Unmanned aerial vehicle(UAV)-borne gamma-ray spectrum survey plays a crucial role in geological mapping,radioactive mineral exploration,and environmental monitoring.However,raw data are often compromised by flight and...Unmanned aerial vehicle(UAV)-borne gamma-ray spectrum survey plays a crucial role in geological mapping,radioactive mineral exploration,and environmental monitoring.However,raw data are often compromised by flight and instrument background noise,as well as detector resolution limitations,which affect the accuracy of geological interpretations.This study aims to explore the application of the Real-ESRGAN algorithm in the super-resolution reconstruction of UAV-borne gamma-ray spectrum images to enhance spatial resolution and the quality of geological feature visualization.We conducted super-resolution reconstruction experiments with 2×,4×and 6×magnification using the Real-ESRGAN algorithm,comparing the results with three other mainstream algorithms(SRCNN,SRGAN,FSRCNN)to verify the superiority in image quality.The experimental results indicate that Real-ESRGAN achieved a structural similarity index(SSIM)value of 0.950 at 2×magnification,significantly higher than the other algorithms,demonstrating its advantage in detail preservation.Furthermore,Real-ESRGAN effectively reduced ringing and overshoot artifacts,enhancing the clarity of geological structures and mineral deposit sites,thus providing high-quality visual information for geological exploration.展开更多
Single Image Super-Resolution(SISR)seeks to reconstruct high-resolution(HR)images from lowresolution(LR)inputs,thereby enhancing visual fidelity and the perception of fine details.While Transformer-based models—such ...Single Image Super-Resolution(SISR)seeks to reconstruct high-resolution(HR)images from lowresolution(LR)inputs,thereby enhancing visual fidelity and the perception of fine details.While Transformer-based models—such as SwinIR,Restormer,and HAT—have recently achieved impressive results in super-resolution tasks by capturing global contextual information,these methods often suffer from substantial computational and memory overhead,which limits their deployment on resource-constrained edge devices.To address these challenges,we propose a novel lightweight super-resolution network,termed Binary Attention-Guided Information Distillation(BAID),which integrates frequency-aware modeling with a binary attention mechanism to significantly reduce computational complexity and parameter count whilemaintaining strong reconstruction performance.The network combines a high–low frequency decoupling strategy with a local–global attention sharing mechanism,enabling efficient compression of redundant computations through binary attention guidance.At the core of the architecture lies the Attention-Guided Distillation Block(AGDB),which retains the strengths of the information distillation framework while introducing a sparse binary attention module to enhance both inference efficiency and feature representation.Extensive×4 superresolution experiments on four standard benchmarks—Set5,Set14,BSD100,and Urban100—demonstrate that BAID achieves Peak Signal-to-Noise Ratio(PSNR)values of 32.13,28.51,27.47,and 26.15,respectively,with only 1.22 million parameters and 26.1 G Floating-Point Operations(FLOPs),outperforming other state-of-the-art lightweight methods such as Information Multi-Distillation Network(IMDN)and Residual Feature Distillation Network(RFDN).These results highlight the proposed model’s ability to deliver high-quality image reconstruction while offering strong deployment efficiency,making it well-suited for image restoration tasks in resource-limited environments.展开更多
Network-on-Chip(NoC)systems are progressively deployed in connecting massively parallel megacore systems in the new computing architecture.As a result,application mapping has become an important aspect of performance ...Network-on-Chip(NoC)systems are progressively deployed in connecting massively parallel megacore systems in the new computing architecture.As a result,application mapping has become an important aspect of performance and scalability,as current trends require the distribution of computation across network nodes/points.In this paper,we survey a large number of mapping and scheduling techniques designed for NoC architectures.This time,we concentrated on 3D systems.We take a systematic literature review approach to analyze existing methods across static,dynamic,hybrid,and machine-learning-based approaches,alongside preliminary AI-based dynamic models in recent works.We classify them into several main aspects covering power-aware mapping,fault tolerance,load-balancing,and adaptive for dynamic workloads.Also,we assess the efficacy of each method against performance parameters,such as latency,throughput,response time,and error rate.Key challenges,including energy efficiency,real-time adaptability,and reinforcement learning integration,are highlighted as well.To the best of our knowledge,this is one of the recent reviews that identifies both traditional and AI-based algorithms for mapping over a modern NoC,and opens research challenges.Finally,we provide directions for future work toward improved adaptability and scalability via lightweight learned models and hierarchical mapping frameworks.展开更多
This study develops a surrogate super-resolution(SR)framework that accelerates finite element method(FEM)-based computational fluid dynamics(CFD)using deep learning.High-resolution(HR)FEM-based CFDremains computationa...This study develops a surrogate super-resolution(SR)framework that accelerates finite element method(FEM)-based computational fluid dynamics(CFD)using deep learning.High-resolution(HR)FEM-based CFDremains computationally prohibitive for time-sensitive applications,including patient-specific aneurysm hemodynamics where rapid turnaround is valuable.The proposed pipeline learns to reconstruct HR velocity-magnitude fields fromlow-resolution(LR)FEM solutions generated under the same governing equations and boundary conditions.It consistsof three modules:(i)offline pre-training of a residual network on representative vascular geometries;(ii)lightweightfine-tuning to adapt the pretrained model to geometric variability,including patient-specific aneurysm morphologies;and(iii)an unstructured-to-structured sampling strategy with region-of-interest upsampling that concentrates resolution in flow-critical zones(e.g.,the aneurysm sac)rather than the full domain.This targeted reconstruction substantiallyreduces inference and post-processing cost while preserving key HR flow features.Experiments on cerebral aneurysmmodels show that HR velocity-magnitude fields can be recovered with accuracy comparable to direct HR simulationsat less than 1%of the direct HR simulation cost per analysis(LR simulation and SR inference),while adaptation to newgeometries requires only lightweight fine-tuning with limited target-specific HR data.While clinical endpoints andadditional variables(e.g.,pressure or wall-based metrics)are left for future work,the results indicate that the proposedsurrogate SR approach can streamline FEM-based CFD workflows toward near real-time hemodynamic analysis acrossmorphologically similar vascular models.展开更多
Spectrum map construction,which is crucial in cognitive radio(CR)system,visualizes the invisible space of the electromagnetic spectrum for spectrum-resource management and allocation.Traditional reconstruction methods...Spectrum map construction,which is crucial in cognitive radio(CR)system,visualizes the invisible space of the electromagnetic spectrum for spectrum-resource management and allocation.Traditional reconstruction methods are generally for twodimensional(2D)spectrum map and driven by abundant sampling data.In this paper,we propose a data-model-knowledge-driven reconstruction scheme to construct the three-dimensional(3D)spectrum map under multi-radiation source scenarios.We firstly design a maximum and minimum path loss difference(MMPLD)clustering algorithm to detect the number of radiation sources in a 3D space.Then,we develop a joint location-power estimation method based on the heuristic population evolutionary optimization algorithm.Considering the variation of electromagnetic environment,we self-learn the path loss(PL)model based on the sampling data.Finally,the 3D spectrum is reconstructed according to the self-learned PL model and the extracted knowledge of radiation sources.Simulations show that the proposed 3D spectrum map reconstruction scheme not only has splendid adaptability to the environment,but also achieves high spectrum construction accuracy even when the sampling rate is very low.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
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
In recent years, improving patients’ medical experience has become increasingly prominent in medical activities, and patient experience has become the core of medical service models. As an emerging visualization tool...In recent years, improving patients’ medical experience has become increasingly prominent in medical activities, and patient experience has become the core of medical service models. As an emerging visualization tool for exploring patient experience, patient journey mapping has been increasingly applied in the field of medical and health services, with unique advantages in exploring patient experience. This study reviews the overview, content and types, application and effects in the nursing field, and presentation methods of results of patient journey mapping, aiming to provide reference for improving patient experience.展开更多
This paper presents an intelligent patrol and security robot integrating 2D LiDAR and RGB-D vision sensors to achieve semantic simultaneous localization and mapping(SLAM),real-time object recognition,and dynamic obsta...This paper presents an intelligent patrol and security robot integrating 2D LiDAR and RGB-D vision sensors to achieve semantic simultaneous localization and mapping(SLAM),real-time object recognition,and dynamic obstacle avoidance.The system employs the YOLOv7 deep-learning framework for semantic detection and SLAM for localization and mapping,fusing geometric and visual data to build a high-fidelity 2D semantic map.This map enables the robot to identify and project object information for improved situational awareness.Experimental results show that object recognition reached 95.4%mAP@0.5.Semantic completeness increased from 68.7%(single view)to 94.1%(multi-view)with an average position error of 3.1 cm.During navigation,the robot achieved 98.0%reliability,avoided moving obstacles in 90.0%of encounters,and replanned paths in 0.42 s on average.The integration of LiDAR-based SLAMwith deep-learning–driven semantic perception establishes a robust foundation for intelligent,adaptive,and safe robotic navigation in dynamic environments.展开更多
Populus species,important economic species combining rapid growth with broad ecological adaptability,play a critical role in sustainable forestry and bioenergy production.In this study,we performed whole-genome resequ...Populus species,important economic species combining rapid growth with broad ecological adaptability,play a critical role in sustainable forestry and bioenergy production.In this study,we performed whole-genome resequencing of 707 individuals from a full-sib family to develop comprehensive single nucleotide polymorphism(SNP)markers and constructed a high-density genetic linkage map of 19 linkage groups.The total genetic length of the map reached 3623.65 cM with an average marker interval of 0.34 cM.By integrating multidimensional phenotypic data,89 quantitative trait loci(QTL)associated with growth,wood physical and chemical properties,disease resistance,and leaf morphology traits were identified,with logarithm of odds(LOD)scores ranging from 3.13 to 21.72 Notably,pleiotropic analysis revealed significant colocaliza and phenotypic variance explained between 1.7% and 11.6%.-tion hotspots on chromosomes LG1,LG5,LG6,LG8,and LG14,with epistatic interaction network analysis confirming genetic basis of coordinated regulation across multiple traits.Functional annotation of 207 candidate genes showed that R2R3-MYB and bHLH transcription factors and pyruvate kinase-encoding genes were significantly enriched,suggesting crucial roles in lignin biosynthesis and carbon metabolic pathways.Allelic effect analysis indicated that the frequency of favorable alleles associated with target traits ranged from 0.20 to 0.55.Incorporation of QTL-derived favorable alleles as random effects into Bayesian-based genomic selection models led to an increase in prediction accuracy ranging from 1% to 21%,with Bayesian ridge regression as the best predictive model.This study provides valuable genomic resources and genetic insights for deciphering complex trait architecture and advancing molecular breeding in poplar.展开更多
Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classificati...Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classification.This limitation becomes critical when hidden secondary cues—potentially more meaningful than the visualized ones—remain undiscovered.This study introduces CasCAM(Cascaded Class Activation Mapping)to address this fundamental limitation through counterfactual reasoning.By asking“if this dominant cue were absent,what other evidence would the model use?”,CasCAM progressively masks the most salient features and systematically uncovers the hierarchy of classification evidence hidden beneath them.Experimental results demonstrate that CasCAM effectively discovers the full spectrum of reasoning evidence and can be universally applied with nine existing interpretation methods.展开更多
Objective:To retrospectively evaluate the diagnostic efficacy of traditional MRI and T2 Mapping quantitative imaging technology for knee joint cartilage injury,clarify the differences in diagnostic value of the two im...Objective:To retrospectively evaluate the diagnostic efficacy of traditional MRI and T2 Mapping quantitative imaging technology for knee joint cartilage injury,clarify the differences in diagnostic value of the two imaging methods in different injury grades and different cartilage subregions,and provide evidence-based basis for the accurate diagnosis of clinical cartilage injury.Methods:Clinical and imaging data of 286 patients with knee joint lesions admitted to the Affiliated Hospital of Xiangtan Medicine and Health Vocational College from January 2020 to June 2023 were collected retrospectively.All patients underwent both traditional MRI sequences and T2 Mapping sequences.The knee joint cartilage was divided into 14 subregions.Two senior radiologists independently diagnosed the images of the two imaging technologies using a blind method and recorded the cartilage injury grades.The sensitivity,specificity,accuracy,positive predictive value,negative predictive value,and area under the receiver operating characteristic curve(AUC)of the two technologies for diagnosing cartilage injury were calculated and compared,and the differences in their diagnostic efficacy in different injury grades and different subregions were analyzed.Results:A total of 4004 cartilage subregions from 286 patients were included in the analysis,including 1836 injured subregions and 2168 normal subregions.The overall sensitivity(89.7%),accuracy(91.2%),and AUC(0.946)of T2 Mapping quantitative imaging for diagnosing cartilage injury were significantly higher than those of traditional MRI(76.3%,82.5%,and 0.852 respectively),with statistically significant differences(p<0.001);there was no significant difference in specificity between the two(93.5%vs 90.8%,p=0.062).Subgroup analysis showed that T2 Mapping had the most significant diagnostic advantage in early cartilage injury(Grade 1),with sensitivity(78.5%)33.2%higher than that of traditional MRI(45.3%)(p<0.001).Conclusion:The diagnostic efficacy of T2 Mapping quantitative imaging for knee joint cartilage injury is significantly superior to that of traditional MRI,especially in the detection of early cartilage injury and accurate evaluation of weight-bearing area injury.Data verify its clinical applicability and reliability.It can be used as an important supplementary method to traditional MRI,and is recommended for the early diagnosis,grading evaluation,and clinical follow-up of cartilage injury.展开更多
基金supported by the National Natural Science Foundation of China(Nos.12205044 and 12265003)2024 Jiangxi Province Civil-Military Integration Research Institute‘BeiDou+’Project Subtopic(No.2024JXRH0Y06).
文摘Unmanned aerial vehicle(UAV)-borne gamma-ray spectrum survey plays a crucial role in geological mapping,radioactive mineral exploration,and environmental monitoring.However,raw data are often compromised by flight and instrument background noise,as well as detector resolution limitations,which affect the accuracy of geological interpretations.This study aims to explore the application of the Real-ESRGAN algorithm in the super-resolution reconstruction of UAV-borne gamma-ray spectrum images to enhance spatial resolution and the quality of geological feature visualization.We conducted super-resolution reconstruction experiments with 2×,4×and 6×magnification using the Real-ESRGAN algorithm,comparing the results with three other mainstream algorithms(SRCNN,SRGAN,FSRCNN)to verify the superiority in image quality.The experimental results indicate that Real-ESRGAN achieved a structural similarity index(SSIM)value of 0.950 at 2×magnification,significantly higher than the other algorithms,demonstrating its advantage in detail preservation.Furthermore,Real-ESRGAN effectively reduced ringing and overshoot artifacts,enhancing the clarity of geological structures and mineral deposit sites,thus providing high-quality visual information for geological exploration.
基金funded by Project of Sichuan Provincial Department of Science and Technology under 2025JDKP0150the Fundamental Research Funds for the Central Universities under 25CAFUC03093.
文摘Single Image Super-Resolution(SISR)seeks to reconstruct high-resolution(HR)images from lowresolution(LR)inputs,thereby enhancing visual fidelity and the perception of fine details.While Transformer-based models—such as SwinIR,Restormer,and HAT—have recently achieved impressive results in super-resolution tasks by capturing global contextual information,these methods often suffer from substantial computational and memory overhead,which limits their deployment on resource-constrained edge devices.To address these challenges,we propose a novel lightweight super-resolution network,termed Binary Attention-Guided Information Distillation(BAID),which integrates frequency-aware modeling with a binary attention mechanism to significantly reduce computational complexity and parameter count whilemaintaining strong reconstruction performance.The network combines a high–low frequency decoupling strategy with a local–global attention sharing mechanism,enabling efficient compression of redundant computations through binary attention guidance.At the core of the architecture lies the Attention-Guided Distillation Block(AGDB),which retains the strengths of the information distillation framework while introducing a sparse binary attention module to enhance both inference efficiency and feature representation.Extensive×4 superresolution experiments on four standard benchmarks—Set5,Set14,BSD100,and Urban100—demonstrate that BAID achieves Peak Signal-to-Noise Ratio(PSNR)values of 32.13,28.51,27.47,and 26.15,respectively,with only 1.22 million parameters and 26.1 G Floating-Point Operations(FLOPs),outperforming other state-of-the-art lightweight methods such as Information Multi-Distillation Network(IMDN)and Residual Feature Distillation Network(RFDN).These results highlight the proposed model’s ability to deliver high-quality image reconstruction while offering strong deployment efficiency,making it well-suited for image restoration tasks in resource-limited environments.
基金the Deanship of Graduate Studies and Scientific Research at University of Bisha for supporting this work through the Fast-Track Research Support Programthe Deanship of Scientific Research at Northern Border University,Arar,KSA for funding this research work through the project number“NBU-FFR-2025-2903-09”.
文摘Network-on-Chip(NoC)systems are progressively deployed in connecting massively parallel megacore systems in the new computing architecture.As a result,application mapping has become an important aspect of performance and scalability,as current trends require the distribution of computation across network nodes/points.In this paper,we survey a large number of mapping and scheduling techniques designed for NoC architectures.This time,we concentrated on 3D systems.We take a systematic literature review approach to analyze existing methods across static,dynamic,hybrid,and machine-learning-based approaches,alongside preliminary AI-based dynamic models in recent works.We classify them into several main aspects covering power-aware mapping,fault tolerance,load-balancing,and adaptive for dynamic workloads.Also,we assess the efficacy of each method against performance parameters,such as latency,throughput,response time,and error rate.Key challenges,including energy efficiency,real-time adaptability,and reinforcement learning integration,are highlighted as well.To the best of our knowledge,this is one of the recent reviews that identifies both traditional and AI-based algorithms for mapping over a modern NoC,and opens research challenges.Finally,we provide directions for future work toward improved adaptability and scalability via lightweight learned models and hierarchical mapping frameworks.
文摘This study develops a surrogate super-resolution(SR)framework that accelerates finite element method(FEM)-based computational fluid dynamics(CFD)using deep learning.High-resolution(HR)FEM-based CFDremains computationally prohibitive for time-sensitive applications,including patient-specific aneurysm hemodynamics where rapid turnaround is valuable.The proposed pipeline learns to reconstruct HR velocity-magnitude fields fromlow-resolution(LR)FEM solutions generated under the same governing equations and boundary conditions.It consistsof three modules:(i)offline pre-training of a residual network on representative vascular geometries;(ii)lightweightfine-tuning to adapt the pretrained model to geometric variability,including patient-specific aneurysm morphologies;and(iii)an unstructured-to-structured sampling strategy with region-of-interest upsampling that concentrates resolution in flow-critical zones(e.g.,the aneurysm sac)rather than the full domain.This targeted reconstruction substantiallyreduces inference and post-processing cost while preserving key HR flow features.Experiments on cerebral aneurysmmodels show that HR velocity-magnitude fields can be recovered with accuracy comparable to direct HR simulationsat less than 1%of the direct HR simulation cost per analysis(LR simulation and SR inference),while adaptation to newgeometries requires only lightweight fine-tuning with limited target-specific HR data.While clinical endpoints andadditional variables(e.g.,pressure or wall-based metrics)are left for future work,the results indicate that the proposedsurrogate SR approach can streamline FEM-based CFD workflows toward near real-time hemodynamic analysis acrossmorphologically similar vascular models.
基金National Key Scientific Instrument and Equipment Development Project under Grant No.61827801the open research fund of State Key Laboratory of Integrated Services Networks,No.ISN22-11+1 种基金Natural Science Foundation of Jiangsu Province,No.BK20211182open research fund of National Mobile Communications Research Laboratory,Southeast University,No.2022D04。
文摘Spectrum map construction,which is crucial in cognitive radio(CR)system,visualizes the invisible space of the electromagnetic spectrum for spectrum-resource management and allocation.Traditional reconstruction methods are generally for twodimensional(2D)spectrum map and driven by abundant sampling data.In this paper,we propose a data-model-knowledge-driven reconstruction scheme to construct the three-dimensional(3D)spectrum map under multi-radiation source scenarios.We firstly design a maximum and minimum path loss difference(MMPLD)clustering algorithm to detect the number of radiation sources in a 3D space.Then,we develop a joint location-power estimation method based on the heuristic population evolutionary optimization algorithm.Considering the variation of electromagnetic environment,we self-learn the path loss(PL)model based on the sampling data.Finally,the 3D spectrum is reconstructed according to the self-learned PL model and the extracted knowledge of radiation sources.Simulations show that the proposed 3D spectrum map reconstruction scheme not only has splendid adaptability to the environment,but also achieves high spectrum construction accuracy even when the sampling rate is very low.
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.
基金Scientific Research Fund Project of Yunnan Open University:“Research on Incentive Mechanisms for Cadres’Responsibility and Action in Yunnan Universities in the New Era and New Journey”(Project No.:23YNOU27)。
文摘In recent years, improving patients’ medical experience has become increasingly prominent in medical activities, and patient experience has become the core of medical service models. As an emerging visualization tool for exploring patient experience, patient journey mapping has been increasingly applied in the field of medical and health services, with unique advantages in exploring patient experience. This study reviews the overview, content and types, application and effects in the nursing field, and presentation methods of results of patient journey mapping, aiming to provide reference for improving patient experience.
基金supported by the National Science and Technology Council of under Grant NSTC 114-2221-E-130-007.
文摘This paper presents an intelligent patrol and security robot integrating 2D LiDAR and RGB-D vision sensors to achieve semantic simultaneous localization and mapping(SLAM),real-time object recognition,and dynamic obstacle avoidance.The system employs the YOLOv7 deep-learning framework for semantic detection and SLAM for localization and mapping,fusing geometric and visual data to build a high-fidelity 2D semantic map.This map enables the robot to identify and project object information for improved situational awareness.Experimental results show that object recognition reached 95.4%mAP@0.5.Semantic completeness increased from 68.7%(single view)to 94.1%(multi-view)with an average position error of 3.1 cm.During navigation,the robot achieved 98.0%reliability,avoided moving obstacles in 90.0%of encounters,and replanned paths in 0.42 s on average.The integration of LiDAR-based SLAMwith deep-learning–driven semantic perception establishes a robust foundation for intelligent,adaptive,and safe robotic navigation in dynamic environments.
基金supported by the National Key Research and Development Plan of China(2021YFD2200202)the Key Research and Development Project of Jiangsu Province,China(BE2021366).
文摘Populus species,important economic species combining rapid growth with broad ecological adaptability,play a critical role in sustainable forestry and bioenergy production.In this study,we performed whole-genome resequencing of 707 individuals from a full-sib family to develop comprehensive single nucleotide polymorphism(SNP)markers and constructed a high-density genetic linkage map of 19 linkage groups.The total genetic length of the map reached 3623.65 cM with an average marker interval of 0.34 cM.By integrating multidimensional phenotypic data,89 quantitative trait loci(QTL)associated with growth,wood physical and chemical properties,disease resistance,and leaf morphology traits were identified,with logarithm of odds(LOD)scores ranging from 3.13 to 21.72 Notably,pleiotropic analysis revealed significant colocaliza and phenotypic variance explained between 1.7% and 11.6%.-tion hotspots on chromosomes LG1,LG5,LG6,LG8,and LG14,with epistatic interaction network analysis confirming genetic basis of coordinated regulation across multiple traits.Functional annotation of 207 candidate genes showed that R2R3-MYB and bHLH transcription factors and pyruvate kinase-encoding genes were significantly enriched,suggesting crucial roles in lignin biosynthesis and carbon metabolic pathways.Allelic effect analysis indicated that the frequency of favorable alleles associated with target traits ranged from 0.20 to 0.55.Incorporation of QTL-derived favorable alleles as random effects into Bayesian-based genomic selection models led to an increase in prediction accuracy ranging from 1% to 21%,with Bayesian ridge regression as the best predictive model.This study provides valuable genomic resources and genetic insights for deciphering complex trait architecture and advancing molecular breeding in poplar.
基金supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF),funded by the Ministry of Education(RS-2023-00249743).
文摘Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classification.This limitation becomes critical when hidden secondary cues—potentially more meaningful than the visualized ones—remain undiscovered.This study introduces CasCAM(Cascaded Class Activation Mapping)to address this fundamental limitation through counterfactual reasoning.By asking“if this dominant cue were absent,what other evidence would the model use?”,CasCAM progressively masks the most salient features and systematically uncovers the hierarchy of classification evidence hidden beneath them.Experimental results demonstrate that CasCAM effectively discovers the full spectrum of reasoning evidence and can be universally applied with nine existing interpretation methods.
基金Application Research of MRI Physiological Quantitative Imaging Technology in the Diagnosis of Cartilage Injury(Project No.:RCYJ2021-04)。
文摘Objective:To retrospectively evaluate the diagnostic efficacy of traditional MRI and T2 Mapping quantitative imaging technology for knee joint cartilage injury,clarify the differences in diagnostic value of the two imaging methods in different injury grades and different cartilage subregions,and provide evidence-based basis for the accurate diagnosis of clinical cartilage injury.Methods:Clinical and imaging data of 286 patients with knee joint lesions admitted to the Affiliated Hospital of Xiangtan Medicine and Health Vocational College from January 2020 to June 2023 were collected retrospectively.All patients underwent both traditional MRI sequences and T2 Mapping sequences.The knee joint cartilage was divided into 14 subregions.Two senior radiologists independently diagnosed the images of the two imaging technologies using a blind method and recorded the cartilage injury grades.The sensitivity,specificity,accuracy,positive predictive value,negative predictive value,and area under the receiver operating characteristic curve(AUC)of the two technologies for diagnosing cartilage injury were calculated and compared,and the differences in their diagnostic efficacy in different injury grades and different subregions were analyzed.Results:A total of 4004 cartilage subregions from 286 patients were included in the analysis,including 1836 injured subregions and 2168 normal subregions.The overall sensitivity(89.7%),accuracy(91.2%),and AUC(0.946)of T2 Mapping quantitative imaging for diagnosing cartilage injury were significantly higher than those of traditional MRI(76.3%,82.5%,and 0.852 respectively),with statistically significant differences(p<0.001);there was no significant difference in specificity between the two(93.5%vs 90.8%,p=0.062).Subgroup analysis showed that T2 Mapping had the most significant diagnostic advantage in early cartilage injury(Grade 1),with sensitivity(78.5%)33.2%higher than that of traditional MRI(45.3%)(p<0.001).Conclusion:The diagnostic efficacy of T2 Mapping quantitative imaging for knee joint cartilage injury is significantly superior to that of traditional MRI,especially in the detection of early cartilage injury and accurate evaluation of weight-bearing area injury.Data verify its clinical applicability and reliability.It can be used as an important supplementary method to traditional MRI,and is recommended for the early diagnosis,grading evaluation,and clinical follow-up of cartilage injury.
