Rice crops are frequently threatened by pests such as rice planthoppers(Nilaparvata lugens,Sogatella furcifera,and Laodelphax striatellus)and leafhoppers(Cicadellidae),which cause significant yield losses.Accurate ide...Rice crops are frequently threatened by pests such as rice planthoppers(Nilaparvata lugens,Sogatella furcifera,and Laodelphax striatellus)and leafhoppers(Cicadellidae),which cause significant yield losses.Accurate identification of both pest developmental stages and their natural predators is crucial for effective pest control and maintaining ecological balance.However,conventional field surveys are often subjective,inefficient,and lack traceability.To overcome these limitations,this study proposed RiceInsectID,a two-stage cascaded detection method designed to identify and count tiny rice pests and their natural predators from white flat plate images captured by head-worn AR glasses.The method recognizes 25 insect classes,including 17 instars of rice planthoppers,2 instars of leafhoppers,4 spider species(Araneae),as well as Miridae and rove beetles(Staphylinidae Latreille).At the first coarse-grained detection stage,16 visually similar classes are consolidated into 6 broader categories and detected using an enhanced YOLOv6 model.To improve small object detection and address class imbalance,the fullregion overlapping sliding slices and target pasting(FOSTP)algorithm was applied,increasing the mean average precision at a 50%IoU threshold(mAP50)by 35.46%over the baseline YOLOv6.Feature extraction and fusion were further improved by incorporating an efficient channel attention path aggregation feature pyramid network(ECA-PAFPN)and adaptive structure feature fusion(ASFF)modules,while the balanced classification mosaic(BCM)enhanced detection of minority classes.With test-time augmentation(TTA),mAP50 improved by an additional 2.06%,reaching 84.71%.At the second fine-grained classification stage,each of the six broad classes from the first stage is further classified using individual ResNet50 models.Online data augmentation and transfer learning were employed to significantly enhance generalization.Compared with the baseline YOLOv6,the two-stage cascaded method improved recall by 4.06%,precision by 3.79%,and the F1-score by 3.92%.Overall,RiceInsectID achieved 82.85%recall,80.62%precision,and an F1-score of 81.72%,demonstrating an efficient and practical solution for monitoring tiny rice pests and their natural predators in paddy fields.This study provides valuable insights for ecosystem monitoring and supporting sustainable pest management in rice agriculture.展开更多
With the iteration and upgrading of medical technology and the continuous growth of public health demands,the quality of nursing services has become a core indicator for measuring the effectiveness of the medical syst...With the iteration and upgrading of medical technology and the continuous growth of public health demands,the quality of nursing services has become a core indicator for measuring the effectiveness of the medical system.The clinical practice ability of nursing staff is directly related to the safety of patient diagnosis and treatment and the rehabilitation process.However,the current clinical nursing talent training model is facing bottlenecks such as limited practical scenarios and fragmented case cognition.This study focuses on the teaching application of augmented reality(AR)technology in hospital Settings and systematically reviews the research progress on the improvement of clinical practice ability of trainee nurses based on the AR immersive teaching model.By constructing a clinical teaching scenario that integrates virtual and real,AR technology can dynamically simulate complex case handling processes and enhance nursing students’three-dimensional cognition of condition assessment,operation norms,and emergency plans.Hospitals,as the core base for practical teaching,can effectively shorten the connection cycle between theoretical teaching and clinical practice by integrating AR technology,improve the clinical practice level of trainee nurses,and provide an innovative model for optimizing the path of clinical nursing talent cultivation.展开更多
Augmented reality(AR)is a technology that superimposes digital information onto real-world objects via head-mounted display devices to improve surgical finesse through visually enhanced medical information.With the ra...Augmented reality(AR)is a technology that superimposes digital information onto real-world objects via head-mounted display devices to improve surgical finesse through visually enhanced medical information.With the rapid development of digital technology,AR has been increasingly adopted in orthopedic surgeries across the globe,especially in total knee arthroplasty procedures which demand high precision.By overlaying digital information onto the surgeon's field of view,AR systems enhance precision,improve alignment accuracy,and reduce the risk of complications associated with malalignment.Some concerns have been raised despite accuracy,including the learning curve,long-term outcomes,and technical limitations.Furthermore,it is essential for health practitioners to gain trust in the utilisation of AR.展开更多
基金supported by the National Key Research Program of China during the 14th Five-Year Plan Period(Grant No.2021YFD1401100)the Zhejiang Provincial Natural Science Foundation of China(Grant No.LTGN24C140007)the‘San Nong Jiu Fang’Sciences and Technologies Cooperation Project of Zhejiang Province,China(Grant No.2024SNJF010)。
文摘Rice crops are frequently threatened by pests such as rice planthoppers(Nilaparvata lugens,Sogatella furcifera,and Laodelphax striatellus)and leafhoppers(Cicadellidae),which cause significant yield losses.Accurate identification of both pest developmental stages and their natural predators is crucial for effective pest control and maintaining ecological balance.However,conventional field surveys are often subjective,inefficient,and lack traceability.To overcome these limitations,this study proposed RiceInsectID,a two-stage cascaded detection method designed to identify and count tiny rice pests and their natural predators from white flat plate images captured by head-worn AR glasses.The method recognizes 25 insect classes,including 17 instars of rice planthoppers,2 instars of leafhoppers,4 spider species(Araneae),as well as Miridae and rove beetles(Staphylinidae Latreille).At the first coarse-grained detection stage,16 visually similar classes are consolidated into 6 broader categories and detected using an enhanced YOLOv6 model.To improve small object detection and address class imbalance,the fullregion overlapping sliding slices and target pasting(FOSTP)algorithm was applied,increasing the mean average precision at a 50%IoU threshold(mAP50)by 35.46%over the baseline YOLOv6.Feature extraction and fusion were further improved by incorporating an efficient channel attention path aggregation feature pyramid network(ECA-PAFPN)and adaptive structure feature fusion(ASFF)modules,while the balanced classification mosaic(BCM)enhanced detection of minority classes.With test-time augmentation(TTA),mAP50 improved by an additional 2.06%,reaching 84.71%.At the second fine-grained classification stage,each of the six broad classes from the first stage is further classified using individual ResNet50 models.Online data augmentation and transfer learning were employed to significantly enhance generalization.Compared with the baseline YOLOv6,the two-stage cascaded method improved recall by 4.06%,precision by 3.79%,and the F1-score by 3.92%.Overall,RiceInsectID achieved 82.85%recall,80.62%precision,and an F1-score of 81.72%,demonstrating an efficient and practical solution for monitoring tiny rice pests and their natural predators in paddy fields.This study provides valuable insights for ecosystem monitoring and supporting sustainable pest management in rice agriculture.
文摘With the iteration and upgrading of medical technology and the continuous growth of public health demands,the quality of nursing services has become a core indicator for measuring the effectiveness of the medical system.The clinical practice ability of nursing staff is directly related to the safety of patient diagnosis and treatment and the rehabilitation process.However,the current clinical nursing talent training model is facing bottlenecks such as limited practical scenarios and fragmented case cognition.This study focuses on the teaching application of augmented reality(AR)technology in hospital Settings and systematically reviews the research progress on the improvement of clinical practice ability of trainee nurses based on the AR immersive teaching model.By constructing a clinical teaching scenario that integrates virtual and real,AR technology can dynamically simulate complex case handling processes and enhance nursing students’three-dimensional cognition of condition assessment,operation norms,and emergency plans.Hospitals,as the core base for practical teaching,can effectively shorten the connection cycle between theoretical teaching and clinical practice by integrating AR technology,improve the clinical practice level of trainee nurses,and provide an innovative model for optimizing the path of clinical nursing talent cultivation.
基金Supported by The Hunan Provincial Natural Science Foundation of China,No.2023JJ30773,No.2025JJ60480,and No.2025JJ60552The Scientific Research Program of The Hunan Provincial Health Commission,No.202204072544+4 种基金The Science and Technology Innovation Program of Hunan Province,No.2024RC3053The CBT ECR/MCR Scheme,No.324910-0028/07National Natural Science Foundation of China,No.32300652The Scientific Research Program of Hunan Provincial Health Commission,No.W20243023The Scientific Research Launch Project for New Employees of The Second Xiangya Hospital of Central South University.
文摘Augmented reality(AR)is a technology that superimposes digital information onto real-world objects via head-mounted display devices to improve surgical finesse through visually enhanced medical information.With the rapid development of digital technology,AR has been increasingly adopted in orthopedic surgeries across the globe,especially in total knee arthroplasty procedures which demand high precision.By overlaying digital information onto the surgeon's field of view,AR systems enhance precision,improve alignment accuracy,and reduce the risk of complications associated with malalignment.Some concerns have been raised despite accuracy,including the learning curve,long-term outcomes,and technical limitations.Furthermore,it is essential for health practitioners to gain trust in the utilisation of AR.
