The progenies differed in amylose and protein contents in grains, which derived from a rice cross, Dongnong 423×Toukei 180, were used to study changes in the activities of ADP-glucose pyrophosphorylase （AGPP）, ...The progenies differed in amylose and protein contents in grains, which derived from a rice cross, Dongnong 423×Toukei 180, were used to study changes in the activities of ADP-glucose pyrophosphorylase （AGPP）, soluble starch synthetase （SSS）, starch branching enzyme （SBE） and glutamine synthetase （GS） in rice grains during grain filling. The activities of AGPP, SSS and SBE gradually increased and then declined as a single-peak curve with the process of grain filling in the progenies with high and low amylose contents in grains. The progenies with high amylose content peaked earlier in the AGPP, SSS and SBE activities and had higher AGPP, SSS and SBE activities at the early grain filling stage than those with low amylose content. The GS activity peaked earlier and was higher at the late stage of grain filling in the progenies with high protein content than in those with low protein content. It is suggested that the activities of key enzymes for starch synthesis and glutamine synthetase could be changed in oriented breeding for amylose and protein contents in grains.展开更多
知识追踪任务旨在根据学生历史学习行为实时追踪学生知识水平变化,并且预测学生在未来学习表现.在学生学习过程中,学习行为与遗忘行为相互交织,学生的遗忘行为对知识追踪影响很大.为了准确建模知识追踪中学习与遗忘行为,提出一种兼顾学...知识追踪任务旨在根据学生历史学习行为实时追踪学生知识水平变化,并且预测学生在未来学习表现.在学生学习过程中,学习行为与遗忘行为相互交织,学生的遗忘行为对知识追踪影响很大.为了准确建模知识追踪中学习与遗忘行为,提出一种兼顾学习与遗忘行为的深度知识追踪模型LFKT(learning and forgetting behavior modeling for knowledge tracing).LFKT模型综合考虑了4个影响知识遗忘因素,包括学生重复学习知识点的间隔时间、重复学习知识点的次数、顺序学习间隔时间以及学生对于知识点的掌握程度.结合遗忘因素,LFKT采用深度神经网络,利用学生答题结果作为知识追踪过程中知识掌握程度的间接反馈,建模融合学习与遗忘行为的知识追踪模型.通过在真实在线教育数据集上的实验,与当前知识追踪模型相比,LFKT可以更好地追踪学生知识掌握状态,并具有较好的预测性能.展开更多
基金supported by the Program for Innovative Research Team of Northeast Agricultural University, Chinathe Project of the Department of Education of Heilongjiang Province, China (Grant No 11531017)
文摘The progenies differed in amylose and protein contents in grains, which derived from a rice cross, Dongnong 423×Toukei 180, were used to study changes in the activities of ADP-glucose pyrophosphorylase （AGPP）, soluble starch synthetase （SSS）, starch branching enzyme （SBE） and glutamine synthetase （GS） in rice grains during grain filling. The activities of AGPP, SSS and SBE gradually increased and then declined as a single-peak curve with the process of grain filling in the progenies with high and low amylose contents in grains. The progenies with high amylose content peaked earlier in the AGPP, SSS and SBE activities and had higher AGPP, SSS and SBE activities at the early grain filling stage than those with low amylose content. The GS activity peaked earlier and was higher at the late stage of grain filling in the progenies with high protein content than in those with low protein content. It is suggested that the activities of key enzymes for starch synthesis and glutamine synthetase could be changed in oriented breeding for amylose and protein contents in grains.
文摘知识追踪任务旨在根据学生历史学习行为实时追踪学生知识水平变化,并且预测学生在未来学习表现.在学生学习过程中,学习行为与遗忘行为相互交织,学生的遗忘行为对知识追踪影响很大.为了准确建模知识追踪中学习与遗忘行为,提出一种兼顾学习与遗忘行为的深度知识追踪模型LFKT(learning and forgetting behavior modeling for knowledge tracing).LFKT模型综合考虑了4个影响知识遗忘因素,包括学生重复学习知识点的间隔时间、重复学习知识点的次数、顺序学习间隔时间以及学生对于知识点的掌握程度.结合遗忘因素,LFKT采用深度神经网络,利用学生答题结果作为知识追踪过程中知识掌握程度的间接反馈,建模融合学习与遗忘行为的知识追踪模型.通过在真实在线教育数据集上的实验,与当前知识追踪模型相比,LFKT可以更好地追踪学生知识掌握状态,并具有较好的预测性能.
