School of Mathematical Sciences, Yangzhou University, Yangzhou, P.R. China.
PLoS One. 2024 Aug 20;19(8):e0307332. doi: 10.1371/journal.pone.0307332. eCollection 2024.
This study investigates the impact of maternal health on infant development by developing a mathematical model that delineates the relationship between maternal health indicators and infant behavioral characteristics and sleep quality. The main contributions of this study are as follows: (1) The use of Spearman's correlation coefficient to conduct correlation analysis and explore the main factors that influence infant behavioral characteristics based on maternal indicators. (2) The development of a combined model using machine learning techniques, including random forest (RF) and multilayer perceptron (MLP) to establish the relationship between maternal health (physical and psychological health) and infant behavioral characteristics. The model is trained and validated by the real data respectively. (3) The use of the Fuzzy C-means (FCM) dynamic clustering model to classify infant sleep quality. An RF regression model is constructed to predict infant sleep quality using maternal indicators. This study is significant in gaining a deeper understanding of the relationship between maternal health indicators and infant development, and provides a basis for future intervention measures.
本研究通过建立一个数学模型，描绘了母婴健康指标与婴儿行为特征和睡眠质量之间的关系，以此来研究母婴健康对婴儿发育的影响。本研究的主要贡献如下：（1）使用斯皮尔曼相关系数进行相关分析，基于母婴指标探讨影响婴儿行为特征的主要因素。（2）采用机器学习技术（包括随机森林（RF）和多层感知器（MLP））开发了一个综合模型，以建立母婴健康（身体和心理健康）与婴儿行为特征之间的关系。该模型分别通过真实数据进行训练和验证。（3）使用模糊 C 均值（FCM）动态聚类模型对婴儿睡眠质量进行分类。构建一个 RF 回归模型，使用母婴指标预测婴儿睡眠质量。本研究对于深入了解母婴健康指标与婴儿发育之间的关系具有重要意义，并为未来的干预措施提供了依据。
