The rapid development of the Internet of Vehicles(IoVs)underscores the importance of Vehicle-to-Everything(V2X)communication for ensuring driving safety.V2X supports control systems by providing reliable and real-time...The rapid development of the Internet of Vehicles(IoVs)underscores the importance of Vehicle-to-Everything(V2X)communication for ensuring driving safety.V2X supports control systems by providing reliable and real-time information,while the control system's decisions,in turn,affect the communication topology and channel state.Depending on the coupling between communication and control,radio resource allocation(RRA)should be controlaware.However,current RRA methods often focus on optimizing communication metrics,neglecting the needs of the control system.To promote the co-design of communication and control,this paper proposes a novel RRA method that integrates both communication and control considerations.From the communication perspective,the Age of Information(AoI)is introduced to measure the freshness of packets.From the control perspective,a weighted utility function based on Time-to-Collision(TTC)and driving distance is designed,emphasizing the neighboring importance and potentially dangerous vehicles.By synthesizing these two metrics,an optimization objective minimizing weighted AoI based on TTC and driving distance is formulated.The RRA process is modeled as a partially observable Markov decision process,and a multi-agent reinforcement learning algorithm incorporating positional encoding and attention mechanisms(PAMARL)is proposed.Simulation results show that PAMARL can reduce Collision Risk(CR)with better Packet Delivery Ratio(PDR)than others.展开更多
目的分析轻度认知功能障碍(mild cognitive impairment,MCI)患者的简易精神状态检查(minimental state examination,MMSE)得分轨迹及阿尔兹海默病(Alzheimer's disease,AD)发病风险,分析MCI向AD转化的危险因素,为疾病干预提供参考...目的分析轻度认知功能障碍(mild cognitive impairment,MCI)患者的简易精神状态检查(minimental state examination,MMSE)得分轨迹及阿尔兹海默病(Alzheimer's disease,AD)发病风险,分析MCI向AD转化的危险因素,为疾病干预提供参考。方法基于AD神经影像学计划数据库2005—2016年的随访数据,采用联合潜在类别模型(joint latent class modle,JLCM)分析不同类别MCI患者MMSE得分变化轨迹及AD发病风险因素。结果共纳入324例患者,随访后113例转化为AD,211例为MCI,两组临床痴呆评分总和量表(clinical dementia rating scale sum of boxes,CDR-SB)得分、功能活动评估(functional activities questionnaire,FAQ)得分、MMSE得分、听觉语言学习测试(rey auditory-verbal learning test,RAVLT)得分、年龄、体质量指数(body mass index,BMI)差异有统计学意义(t=-17.14、-16.97、11.33、11.42、-2.41、2.98,P<0.05)。根据MMSE的动态变化轨迹将人群划分为高危组和低危组,JLCM分析发现,在高危组中,CDR-SB得分(HR=1.55,95%CI:1.05~2.29)和FAQ得分(HR=1.10,95%CI:1.03~1.18)越高,BMI(HR=0.91,95%CI:0.85~0.97)越低,AD发病风险越高;在低危组中,CDR-SB得分(HR=1.30,95%CI:1.03~1.65)、糖蛋白-N-乙酰(glycoproteinN-acetyl,GlycA)(HR=13.30,95%CI:3.46~51.14)和FAQ得分(HR=1.06,95%CI:1.01~1.11)越高,RAVLT得分越低(HR=0.95,95%CI:0.93~0.97),AD发病风险越高。相较于女性,男性高危组中BMI越低(HR=0.91,95%CI:0.85~0.97),AD发病风险越高;而男性低危组中GlycA越高(HR=13.32,95%CI:3.46~51.42),AD发病风险越高。结论JLCM模型能识别MCI人群中MMSE评分变化的异质性,发现不同风险MCI人群发生AD的危险因素,从而实现AD的个性化预防和干预,为AD的有效防控提供实践依据。展开更多
基金supported by Beijing Natural Science Foundation under Grant L202018the National Natural Science Foundation of China under Grant 61931005+1 种基金the Key Laboratory of Internet of Vehicle Technical Innovation and Testing(CAICT),Ministry of Industry and Information Technology under Grant No.KL-2023-001the High-performance Computing Platform of BUPT。
文摘The rapid development of the Internet of Vehicles(IoVs)underscores the importance of Vehicle-to-Everything(V2X)communication for ensuring driving safety.V2X supports control systems by providing reliable and real-time information,while the control system's decisions,in turn,affect the communication topology and channel state.Depending on the coupling between communication and control,radio resource allocation(RRA)should be controlaware.However,current RRA methods often focus on optimizing communication metrics,neglecting the needs of the control system.To promote the co-design of communication and control,this paper proposes a novel RRA method that integrates both communication and control considerations.From the communication perspective,the Age of Information(AoI)is introduced to measure the freshness of packets.From the control perspective,a weighted utility function based on Time-to-Collision(TTC)and driving distance is designed,emphasizing the neighboring importance and potentially dangerous vehicles.By synthesizing these two metrics,an optimization objective minimizing weighted AoI based on TTC and driving distance is formulated.The RRA process is modeled as a partially observable Markov decision process,and a multi-agent reinforcement learning algorithm incorporating positional encoding and attention mechanisms(PAMARL)is proposed.Simulation results show that PAMARL can reduce Collision Risk(CR)with better Packet Delivery Ratio(PDR)than others.
文摘目的分析轻度认知功能障碍(mild cognitive impairment,MCI)患者的简易精神状态检查(minimental state examination,MMSE)得分轨迹及阿尔兹海默病(Alzheimer's disease,AD)发病风险,分析MCI向AD转化的危险因素,为疾病干预提供参考。方法基于AD神经影像学计划数据库2005—2016年的随访数据,采用联合潜在类别模型(joint latent class modle,JLCM)分析不同类别MCI患者MMSE得分变化轨迹及AD发病风险因素。结果共纳入324例患者,随访后113例转化为AD,211例为MCI,两组临床痴呆评分总和量表(clinical dementia rating scale sum of boxes,CDR-SB)得分、功能活动评估(functional activities questionnaire,FAQ)得分、MMSE得分、听觉语言学习测试(rey auditory-verbal learning test,RAVLT)得分、年龄、体质量指数(body mass index,BMI)差异有统计学意义(t=-17.14、-16.97、11.33、11.42、-2.41、2.98,P<0.05)。根据MMSE的动态变化轨迹将人群划分为高危组和低危组,JLCM分析发现,在高危组中,CDR-SB得分(HR=1.55,95%CI:1.05~2.29)和FAQ得分(HR=1.10,95%CI:1.03~1.18)越高,BMI(HR=0.91,95%CI:0.85~0.97)越低,AD发病风险越高;在低危组中,CDR-SB得分(HR=1.30,95%CI:1.03~1.65)、糖蛋白-N-乙酰(glycoproteinN-acetyl,GlycA)(HR=13.30,95%CI:3.46~51.14)和FAQ得分(HR=1.06,95%CI:1.01~1.11)越高,RAVLT得分越低(HR=0.95,95%CI:0.93~0.97),AD发病风险越高。相较于女性,男性高危组中BMI越低(HR=0.91,95%CI:0.85~0.97),AD发病风险越高;而男性低危组中GlycA越高(HR=13.32,95%CI:3.46~51.42),AD发病风险越高。结论JLCM模型能识别MCI人群中MMSE评分变化的异质性,发现不同风险MCI人群发生AD的危险因素,从而实现AD的个性化预防和干预,为AD的有效防控提供实践依据。
