Objective. This paper proposes a conditional GAN (cGAN)-based method to perform data enhancement of ultrasound images and segmentation of tumors in breast ultrasound images, which improves the reality of the enhenced breast ultrasound image and obtains a more accurate segmentation result. Approach. We use the idea of generative adversarial training to accomplish the following two tasks: (1) In this paper, we use generative adversarial networks to generate a batch of samples with labels from the perspective of label-generated images to expand the dataset from a data enhancement perspective. (2) In this paper, we use adversarial training instead of postprocessing steps such as conditional random fields to enhance higher-level spatial consistency. In addition, this work proposes a new network, EfficientUNet, based on U-Net, which combines ResNet18, an attention mechanism and a deep supervision technique. This segmentation model uses the residual network as an encoder to retain the lost information in the original encoder and can avoid the gradient disappearance problem to improve the feature extraction ability of the model, and it also uses deep supervision techniques to speed up the convergence of the model. The channel-by-channel weighting module of SENet is then used to enable the model to capture the tumor boundary more accurately. Main results. The paper concludes with experiments to verify the validity of these efforts by comparing them with mainstream methods on Dataset B. The Dice score and IoU score reaches 0.8856 and 0.8111, respectively. Significance. This study successfully combines cGAN and optimized EfficientUNet for the segmentation of breast tumor ultrasound images. The conditional generative adversarial network has a good performance in data enhancement, and the optimized EfficientUNet makes the segmentation more accurate.

In this study, we propose a model to accurately predict the ground subsidence caused by subway excavation using the wavelet denoising model and BP neural network. First, we develop an optimal denoising model by comparing and analyzing the denoising effect of different wavelet denoising parameters. The model is used to reduce the noise of the monitoring data. Then, we utilize BP neural network to develop a prediction model in which the proposed denoising model is used. Finally, we apply the proposed model to Urumqi subway. The results demonstrate the rationality and accuracy of the proposed model.

No abstract

As a typical cyborg intelligent system, ratbots possess not only their own biological brain but machine visual sensation, memory and computation. Electrodes implanted in the medial forebrain bundle (MFB) connect the rats biological brain with the computer, which presents a hybrid bio-machine parallel memory system in the ratbot. For the novel multiple parallel memory system (MPMS) with real-time MFB stimuli, a computational model is proposed to explain the learning and memory processes underlying the enhanced performance of the ratbots in maze navigation tasks. It is shown that the proposed computational model can predict the finish trial number of the maze learning task which matches well with the behavioral experiments. This work will be helpful to understand the memory and learning mechanisms of cyborg intelligent systems and has the potential significance of optimizing the cognitive performance of these systems as well.

No abstract