With the popularity and development of artificial intelligence(AI),disease screening systems based on AI algorithms are gradually emerging in the medical field.Such systems can be used for primary screening of disease...With the popularity and development of artificial intelligence(AI),disease screening systems based on AI algorithms are gradually emerging in the medical field.Such systems can be used for primary screening of diseases to relieve the pressure on primary health care.In recent years,AI algorithms have demonstrated good performance in the analysis and identification of lesion signs in the macular region of fundus color photography,and a screening system for fundus lesion signs applicable to primary screening is bound to emerge in the future.Therefore,to standardize the design and clinical application of macular region lesion sign screening systems based on AI algorithms,the Ocular Fundus Diseases Group of Chinese Ophthalmological Society,in collaboration with relevant experts,developed this guideline after investigating issues,discussing production evidence,and holding guideline workshops.It aimed to establish uniform standards for the definition of the macular region and lesion signs,AI adoption scenarios,algorithm model construction,dataset establishment and labeling,architecture and function design,and image data acquisition for the screening system to guide the implementation of the screening work.展开更多
1.Scope This article sets terms and definitions,basic requirements,annotat-ing requirements,and quality control for fundus color photograph an-notating.This article applies to the fundus color photograph of annotating...1.Scope This article sets terms and definitions,basic requirements,annotat-ing requirements,and quality control for fundus color photograph an-notating.This article applies to the fundus color photograph of annotating and quality control of four ocular diseases signs for the purpose of referral or screening,including glaucoma,macular disorders,high myopic macular degeneration and diabetic retinopathy.Note:When referring to this article,please pay attention to the scope of annotating the signs of macular disorders in this document.展开更多
Efficient and precise traffic flow prediction is highly important in effective traffic management.This research presents a novel prediction model that integrates highway spatial changes and flow-related information(sp...Efficient and precise traffic flow prediction is highly important in effective traffic management.This research presents a novel prediction model that integrates highway spatial changes and flow-related information(speed and vehicle composition).The highway is divided into segments,using key reference points like tunnels,toll stations and ramps.An adaptive graph convolutional network is employed to capture relationships between these segments.The network automatically adjusts adjacency matrix weights,facilitating the extraction of spatial flow features.Incorporating flow-related information,a multi-task module attention fusion network is introduced.The main task is traffic flow prediction,with average travel speed and vehicle composition as auxiliary tasks.This approach enhances feature acquisition and improves prediction accuracy.In experiments using Fuzhou–Jingtan Expressway data,the model significantly enhances prediction accuracy by at least 55%.Ablation experiments validate the effectiveness of the designed modules,improving the model’s accuracy from 20%to 45%.展开更多
Tunnels on freeways,as one of the critical bottlenecks,frequently cause severe congestion and passenger delay.To solve the tunnel bottleneck problem,most of the existing research can be divided into two types.One is t...Tunnels on freeways,as one of the critical bottlenecks,frequently cause severe congestion and passenger delay.To solve the tunnel bottleneck problem,most of the existing research can be divided into two types.One is to adopt variable speed limits(VSLs)to regulate a predetermined speed for vehicles to get through a bottleneck smoothly.The other is to adopt high-occupancy vehicle(HOV)lane management.In HOV lane management strategies,all traffic is divided into HOVs and low-occupancy vehicles(LOVs).HOVs are vehicles with a driver and one or more passengers.LOVs are vehicles with only a driver.This kind of research can grant priority to HOVs by providing a dedicated HOV lane.However,the existing research cannot both mitigate congestion and maximize passenger-oriented benefits.To address the research gap,this paper leverages connected and automated vehicle(CAV)technologies on intelligent freeways and develops a tunnel bottleneck management strategy with a dynamic HOV lane(DHL).The strategy bears the following features:1)enables tunnel bottleneck management at a microscopic level;2)maximizes passenger-oriented benefits;3)grants priority to HOVs even when the HOV lane is open to LOVs;4)allocates right-of-way segments for HOVs and LOVs in real time;and 5)performs well in a mixed-traffic environment.The proposed strategy is evaluated through comparison against the non-control baseline and a VSL strategy.Sensitivity analysis is conducted under different congestion levels and penetration rates.The results demonstrate that the proposed strategy outperforms in terms of passenger-oriented delay reduction and HOVs’priority level improvement.展开更多
文摘With the popularity and development of artificial intelligence(AI),disease screening systems based on AI algorithms are gradually emerging in the medical field.Such systems can be used for primary screening of diseases to relieve the pressure on primary health care.In recent years,AI algorithms have demonstrated good performance in the analysis and identification of lesion signs in the macular region of fundus color photography,and a screening system for fundus lesion signs applicable to primary screening is bound to emerge in the future.Therefore,to standardize the design and clinical application of macular region lesion sign screening systems based on AI algorithms,the Ocular Fundus Diseases Group of Chinese Ophthalmological Society,in collaboration with relevant experts,developed this guideline after investigating issues,discussing production evidence,and holding guideline workshops.It aimed to establish uniform standards for the definition of the macular region and lesion signs,AI adoption scenarios,algorithm model construction,dataset establishment and labeling,architecture and function design,and image data acquisition for the screening system to guide the implementation of the screening work.
文摘1.Scope This article sets terms and definitions,basic requirements,annotat-ing requirements,and quality control for fundus color photograph an-notating.This article applies to the fundus color photograph of annotating and quality control of four ocular diseases signs for the purpose of referral or screening,including glaucoma,macular disorders,high myopic macular degeneration and diabetic retinopathy.Note:When referring to this article,please pay attention to the scope of annotating the signs of macular disorders in this document.
基金supported by National Science and Technology Major Project(Grant No.2022ZD0115501)National Key R&D Program of China(Grant No.2022YFF0604905).
文摘Efficient and precise traffic flow prediction is highly important in effective traffic management.This research presents a novel prediction model that integrates highway spatial changes and flow-related information(speed and vehicle composition).The highway is divided into segments,using key reference points like tunnels,toll stations and ramps.An adaptive graph convolutional network is employed to capture relationships between these segments.The network automatically adjusts adjacency matrix weights,facilitating the extraction of spatial flow features.Incorporating flow-related information,a multi-task module attention fusion network is introduced.The main task is traffic flow prediction,with average travel speed and vehicle composition as auxiliary tasks.This approach enhances feature acquisition and improves prediction accuracy.In experiments using Fuzhou–Jingtan Expressway data,the model significantly enhances prediction accuracy by at least 55%.Ablation experiments validate the effectiveness of the designed modules,improving the model’s accuracy from 20%to 45%.
基金supported by the National Key R&D Pro-gram of China(Grant No.2022YFF0604905)the National Natural Science Foundation of China(Grant No.52072264)+2 种基金the Zhengzhou Major Science and Technology Project(Grant No.2021KJZX0060-9)the Shanghai Automotive Industry Science and Technology De-velopment Foundation(Grant No.2213)the Tongji Zhongte Chair Professor Foundation(Grant No.000000375-2018082).
文摘Tunnels on freeways,as one of the critical bottlenecks,frequently cause severe congestion and passenger delay.To solve the tunnel bottleneck problem,most of the existing research can be divided into two types.One is to adopt variable speed limits(VSLs)to regulate a predetermined speed for vehicles to get through a bottleneck smoothly.The other is to adopt high-occupancy vehicle(HOV)lane management.In HOV lane management strategies,all traffic is divided into HOVs and low-occupancy vehicles(LOVs).HOVs are vehicles with a driver and one or more passengers.LOVs are vehicles with only a driver.This kind of research can grant priority to HOVs by providing a dedicated HOV lane.However,the existing research cannot both mitigate congestion and maximize passenger-oriented benefits.To address the research gap,this paper leverages connected and automated vehicle(CAV)technologies on intelligent freeways and develops a tunnel bottleneck management strategy with a dynamic HOV lane(DHL).The strategy bears the following features:1)enables tunnel bottleneck management at a microscopic level;2)maximizes passenger-oriented benefits;3)grants priority to HOVs even when the HOV lane is open to LOVs;4)allocates right-of-way segments for HOVs and LOVs in real time;and 5)performs well in a mixed-traffic environment.The proposed strategy is evaluated through comparison against the non-control baseline and a VSL strategy.Sensitivity analysis is conducted under different congestion levels and penetration rates.The results demonstrate that the proposed strategy outperforms in terms of passenger-oriented delay reduction and HOVs’priority level improvement.
