Rapid diagnosis of Salmonella is crucial for the effective control of food safety incidents, especially in regions with poor hygiene conditions. Polymerase chain reaction(PCR), as a promising tool for Salmonella detec...Rapid diagnosis of Salmonella is crucial for the effective control of food safety incidents, especially in regions with poor hygiene conditions. Polymerase chain reaction(PCR), as a promising tool for Salmonella detection, is facing a lack of simple and fast sensing methods that are compatible with field applications in resource-limited areas. In this work, we developed a sensing approach to identify PCR-amplified Salmonella genomic DNA with the naked eye in a snapshot. Based on the ratiometric fiuorescence signals from SYBR Green Ⅰ and Hydroxyl naphthol blue, positive samples stood out from negative ones with a distinct color pattern under UV exposure. The proposed sensing scheme enabled highly specific identification of Salmonella with a detection limit at the single-copy level. Also, as a supplement to the intuitive naked-eye visualization results, numerical analysis of the colored images was available with a smartphone app to extract RGB values from colored images. This work provides a simple, rapid, and user-friendly solution for PCR identification, which promises great potential in molecular diagnosis of Salmonella and other pathogens in field.展开更多
This work is devoted to numerical analysis of thermo-hydromechanical problem and cracking process in saturated porous media in the context of deep geological disposal of radioactive waste.The fundamental background of...This work is devoted to numerical analysis of thermo-hydromechanical problem and cracking process in saturated porous media in the context of deep geological disposal of radioactive waste.The fundamental background of thermo-poro-elastoplasticity theory is first summarized.The emphasis is put on the effect of pore fluid pressure on plastic deformation.A micromechanics-based elastoplastic model is then presented for a class of clayey rocks considered as host rock.Based on linear and nonlinear homogenization techniques,the proposed model is able to systematically account for the influences of porosity and mineral composition on macroscopic elastic properties and plastic yield strength.The initial anisotropy and time-dependent deformation are also taken into account.The induced cracking process is described by using a non-local damage model.A specific hybrid formulation is proposed,able to conveniently capture tensile,shear and mixed cracks.In particular,the influences of pore pressure and confining stress on the shear cracking mechanism are taken into account.The proposed model is applied to investigating thermo-hydromechanical responses and induced damage evolution in laboratory tests at the sample scale.In the last part,an in situ heating experiment is analyzed by using the proposed model.Numerical results are compared with experimental data and field measurements in terms of temperature variation,pore fluid pressure change and induced damaged zone.展开更多
The ascent of the metaverse signifies a profound transformation in our digital landscape, ushering in a complex network of interlinked virtual domains and digital spaces. In this burgeoning metaverse, a paradigm shift...The ascent of the metaverse signifies a profound transformation in our digital landscape, ushering in a complex network of interlinked virtual domains and digital spaces. In this burgeoning metaverse, a paradigm shift is seen in how people engage, collaborate, and become immersed in digital environments. An especially intriguing concept taking root within this metaverse landscape is that of digital twins. Initially rooted in industrial and Internet of Things(IoT) contexts, digital twins are now making their mark in the metaverse, presenting opportunities to elevate user experiences, introduce novel dimensions of interaction, and seamlessly bridge the divide between the virtual and physical realms. Digital twins, conceived initially to replicate physical entities in real-time, have transcended their industrial origins in this new metaverse context. They no longer solely replicate physical objects but extend their domain to encompass digital entities, avatars, virtual environments, and users. Despite the vital contributions of digital twins in the metaverse, there has been no research that has explored the applications and scope of digital twins in the metaverse comprehensively. However, there are a few papers focusing on some particular applications. Addressing this research gap, we present an in-depth review of the pivotal role of application digital twins in the metaverse. We present 15 digital twin applications in the metaverse, ranging from simulation and training to emergency preparedness. This study outlines the critical limitations of integrating digital twins and metaverse and several future research directions.展开更多
Techniques in deep learning have significantly boosted the accuracy and productivity of computer vision segmentation tasks.This article offers an intriguing architecture for semantic,instance,and panoptic segmentation...Techniques in deep learning have significantly boosted the accuracy and productivity of computer vision segmentation tasks.This article offers an intriguing architecture for semantic,instance,and panoptic segmentation using EfficientNet-B7 and Bidirectional Feature Pyramid Networks(Bi-FPN).When implemented in place of the EfficientNet-B5 backbone,EfficientNet-B7 strengthens the model’s feature extraction capabilities and is far more appropriate for real-world applications.By ensuring superior multi-scale feature fusion,Bi-FPN integration enhances the segmentation of complex objects across various urban environments.The design suggested is examined on rigorous datasets,encompassing Cityscapes,Common Objects in Context,KITTI Karlsruhe Institute of Technology and Toyota Technological Institute,and Indian Driving Dataset,which replicate numerous real-world driving conditions.During extensive training,validation,and testing,the model showcases major gains in segmentation accuracy and surpasses state-of-the-art performance in semantic,instance,and panoptic segmentation tasks.Outperforming present methods,the recommended approach generates noteworthy gains in Panoptic Quality:+0.4%on Cityscapes,+0.2%on COCO,+1.7%on KITTI,and+0.4%on IDD.These changes show just how efficient it is in various driving circumstances and datasets.This study emphasizes the potential of EfficientNet-B7 and Bi-FPN to provide dependable,high-precision segmentation in computer vision applications,primarily autonomous driving.The research results suggest that this framework efficiently tackles the constraints of practical situations while delivering a robust solution for high-performance tasks involving segmentation.展开更多
Integrating multiple medical imaging techniques,including Magnetic Resonance Imaging(MRI),Computed Tomography,Positron Emission Tomography(PET),and ultrasound,provides a comprehensive view of the patient health status...Integrating multiple medical imaging techniques,including Magnetic Resonance Imaging(MRI),Computed Tomography,Positron Emission Tomography(PET),and ultrasound,provides a comprehensive view of the patient health status.Each of these methods contributes unique diagnostic insights,enhancing the overall assessment of patient condition.Nevertheless,the amalgamation of data from multiple modalities presents difficulties due to disparities in resolution,data collection methods,and noise levels.While traditional models like Convolutional Neural Networks(CNNs)excel in single-modality tasks,they struggle to handle multi-modal complexities,lacking the capacity to model global relationships.This research presents a novel approach for examining multi-modal medical imagery using a transformer-based system.The framework employs self-attention and cross-attention mechanisms to synchronize and integrate features across various modalities.Additionally,it shows resilience to variations in noise and image quality,making it adaptable for real-time clinical use.To address the computational hurdles linked to transformer models,particularly in real-time clinical applications in resource-constrained environments,several optimization techniques have been integrated to boost scalability and efficiency.Initially,a streamlined transformer architecture was adopted to minimize the computational load while maintaining model effectiveness.Methods such as model pruning,quantization,and knowledge distillation have been applied to reduce the parameter count and enhance the inference speed.Furthermore,efficient attention mechanisms such as linear or sparse attention were employed to alleviate the substantial memory and processing requirements of traditional self-attention operations.For further deployment optimization,researchers have implemented hardware-aware acceleration strategies,including the use of TensorRT and ONNX-based model compression,to ensure efficient execution on edge devices.These optimizations allow the approach to function effectively in real-time clinical settings,ensuring viability even in environments with limited resources.Future research directions include integrating non-imaging data to facilitate personalized treatment and enhancing computational efficiency for implementation in resource-limited environments.This study highlights the transformative potential of transformer models in multi-modal medical imaging,offering improvements in diagnostic accuracy and patient care outcomes.展开更多
This article reviews recent advancements,innovative strategies,and the key challenges in Drug Delivery Systems(DDS)for bone regeneration,focusing on tissue engineering.It highlights the limitations of current surgical...This article reviews recent advancements,innovative strategies,and the key challenges in Drug Delivery Systems(DDS)for bone regeneration,focusing on tissue engineering.It highlights the limitations of current surgical interventions forbone regeneration,particularly autogenic bone grafts,and discusses the exploration of alternative materials and methods,including allogeneic and xenogeneic bone grafts,synthetic materials,and biodegradable polymers.The objective is to provide a comprehensive understanding of how contemporary DDS can be optimized and integrated with tissue engineering approaches for more effective bone regeneration therapies.The review explained the mechanisms through which DDS enhance bone repair processes,identifies critical factors influencing their efficacy and safety,and offers an overview of current trends and future perspectives in the field.It emphasizes the need for advanced strategies in bone regeneration that focus on precise control of DDS to address bone conditions such as osteoporosis,trauma,and genetic predispositions leading to fractures.展开更多
Reliable and efficient communication is essential for Unmanned Aerial Vehicle(UAV)networks,especially in dynamic and resource-constrained environments such as disaster management,surveillance,and environmental monitor...Reliable and efficient communication is essential for Unmanned Aerial Vehicle(UAV)networks,especially in dynamic and resource-constrained environments such as disaster management,surveillance,and environmental monitoring.Frequent topology changes,high mobility,and limited energy availability pose significant challenges to maintaining stable and high-performance routing.Traditional routing protocols,such as Ad hoc On-Demand Distance Vector(AODV),Load-Balanced Optimized Predictive Ad hoc Routing(LB-OPAR),and Destination-Sequenced Distance Vector(DSDV),often experience performance degradation under such conditions.To address these limitations,this study evaluates the effectiveness of Dynamic Adaptive Routing(DAR),a protocol designed to adapt routing decisions in real time based on network dynamics and resource constraints.The research utilizes the Network Simulator 3(NS-3)platform to conduct controlled simulations,measuring key performance indicators such as latency,Packet Delivery Ratio(PDR),energy consumption,and throughput.Comparative analysis reveals that DAR consistently outperforms conventional protocols,achieving a 20%-30% reduction in latency,a 25% decrease in energy consumption,and marked improvements in throughput and PDR.These results highlight DAR’s ability to maintain high communication reliability while optimizing resource usage in challenging operational scenarios.By providing empirical evidence of DAR’s advantages in highly dynamic UAV network environments,this study contributes to advancing adaptive routing strategies.The findings not only validate DAR’s robustness and scalability but also lay the groundwork for integrating artificial intelligence-driven decision-making and real-world UAV deployment.Future work will explore cross-layer optimization,multi-UAV coordination,and experimental validation in field trials,aiming to further enhance communication resilience and energy efficiency in next-generation aerial networks.展开更多
The integration of the dynamic adaptive routing(DAR)algorithm in unmanned aerial vehicle(UAV)networks offers a significant advancement in addressing the challenges posed by next-generation communication systems like 6...The integration of the dynamic adaptive routing(DAR)algorithm in unmanned aerial vehicle(UAV)networks offers a significant advancement in addressing the challenges posed by next-generation communication systems like 6G.DAR’s innovative framework incorporates real-time path adjustments,energy-aware routing,and predictive models,optimizing reliability,latency,and energy efficiency in UAV operations.This study demonstrated DAR’s superior performance in dynamic,large-scale environments,proving its adaptability and scalability for real-time applications.As 6G networks evolve,challenges such as bandwidth demands,global spectrum management,security vulnerabilities,and financial feasibility become prominent.DAR aligns with these demands by offering robust solutions that enhance data transmission while ensuring network reliability.However,obstacles like global route optimization and signal interference in urban areas necessitate further refinement.Future directions should explore hybrid approaches,the integration of machine learning,and comprehensive real-world testing to maximize DAR’s capabilities.The findings underscore DAR’s pivotal role in enabling efficient and sustainable UAV communication systems,contributing to the broader landscape of wireless technology and laying a foundation for the seamless transition to 6G networks.展开更多
The Yellow River Delta(YRD)of China is one of the most active land-sea interaction deltas in the world.However,due to human activities and climate change,it has undergone significant changes,including the degradation ...The Yellow River Delta(YRD)of China is one of the most active land-sea interaction deltas in the world.However,due to human activities and climate change,it has undergone significant changes,including the degradation of natural wetlands and saltwater intrusion.As an integral part of soil microorganisms,fungi play a crucial role in maintaining and stabilizing the function of wetland ecosystems.To better understand the composition and diversity changes of fungal communities along a salinity gradient in the YRD of China and their relationship with environmental factors,fungal diversity,abundance,and composition in the sediments of four typical vegetation communities spanning from the riverbank to the seaside were investigated.The results showed that the electrical conductivity(EC)increased significantly from the riverbank to the coastal area(P<0.05),but the levels of total nitrogen(TN),total carbon(TC),total sulfur(TS),available phosphorous(AP),and ammonium(NH_(4)^(+)-N)increased in Phragmites australis community and then experienced a significant decrease in Tamarix chinensis community and Suaeda salsa community(P<0.05).The alpha diversity(Shannon and Simpson indices)of the soil fungal community exhibited a negative correlation with EC.There was a significant alteration in the structure of the fungal community,primarily influenced by EC and NO_(3)^(-)-N.Ascomycota was found to be the most abundant phylum,and its relative abundance is positively correlated with pH and TS.The relative abundance of Sordariomycetes,the second-largest class of Ascomycota,reached 38.95%.Salinity was identified as the most important factor driving changes in soil fungal community composition.In summary,the fungal community changed significantly along the salinity gradient,and different environmental factors impacted various tiers of fungal populations differently.The findings of this study lay the groundwork for comprehending soil fungal communities and their primary influencing factors in newly formed wetlands.展开更多
Scarcity of empirical studies turning the concepts into cost-effective practices is a barrier in achieving the desired trajectory and scale of ecosystem restoration.The present study aimed to assess(i)potential of tre...Scarcity of empirical studies turning the concepts into cost-effective practices is a barrier in achieving the desired trajectory and scale of ecosystem restoration.The present study aimed to assess(i)potential of tree-bamboo-medicinal herb mixed plantation founded on the concept of adaptive comanagement in restoration of degraded community forest in a temperate village of Indian Himalaya and(ii)persistence of offer of local people to voluntarily maintain and expand the trial after its economic benefit/cost ratio became>1.0.Biodiversity,carbon stock and economic benefits were assessed in the restored forest 1,3 and 10 years after 7-year-long funding phase(i.e.,8,10 and 20 years after initial planting in 1991),and other land uses in the village landscape.Significant economic loss occurred from gregarious flowering induced mass mortality of bamboo in the 2nd year after funding phase but it was outweighed by the gain from walnut fruiting.People maintained recovery by transplanting Nepalese Alder(Alnus nepalensis)in gaps.The 20-year-old restored forest land had 17%of aboveground and 75%of belowground carbon stocks,and 39%of flowering species present in the intact forest.Restored forest had only four of the eight Near-threatened/Threatened species present in intact forest.Further,intact forest was monetarily the most efficient land use despite absence of payments for its ecosystem services.People did not expand the trial or medicinal plant cultivation in farms induced by it.They abandoned cropping in 39%farm area and leased 24%abandoned area to a company.Flowering plant species richness and carbon stocks changed at the ecosystem scale but not at the village landscape scale.Emission from agricultural abandonment nullified carbon sequestration by forest restoration.Community forest restoration should render both material/monetary and nonmaterial/non-monetary benefits to people.Cultural landscapes should be taken as spatial units for ecosystem restoration planning,monitoring and evaluation.展开更多
The Miombo ecoregion covers eastern and southern Africa,with variations in plant species composition,structure,and biomass across a broad precipitation gradient.Most studies of woody plant communities focus exclusivel...The Miombo ecoregion covers eastern and southern Africa,with variations in plant species composition,structure,and biomass across a broad precipitation gradient.Most studies of woody plant communities focus exclusively on larger overstorey trees(≥5 or≥10cm stem diameter),overlooking the contribution of small trees and shrubs in the understorey,which can comprise a significant portion of total biomass and diversity.Here,we evaluate the contribution of both large overstorey and small understorey woody plants to species diversity and above-ground biomass(AGB),with 17 plots(0.5-1ha)across five sites representing both extremes of rainfall gradient spanning the Miombo ecoregion,in northeast Namibia(500-700mm mean annual precipitation,MAP)and southern Democratic Republic of Congo(DRC)(>1,200mm MAP).Mean AGB per site ranged from 21 to 119Mg·ha^(-1),increasing with rainfall,while the proportional AGB contribution of small trees,saplings,and shrubs decreased.In dry Namibia,small trees,saplings,and shrubs(<5cm DBH)contributed up to 28.2%of total AGB(mean±standard deviation:18.3%±3.4%),whereas in wet DRC,they contributed only up to 2.5%(2.3%±1.4%).Namibian sites,on average,contained a large proportion of woody species diversity exclusively in small trees and shrubs(<5cm DBH),with 55 species representing 59.4%of the total diversity.In contrast,DRC sites had higher overall small woody plant diversity(66 species)but fewer species found exclusively as small individuals(25.2%),with many saplings that grow to larger trees.Understorey composition also differed,with saplings of overstorey trees dominating in DRC,while shrubs dominated in Namibia.Our findings show that woody biomass and diversity in dry woodlands are substantially underestimated when studies focus only on larger trees.This highlights the need to consider all woody vegetation to better understand woody plant diversity and biomass variation.展开更多
Cardiovascular diseases(CVDs)remain one of the foremost causes of death globally;hence,the need for several must-have,advanced automated diagnostic solutions towards early detection and intervention.Traditional auscul...Cardiovascular diseases(CVDs)remain one of the foremost causes of death globally;hence,the need for several must-have,advanced automated diagnostic solutions towards early detection and intervention.Traditional auscultation of cardiovascular sounds is heavily reliant on clinical expertise and subject to high variability.To counter this limitation,this study proposes an AI-driven classification system for cardiovascular sounds whereby deep learning techniques are engaged to automate the detection of an abnormal heartbeat.We employ FastAI vision-learner-based convolutional neural networks(CNNs)that include ResNet,DenseNet,VGG,ConvNeXt,SqueezeNet,and AlexNet to classify heart sound recordings.Instead of raw waveform analysis,the proposed approach transforms preprocessed cardiovascular audio signals into spectrograms,which are suited for capturing temporal and frequency-wise patterns.The models are trained on the PASCAL Cardiovascular Challenge dataset while taking into consideration the recording variations,noise levels,and acoustic distortions.To demonstrate generalization,external validation using Google’s Audio set Heartbeat Sound dataset was performed using a dataset rich in cardiovascular sounds.Comparative analysis revealed that DenseNet-201,ConvNext Large,and ResNet-152 could deliver superior performance to the other architectures,achieving an accuracy of 81.50%,a precision of 85.50%,and an F1-score of 84.50%.In the process,we performed statistical significance testing,such as the Wilcoxon signed-rank test,to validate performance improvements over traditional classification methods.Beyond the technical contributions,the research underscores clinical integration,outlining a pathway in which the proposed system can augment conventional electronic stethoscopes and telemedicine platforms in the AI-assisted diagnostic workflows.We also discuss in detail issues of computational efficiency,model interpretability,and ethical considerations,particularly concerning algorithmic bias stemming from imbalanced datasets and the need for real-time processing in clinical settings.The study describes a scalable,automated system combining deep learning,feature extraction using spectrograms,and external validation that can assist healthcare providers in the early and accurate detection of cardiovascular disease.AI-driven solutions can be viable in improving access,reducing delays in diagnosis,and ultimately even the continued global burden of heart disease.展开更多
为促进居民用户柔性负荷高效参与需求响应,帮助用户从被动角色转变为主动角色,实现需求侧最大效益。该文在智能电网环境下,根据用电设备的特性,以概率论的角度对家电设备状态进行描述定义,基于异步深度强化学习(asynchronous deep reinf...为促进居民用户柔性负荷高效参与需求响应,帮助用户从被动角色转变为主动角色,实现需求侧最大效益。该文在智能电网环境下,根据用电设备的特性,以概率论的角度对家电设备状态进行描述定义,基于异步深度强化学习(asynchronous deep reinforcement learning,ADRL)进行家庭能源管理系统调度的在线优化。学习过程采用异步优势演员–评判家(asynchronous advantage actor-critic,A3C)方法,联合用户历史用电设备运行状态的概率分布,通过多智能体利用CPU多线程功能同时执行多个动作的决策。该方法在包括光伏发电、电动汽车和居民住宅电器设备信息的某高维数据库上进行仿真验证。最后通过不同住宅情境下的优化决策效果对比分析可知,所提在线能耗调度策略可用于向电力用户提供实时反馈,以实现用户用电经济性目标。展开更多
基金supported by the Macao Science and Technology Development Fund(FDCT)(Nos.FDCT 0029/2021/A1,FDCT0002/2021/AKP,004/2023/SKL,0036/2021/APD)University of Macao(No.MYRG-GRG2023-00034-IME,SRG2024-00057IME)+2 种基金Dr.Stanley Ho Medical Development Foundation(No.SHMDF-OIRFS/2024/001)Zhuhai Huafa Group(No.HF-006-2021)Guangdong Science and Technology Department(No.2022A0505030022)。
文摘Rapid diagnosis of Salmonella is crucial for the effective control of food safety incidents, especially in regions with poor hygiene conditions. Polymerase chain reaction(PCR), as a promising tool for Salmonella detection, is facing a lack of simple and fast sensing methods that are compatible with field applications in resource-limited areas. In this work, we developed a sensing approach to identify PCR-amplified Salmonella genomic DNA with the naked eye in a snapshot. Based on the ratiometric fiuorescence signals from SYBR Green Ⅰ and Hydroxyl naphthol blue, positive samples stood out from negative ones with a distinct color pattern under UV exposure. The proposed sensing scheme enabled highly specific identification of Salmonella with a detection limit at the single-copy level. Also, as a supplement to the intuitive naked-eye visualization results, numerical analysis of the colored images was available with a smartphone app to extract RGB values from colored images. This work provides a simple, rapid, and user-friendly solution for PCR identification, which promises great potential in molecular diagnosis of Salmonella and other pathogens in field.
基金supported by the French National Agency for radioactive waste management(ANDRA).
文摘This work is devoted to numerical analysis of thermo-hydromechanical problem and cracking process in saturated porous media in the context of deep geological disposal of radioactive waste.The fundamental background of thermo-poro-elastoplasticity theory is first summarized.The emphasis is put on the effect of pore fluid pressure on plastic deformation.A micromechanics-based elastoplastic model is then presented for a class of clayey rocks considered as host rock.Based on linear and nonlinear homogenization techniques,the proposed model is able to systematically account for the influences of porosity and mineral composition on macroscopic elastic properties and plastic yield strength.The initial anisotropy and time-dependent deformation are also taken into account.The induced cracking process is described by using a non-local damage model.A specific hybrid formulation is proposed,able to conveniently capture tensile,shear and mixed cracks.In particular,the influences of pore pressure and confining stress on the shear cracking mechanism are taken into account.The proposed model is applied to investigating thermo-hydromechanical responses and induced damage evolution in laboratory tests at the sample scale.In the last part,an in situ heating experiment is analyzed by using the proposed model.Numerical results are compared with experimental data and field measurements in terms of temperature variation,pore fluid pressure change and induced damaged zone.
文摘The ascent of the metaverse signifies a profound transformation in our digital landscape, ushering in a complex network of interlinked virtual domains and digital spaces. In this burgeoning metaverse, a paradigm shift is seen in how people engage, collaborate, and become immersed in digital environments. An especially intriguing concept taking root within this metaverse landscape is that of digital twins. Initially rooted in industrial and Internet of Things(IoT) contexts, digital twins are now making their mark in the metaverse, presenting opportunities to elevate user experiences, introduce novel dimensions of interaction, and seamlessly bridge the divide between the virtual and physical realms. Digital twins, conceived initially to replicate physical entities in real-time, have transcended their industrial origins in this new metaverse context. They no longer solely replicate physical objects but extend their domain to encompass digital entities, avatars, virtual environments, and users. Despite the vital contributions of digital twins in the metaverse, there has been no research that has explored the applications and scope of digital twins in the metaverse comprehensively. However, there are a few papers focusing on some particular applications. Addressing this research gap, we present an in-depth review of the pivotal role of application digital twins in the metaverse. We present 15 digital twin applications in the metaverse, ranging from simulation and training to emergency preparedness. This study outlines the critical limitations of integrating digital twins and metaverse and several future research directions.
文摘Techniques in deep learning have significantly boosted the accuracy and productivity of computer vision segmentation tasks.This article offers an intriguing architecture for semantic,instance,and panoptic segmentation using EfficientNet-B7 and Bidirectional Feature Pyramid Networks(Bi-FPN).When implemented in place of the EfficientNet-B5 backbone,EfficientNet-B7 strengthens the model’s feature extraction capabilities and is far more appropriate for real-world applications.By ensuring superior multi-scale feature fusion,Bi-FPN integration enhances the segmentation of complex objects across various urban environments.The design suggested is examined on rigorous datasets,encompassing Cityscapes,Common Objects in Context,KITTI Karlsruhe Institute of Technology and Toyota Technological Institute,and Indian Driving Dataset,which replicate numerous real-world driving conditions.During extensive training,validation,and testing,the model showcases major gains in segmentation accuracy and surpasses state-of-the-art performance in semantic,instance,and panoptic segmentation tasks.Outperforming present methods,the recommended approach generates noteworthy gains in Panoptic Quality:+0.4%on Cityscapes,+0.2%on COCO,+1.7%on KITTI,and+0.4%on IDD.These changes show just how efficient it is in various driving circumstances and datasets.This study emphasizes the potential of EfficientNet-B7 and Bi-FPN to provide dependable,high-precision segmentation in computer vision applications,primarily autonomous driving.The research results suggest that this framework efficiently tackles the constraints of practical situations while delivering a robust solution for high-performance tasks involving segmentation.
基金supported by the Deanship of Research and Graduate Studies at King Khalid University under Small Research Project grant number RGP1/139/45.
文摘Integrating multiple medical imaging techniques,including Magnetic Resonance Imaging(MRI),Computed Tomography,Positron Emission Tomography(PET),and ultrasound,provides a comprehensive view of the patient health status.Each of these methods contributes unique diagnostic insights,enhancing the overall assessment of patient condition.Nevertheless,the amalgamation of data from multiple modalities presents difficulties due to disparities in resolution,data collection methods,and noise levels.While traditional models like Convolutional Neural Networks(CNNs)excel in single-modality tasks,they struggle to handle multi-modal complexities,lacking the capacity to model global relationships.This research presents a novel approach for examining multi-modal medical imagery using a transformer-based system.The framework employs self-attention and cross-attention mechanisms to synchronize and integrate features across various modalities.Additionally,it shows resilience to variations in noise and image quality,making it adaptable for real-time clinical use.To address the computational hurdles linked to transformer models,particularly in real-time clinical applications in resource-constrained environments,several optimization techniques have been integrated to boost scalability and efficiency.Initially,a streamlined transformer architecture was adopted to minimize the computational load while maintaining model effectiveness.Methods such as model pruning,quantization,and knowledge distillation have been applied to reduce the parameter count and enhance the inference speed.Furthermore,efficient attention mechanisms such as linear or sparse attention were employed to alleviate the substantial memory and processing requirements of traditional self-attention operations.For further deployment optimization,researchers have implemented hardware-aware acceleration strategies,including the use of TensorRT and ONNX-based model compression,to ensure efficient execution on edge devices.These optimizations allow the approach to function effectively in real-time clinical settings,ensuring viability even in environments with limited resources.Future research directions include integrating non-imaging data to facilitate personalized treatment and enhancing computational efficiency for implementation in resource-limited environments.This study highlights the transformative potential of transformer models in multi-modal medical imaging,offering improvements in diagnostic accuracy and patient care outcomes.
文摘This article reviews recent advancements,innovative strategies,and the key challenges in Drug Delivery Systems(DDS)for bone regeneration,focusing on tissue engineering.It highlights the limitations of current surgical interventions forbone regeneration,particularly autogenic bone grafts,and discusses the exploration of alternative materials and methods,including allogeneic and xenogeneic bone grafts,synthetic materials,and biodegradable polymers.The objective is to provide a comprehensive understanding of how contemporary DDS can be optimized and integrated with tissue engineering approaches for more effective bone regeneration therapies.The review explained the mechanisms through which DDS enhance bone repair processes,identifies critical factors influencing their efficacy and safety,and offers an overview of current trends and future perspectives in the field.It emphasizes the need for advanced strategies in bone regeneration that focus on precise control of DDS to address bone conditions such as osteoporosis,trauma,and genetic predispositions leading to fractures.
文摘Reliable and efficient communication is essential for Unmanned Aerial Vehicle(UAV)networks,especially in dynamic and resource-constrained environments such as disaster management,surveillance,and environmental monitoring.Frequent topology changes,high mobility,and limited energy availability pose significant challenges to maintaining stable and high-performance routing.Traditional routing protocols,such as Ad hoc On-Demand Distance Vector(AODV),Load-Balanced Optimized Predictive Ad hoc Routing(LB-OPAR),and Destination-Sequenced Distance Vector(DSDV),often experience performance degradation under such conditions.To address these limitations,this study evaluates the effectiveness of Dynamic Adaptive Routing(DAR),a protocol designed to adapt routing decisions in real time based on network dynamics and resource constraints.The research utilizes the Network Simulator 3(NS-3)platform to conduct controlled simulations,measuring key performance indicators such as latency,Packet Delivery Ratio(PDR),energy consumption,and throughput.Comparative analysis reveals that DAR consistently outperforms conventional protocols,achieving a 20%-30% reduction in latency,a 25% decrease in energy consumption,and marked improvements in throughput and PDR.These results highlight DAR’s ability to maintain high communication reliability while optimizing resource usage in challenging operational scenarios.By providing empirical evidence of DAR’s advantages in highly dynamic UAV network environments,this study contributes to advancing adaptive routing strategies.The findings not only validate DAR’s robustness and scalability but also lay the groundwork for integrating artificial intelligence-driven decision-making and real-world UAV deployment.Future work will explore cross-layer optimization,multi-UAV coordination,and experimental validation in field trials,aiming to further enhance communication resilience and energy efficiency in next-generation aerial networks.
文摘The integration of the dynamic adaptive routing(DAR)algorithm in unmanned aerial vehicle(UAV)networks offers a significant advancement in addressing the challenges posed by next-generation communication systems like 6G.DAR’s innovative framework incorporates real-time path adjustments,energy-aware routing,and predictive models,optimizing reliability,latency,and energy efficiency in UAV operations.This study demonstrated DAR’s superior performance in dynamic,large-scale environments,proving its adaptability and scalability for real-time applications.As 6G networks evolve,challenges such as bandwidth demands,global spectrum management,security vulnerabilities,and financial feasibility become prominent.DAR aligns with these demands by offering robust solutions that enhance data transmission while ensuring network reliability.However,obstacles like global route optimization and signal interference in urban areas necessitate further refinement.Future directions should explore hybrid approaches,the integration of machine learning,and comprehensive real-world testing to maximize DAR’s capabilities.The findings underscore DAR’s pivotal role in enabling efficient and sustainable UAV communication systems,contributing to the broader landscape of wireless technology and laying a foundation for the seamless transition to 6G networks.
基金Under the auspices of the National Natural Science Foundation of China(No.42471111,42107419)the Natural Science Foundation of Shandong Province(No.ZR2023MD076)+2 种基金Talent Induction Program for Youth Innovation Teams in Colleges and Universities of Shandong Province(No.2022-2024)Youth Innovation Teams in Colleges and Universities of Shandong Province(No.2022KJ118)Jilin Provincial Department of Science and Technology Project(No.20230203174SF)。
文摘The Yellow River Delta(YRD)of China is one of the most active land-sea interaction deltas in the world.However,due to human activities and climate change,it has undergone significant changes,including the degradation of natural wetlands and saltwater intrusion.As an integral part of soil microorganisms,fungi play a crucial role in maintaining and stabilizing the function of wetland ecosystems.To better understand the composition and diversity changes of fungal communities along a salinity gradient in the YRD of China and their relationship with environmental factors,fungal diversity,abundance,and composition in the sediments of four typical vegetation communities spanning from the riverbank to the seaside were investigated.The results showed that the electrical conductivity(EC)increased significantly from the riverbank to the coastal area(P<0.05),but the levels of total nitrogen(TN),total carbon(TC),total sulfur(TS),available phosphorous(AP),and ammonium(NH_(4)^(+)-N)increased in Phragmites australis community and then experienced a significant decrease in Tamarix chinensis community and Suaeda salsa community(P<0.05).The alpha diversity(Shannon and Simpson indices)of the soil fungal community exhibited a negative correlation with EC.There was a significant alteration in the structure of the fungal community,primarily influenced by EC and NO_(3)^(-)-N.Ascomycota was found to be the most abundant phylum,and its relative abundance is positively correlated with pH and TS.The relative abundance of Sordariomycetes,the second-largest class of Ascomycota,reached 38.95%.Salinity was identified as the most important factor driving changes in soil fungal community composition.In summary,the fungal community changed significantly along the salinity gradient,and different environmental factors impacted various tiers of fungal populations differently.The findings of this study lay the groundwork for comprehending soil fungal communities and their primary influencing factors in newly formed wetlands.
文摘Scarcity of empirical studies turning the concepts into cost-effective practices is a barrier in achieving the desired trajectory and scale of ecosystem restoration.The present study aimed to assess(i)potential of tree-bamboo-medicinal herb mixed plantation founded on the concept of adaptive comanagement in restoration of degraded community forest in a temperate village of Indian Himalaya and(ii)persistence of offer of local people to voluntarily maintain and expand the trial after its economic benefit/cost ratio became>1.0.Biodiversity,carbon stock and economic benefits were assessed in the restored forest 1,3 and 10 years after 7-year-long funding phase(i.e.,8,10 and 20 years after initial planting in 1991),and other land uses in the village landscape.Significant economic loss occurred from gregarious flowering induced mass mortality of bamboo in the 2nd year after funding phase but it was outweighed by the gain from walnut fruiting.People maintained recovery by transplanting Nepalese Alder(Alnus nepalensis)in gaps.The 20-year-old restored forest land had 17%of aboveground and 75%of belowground carbon stocks,and 39%of flowering species present in the intact forest.Restored forest had only four of the eight Near-threatened/Threatened species present in intact forest.Further,intact forest was monetarily the most efficient land use despite absence of payments for its ecosystem services.People did not expand the trial or medicinal plant cultivation in farms induced by it.They abandoned cropping in 39%farm area and leased 24%abandoned area to a company.Flowering plant species richness and carbon stocks changed at the ecosystem scale but not at the village landscape scale.Emission from agricultural abandonment nullified carbon sequestration by forest restoration.Community forest restoration should render both material/monetary and nonmaterial/non-monetary benefits to people.Cultural landscapes should be taken as spatial units for ecosystem restoration planning,monitoring and evaluation.
基金funded by the following grants:the Natural Environ-ment Research Council-Funded SECO Project(NE/T01279X/1)the Fostering Research&Intra-African Knowledge Transfer Through Mobility&Education(FRAME)Conservation Action Research Network(CARN)through the ASPIRE Grant Programme.
文摘The Miombo ecoregion covers eastern and southern Africa,with variations in plant species composition,structure,and biomass across a broad precipitation gradient.Most studies of woody plant communities focus exclusively on larger overstorey trees(≥5 or≥10cm stem diameter),overlooking the contribution of small trees and shrubs in the understorey,which can comprise a significant portion of total biomass and diversity.Here,we evaluate the contribution of both large overstorey and small understorey woody plants to species diversity and above-ground biomass(AGB),with 17 plots(0.5-1ha)across five sites representing both extremes of rainfall gradient spanning the Miombo ecoregion,in northeast Namibia(500-700mm mean annual precipitation,MAP)and southern Democratic Republic of Congo(DRC)(>1,200mm MAP).Mean AGB per site ranged from 21 to 119Mg·ha^(-1),increasing with rainfall,while the proportional AGB contribution of small trees,saplings,and shrubs decreased.In dry Namibia,small trees,saplings,and shrubs(<5cm DBH)contributed up to 28.2%of total AGB(mean±standard deviation:18.3%±3.4%),whereas in wet DRC,they contributed only up to 2.5%(2.3%±1.4%).Namibian sites,on average,contained a large proportion of woody species diversity exclusively in small trees and shrubs(<5cm DBH),with 55 species representing 59.4%of the total diversity.In contrast,DRC sites had higher overall small woody plant diversity(66 species)but fewer species found exclusively as small individuals(25.2%),with many saplings that grow to larger trees.Understorey composition also differed,with saplings of overstorey trees dominating in DRC,while shrubs dominated in Namibia.Our findings show that woody biomass and diversity in dry woodlands are substantially underestimated when studies focus only on larger trees.This highlights the need to consider all woody vegetation to better understand woody plant diversity and biomass variation.
基金funded by the deanship of scientific research(DSR),King Abdulaziz University,Jeddah,under grant No.(G-1436-611-309).
文摘Cardiovascular diseases(CVDs)remain one of the foremost causes of death globally;hence,the need for several must-have,advanced automated diagnostic solutions towards early detection and intervention.Traditional auscultation of cardiovascular sounds is heavily reliant on clinical expertise and subject to high variability.To counter this limitation,this study proposes an AI-driven classification system for cardiovascular sounds whereby deep learning techniques are engaged to automate the detection of an abnormal heartbeat.We employ FastAI vision-learner-based convolutional neural networks(CNNs)that include ResNet,DenseNet,VGG,ConvNeXt,SqueezeNet,and AlexNet to classify heart sound recordings.Instead of raw waveform analysis,the proposed approach transforms preprocessed cardiovascular audio signals into spectrograms,which are suited for capturing temporal and frequency-wise patterns.The models are trained on the PASCAL Cardiovascular Challenge dataset while taking into consideration the recording variations,noise levels,and acoustic distortions.To demonstrate generalization,external validation using Google’s Audio set Heartbeat Sound dataset was performed using a dataset rich in cardiovascular sounds.Comparative analysis revealed that DenseNet-201,ConvNext Large,and ResNet-152 could deliver superior performance to the other architectures,achieving an accuracy of 81.50%,a precision of 85.50%,and an F1-score of 84.50%.In the process,we performed statistical significance testing,such as the Wilcoxon signed-rank test,to validate performance improvements over traditional classification methods.Beyond the technical contributions,the research underscores clinical integration,outlining a pathway in which the proposed system can augment conventional electronic stethoscopes and telemedicine platforms in the AI-assisted diagnostic workflows.We also discuss in detail issues of computational efficiency,model interpretability,and ethical considerations,particularly concerning algorithmic bias stemming from imbalanced datasets and the need for real-time processing in clinical settings.The study describes a scalable,automated system combining deep learning,feature extraction using spectrograms,and external validation that can assist healthcare providers in the early and accurate detection of cardiovascular disease.AI-driven solutions can be viable in improving access,reducing delays in diagnosis,and ultimately even the continued global burden of heart disease.
