Most image-based object detection methods employ horizontal bounding boxes(HBBs)to capture objects in tunnel images.However,these bounding boxes often fail to effectively enclose objects oriented in arbitrary directio...Most image-based object detection methods employ horizontal bounding boxes(HBBs)to capture objects in tunnel images.However,these bounding boxes often fail to effectively enclose objects oriented in arbitrary directions,resulting in reduced accuracy and suboptimal detection performance.Moreover,HBBs cannot provide directional information for rotated objects.This study proposes a rotated detection method for identifying apparent defects in shield tunnels.Specifically,the oriented region-convolutional neural network(oriented R-CNN)is utilized to detect rotated objects in tunnel images.To enhance feature extraction,a novel hybrid backbone combining CNN-based networks with Swin Transformers is proposed.A feature fusion strategy is employed to integrate features extracted from both networks.Additionally,a neck network based on the bidirectional-feature pyramid network(Bi-FPN)is designed to combine multi-scale object features.The bolt hole dataset is curated to evaluate the efficacyof the proposed method.In addition,a dedicated pre-processing approach is developed for large-sized images to accommodate the rotated,dense,and small-scale characteristics of objects in tunnel images.Experimental results demonstrate that the proposed method achieves a more than 4%improvement in mAP_(50-95)compared to other rotated detectors and a 6.6%-12.7%improvement over mainstream horizontal detectors.Furthermore,the proposed method outperforms mainstream methods by 6.5%-14.7%in detecting leakage bolt holes,underscoring its significant engineering applicability.展开更多
Background Selective attention is considered one of the main components of cognitive functioning.A number of studies have demonstrated gender differences in cognition.This study aimed to investigate the gender differe...Background Selective attention is considered one of the main components of cognitive functioning.A number of studies have demonstrated gender differences in cognition.This study aimed to investigate the gender differences in selective attention in healthy subjects.Methods The present experiment examined the gender differences associated with the efficiency of three attentional networks：alerting,orienting,and executive control attention in 73 healthy subjects （38 males）.All participants performed a modified version of the Attention Network Test （ANT）.Results Females had higher orienting scores than males （t=2.172,P 〈0.05）.Specifically,females were faster at covert orienting of attention to a spatially cued location.There were no gender differences between males and females in alerting （t=0.813,P 〉0.05） and executive control （t=0.945,P 〉0.05） attention networks.Conclusions There was a significant gender difference between males and females associated with the orienting network.Enhanced orienting attention in females may function to motivate females to direct their attention to a spatially cued location.展开更多
Innovations in new applications and technological advancements are driving the evolution of network architectures towards flexibility and automation.Network Function Virtualization(NFV)deploys Network Functions(NFs)as...Innovations in new applications and technological advancements are driving the evolution of network architectures towards flexibility and automation.Network Function Virtualization(NFV)deploys Network Functions(NFs)as software applications onto cloud infrastructures,redefining the development,deployment,and operation models of communication networks,thereby meeting the evolution demands of networks.However,after more than a decade of development,the progress of network service operators in NFV has not met expectations,partly because some key technologies remain unresolved.To accelerate the large-scale commercial use of NFV,this paper focuses on reviewing relevant literature from the past five years.Based on practical applications and insights into future trends,we explore the three directions of network virtualization,network cloudification,and network service orientation.We investigate the most representative technologies and the latest research progress in these fields,analyze the current problems and challenges,and provide corresponding suggestions on how to deal with them.Finally,we forecast future directions of technological development.展开更多
Software-Defined Networking（SDN） decouples the control plane and the data plane in network switches and routers, which enables the rapid innovation and optimization of routing and switching configurations. However,t...Software-Defined Networking（SDN） decouples the control plane and the data plane in network switches and routers, which enables the rapid innovation and optimization of routing and switching configurations. However,traditional routing mechanisms in SDN, based on the Dijkstra shortest path, do not take the capacity of nodes into account, which may lead to network congestion. Moreover, security resource utilization in SDN is inefficient and is not addressed by existing routing algorithms. In this paper, we propose Route Guardian, a reliable securityoriented SDN routing mechanism, which considers the capabilities of SDN switch nodes combined with a Network Security Virtualization framework. Our scheme employs the distributed network security devices effectively to ensure analysis of abnormal traffic and malicious node isolation. Furthermore, Route Guardian supports dynamic routing reconfiguration according to the latest network status. We prototyped Route Guardian and conducted theoretical analysis and performance evaluation. Our results demonstrate that this approach can effectively use the existing security devices and mechanisms in SDN.展开更多
基金support from the National Natural Science Foundation of China(Grant Nos.52025084 and 52408420)the Beijing Natural Science Foundation(Grant No.8244058).
文摘Most image-based object detection methods employ horizontal bounding boxes(HBBs)to capture objects in tunnel images.However,these bounding boxes often fail to effectively enclose objects oriented in arbitrary directions,resulting in reduced accuracy and suboptimal detection performance.Moreover,HBBs cannot provide directional information for rotated objects.This study proposes a rotated detection method for identifying apparent defects in shield tunnels.Specifically,the oriented region-convolutional neural network(oriented R-CNN)is utilized to detect rotated objects in tunnel images.To enhance feature extraction,a novel hybrid backbone combining CNN-based networks with Swin Transformers is proposed.A feature fusion strategy is employed to integrate features extracted from both networks.Additionally,a neck network based on the bidirectional-feature pyramid network(Bi-FPN)is designed to combine multi-scale object features.The bolt hole dataset is curated to evaluate the efficacyof the proposed method.In addition,a dedicated pre-processing approach is developed for large-sized images to accommodate the rotated,dense,and small-scale characteristics of objects in tunnel images.Experimental results demonstrate that the proposed method achieves a more than 4%improvement in mAP_(50-95)compared to other rotated detectors and a 6.6%-12.7%improvement over mainstream horizontal detectors.Furthermore,the proposed method outperforms mainstream methods by 6.5%-14.7%in detecting leakage bolt holes,underscoring its significant engineering applicability.
基金This work was supported by grants from the National Natural Science Foundation of China （No. 30870766）, the National Basic Research Program of China （973 Program） （No. 2011CB707805）, and International Program of Anhui Province （No. 10080703040）. Conflict of interest： None.
文摘Background Selective attention is considered one of the main components of cognitive functioning.A number of studies have demonstrated gender differences in cognition.This study aimed to investigate the gender differences in selective attention in healthy subjects.Methods The present experiment examined the gender differences associated with the efficiency of three attentional networks：alerting,orienting,and executive control attention in 73 healthy subjects （38 males）.All participants performed a modified version of the Attention Network Test （ANT）.Results Females had higher orienting scores than males （t=2.172,P 〈0.05）.Specifically,females were faster at covert orienting of attention to a spatially cued location.There were no gender differences between males and females in alerting （t=0.813,P 〉0.05） and executive control （t=0.945,P 〉0.05） attention networks.Conclusions There was a significant gender difference between males and females associated with the orienting network.Enhanced orienting attention in females may function to motivate females to direct their attention to a spatially cued location.
文摘Innovations in new applications and technological advancements are driving the evolution of network architectures towards flexibility and automation.Network Function Virtualization(NFV)deploys Network Functions(NFs)as software applications onto cloud infrastructures,redefining the development,deployment,and operation models of communication networks,thereby meeting the evolution demands of networks.However,after more than a decade of development,the progress of network service operators in NFV has not met expectations,partly because some key technologies remain unresolved.To accelerate the large-scale commercial use of NFV,this paper focuses on reviewing relevant literature from the past five years.Based on practical applications and insights into future trends,we explore the three directions of network virtualization,network cloudification,and network service orientation.We investigate the most representative technologies and the latest research progress in these fields,analyze the current problems and challenges,and provide corresponding suggestions on how to deal with them.Finally,we forecast future directions of technological development.
基金supported in part by the National Natural Science Foundation of China (Nos. 61402029, 61370190, and 61379002)the National Key Basic Research Program (973) of China (No. 2012CB315905)
文摘Software-Defined Networking（SDN） decouples the control plane and the data plane in network switches and routers, which enables the rapid innovation and optimization of routing and switching configurations. However,traditional routing mechanisms in SDN, based on the Dijkstra shortest path, do not take the capacity of nodes into account, which may lead to network congestion. Moreover, security resource utilization in SDN is inefficient and is not addressed by existing routing algorithms. In this paper, we propose Route Guardian, a reliable securityoriented SDN routing mechanism, which considers the capabilities of SDN switch nodes combined with a Network Security Virtualization framework. Our scheme employs the distributed network security devices effectively to ensure analysis of abnormal traffic and malicious node isolation. Furthermore, Route Guardian supports dynamic routing reconfiguration according to the latest network status. We prototyped Route Guardian and conducted theoretical analysis and performance evaluation. Our results demonstrate that this approach can effectively use the existing security devices and mechanisms in SDN.
