With the rapid development of intelligent video surveillance technology,pedestrian re-identification has become increasingly important inmulti-camera surveillance systems.This technology plays a critical role in enhan...With the rapid development of intelligent video surveillance technology,pedestrian re-identification has become increasingly important inmulti-camera surveillance systems.This technology plays a critical role in enhancing public safety.However,traditional methods typically process images and text separately,applying upstream models directly to downstream tasks.This approach significantly increases the complexity ofmodel training and computational costs.Furthermore,the common class imbalance in existing training datasets limitsmodel performance improvement.To address these challenges,we propose an innovative framework named Person Re-ID Network Based on Visual Prompt Technology andMulti-Instance Negative Pooling(VPM-Net).First,we incorporate the Contrastive Language-Image Pre-training(CLIP)pre-trained model to accurately map visual and textual features into a unified embedding space,effectively mitigating inconsistencies in data distribution and the training process.To enhancemodel adaptability and generalization,we introduce an efficient and task-specific Visual Prompt Tuning(VPT)technique,which improves the model’s relevance to specific tasks.Additionally,we design two key modules:the Knowledge-Aware Network(KAN)and theMulti-Instance Negative Pooling(MINP)module.The KAN module significantly enhances the model’s understanding of complex scenarios through deep contextual semantic modeling.MINP module handles samples,effectively improving the model’s ability to distinguish fine-grained features.The experimental outcomes across diverse datasets underscore the remarkable performance of VPM-Net.These results vividly demonstrate the unique advantages and robust reliability of VPM-Net in fine-grained retrieval tasks.展开更多
This study focuses on tool condition recognition through data-driven approaches to enhance the intelligence level of computerized numerical control(CNC)machining processes and improve tool utilization efficiency.Tradi...This study focuses on tool condition recognition through data-driven approaches to enhance the intelligence level of computerized numerical control(CNC)machining processes and improve tool utilization efficiency.Traditional tool monitoring methods that rely on empirical knowledge or limited mathematical models struggle to adapt to complex and dynamic machining environments.To address this,we implement real-time tool condition recognition by introducing deep learning technology.Aiming to the insufficient recognition accuracy,we propose a pyramid pooling-based vision Transformer network(P2ViT-Net)method for tool condition recognition.Using images as input effectively mitigates the issue of low-dimensional signal features.We enhance the vision Transformer(ViT)framework for image classification by developing the P2ViT model and adapt it to tool condition recognition.Experimental results demonstrate that our improved P2ViT model achieves 94.4%recognition accuracy,showing a 10%improvement over conventional ViT and outperforming all comparative convolutional neural network models.展开更多
In convolutional neural networks,pooling methods are used to reduce both the size of the data and the number of parameters after the convolution of the models.These methods reduce the computational amount of convoluti...In convolutional neural networks,pooling methods are used to reduce both the size of the data and the number of parameters after the convolution of the models.These methods reduce the computational amount of convolutional neural networks,making the neural network more efficient.Maximum pooling,average pooling,and minimum pooling methods are generally used in convolutional neural networks.However,these pooling methods are not suitable for all datasets used in neural network applications.In this study,a new pooling approach to the literature is proposed to increase the efficiency and success rates of convolutional neural networks.This method,which we call MAM(Maximum Average Minimum)pooling,is more interactive than other traditional maximum pooling,average pooling,and minimum pooling methods and reduces data loss by calculating the more appropriate pixel value.The proposed MAM pooling method increases the performance of the neural network by calculating the optimal value during the training of convolutional neural networks.To determine the success accuracy of the proposed MAM pooling method and compare it with other traditional pooling methods,training was carried out on the LeNet-5 model using CIFAR-10,CIFAR-100,and MNIST datasets.According to the results obtained,the proposed MAM pooling method performed better than the maximum pooling,average pooling,and minimum pooling methods in all pool sizes on three different datasets.展开更多
Aiming at the problem of low surface defect detection accuracy of industrial products, an object detection method based on simplified spatial pyramid pooling fast(Sim SPPF) hybrid pooling improved you only look once v...Aiming at the problem of low surface defect detection accuracy of industrial products, an object detection method based on simplified spatial pyramid pooling fast(Sim SPPF) hybrid pooling improved you only look once version 5s(YOLOV5s) model is proposed. The algorithm introduces channel attention(CA) module, simplified SPPF feature vector pyramid and efficient intersection over union(EIOU) loss function. Feature vector pyramids fuse high-dimensional and low-dimensional features, which makes semantic information richer. The CA mechanism performs maximum pooling and average pooling operations on the feature map. Hybrid pooling comprehensively improves detection computing efficiency and accurate deployment ability. The results show that the improved YOLOV5s model is better than the original YOLOV5s model. The average test accuracy(mAP) can reach 91.8%, which can be increased by 17.4%, and the detection speed can reach 108 FPS, which can be increased by 18 FPS. The improved model is practicable, and the overall performance is better than other conventional models.展开更多
Pooling,unpooling/specialization,and discretionary task completion are typical operational strategies in queueing systems that arise in healthcare,call centers,and online sales.These strategies may have advantages and...Pooling,unpooling/specialization,and discretionary task completion are typical operational strategies in queueing systems that arise in healthcare,call centers,and online sales.These strategies may have advantages and disadvantages in different operational environments.This paper uses the M/M/1 and M/M/2 queues to study the impact of pooling,specialization,and discretionary task completion on the average queue length.Closed-form solutions for the average M/M/2 queue length are derived.Computational examples illustrate how the average queue length changes with the strength of pooling,specialization,and discretionary task completion.Finally,several conjectures are made in the paper.展开更多
The state of in situ stress is a crucial parameter in subsurface engineering,especially for critical projects like nuclear waste repository.As one of the two ISRM suggested methods,the overcoring(OC)method is widely u...The state of in situ stress is a crucial parameter in subsurface engineering,especially for critical projects like nuclear waste repository.As one of the two ISRM suggested methods,the overcoring(OC)method is widely used to estimate the full stress tensors in rocks by independent regression analysis of the data from each OC test.However,such customary independent analysis of individual OC tests,known as no pooling,is liable to yield unreliable test-specific stress estimates due to various uncertainty sources involved in the OC method.To address this problem,a practical and no-cost solution is considered by incorporating into OC data analysis additional information implied within adjacent OC tests,which are usually available in OC measurement campaigns.Hence,this paper presents a Bayesian partial pooling(hierarchical)model for combined analysis of adjacent OC tests.We performed five case studies using OC test data made at a nuclear waste repository research site of Sweden.The results demonstrate that partial pooling of adjacent OC tests indeed allows borrowing of information across adjacent tests,and yields improved stress tensor estimates with reduced uncertainties simultaneously for all individual tests than they are independently analysed as no pooling,particularly for those unreliable no pooling stress estimates.A further model comparison shows that the partial pooling model also gives better predictive performance,and thus confirms that the information borrowed across adjacent OC tests is relevant and effective.展开更多
Convolutional Neural Networks(CNNs)have shown remarkable capabilities in extracting local features from images,yet they often overlook the underlying relationships between pixels.To address this limitation,previous ap...Convolutional Neural Networks(CNNs)have shown remarkable capabilities in extracting local features from images,yet they often overlook the underlying relationships between pixels.To address this limitation,previous approaches have attempted to combine CNNs with Graph Convolutional Networks(GCNs)to capture global features.However,these approaches typically neglect the topological structure information of the graph during the global feature extraction stage.This paper proposes a novel end-to-end hybrid architecture called the Multi-Graph Pooling Network(MGPN),which is designed explicitly for chest X-ray image classification.Our approach sequentially combines CNNs and GCNs,enabling the learning of both local and global features from individual images.Recognizing that different nodes contribute differently to the final graph representation,we introduce an NI-GTP module to enhance the extraction of ultimate global features.Additionally,we introduce a G-LFF module to fuse the local and global features effectively.展开更多
In order to enhance the performance of the CNN-based segmentation models for bone metastases, this study proposes a segmentation method that integrates dual-pooling, DAC, and RMP modules. The network consists of disti...In order to enhance the performance of the CNN-based segmentation models for bone metastases, this study proposes a segmentation method that integrates dual-pooling, DAC, and RMP modules. The network consists of distinct feature encoding and decoding stages, with dual-pooling modules employed in encoding stages to maintain the background information needed for bone scintigrams diagnosis. Both the DAC and RMP modules are utilized in the bottleneck layer to address the multi-scale problem of metastatic lesions. Experimental evaluations on 306 clinical SPECT data have demonstrated that the proposed method showcases a substantial improvement in both DSC and Recall scores by 3.28% and 6.55% compared the baseline. Exhaustive case studies illustrate the superiority of the methodology.展开更多
Addressing global warming,a common change today,requires achieving peak carbon dioxide emissions and carbon neutrality(also referred to as the dual carbon goals).Enhancing research on the carbon cycle is urgently need...Addressing global warming,a common change today,requires achieving peak carbon dioxide emissions and carbon neutrality(also referred to as the dual carbon goals).Enhancing research on the carbon cycle is urgently needed as the foundation.Water,a key carrier in the carbon cycle,necessitates investigation into groundwater carbon pools’contribution to atmospheric carbon sinks.This study assessed carbon stocks in the Yinchuan Basin’s soil and groundwater carbon pools.Findings indicate the basin’s surface soils contain approximately 24.16 Tg of organic carbon and a total of 60.01 Tg of carbon.In contrast,the basin’s groundwater holds around 4.90 Tg of carbon,roughly one-fifth of the organic carbon in surface soils.Thus,groundwater and soil carbon pools possess comparable carbon stocks,underscoring the importance of the groundwater carbon pool.Studies on terrestrial carbon balance should incorporate groundwater carbon pools,which deserve increased focus.Evaluating groundwater carbon pools’contributions is vital for achieving the dual carbon goals.展开更多
Disinfection of swimming pool water is critical to ensure the safety of the recreational activity for swimmers.However,swimming pools have a constant loading of organic matter from input water and anthropogenic contam...Disinfection of swimming pool water is critical to ensure the safety of the recreational activity for swimmers.However,swimming pools have a constant loading of organic matter from input water and anthropogenic contamination,leading to elevated levels of disinfection byproducts(DBPs).Epidemiological studies have associated increased risks of adverse health effects with frequent exposure to DBPs in swimming pools.Zhang et al.(2023b)investigated the occurrence of trihalomethanes(THMs),haloacetic acids(HAAs),haloacetonitriles(HANs),and haloacetaldehydes(HALs)in eight swimming pools and the corresponding input water in a city in Eastern China.The concentrations of THMs,HAAs,HANs,and HALs in swimming poolswere 1–2 orders of magnitude higher than those detected in the input water.The total lifetime cancer and non-cancer health risks of swimmers through oral,dermal,inhalation,buccal,and aural exposure pathways were assessed using the United States Environmental Protection Agency’s(USEPA)standard model and Swimmer Exposure Assessment Model(SWIMODEL).The results showed that dermal and inhalation pathways were the most significant for the associated cancer and non-cancer risks.This article provides an overview and perspectives of DBPs in swimming pools,the benefits of swimming,the need to improve the monitoring of DBPs,and the importance of swimmers’hygiene practices to keep swimming pools clean.The benefits of swimming outweigh the risks from DBP exposure for the promotion of public health.展开更多
The degradation of animal carcasses can lead to rapid waste release(e.g.,pathogenic bacteria,viruses,prions,or parasites)and also result in nutrient accumulation in the surrounding environment.However,how viral profil...The degradation of animal carcasses can lead to rapid waste release(e.g.,pathogenic bacteria,viruses,prions,or parasites)and also result in nutrient accumulation in the surrounding environment.However,how viral profile responds and influences nutrient pool(carbon(C),nitrogen(N),phosphorus(P)and sulfur(S))in polluted water caused by animal carcass decomposition had not been explored.Here,we combined metagenomic analysis,16S rRNA gene sequencing and water physicochemical assessment to explore the response of viral communities under different temperatures(23℃,26℃,29℃,32℃,and 35℃)in water polluted by cadaver,as well as compare the contribution of viral/bacterial communities on water nutrient pool.We found that a total of 15,240 viral species were classified and mainly consisted of Siphoviridae.Both temperature and carrion reduced the viral diversity and abundance.Only a small portion of the viruses(∼8.8%)had significant negative correlations with temperature,while most were not sensitive.Our results revealed that the viruses had lager contribution on nutrient pool than bacteria.Besides,viral-related functional genes involved in C,N,P and S cycling.These functional genes declined during carcass decomposition and covered part of the central nutrient cycle metabolism(including carbon sugar transformation,denitrification,P mineralization and extracelluar sulfate transfer,etc.).Our result implies that human regulation of virus communities may be more important than bacterial communities in regulating and managing polluted water quality and nutrition.展开更多
Paediatric liver transplantation(PLT)is a life-saving procedure for children with advanced liver disease or hepatoblastoma.The number of available grafts is limited in relation to the number of children on PLT waiting...Paediatric liver transplantation(PLT)is a life-saving procedure for children with advanced liver disease or hepatoblastoma.The number of available grafts is limited in relation to the number of children on PLT waiting list.This graft shortage has led transplant societies and healthcare organizations to explore ways to investigate possible options and expand the donor pool.The safe use of grafts from obese donors has always been a subject of debate among PLT specialists.Donors’obesity is strongly associated with hepatic steatosis which can affect graft function by impairing microcirculation and maximizing the potential of ischemiareperfusion injury.Donor body mass index consideration should go hand in hand with the workup for hepatic steatosis which is an independent predictor for early graft dysfunction.New strategies to optimize the grafts before PLT such as normothermic regional perfusion and ex vivo liver perfusion can potentially mitigate the risk of using grafts from obese donors.This review summarizes the available evidence about the impact of donor obesity on PLT and highlights the current policies to widen the graft pool and suggest future research directions to improve donor selection and patient outcomes.展开更多
Large-sized titanium alloy ingots produced by vacuum arc remelting(VAR)technology are susceptible to metallurgical imperfections such as compositional segregation,inconsistent solidification microstructures,black spot...Large-sized titanium alloy ingots produced by vacuum arc remelting(VAR)technology are susceptible to metallurgical imperfections such as compositional segregation,inconsistent solidification microstructures,black spots,and inclusions.These defects are intricately linked to the electromagnetic effects,temperature distribution,and fluid dynamics during the melting process.The self-induced magnetic field created by the electric current,along with the axial magnetic field applied to stabilize the arc,significantly influences the solidification of titanium alloy ingots.A mathematical model optimized for the integrated analysis of multiple fields—electromagnetic,fluid,and thermal—was developed for the VAR solidification process of titanium alloys.The influence mechanism of electromagnetic field on the macroscopic solidification process of titanium alloy was investigated.The findings indicate the presence of two competing forces within the VAR molten pool,namely,thermal buoyancy and the Lorentz force.Introducing a coupled self-induced magnetic field and elevating the current to 15 kA led to an increase in the molten pool depth by 42.9%and a reduction in the thickness of the mushy zone by 25.2%.The application of a constant axial magnetic field enhances a unidirectional momentum buildup within the molten pool,thereby enhancing the flow velocity and cooling efficiency of melt.展开更多
The extended Kalman filter(EKF)is extensively applied in integrated navigation systems that combine the global navigation satellite system(GNSS)and strap-down inertial navigation system(SINS).However,the performance o...The extended Kalman filter(EKF)is extensively applied in integrated navigation systems that combine the global navigation satellite system(GNSS)and strap-down inertial navigation system(SINS).However,the performance of the EKF can be severely impacted by non-Gaussian noise and measurement noise uncertainties,making it difficult to achieve optimal GNSS/INS integration.Dealing with non-Gaussian noise remains a significant challenge in filter development today.Therefore,the maximum correntropy criterion(MCC)is utilized in EKFs to manage heavytailed measurement noise.However,its capability to handle non-Gaussian process noise and unknown disturbances remains largely unexplored.In this paper,we extend correntropy from using a single kernel to a multi-kernel approach.This leads to the development of a multi-kernel maximum correntropy extended Kalman filter(MKMC-EKF),which is designed to effectively manage multivariate non-Gaussian noise and disturbances.Further,theoretical analysis,including advanced stability proofs,can enhance understanding,while hybrid approaches integrating MKMC-EKF with particle filters may improve performance in nonlinear systems.The MKMC-EKF enhances estimation accuracy using a multi-kernel bandwidth approach.As bandwidth increases,the filter’s sensitivity to non-Gaussian features decreases,and its behavior progressively approximates that of the iterated EKF.The proposed approach for enhancing positioning in navigation is validated through performance evaluations,which demonstrate its practical applications in real-world systems like GPS navigation and measuring radar targets.展开更多
Cold pools(CPs)significantly influence coastal heavy rainfall,but detailed observations of them are limited due to the lack of vertical measurement instruments.This study statistically characterizes CPs in the coastal...Cold pools(CPs)significantly influence coastal heavy rainfall,but detailed observations of them are limited due to the lack of vertical measurement instruments.This study statistically characterizes CPs in the coastal monsoon region of South China using unique data from the 356-m-high Shenzhen Meteorological Tower.CP occurrence correlates with convective activities influenced by the summer monsoon in the seasonal variations and land–sea breeze activities in the diurnal cycle.The CPs predominantly dry the atmosphere,highlighting the dominant role of dry entrainment through convective downdrafts in their formation,with a minor role of hydrometeor evaporation.The average CP depth is estimated at 668.0 m,deeper than tropical CPs but shallower than midlatitude counterparts.The CP properties exhibit diurnal variability,largely influenced by mesoscale convective system(MCS)activities.MCS-induced CPs are deeper and more intense than those from individual convective cells,while linear-MCS-produced CPs are the most intense.These observations from the coastal monsoon region contribute to a comprehensive global understanding of CP characteristics,complementing existing studies from midlatitude and tropical regions.展开更多
In modern engineering,enhancing boiling heat transfer efficiency is crucial for optimizing energy use and several industrial processes involving different types of materials.This study explores the enhancement of pool...In modern engineering,enhancing boiling heat transfer efficiency is crucial for optimizing energy use and several industrial processes involving different types of materials.This study explores the enhancement of pool boiling heat transfer potentially induced by combining perforated copper particles on a heated surface with a sodium dodecyl sulfate(SDS)surfactant in saturated deionized water.Experiments were conducted at standard atmospheric pressure,with heat flux ranging from 20 to 100 kW/m2.The heating surface,positioned below the layer of freely moving copper beads,allowed the particle layer to shift due to liquid convection and steam nucleation.The study reports on the influence of copper bead diameter(2,3,4,and 5 mm),particle quantity,arrangement,and SDS concentration(20,200,and 500 ppm).It is shown that the combination of 5 mm particles and a 500 ppm SDS concentration can yield a remarkable 139%improvement in heat transfer efficiency.As demonstrated by direct flow visualization,bubble formation occurs primarily in the gaps between the particles and the heated surface,with the presence of SDS reducing bubble size and accelerating bubble detachment.展开更多
With the rise in drowning accidents in swimming pools,the demand for the precision and speed in artificial intelligence(AI)drowning detection methods has become increasingly crucial.Here,an improved YOLO-based method,...With the rise in drowning accidents in swimming pools,the demand for the precision and speed in artificial intelligence(AI)drowning detection methods has become increasingly crucial.Here,an improved YOLO-based method,named DrownACB-YOLO,for drowning detection in swimming pools is proposed.Since existing methods focus on the drowned state,a transition label is added to the original dataset to provide timely alerts.Following this expanded dataset,two improvements are implemented in the original YOLOv5.Firstly,the spatial pyramid pooling(SPP)module and the default upsampling operator are replaced by the atrous spatial pyramid pooling(ASPP)module and the content-aware reassembly of feature(CARAFE)module,respectively.Secondly,the cross stage partial bottleneck with three convolutions(C3)module at the end of the backbone is replaced with the bottleneck transformer(BotNet)module.The results of comparison experiments demonstrate that DrownACB-YOLO performs better than other models.展开更多
To build a community of scientific innovation,serve the country’s goals of carbon peak and carbon neutrality,promote application of scientific research outcomes in the Guangdong-Hong Kong-Macao Greater Bay Area(GBA),...To build a community of scientific innovation,serve the country’s goals of carbon peak and carbon neutrality,promote application of scientific research outcomes in the Guangdong-Hong Kong-Macao Greater Bay Area(GBA),and accelerate the formation of new quality productive forces in the green energy industry,the Yangjiang Offshore Wind Power Laboratory and the GBA Institute of Industry and Talent(GBAIIT)recently signed a strategic cooperation agreement.展开更多
基金funded by the Key Research and Development Program of Hubei Province,China(Grant No.2023BEB024)the Young and Middle-aged Scientific and Technological Innova-tion Team Plan in Higher Education Institutions inHubei Province,China(GrantNo.T2023007)the key projects ofHubei Provincial Department of Education(No.D20161403).
文摘With the rapid development of intelligent video surveillance technology,pedestrian re-identification has become increasingly important inmulti-camera surveillance systems.This technology plays a critical role in enhancing public safety.However,traditional methods typically process images and text separately,applying upstream models directly to downstream tasks.This approach significantly increases the complexity ofmodel training and computational costs.Furthermore,the common class imbalance in existing training datasets limitsmodel performance improvement.To address these challenges,we propose an innovative framework named Person Re-ID Network Based on Visual Prompt Technology andMulti-Instance Negative Pooling(VPM-Net).First,we incorporate the Contrastive Language-Image Pre-training(CLIP)pre-trained model to accurately map visual and textual features into a unified embedding space,effectively mitigating inconsistencies in data distribution and the training process.To enhancemodel adaptability and generalization,we introduce an efficient and task-specific Visual Prompt Tuning(VPT)technique,which improves the model’s relevance to specific tasks.Additionally,we design two key modules:the Knowledge-Aware Network(KAN)and theMulti-Instance Negative Pooling(MINP)module.The KAN module significantly enhances the model’s understanding of complex scenarios through deep contextual semantic modeling.MINP module handles samples,effectively improving the model’s ability to distinguish fine-grained features.The experimental outcomes across diverse datasets underscore the remarkable performance of VPM-Net.These results vividly demonstrate the unique advantages and robust reliability of VPM-Net in fine-grained retrieval tasks.
基金supported by China Postdoctoral Science Foundation(No.2024M754122)the Postdoctoral Fellowship Programof CPSF(No.GZB20240972)+3 种基金the Jiangsu Funding Program for Excellent Postdoctoral Talent(No.2024ZB194)Natural Science Foundation of Jiangsu Province(No.BK20241389)Basic Science ResearchFund of China(No.JCKY2023203C026)2024 Jiangsu Province Talent Programme Qinglan Project.
文摘This study focuses on tool condition recognition through data-driven approaches to enhance the intelligence level of computerized numerical control(CNC)machining processes and improve tool utilization efficiency.Traditional tool monitoring methods that rely on empirical knowledge or limited mathematical models struggle to adapt to complex and dynamic machining environments.To address this,we implement real-time tool condition recognition by introducing deep learning technology.Aiming to the insufficient recognition accuracy,we propose a pyramid pooling-based vision Transformer network(P2ViT-Net)method for tool condition recognition.Using images as input effectively mitigates the issue of low-dimensional signal features.We enhance the vision Transformer(ViT)framework for image classification by developing the P2ViT model and adapt it to tool condition recognition.Experimental results demonstrate that our improved P2ViT model achieves 94.4%recognition accuracy,showing a 10%improvement over conventional ViT and outperforming all comparative convolutional neural network models.
文摘In convolutional neural networks,pooling methods are used to reduce both the size of the data and the number of parameters after the convolution of the models.These methods reduce the computational amount of convolutional neural networks,making the neural network more efficient.Maximum pooling,average pooling,and minimum pooling methods are generally used in convolutional neural networks.However,these pooling methods are not suitable for all datasets used in neural network applications.In this study,a new pooling approach to the literature is proposed to increase the efficiency and success rates of convolutional neural networks.This method,which we call MAM(Maximum Average Minimum)pooling,is more interactive than other traditional maximum pooling,average pooling,and minimum pooling methods and reduces data loss by calculating the more appropriate pixel value.The proposed MAM pooling method increases the performance of the neural network by calculating the optimal value during the training of convolutional neural networks.To determine the success accuracy of the proposed MAM pooling method and compare it with other traditional pooling methods,training was carried out on the LeNet-5 model using CIFAR-10,CIFAR-100,and MNIST datasets.According to the results obtained,the proposed MAM pooling method performed better than the maximum pooling,average pooling,and minimum pooling methods in all pool sizes on three different datasets.
基金supported by the Tianjin Postgraduate Research Innovation Project (No.2022SKY286)the National Science and the National Key Research and Development Program (No.2022YFF0706000)。
文摘Aiming at the problem of low surface defect detection accuracy of industrial products, an object detection method based on simplified spatial pyramid pooling fast(Sim SPPF) hybrid pooling improved you only look once version 5s(YOLOV5s) model is proposed. The algorithm introduces channel attention(CA) module, simplified SPPF feature vector pyramid and efficient intersection over union(EIOU) loss function. Feature vector pyramids fuse high-dimensional and low-dimensional features, which makes semantic information richer. The CA mechanism performs maximum pooling and average pooling operations on the feature map. Hybrid pooling comprehensively improves detection computing efficiency and accurate deployment ability. The results show that the improved YOLOV5s model is better than the original YOLOV5s model. The average test accuracy(mAP) can reach 91.8%, which can be increased by 17.4%, and the detection speed can reach 108 FPS, which can be increased by 18 FPS. The improved model is practicable, and the overall performance is better than other conventional models.
文摘Pooling,unpooling/specialization,and discretionary task completion are typical operational strategies in queueing systems that arise in healthcare,call centers,and online sales.These strategies may have advantages and disadvantages in different operational environments.This paper uses the M/M/1 and M/M/2 queues to study the impact of pooling,specialization,and discretionary task completion on the average queue length.Closed-form solutions for the average M/M/2 queue length are derived.Computational examples illustrate how the average queue length changes with the strength of pooling,specialization,and discretionary task completion.Finally,several conjectures are made in the paper.
基金supported by the Guangdong Basic and Applied Basic Research Foundation(2023A1515011244).
文摘The state of in situ stress is a crucial parameter in subsurface engineering,especially for critical projects like nuclear waste repository.As one of the two ISRM suggested methods,the overcoring(OC)method is widely used to estimate the full stress tensors in rocks by independent regression analysis of the data from each OC test.However,such customary independent analysis of individual OC tests,known as no pooling,is liable to yield unreliable test-specific stress estimates due to various uncertainty sources involved in the OC method.To address this problem,a practical and no-cost solution is considered by incorporating into OC data analysis additional information implied within adjacent OC tests,which are usually available in OC measurement campaigns.Hence,this paper presents a Bayesian partial pooling(hierarchical)model for combined analysis of adjacent OC tests.We performed five case studies using OC test data made at a nuclear waste repository research site of Sweden.The results demonstrate that partial pooling of adjacent OC tests indeed allows borrowing of information across adjacent tests,and yields improved stress tensor estimates with reduced uncertainties simultaneously for all individual tests than they are independently analysed as no pooling,particularly for those unreliable no pooling stress estimates.A further model comparison shows that the partial pooling model also gives better predictive performance,and thus confirms that the information borrowed across adjacent OC tests is relevant and effective.
基金supported by the National Natural Science Foundation of China(62276092,62303167)Key Science and Technology Program of Henan Province(212102310084)+11 种基金MRC(MC_PC_17171)Royal Society(RP202G0230)BHF(AA/18/3/34220)Hope Foundation for Cancer Research(RM60G0680)GCRF(P202PF11).Sino-UK Industrial Fund(RP202G0289)LIAS(P202ED10,P202RE969)Key Scientific Research Projects of Colleges and Universities in Henan Province(25A520009)Data Science Enhancement Fund(P202RE237)Fight for Sight(24NN201)Sino-UK Education Fund(OP202006)BBSRC(RM32G0178B8).
文摘Convolutional Neural Networks(CNNs)have shown remarkable capabilities in extracting local features from images,yet they often overlook the underlying relationships between pixels.To address this limitation,previous approaches have attempted to combine CNNs with Graph Convolutional Networks(GCNs)to capture global features.However,these approaches typically neglect the topological structure information of the graph during the global feature extraction stage.This paper proposes a novel end-to-end hybrid architecture called the Multi-Graph Pooling Network(MGPN),which is designed explicitly for chest X-ray image classification.Our approach sequentially combines CNNs and GCNs,enabling the learning of both local and global features from individual images.Recognizing that different nodes contribute differently to the final graph representation,we introduce an NI-GTP module to enhance the extraction of ultimate global features.Additionally,we introduce a G-LFF module to fuse the local and global features effectively.
文摘In order to enhance the performance of the CNN-based segmentation models for bone metastases, this study proposes a segmentation method that integrates dual-pooling, DAC, and RMP modules. The network consists of distinct feature encoding and decoding stages, with dual-pooling modules employed in encoding stages to maintain the background information needed for bone scintigrams diagnosis. Both the DAC and RMP modules are utilized in the bottleneck layer to address the multi-scale problem of metastatic lesions. Experimental evaluations on 306 clinical SPECT data have demonstrated that the proposed method showcases a substantial improvement in both DSC and Recall scores by 3.28% and 6.55% compared the baseline. Exhaustive case studies illustrate the superiority of the methodology.
基金supported by the third scientific survey project in Xinjiang(2022xjkk0300)the public welfare geological survey projects initiated by the China Geological Survey(DD20190296,DD20221731).
文摘Addressing global warming,a common change today,requires achieving peak carbon dioxide emissions and carbon neutrality(also referred to as the dual carbon goals).Enhancing research on the carbon cycle is urgently needed as the foundation.Water,a key carrier in the carbon cycle,necessitates investigation into groundwater carbon pools’contribution to atmospheric carbon sinks.This study assessed carbon stocks in the Yinchuan Basin’s soil and groundwater carbon pools.Findings indicate the basin’s surface soils contain approximately 24.16 Tg of organic carbon and a total of 60.01 Tg of carbon.In contrast,the basin’s groundwater holds around 4.90 Tg of carbon,roughly one-fifth of the organic carbon in surface soils.Thus,groundwater and soil carbon pools possess comparable carbon stocks,underscoring the importance of the groundwater carbon pool.Studies on terrestrial carbon balance should incorporate groundwater carbon pools,which deserve increased focus.Evaluating groundwater carbon pools’contributions is vital for achieving the dual carbon goals.
文摘Disinfection of swimming pool water is critical to ensure the safety of the recreational activity for swimmers.However,swimming pools have a constant loading of organic matter from input water and anthropogenic contamination,leading to elevated levels of disinfection byproducts(DBPs).Epidemiological studies have associated increased risks of adverse health effects with frequent exposure to DBPs in swimming pools.Zhang et al.(2023b)investigated the occurrence of trihalomethanes(THMs),haloacetic acids(HAAs),haloacetonitriles(HANs),and haloacetaldehydes(HALs)in eight swimming pools and the corresponding input water in a city in Eastern China.The concentrations of THMs,HAAs,HANs,and HALs in swimming poolswere 1–2 orders of magnitude higher than those detected in the input water.The total lifetime cancer and non-cancer health risks of swimmers through oral,dermal,inhalation,buccal,and aural exposure pathways were assessed using the United States Environmental Protection Agency’s(USEPA)standard model and Swimmer Exposure Assessment Model(SWIMODEL).The results showed that dermal and inhalation pathways were the most significant for the associated cancer and non-cancer risks.This article provides an overview and perspectives of DBPs in swimming pools,the benefits of swimming,the need to improve the monitoring of DBPs,and the importance of swimmers’hygiene practices to keep swimming pools clean.The benefits of swimming outweigh the risks from DBP exposure for the promotion of public health.
基金supported by the National Natural Science Foundation of China (No.42007026)the Medical Innovation and Development Project of Lanzhou University (lzuyxcx-2022-172)
文摘The degradation of animal carcasses can lead to rapid waste release(e.g.,pathogenic bacteria,viruses,prions,or parasites)and also result in nutrient accumulation in the surrounding environment.However,how viral profile responds and influences nutrient pool(carbon(C),nitrogen(N),phosphorus(P)and sulfur(S))in polluted water caused by animal carcass decomposition had not been explored.Here,we combined metagenomic analysis,16S rRNA gene sequencing and water physicochemical assessment to explore the response of viral communities under different temperatures(23℃,26℃,29℃,32℃,and 35℃)in water polluted by cadaver,as well as compare the contribution of viral/bacterial communities on water nutrient pool.We found that a total of 15,240 viral species were classified and mainly consisted of Siphoviridae.Both temperature and carrion reduced the viral diversity and abundance.Only a small portion of the viruses(∼8.8%)had significant negative correlations with temperature,while most were not sensitive.Our results revealed that the viruses had lager contribution on nutrient pool than bacteria.Besides,viral-related functional genes involved in C,N,P and S cycling.These functional genes declined during carcass decomposition and covered part of the central nutrient cycle metabolism(including carbon sugar transformation,denitrification,P mineralization and extracelluar sulfate transfer,etc.).Our result implies that human regulation of virus communities may be more important than bacterial communities in regulating and managing polluted water quality and nutrition.
文摘Paediatric liver transplantation(PLT)is a life-saving procedure for children with advanced liver disease or hepatoblastoma.The number of available grafts is limited in relation to the number of children on PLT waiting list.This graft shortage has led transplant societies and healthcare organizations to explore ways to investigate possible options and expand the donor pool.The safe use of grafts from obese donors has always been a subject of debate among PLT specialists.Donors’obesity is strongly associated with hepatic steatosis which can affect graft function by impairing microcirculation and maximizing the potential of ischemiareperfusion injury.Donor body mass index consideration should go hand in hand with the workup for hepatic steatosis which is an independent predictor for early graft dysfunction.New strategies to optimize the grafts before PLT such as normothermic regional perfusion and ex vivo liver perfusion can potentially mitigate the risk of using grafts from obese donors.This review summarizes the available evidence about the impact of donor obesity on PLT and highlights the current policies to widen the graft pool and suggest future research directions to improve donor selection and patient outcomes.
基金financially supported by the National Natural Science Foundation of China(Nos.52422408 and 52171031)the Excellent Youth Fund of Liaoning Natural Science Foundation(No.2023JH3/10200001)the Liaoning Xingliao Talents-Top-notch Young Talents Project(No.XLYC2203064).
文摘Large-sized titanium alloy ingots produced by vacuum arc remelting(VAR)technology are susceptible to metallurgical imperfections such as compositional segregation,inconsistent solidification microstructures,black spots,and inclusions.These defects are intricately linked to the electromagnetic effects,temperature distribution,and fluid dynamics during the melting process.The self-induced magnetic field created by the electric current,along with the axial magnetic field applied to stabilize the arc,significantly influences the solidification of titanium alloy ingots.A mathematical model optimized for the integrated analysis of multiple fields—electromagnetic,fluid,and thermal—was developed for the VAR solidification process of titanium alloys.The influence mechanism of electromagnetic field on the macroscopic solidification process of titanium alloy was investigated.The findings indicate the presence of two competing forces within the VAR molten pool,namely,thermal buoyancy and the Lorentz force.Introducing a coupled self-induced magnetic field and elevating the current to 15 kA led to an increase in the molten pool depth by 42.9%and a reduction in the thickness of the mushy zone by 25.2%.The application of a constant axial magnetic field enhances a unidirectional momentum buildup within the molten pool,thereby enhancing the flow velocity and cooling efficiency of melt.
基金the support from National Science and Technology Council,Taiwan under grant numbers NSTC 113-2811-E-019-001 and NSTC 113-2221-E-019-059.
文摘The extended Kalman filter(EKF)is extensively applied in integrated navigation systems that combine the global navigation satellite system(GNSS)and strap-down inertial navigation system(SINS).However,the performance of the EKF can be severely impacted by non-Gaussian noise and measurement noise uncertainties,making it difficult to achieve optimal GNSS/INS integration.Dealing with non-Gaussian noise remains a significant challenge in filter development today.Therefore,the maximum correntropy criterion(MCC)is utilized in EKFs to manage heavytailed measurement noise.However,its capability to handle non-Gaussian process noise and unknown disturbances remains largely unexplored.In this paper,we extend correntropy from using a single kernel to a multi-kernel approach.This leads to the development of a multi-kernel maximum correntropy extended Kalman filter(MKMC-EKF),which is designed to effectively manage multivariate non-Gaussian noise and disturbances.Further,theoretical analysis,including advanced stability proofs,can enhance understanding,while hybrid approaches integrating MKMC-EKF with particle filters may improve performance in nonlinear systems.The MKMC-EKF enhances estimation accuracy using a multi-kernel bandwidth approach.As bandwidth increases,the filter’s sensitivity to non-Gaussian features decreases,and its behavior progressively approximates that of the iterated EKF.The proposed approach for enhancing positioning in navigation is validated through performance evaluations,which demonstrate its practical applications in real-world systems like GPS navigation and measuring radar targets.
基金supported by the National Key Research and Development Program of China (Grant No. 2024YFC3013003)the National Natural Science Foundation of China (Grant No. 42475002)+2 种基金the Innovation Group Project of Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai) (Grant Nos. SML2024SP035, SML2024SP012, and 311024001)the Guangdong Basic and Applied Basic Research Foundation (Grant Nos. 2025A1515011974, 2024A1515510005 and 2020B0301030004)the Key Innovation Team of China Meteorological Administration (Grant No. CMA2023ZD08)
文摘Cold pools(CPs)significantly influence coastal heavy rainfall,but detailed observations of them are limited due to the lack of vertical measurement instruments.This study statistically characterizes CPs in the coastal monsoon region of South China using unique data from the 356-m-high Shenzhen Meteorological Tower.CP occurrence correlates with convective activities influenced by the summer monsoon in the seasonal variations and land–sea breeze activities in the diurnal cycle.The CPs predominantly dry the atmosphere,highlighting the dominant role of dry entrainment through convective downdrafts in their formation,with a minor role of hydrometeor evaporation.The average CP depth is estimated at 668.0 m,deeper than tropical CPs but shallower than midlatitude counterparts.The CP properties exhibit diurnal variability,largely influenced by mesoscale convective system(MCS)activities.MCS-induced CPs are deeper and more intense than those from individual convective cells,while linear-MCS-produced CPs are the most intense.These observations from the coastal monsoon region contribute to a comprehensive global understanding of CP characteristics,complementing existing studies from midlatitude and tropical regions.
基金supported by the National Natural Science Foundation of China(Project No.52166004)the National Key Research and Development Program of China(Project No.2022YFC3902000)+2 种基金the Major Science and Technology Special Project of Yunnan Province(Project Nos.202202AG050007202202AG050002)the Research on the Development of Complete Sets of Technology for Extraction of Aromatic Substances from Tobacco Waste and Its Application,Applied Research-Pyrolysis Process Technology Research(2023QT01).
文摘In modern engineering,enhancing boiling heat transfer efficiency is crucial for optimizing energy use and several industrial processes involving different types of materials.This study explores the enhancement of pool boiling heat transfer potentially induced by combining perforated copper particles on a heated surface with a sodium dodecyl sulfate(SDS)surfactant in saturated deionized water.Experiments were conducted at standard atmospheric pressure,with heat flux ranging from 20 to 100 kW/m2.The heating surface,positioned below the layer of freely moving copper beads,allowed the particle layer to shift due to liquid convection and steam nucleation.The study reports on the influence of copper bead diameter(2,3,4,and 5 mm),particle quantity,arrangement,and SDS concentration(20,200,and 500 ppm).It is shown that the combination of 5 mm particles and a 500 ppm SDS concentration can yield a remarkable 139%improvement in heat transfer efficiency.As demonstrated by direct flow visualization,bubble formation occurs primarily in the gaps between the particles and the heated surface,with the presence of SDS reducing bubble size and accelerating bubble detachment.
文摘With the rise in drowning accidents in swimming pools,the demand for the precision and speed in artificial intelligence(AI)drowning detection methods has become increasingly crucial.Here,an improved YOLO-based method,named DrownACB-YOLO,for drowning detection in swimming pools is proposed.Since existing methods focus on the drowned state,a transition label is added to the original dataset to provide timely alerts.Following this expanded dataset,two improvements are implemented in the original YOLOv5.Firstly,the spatial pyramid pooling(SPP)module and the default upsampling operator are replaced by the atrous spatial pyramid pooling(ASPP)module and the content-aware reassembly of feature(CARAFE)module,respectively.Secondly,the cross stage partial bottleneck with three convolutions(C3)module at the end of the backbone is replaced with the bottleneck transformer(BotNet)module.The results of comparison experiments demonstrate that DrownACB-YOLO performs better than other models.
文摘To build a community of scientific innovation,serve the country’s goals of carbon peak and carbon neutrality,promote application of scientific research outcomes in the Guangdong-Hong Kong-Macao Greater Bay Area(GBA),and accelerate the formation of new quality productive forces in the green energy industry,the Yangjiang Offshore Wind Power Laboratory and the GBA Institute of Industry and Talent(GBAIIT)recently signed a strategic cooperation agreement.
