In order to improve the image quality of a specific class of crack images, as well as to solve the problems of insufficient size of the number of crack datasets and small number of complex crack images, a crack image generation model based on DCGAN (Deep Convolutional Generative Adversarial Network, DCGAN) is proposed, which has superior training stability and convergence speed. The experimental results show that DCGAN can generate a large number of real crack images with complex backgrounds more reliably than traditional image augmentation methods, effectively solving the problem of lack of crack images in special cases and greatly reducing the cost of crack image acquisition tasks.
To address the current problem of single-site prediction and inadequate extraction of spatial features for PM2.5 hourly concentration prediction, a graphical convolutional neural network (GCN) is proposed to obtain the spatial correlation between PM2.5 monitoring stations in Beijing by considering the features of time series in time and space, and assign weights according to the distance between stations to abstract into an undirected topological map. The missing data sequences are complemented by using a long and short-term memory network to extract temporal features on the time-series dataset, which are normalized and then fused with the components extracted by the GCN to make predictions. The experimental results show that GCN-BiLSTM has higher prediction accuracy and better results than single RNN, LSTM, and BiLSTM algorithms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.