目的 利用事件相关电位(ERP)技术探讨单次不同强度乒乓球运动对抑郁症状大学生工作记忆的影响及其认知神经加工机制。方法 采用方便抽样法,在某高校招募100名有抑郁症状的大学生,按1∶1∶1∶1比例随机分为低强度运动组、中强度运动组、...目的 利用事件相关电位(ERP)技术探讨单次不同强度乒乓球运动对抑郁症状大学生工作记忆的影响及其认知神经加工机制。方法 采用方便抽样法,在某高校招募100名有抑郁症状的大学生,按1∶1∶1∶1比例随机分为低强度运动组、中强度运动组、高强度运动组和对照组,低强度运动组、中强度运动组、高强度运动组分别接受强度为57%~64%最大心率(HRmax)和主观疲劳感觉分级量表(RPE)评分9~11分、65%~75% HRmax和RPE评分12~13分、76%~95% HRmax和RPE评分14~17分的单次乒乓球运动干预30 min(5 min热身、20 min监控锻炼、5 min整理),对照组不接受运动干预。干预前后进行言语工作记忆(VWM)和空间工作记忆(SWM)测量,并记录任务期间的ERP成分(N2、P3的波幅和潜伏期)。结果 最终纳入91名受试者(低强度运动组20人、中强度运动组25人、高强度运动组23人、对照组23人)进行分析。在VWM任务中,正确率的时间主效应显著(F_(1,89)=5.942,P=0.017,偏η^(2)=0.064),干预后中强度运动组和高强度运动组正确率提高(差值=0.027,95% CI 0.001~0.053,P=0.037;差值=0.029,95% CI 0.002~0.055,P=0.040);反应时的时间主效应显著(F_(1,89)=7.244,P=0.009,偏η^(2)=0.077),组别与时间的交互效应显著(F_(3,87)=2.844,P=0.042,偏η^(2)=0.089),干预后低强度运动组和中强度运动组反应时缩短(差值=-0.095,95% CI -0.183~-0.007,P=0.035;差值=-0.079,95% CI -0.158~0,P=0.049);ERP成分中P3潜伏期的时间与脑区电极位置的交互效应显著(F_(3,87)=5.785,P<0.001,偏η^(2)=0.062),其余各阶交互效应均不显著(均P>0.05)。在SWM任务中,正确率的时间主效应显著(F_(1,89)=5.092,P=0.027,偏η^(2)=0.055),组别与时间的交互效应不显著(F_(3,87)=0.799,P=0.498,偏η^(2)=0.027),干预后中强度运动组正确率提高(差值=0.019,95% CI 0~0.037,P=0.046);反应时的时间主效应显著(F_(1,89)=14.322,P<0.001,偏η^(2)=0.141),组别与时间的交互效应不显著(F_(3,87)=1.521,P=0.215,偏η^(2)=0.050),干预后中强度运动组和高强度运动组反应时缩短(差值=-0.082,95% CI -0.136~-0.027,P=0.004;差值=-0.075,95% CI -0.131~-0.018,P=0.029);ERP成分中P3波幅的时间与脑区电极位置的交互效应显著(F_(3,87)=5.475,P=0.001,偏η^(2)=0.059),其余各阶交互效应均不显著(均P>0.05)。结论 单次不同强度乒乓球运动对抑郁症状大学生工作记忆具有积极作用:中、高强度运动可提升VWM正确率,低、中强度运动可降低VWM反应时,中强度运动可提升SWM正确率,而中、高强度运动可降低SWM反应时。同时,高强度运动对ERP成分的激活程度更高。展开更多
[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-base...[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.展开更多
目的通过事件相关电位(ERP)技术,探究8周中强度乒乓球运动对抑郁症状大学生言语工作记忆(Verbal Working Memory,VWM)的干预效果及其认知神经加工机制。方法招募60名抑郁症状大学生,按1∶1的比例随机分配为实验组和对照组,实验组接受为...目的通过事件相关电位(ERP)技术,探究8周中强度乒乓球运动对抑郁症状大学生言语工作记忆(Verbal Working Memory,VWM)的干预效果及其认知神经加工机制。方法招募60名抑郁症状大学生,按1∶1的比例随机分配为实验组和对照组,实验组接受为期8周、每周3次、每次30 min(5 min热身+20 min乒乓球运动+5 min整理)、心率为65%~75%HR_(max)的乒乓球运动,对照组不进行任何形式的干预。在实验前后测试VWM及其ERP成分(N2、P3)和抑郁症状。结果实际纳入52名抑郁症状大学生(实验组25人,对照组27人)。VWM正确率的组别与时间交互效应显著(F(1,50)=4.269,P=0.044,偏η^(2)=0.079),实验组正确率在运动干预后显著提高(平均差异为0.039,95%CI为0.015~0.062,P=0.002),反应时的组别与时间交互效应不显著(F(1,50)=2.291,P=0.136,偏η^(2)=0.044),N2潜伏期的组别和时间交互效应显著(F(1,50)=4.588,P=0.037,偏η2=0.084),N2波幅、P3潜伏期与波幅的各阶交互效应均不显著。结论8周中强度乒乓球运动可有效缓解大学生抑郁症状,并提高言语工作记忆的正确率,缩短任务态N2潜伏期。展开更多
文摘目的 利用事件相关电位(ERP)技术探讨单次不同强度乒乓球运动对抑郁症状大学生工作记忆的影响及其认知神经加工机制。方法 采用方便抽样法,在某高校招募100名有抑郁症状的大学生,按1∶1∶1∶1比例随机分为低强度运动组、中强度运动组、高强度运动组和对照组,低强度运动组、中强度运动组、高强度运动组分别接受强度为57%~64%最大心率(HRmax)和主观疲劳感觉分级量表(RPE)评分9~11分、65%~75% HRmax和RPE评分12~13分、76%~95% HRmax和RPE评分14~17分的单次乒乓球运动干预30 min(5 min热身、20 min监控锻炼、5 min整理),对照组不接受运动干预。干预前后进行言语工作记忆(VWM)和空间工作记忆(SWM)测量,并记录任务期间的ERP成分(N2、P3的波幅和潜伏期)。结果 最终纳入91名受试者(低强度运动组20人、中强度运动组25人、高强度运动组23人、对照组23人)进行分析。在VWM任务中,正确率的时间主效应显著(F_(1,89)=5.942,P=0.017,偏η^(2)=0.064),干预后中强度运动组和高强度运动组正确率提高(差值=0.027,95% CI 0.001~0.053,P=0.037;差值=0.029,95% CI 0.002~0.055,P=0.040);反应时的时间主效应显著(F_(1,89)=7.244,P=0.009,偏η^(2)=0.077),组别与时间的交互效应显著(F_(3,87)=2.844,P=0.042,偏η^(2)=0.089),干预后低强度运动组和中强度运动组反应时缩短(差值=-0.095,95% CI -0.183~-0.007,P=0.035;差值=-0.079,95% CI -0.158~0,P=0.049);ERP成分中P3潜伏期的时间与脑区电极位置的交互效应显著(F_(3,87)=5.785,P<0.001,偏η^(2)=0.062),其余各阶交互效应均不显著(均P>0.05)。在SWM任务中,正确率的时间主效应显著(F_(1,89)=5.092,P=0.027,偏η^(2)=0.055),组别与时间的交互效应不显著(F_(3,87)=0.799,P=0.498,偏η^(2)=0.027),干预后中强度运动组正确率提高(差值=0.019,95% CI 0~0.037,P=0.046);反应时的时间主效应显著(F_(1,89)=14.322,P<0.001,偏η^(2)=0.141),组别与时间的交互效应不显著(F_(3,87)=1.521,P=0.215,偏η^(2)=0.050),干预后中强度运动组和高强度运动组反应时缩短(差值=-0.082,95% CI -0.136~-0.027,P=0.004;差值=-0.075,95% CI -0.131~-0.018,P=0.029);ERP成分中P3波幅的时间与脑区电极位置的交互效应显著(F_(3,87)=5.475,P=0.001,偏η^(2)=0.059),其余各阶交互效应均不显著(均P>0.05)。结论 单次不同强度乒乓球运动对抑郁症状大学生工作记忆具有积极作用:中、高强度运动可提升VWM正确率,低、中强度运动可降低VWM反应时,中强度运动可提升SWM正确率,而中、高强度运动可降低SWM反应时。同时,高强度运动对ERP成分的激活程度更高。
文摘[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.
