Remote sensing image scene classification is an important method for understanding the high-resolution remote sensing images. Based on Convolutional Neural Network, various classification methods have been applied into this field and achieved remarkable results. These methods mainly rely on the semantic information to improve the classification performance. However, as the network goes deeper, the highly abstract and global semantic information makes it difficult for the network to accurately classify scene images with similar layout and structures, limiting the further improvement of classification accuracy. Relying on the semantic information only is not sufficient to effectively classify these similar scene images and the network needs spatial information to enhance the classification capability. To solve this dilemma, this paper proposes a best representation branch model, which reaches the optimal balance point where the network can make use of both the semantic information and spatial information to improve the final classification accuracy. In the proposed method, ResNet50 pretrained on the ImageNet dataset is first divided into four branches with different depths to extract feature maps and Capsule Network is used as the classifier. The Grad-CAM algorithm is adopted to explain the mechanism of the optimal balance point from the perspective of attention and guide the further feature fusion. In addition, ablation studies are conducted to prove the effectiveness of our method and extensive experiments are conducted on three public benchmark remote sensing datasets. The results demonstrate that the proposed method can achieve competitive classification performance compared to the state-of-the-art methods.

Background: Mild cognitive impairment (MCI) is a condition between normal aging and dementia; nearly 10–15% of MCI patients develop dementia annually. There are no effective interventions for MCI progression. Repetitive transcranial magnetic stimulation (rTMS) is a non-invasive brain stimulation technique that has attempted to improve the overall cognitive function of MCI patients. However, it does not affect episodic memory improvement.Methods: In this study, we engaged 15 clinically diagnosed MCI patients and normal controls to explore the effect of dual-targeted rTMS on progressing cognitive function, particularly episodic memory in MCI patients. Resting-state EEG recordings and neuropsychological assessments were conducted before and after the intervention. EEG features were extracted using an adaptive algorithm to calculate functional connectivity alterations in relevant brain regions and the mechanisms of altered brain functional networks in response to dual-target rTMS.Results: The study revealed that the functional brain connectivity between the right posterior cingulate gyrus (PCC) and the right dorsal caudate nucleus (DC) was significantly reduced in MCI patients compared to normal controls (p < 0.001). Dual-target rTMS increased the strength of the reduced functional connectivity (p < 0.001), which was related to cognitive enhancement (p < 0.05).Conclusion: This study provides a new stimulation protocol for rTMS intervention. Improving the functional connectivity of the right PCC to the right DC is a possible mechanism by which rTMS improves overall cognitive and memory function in MCI patients.

At present, the classification accuracy of high-resolution Remote Sensing Image Scene Classification (RSISC) has reached a quite high level on standard datasets. However, when coming to practical application, the intrinsic noise of satellite sensors and the disturbance of atmospheric environment often degrade real Remote Sensing (RS) images. It introduces defects to them, which affects the performance and reduces the robustness of RSISC methods. Moreover, due to the restriction of memory and power consumption, the methods also need a small number of parameters and fast computing speed to be implemented on small portable systems such as unmanned aerial vehicles. In this paper, a Lightweight Progressive Inpainting Network (LPIN) and a novel combined approach of LPIN and the existing RSISC methods are proposed to improve the robustness of RSISC tasks and satisfy the requirement of methods on portable systems. The defects in real RS images are inpainted by LPIN to provide a purified input for classification. With the combined approach, the classification accuracy on RS images with defects can be improved to the original level of those without defects. The LPIN is designed on the consideration of lightweight model. Measures are adopted to ensure a high gradient transmission efficiency while reducing the number of network parameters. Multiple loss functions are used to get reasonable and realistic inpainting results. Extensive tests of image inpainting of LPIN and classification tests with the combined approach on NWPU-RESISC45, UC Merced Land-Use and AID datasets are carried out which indicate that the LPIN achieves a state-of-the-art inpainting quality with less parameters and a faster inpainting speed. Furthermore, the combined approach keeps the comparable classification accuracy level on RS images with defects as that without defects, which will improve the robustness of high-resolution RSISC tasks.