11 March 2022 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Remote sensing image change detection (RSICD) is a technique that explores the change of surface coverage in a certain time series by studying the difference between multiple remote sensing images (RSIs) collected over the same area. Traditional RSICD algorithms exhibit poor performance on complex change detection (CD) tasks. In recent years, deep learning (DL) techniques have achieved outstanding results in the fields of RSI segmentation and target recognition. In CD research, most of the methods treat multitemporal remote sensing data as one input and directly apply DL-based image segmentation theory on it while ignoring the spatio-temporal information in these images. In this article, a new siamese neural network is designed by combing an attention mechanism (Siamese_AUNet) with UNet to solve the problems of RSICD algorithms. SiameseNet encodes the feature extraction of RSIs by two branches in the siamese network, respectively. The weights are shared between these two branches in siamese networks. Subsequently, an attention mechanism is added to the model in order to improve its detection ability for changed objects. The models are then compared with conventional neural networks using three benchmark datasets. The results show that the Siamese_AUNet newly proposed in this article exhibits better performance than other standard methods when solving problems related to weak CD and noise suppression.
15 November 2023 in Highlights in Science, Engineering and Technology
The physical and mental health of the mother is one of the main factors affecting the healthy development of the infant. It is important to study the physical and psychological indicators of mothers and the corresponding interventions for the healthy growth of infants. In this paper, the relationship between mothers' physical and mental health and infants' behavior was investigated. Structural equation modeling (SEM) was used to analyze the standardized data, analyze the relationship between the influence of the paths of each factor, understand the composition of the paths of each factor node from a global perspective, and filter the quantitative variables within the factor through the factor loading coefficients, record the standardized coefficients and test the significance of the data to eliminate invalid paths, which in turn led to the correlation law. At the same time, the relationship model of the infant's behavioral characteristics with the mother's physical and psychological indicators was established using the LightGBM regression model for classification, so as to establish the relationship model, and get the model with good performance.