial Network(SRGAN)framework and introduces several key innovations.First,the Enhanced Residual Unit(ERU)enhances feature reuse and stabilizes training through deep residual connections.Second,the Self-Attention Residual Block(SARB)incorporates a self-attentionmechanism into the Improved Residual Module(IRM)to effectivelymodel long-range dependencies and automatically emphasize salient features.Additionally,the IRM adopts amulti-scale feature fusion strategy to facilitate synergistic interactions between local detail and global semantic information.The effectiveness of each component is validated through ablation studies,while comprehensive comparative experiments on standard remote sensing datasets demonstrate that IRMANet significantly outperforms both the baseline and state-of-the-art methods in terms of perceptual quality and quantitative metrics.Specifically,compared to the baseline model,at a magnification factor of 2,IRMANet achieves an improvement of 0.24 dB in peak signal-to-noise ratio(PSNR)and 0.54 in structural similarity index(SSIM);at a magnification factor of 4,it achieves gains of 0.22 dB in PSNR and 0.51 in SSIM.These results confirm that the proposedmethod effectively enhances detail representation and structural reconstruction accuracy in complex remote sensing scenarios,offering robust technical support for high-precision detection and identification of both military and civilian aircraft.展开更多
Recommending personalized travel routes from sparse,implicit feedback poses a significant challenge,as conventional systems often struggle with information overload and fail to capture the complex,sequential nature of...Recommending personalized travel routes from sparse,implicit feedback poses a significant challenge,as conventional systems often struggle with information overload and fail to capture the complex,sequential nature of user preferences.To address this,we propose a Conditional Generative Adversarial Network(CGAN)that generates diverse and highly relevant itineraries.Our approach begins by constructing a conditional vector that encapsulates a user’s profile.This vector uniquely fuses embeddings from a Heterogeneous Information Network(HIN)to model complex user-place-route relationships,a Recurrent Neural Network(RNN)to capture sequential path dynamics,and Neural Collaborative Filtering(NCF)to incorporate collaborative signals from the wider user base.This comprehensive condition,further enhanced with features representing user interaction confidence and uncertainty,steers a CGAN stabilized by spectral normalization to generate high-fidelity latent route representations,effectively mitigating the data sparsity problem.Recommendations are then formulated using an Anchor-and-Expand algorithm,which selects relevant starting Points of Interest(POI)based on user history,then expands routes through latent similarity matching and geographic coherence optimization,culminating in Traveling Salesman Problem(TSP)-based route optimization for practical travel distances.Experiments on a real-world check-in dataset validate our model’s unique generative capability,achieving F1 scores ranging from 0.163 to 0.305,and near-zero pairs−F1 scores between 0.002 and 0.022.These results confirm the model’s success in generating novel travel routes by recommending new locations and sequences rather than replicating users’past itineraries.This work provides a robust solution for personalized travel planning,capable of generating novel and compelling routes for both new and existing users by learning from collective travel intelligence.展开更多
Remote sensing image super-resolution technology is pivotal for enhancing image quality in critical applications including environmental monitoring,urban planning,and disaster assessment.However,traditional methods ex...Remote sensing image super-resolution technology is pivotal for enhancing image quality in critical applications including environmental monitoring,urban planning,and disaster assessment.However,traditional methods exhibit deficiencies in detail recovery and noise suppression,particularly when processing complex landscapes(e.g.,forests,farmlands),leading to artifacts and spectral distortions that limit practical utility.To address this,we propose an enhanced Super-Resolution Generative Adversarial Network(SRGAN)framework featuring three key innovations:(1)Replacement of L1/L2 loss with a robust Charbonnier loss to suppress noise while preserving edge details via adaptive gradient balancing;(2)A multi-loss joint optimization strategy dynamically weighting Charbonnier loss(β=0.5),Visual Geometry Group(VGG)perceptual loss(α=1),and adversarial loss(γ=0.1)to synergize pixel-level accuracy and perceptual quality;(3)A multi-scale residual network(MSRN)capturing cross-scale texture features(e.g.,forest canopies,mountain contours).Validated on Sentinel-2(10 m)and SPOT-6/7(2.5 m)datasets covering 904 km2 in Motuo County,Xizang,our method outperforms the SRGAN baseline(SR4RS)with Peak Signal-to-Noise Ratio(PSNR)gains of 0.29 dB and Structural Similarity Index(SSIM)improvements of 3.08%on forest imagery.Visual comparisons confirm enhanced texture continuity despite marginal Learned Perceptual Image Patch Similarity(LPIPS)increases.The method significantly improves noise robustness and edge retention in complex geomorphology,demonstrating 18%faster response in forest fire early warning and providing high-resolution support for agricultural/urban monitoring.Future work will integrate spectral constraints and lightweight architectures.展开更多
文摘The existence of absorption and reflection of light underwater leads to problems such as color distortion and blue-green bias in underwater images.In this study,a depthwise separable convolution-based generative adversarial network(GAN)algorithm was proposed.Taking GAN as the basic framework,it combined a depthwise separable convolution module,attention mechanism,and reconstructed convolution module to realize the enhancement of underwater degraded images.Multi-scale features were captured by the depthwise separable convolution module,and the attention mechanism was utilized to enhance attention to important features.The reconstructed convolution module further extracts and fuses local and global features.Experimental results showed that the algorithm performs well in improving the color bias and blurring of underwater images,with PSNR reaching 27.835,SSIM reaching 0.883,UIQM reaching 3.205,and UCIQE reaching 0.713.The enhanced image outperforms the comparison algorithm in both subjective and objective metrics.
基金funded by theWuxi“Taihu Light”Science and Technology Key Project(Basic Research)(K20241046)the National Natural Science Foundation of China(Grant Nos.62102189,62122032,42305158)+1 种基金the Open Project of the National Engineering Research Center for Sensor Networks(2024YJZXKFKT02)Wuxi University Research Start-up Fund for High-Level Talents(No.2022r043).
文摘Generative steganography uses generative stego images to transmit secret message.It also effectively defends against statistical steganalysis.However,most existing methods focus primarily on matching the feature distribution of training data,often neglecting the sequential continuity between moves in the game.This oversight can result in unnatural patterns that deviate from real user behavior,thereby reducing the security of the hidden communication.To address this issue,we design a Gomoku agent based on the AlphaZero algorithm.The model engages in self-play to generate a sequence of plausible moves.These moves formthe basis of the stego images.We then apply an attractionmatrix at each step.It guides themove selection so that themoves appearmore natural.Thismethod helps maintain logical flow between moves.It also extends the game length,which increases the embedding capacity.Next,we filter and prioritize the generated moves.The selected moves are embedded into a move pool.Secret message is mapped to thesemoves.It is then embedded step by step as the game progresses.The finalmove sequence constitutes a complete steganographic game record.The receiver can extract the secret message using this record and a predefined mapping rule.Experiments show that our method reaches a maximum embedding capacity of 223 bits per carrier.Detection accuracy is 0.500 under XuNet and 0.498 under YeNet.These results are equal to random guessing,showing strong imperceptibility.The proposed method demonstrates superior concealment,higher embedding capacity,and greater robustness against common image distortions and steganalysis attacks.
基金supported by Deanship of Research and Graduate Studies at King Khalid University for funding this work through Large Research Project under grant number RGP2/540/46.
文摘Over the years,Generative Adversarial Networks(GANs)have revolutionized the medical imaging industry for applications such as image synthesis,denoising,super resolution,data augmentation,and cross-modality translation.The objective of this review is to evaluate the advances,relevances,and limitations of GANs in medical imaging.An organised literature review was conducted following the guidelines of PRISMA(Preferred Reporting Items for Systematic Reviews and Meta-Analyses).The literature considered included peer-reviewed papers published between 2020 and 2025 across databases including PubMed,IEEE Xplore,and Scopus.The studies related to applications of GAN architectures in medical imaging with reported experimental outcomes and published in English in reputable journals and conferences were considered for the review.Thesis,white papers,communication letters,and non-English articles were not included for the same.CLAIM based quality assessment criteria were applied to the included studies to assess the quality.The study classifies diverse GAN architectures,summarizing their clinical applications,technical performances,and their implementation hardships.Key findings reveal the increasing applications of GANs for enhancing diagnostic accuracy,reducing data scarcity through synthetic data generation,and supporting modality translation.However,concerns such as limited generalizability,lack of clinical validation,and regulatory constraints persist.This review provides a comprehensive study of the prevailing scenario of GANs in medical imaging and highlights crucial research gaps and future directions.Though GANs hold transformative capability for medical imaging,their integration into clinical use demands further validation,interpretability,and regulatory alignment.
基金supported by the Shanghai Municipal Education Research Project“Exploring the Practical Application of Generative Artificial Intelligence in Cultivating Innovative Thinking and Capabilities of Interdisciplinary Application Technology Talents‘Practice Path’”(C2025299)the university-level postgraduate course project“Software Process Management”(PX-2025251502)of Shanghai Sanda Universitythe key course project at the university level of Shanghai Sanda University,“Introduction to Software Engineering”(PX-5241216).
文摘With the advent of the AI era,how can students effectively utilize generative AI large models to assist in course learning?At the same time,how can teachers utilize generative AI tools and the teaching concept of OBE to stimulate students’innovative consciousness and teamwork ability,enabling students to identify some problems in a certain industry or field and creatively propose feasible solutions,and truly achieve the cultivation of new models in software engineering course teaching with the assistance of generative AI tools?This paper presents research and practice on a new model for cultivating software engineering courses that integrates generative AI and OBE,introduces the specific process of teaching reform and practice,and finally explains the achievements of teaching reform.
基金supported by National Natural Science Foundation of China(No.52025055 and 52275571)Basic Research Operation Fund of China(No.xzy012024024).
文摘Tilted metasurface nanostructures,with excellent physical properties and enormous application potential,pose an urgent need for manufacturing methods.Here,electric-field-driven generative-nanoimprinting technique is proposed.The electric field applied between the template and the substrate drives the contact,tilting,filling,and holding processes.By accurately controlling the introduced included angle between the flexible template and the substrate,tilted nanostructures with a controllable angle are imprinted onto the substrate,although they are vertical on the template.By flexibly adjusting the electric field intensity and the included angle,large-area uniform-tilted,gradient-tilted,and high-angle-tilted nanostructures are fabricated.In contrast to traditional replication,the morphology of the nanoimprinting structure is extended to customized control.This work provides a cost-effective,efficient,and versatile technology for the fabrication of various large-area tilted metasurface structures.As an illustration,a tilted nanograting with a high coupling efficiency is fabricated and integrated into augmented reality displays,demonstrating superior imaging quality.
基金funded by the Henan Province Key R&D Program Project,“Research and Application Demonstration of Class Ⅱ Superlattice Medium Wave High Temperature Infrared Detector Technology”,grant number 231111210400.
文摘High-resolution remote sensing imagery is essential for critical applications such as precision agriculture,urban management planning,and military reconnaissance.Although significant progress has been made in singleimage super-resolution(SISR)using generative adversarial networks(GANs),existing approaches still face challenges in recovering high-frequency details,effectively utilizing features,maintaining structural integrity,and ensuring training stability—particularly when dealing with the complex textures characteristic of remote sensing imagery.To address these limitations,this paper proposes the Improved ResidualModule and AttentionMechanism Network(IRMANet),a novel architecture specifically designed for remote sensing image reconstruction.IRMANet builds upon the Super-Resolution Generative Adversarial Network(SRGAN)framework and introduces several key innovations.First,the Enhanced Residual Unit(ERU)enhances feature reuse and stabilizes training through deep residual connections.Second,the Self-Attention Residual Block(SARB)incorporates a self-attentionmechanism into the Improved Residual Module(IRM)to effectivelymodel long-range dependencies and automatically emphasize salient features.Additionally,the IRM adopts amulti-scale feature fusion strategy to facilitate synergistic interactions between local detail and global semantic information.The effectiveness of each component is validated through ablation studies,while comprehensive comparative experiments on standard remote sensing datasets demonstrate that IRMANet significantly outperforms both the baseline and state-of-the-art methods in terms of perceptual quality and quantitative metrics.Specifically,compared to the baseline model,at a magnification factor of 2,IRMANet achieves an improvement of 0.24 dB in peak signal-to-noise ratio(PSNR)and 0.54 in structural similarity index(SSIM);at a magnification factor of 4,it achieves gains of 0.22 dB in PSNR and 0.51 in SSIM.These results confirm that the proposedmethod effectively enhances detail representation and structural reconstruction accuracy in complex remote sensing scenarios,offering robust technical support for high-precision detection and identification of both military and civilian aircraft.
基金supported by the Chung-Ang University Research Grants in 2023.Alsothe work is supported by the ELLIIT Excellence Center at Linköping–Lund in Information Technology in Sweden.
文摘Recommending personalized travel routes from sparse,implicit feedback poses a significant challenge,as conventional systems often struggle with information overload and fail to capture the complex,sequential nature of user preferences.To address this,we propose a Conditional Generative Adversarial Network(CGAN)that generates diverse and highly relevant itineraries.Our approach begins by constructing a conditional vector that encapsulates a user’s profile.This vector uniquely fuses embeddings from a Heterogeneous Information Network(HIN)to model complex user-place-route relationships,a Recurrent Neural Network(RNN)to capture sequential path dynamics,and Neural Collaborative Filtering(NCF)to incorporate collaborative signals from the wider user base.This comprehensive condition,further enhanced with features representing user interaction confidence and uncertainty,steers a CGAN stabilized by spectral normalization to generate high-fidelity latent route representations,effectively mitigating the data sparsity problem.Recommendations are then formulated using an Anchor-and-Expand algorithm,which selects relevant starting Points of Interest(POI)based on user history,then expands routes through latent similarity matching and geographic coherence optimization,culminating in Traveling Salesman Problem(TSP)-based route optimization for practical travel distances.Experiments on a real-world check-in dataset validate our model’s unique generative capability,achieving F1 scores ranging from 0.163 to 0.305,and near-zero pairs−F1 scores between 0.002 and 0.022.These results confirm the model’s success in generating novel travel routes by recommending new locations and sequences rather than replicating users’past itineraries.This work provides a robust solution for personalized travel planning,capable of generating novel and compelling routes for both new and existing users by learning from collective travel intelligence.
基金This study was supported by:Inner Mongolia Academy of Forestry Sciences Open Research Project(Grant No.KF2024MS03)The Project to Improve the Scientific Research Capacity of the Inner Mongolia Academy of Forestry Sciences(Grant No.2024NLTS04)The Innovation and Entrepreneurship Training Program for Undergraduates of Beijing Forestry University(Grant No.X202410022268).
文摘Remote sensing image super-resolution technology is pivotal for enhancing image quality in critical applications including environmental monitoring,urban planning,and disaster assessment.However,traditional methods exhibit deficiencies in detail recovery and noise suppression,particularly when processing complex landscapes(e.g.,forests,farmlands),leading to artifacts and spectral distortions that limit practical utility.To address this,we propose an enhanced Super-Resolution Generative Adversarial Network(SRGAN)framework featuring three key innovations:(1)Replacement of L1/L2 loss with a robust Charbonnier loss to suppress noise while preserving edge details via adaptive gradient balancing;(2)A multi-loss joint optimization strategy dynamically weighting Charbonnier loss(β=0.5),Visual Geometry Group(VGG)perceptual loss(α=1),and adversarial loss(γ=0.1)to synergize pixel-level accuracy and perceptual quality;(3)A multi-scale residual network(MSRN)capturing cross-scale texture features(e.g.,forest canopies,mountain contours).Validated on Sentinel-2(10 m)and SPOT-6/7(2.5 m)datasets covering 904 km2 in Motuo County,Xizang,our method outperforms the SRGAN baseline(SR4RS)with Peak Signal-to-Noise Ratio(PSNR)gains of 0.29 dB and Structural Similarity Index(SSIM)improvements of 3.08%on forest imagery.Visual comparisons confirm enhanced texture continuity despite marginal Learned Perceptual Image Patch Similarity(LPIPS)increases.The method significantly improves noise robustness and edge retention in complex geomorphology,demonstrating 18%faster response in forest fire early warning and providing high-resolution support for agricultural/urban monitoring.Future work will integrate spectral constraints and lightweight architectures.
