Land-cover change detection with hyperspectral remote sensing images (HyperCD) has become attractive in the applications of remote sensing images. Many existing studies have indicated that attention mechanisms play an important role in HyperCD. However, methods based on attention enhancement for HyperCD require further improvement. In this letter, we propose a novel multiscale difference feature-fusion network (MDFN) to improve the detection performance of HyperCD. First, a submodule named multiattention feature enhancement (MAFE) module was designed and embedded on each scale in the backbone of the proposed MDFN to capture subtle changes. Second, with the motivation of exploring the feature connection of a target on different scales, the attention feature maps from each scale were fused via a proposed novel cross-scale residual fusion module (CS-RFM). Finally, a softmax function was adopted to generate a binary change detection map based on the fused features. Experimental results based on comparison with five existing related works indicated that the proposed MDFN not only has some advantages in improving change detection performance with real hyperspectral remote sensing images (HRSIs) but also exhibits superiority in the requirement of training samples that are preferred in practical applications. For instance, using only 5% of the training samples, the average accuracy (AA) on the Farmland dataset is improved by 0.63%. The code will be available athttps://github.com/ImgSciGroup/2024-MDFN.

Whether the railway track can run smoothly for a long time directly affects the safety of the railway. In view of the nonlinear, random, and sudden characteristics of the time series data of railway track, we propose a WT-GA-GRU model to forecast the track irregularity of high-speed railway. Firstly, the original time series is decomposed by wavelet transform (WT), and the decomposed multiple time series are forecasted by the gated recurrent unit (GRU) networks optimized by genetic algorithm (GA). Then the forecasted results are obtained by wavelet reconstruction. Experimental results show that, compared with support vector machine (SVM) and long short-term memory (LSTM) model, the combined WT-GA-GRU model proposed in this paper has higher forecasting accuracy.

Summary Predicting the daily tourism flow of scenic spots is of great significance for improving the management quality and the tourist experience. Affected by complex factors, daily tourism flow data have strong nonlinear characteristics. In this article, a multilayer neural network S‐CNNLSTM is put forward to make accurate short‐term tourism flow prediction. First, to reduce the redundant information between the influencing factors, sparse principal component analysis is adopted to reduce the data dimension. Then the processed data is input into a deep neural network framework that combines the convolutional neural network (CNN) and long short‐term memory (LSTM) network. CNN extracts local trends, and LSTM is introduced to learn the inner law of time series and make prediction. Finally, through the experiments with real data and the comparison algorithms, the stability and practicability of the proposed method are verified.