在教育数字化转型的背景下,本研究识别混合式学习作为提高高职学生学习参与度的策略。通过理论分析,本研究确立了面授学习、实践学习、线上学习及合作学习四个关键维度。为量化这些维度的影响,设计并实施了包含相关问题的问卷,随后进行信度与效度的系统评估。研究采用探索性因子分析确定问题权重,以及多元线性回归模型来评估各维度对学习参与度的具体贡献。模型的准确性和稳定性通过残差分析、交叉验证以及多重共线性检验来验证。研究结果揭示,所有学习维度均显著正向影响学习参与度,其中合作学习的贡献最为突出。基于以上发现,提出针对性策略以优化混合式学习环境,从而提升学习参与度,并促进教育质量的提升及数字化转型的实施。In the context of the digital transformation of education, this study identifies blended learning as a strategy to enhance student engagement in vocational education. Through theoretical analysis, the study establishes four key dimensions: face-to-face learning, practical learning, online learning, and collaborative learning. To quantify the impact of these dimensions, a questionnaire containing relevant questions was designed and administered, followed by a systematic evaluation of reliability and validity. The study employs exploratory factor analysis to determine the weighting of questions and multiple linear regression models to assess the specific contributions of each dimension to learning engagement. The accuracy and stability of the models were verified through residual analysis, cross-validation, and multicollinearity tests. The results reveal that all learning dimensions significantly and positively influence learning engagement, with collaborative learning making the most substantial contribution. Based on these findings, targeted strategies are proposed to optimize the blended learning environment, thereby enhancing learning engagement and promoting the improvement of education quality and the implementation of digital transformation.
以旅游大数据为基础,考虑长时间范围内的滞后效应以及不同搜索强度指数(Search Intensity Index,SII)之间的多任务影响,提出一种基于大数据的多任务旅游信息分析(Multi-tasking Tourism Information Analysis Based on Big Data,MTIABD...
详细信息
以旅游大数据为基础,考虑长时间范围内的滞后效应以及不同搜索强度指数(Search Intensity Index,SII)之间的多任务影响,提出一种基于大数据的多任务旅游信息分析(Multi-tasking Tourism Information Analysis Based on Big Data,MTIABD)框架。使用融合信息重排序技术预测旅游需求,具体根据图引导结构模拟历史变量对未来变量的滞后影响。每个变量通过时间维度上的卷积神经网络(Convolutional Neural Network,CNN)进行独立编码,利用二分图动态建模滞后效应,通过图聚合进行挖掘,实现对旅游需求的精准预测。基于上述技术,构建旅游需求预测系统,旅游者能够根据需求检索不同景点的信息。在真实数据集上进行大量实验,结果表明所提出的MTIABD框架在一步和多步预测方面均优于现有方法。在平均绝对百分比误差(Mean Absolute Percentage Error,MAPE)指标下,相较于基于实例的多变量时间序列图预测框架(Instance-wise Graph-rased Framework for Multivariate Time Series Forecasting,IGMTF),MTIABD在HK-2021数据集上的性能提高了16.75%,在MO-2021数据集上的性能提高了19.79%。
暂无评论