Traditional image steganography often leans interests towards safely embedding hidden information into cover images with payload capacity almost neglected. This paper combines recent deep convolutional neural network methods with image-into-image steganography. It successfully hides the same size images with a decoding rate of 98.2% or bpp (bits per pixel) of 23.57 by changing only 0.76% of the cover image on average. Our method directly learns end-to-end mappings between the cover image and the embedded image and between the hidden image and the decoded image. We further show that our embedded image, while with mega payload capacity, is still robust to statistical analysis.

In this paper, a novel reduced order model based on a convolutional auto-encoder with self-attention (SACAE ROM) is proposed. The proposed model is a non-intrusive reduced order model, which uses a convolutional neural network and a long short-term memory network to extract temporal feature relationships from high-fidelity numerical solutions. The self-attention is introduced into the convolutional neural network to enhance the non-local information perception ability of the convolutional neural network and improve the feature extraction ability of the network. The model adopts a joint construction method, which overcomes the problem of propagating error in each process of the model. The model proposed in this paper has been verified on the problem of the flow around a cylinder. The experimental results indicate that the SACAE ROM has higher robustness and accuracy. Compared with the ROM based on a convolutional auto-encoder, the prediction error of the SACAE ROM is reduced by 42.9%. As with other ROMs based on deep neural networks, the SACAE ROM takes a long time to train. To solve this problem, the transfer and generalization ability of the model is studied in this paper. In the experiment, the flow velocity and spoiler of the flow around the cylinder were changed, and the training time of the transfer model was reduced by about 50% to 60%. This result demonstrates that the problem of too long training time can be solved by transfer learning.

The prediction of roll motion in unmanned surface vehicles (USVs) is vital for marine safety and the efficiency of USV operations. However, the USV roll motion at sea is a complex time-varying nonlinear and non-stationary dynamic system, which varies with time-varying environmental disturbances as well as various sailing conditions. The conventional methods have the disadvantages of low accuracy, poor robustness, and insufficient practical application ability. The rise of deep learning provides new opportunities for USV motion modeling and prediction. In this paper, a data-driven neural network model is constructed by combining a convolution neural network (CNN) with long short-term memory (LSTM) for USV roll motion prediction. The CNN is used to extract spatially relevant and local time series features of the USV sensor data. The LSTM layer is exploited to reflect the long-term movement process of the USV and predict roll motion for the next moment. The fully connected layer is utilized to decode the LSTM output and calculate the final prediction results. The effectiveness of the proposed model was proved using USV roll motion prediction experiments based on two case studies from “JingHai-VI” and “JingHai-III” USVS of Shanghai University. Experimental results on a real data set indicated that our proposed model obviously outperformed the state-of-the-art methods.

In this paper, a novel method to construct non-intrusive reduced order model (ROM) is proposed. The method is based on proper orthogonal decomposition and transformer neural network. Proper orthogonal decomposition is used to generate the basis functions of the low-dimensional flow field, and the coefficients are taken as low-dimensional flow field features. Transformer network is used to extract temporal feature relationships from low-dimensional features. Compared with recurrent neural network and convolutional neural network, transformer network can better capture flow dynamics. At online stage, the input temporal flow sequences are calculated in parallel and can effectively reduce online calculation time. The model proposed in this paper has been verified in two scenarios: two-dimensional flow past a cylinder and two-dimensional flow past a building group. Experimental results show that our model can better capture the flowing change details and has higher accuracy. Compared with the ROM based on long short-term memory and temporal convolutional network, the prediction error is reduced by 35% and 60%, and the time cost is reduced by 65% and 60%. Finally, we apply the ROMs to a practical three-dimensional complicated scenario, flow past London South Bank University, and discuss future development of ROMs.