Information entropy-based fitting of the disease trajectory of brain ischemia-induced vascular cognitive impairment

The present study investigated the disease trajectory of vascular cognitive impairment using the entropy of information in a neural network mathematical simulation based on the free radical and excitatory amino acids theories. Glutamate, malondialdehyde, and inducible nitric oxide synthase content was significantly elevated, but acetylcholine, catalase, superoxide dismutase, glutathione peroxidase and constitutive nitric oxide synthase content was significantly decreased in our vascular cognitive impairment model. The fitting curves for each factor were obtained using Matlab software. Nineteen, 30 and 49 days post ischemia were the main output time frames of the influence of these seven factors. Our results demonstrated that vascular cognitive impairment involves multiple factors. These factors include excitatory amino acid toxicity and nitric oxide toxicity. These toxicities disrupt the dynamic equilibrium of the production and removal of oxygen free radicals after cerebral ischemia, reducing the ability to clear oxygen free radicals and worsening brain injury.

Calibration of Camera with Large Field-of-View Based on Flexible Planar Target

For high precision calibration of camera with large field-of-view,massive calibration points will be needed if traditional methods are selected,which makes the calibration complex and time-consuming.In order to solve this problem,a calibration method based on flexible planar target is proposed.In this method,distortion factor is firstly acquired by the invariance of cross ratio,and existing feature points are adjusted with the distortion factor.Then,a large number of points that will be used for the calibration are constructed with the adjusted feature points.Simultaneously,Tsai method is modified so as to reduce the complexity of calibration,which makes the process linear.The simulation and real experiments show that the method proposed in this paper is simple,linear,accurate and robust,and the precision of this method is close to that of Tsai method using abundant points.The method can satisfy the requirement of high precision calibration for camera with large field-of-view.

Target localization method of non-cooperative spacecraft on on-orbit service

With the explosion of the number of meteoroid/orbital debris in terrestrial space in recent years, the detection environment of spacecraft becomes more complex. This phenomenon causes most current detection methods based on machine learning intractable to break through the two difficulties of solving scale transformation problem of the targets in image and accelerating detection rate of high-resolution images. To overcome the two challenges, we propose a novel noncooperative target detection method using the framework of deep convolutional neural network.Firstly, a specific spacecraft simulation dataset using over one thousand images to train and test our detection model is built. The deep separable convolution structure is applied and combined with the residual network module to improve the network’s backbone. To count the different shapes of the spacecrafts in the dataset, a particular prior-box generation method based on K-means cluster algorithm is designed for each detection head with different scales. Finally, a comprehensive loss function is presented considering category confidence, box parameters, as well as box confidence. The experimental results verify that the proposed method has strong robustness against varying degrees of luminance change, and can suppress the interference caused by Gaussian noise and background complexity. The mean accuracy precision of our proposed method reaches 93.28%, and the global loss value is 13.252. The comparative experiment results show that under the same epoch and batchsize, the speed of our method is compressed by about 20% in comparison of YOLOv3, the detection accuracy is increased by about 12%, and the size of the model is reduced by nearly 50%.