Accurate diagnosis of Mild Cognitive Impairment (MCI) is critical to the prevention and treatment of Alzheimer's Disease (AD). Currently, deep learning and resting-state functional Magnetic Resonance Imaging (rs-fMRI) are often used to assist the diagnosis of MCI. The commonly used Pearson correlation method and Window Pearson (WP) correlation method can represent the brain Functional Connectivity (FC) in the time dimension, but cannot decompose and represent the information in different frequency dimensions. In order to solve this problem, a new method of using FC coefficients in different frequency dimensions as the input features of the existing deep learning was proposed to improve the accuracy of MCI classification. Firstly, the data of the subjects were spliced and then subjected to Multivariate Empirical Model Decomposition (MEMD). Secondly, the FC coefficients in different frequency dimensions were obtained after segmenting. Finally, VGG16 and Long Short-Term Memory (LSTM) network were used for testing. Experimental results show that, when the proposed FC coefficients ars used, the classification accuracy of MCI can reach up to 84.33%, which is 18.33-21.00 percentage points higher than the accuracy with the use of the traditional FC coefficients. In addition, the FC coefficients of different frequency dimensions have different resolutions for MCI.

Concerning the problem that the existence of moving objects in the application scenes will reduce the positioning accuracy and robustness of the visual Synchronous Localization And Mapping (SLAM) system, a semantic information based visual SLAM algorithm in dynamic environment was proposed. Firstly, the traditional visual SLAM front end was combined with the YOLOv4 object detection algorithm, during the extraction of ORB (Oriented FAST and Rotated BRIEF) features of the input image, the image was semantically segmented. Then, the object type was judged to obtain the area of the dynamic object in the image, and the feature points distributed on the dynamic object were eliminated. Finally, the camera pose was solved by using inter-frame matching between the processed feature points and the adjacent frames. The test results on TUM dataset show that, the accuracy of the pose estimation of this algorithm is 96.78% higher than that of ORB-SLAM2 (Orient FAST and Rotated BRIEF SLAM2) in a high dynamic environment, and the average consumption time per frame of tracking thread of the algorithm is 0.065 5 s, which is the shortest time consumption compared to those of the other SLAM algorithms used in dynamic environment. The above experimental results illustrate that the proposed algorithm can realize real-time precise positioning and mapping in dynamic environment.

Aiming at the problems of low accuracy of driving command prediction, bulky model structure and a large amount of information redundancy in existing end-to-end autonomous driving methods, a new end-to-end autonomous driving model based on deep visual attention neural network was proposed. In order to effectively extract features of autonomous driving scenes, a deep visual attention neural network, which is composed of the convolutional neural network, the visual attention layer and the long short-term memory network, was proposed by introducing a visual attention mechanism into the end-to-end autonomous driving model. The proposed model was able to effectively extract spatial and temporal features of driving scene images, focus on important information and reduce information redundancy for realizing the end-to-end autonomous driving that predicts driving commands from sequential images input by front-facing camera. The data from a simulated driving environment were used for training and testing. The root mean square errors of the proposed model for prediction of the steering angle in four scenes including country road, highway, tunnel and mountain road are 0.009 14, 0.009 48, 0.002 89 and 0.010 78 respectively, which are all lower than the results of the method proposed by NVIDIA and the method based on the deep cascaded neural network. Moreover, the proposed model has fewer network layers compared with the networks without the visual attention mechanism.

To handle the issues of lacking paired training samples and inconsistency between frames in translation from virtual to real driving scenes, a video translation model based on Generative Adversarial Networks was proposed in this paper. In order to solve the problem of lacking data samples, the model adopted a “dual networks” architecture, where the semantic segmentation scene was used as an intermediate transition to build front-part and back-part networks, respectively. In the front-part network, a convolution network and a deconvolution network were adopted, and the optical flow network was also used to extract the dynamic information between frames to implement continuous video translation from virtual to semantic segmentation scenes. In the back-part network, a conditional generative adversarial network was used in which a generator, an image discriminator and a video discriminator were designed and combined with the optical flow network to implement continuous video translation from semantic segmentation to real scenes. Data collected from an autonomous driving simulator and a public data set were used for training and testing. Virtual to real scene translation can be achieved in a variety of driving scenarios, and the translation effect is significantly better than the comparative algorithms. Experimental results show that the proposed model can handle the problems of the discontinuity between frames and the ambiguity for moving obstacles to obtain more continuous videos when applying in various driving scenarios.

As the most widely used autonomous intra-domain routing protocol for large-scale network, the security of Open Shortest Path First (OSPF) is not only about the normal running of autonomous intra-domain, but also closely related to inter-domain even the whole network. Based on asymmetric encryption algorithm, the traditional digital signature solution can realize the security validation of end-to-end; however, it ignores the issue of point-to-point. Additionally, the problem of storage and extra overhead also needs to be solved urgently. On the basis of symmetrical encryption algorithm, a new solution named HS-OSPF was put forward. HS-OSPF extended the original two-level hierarchical structure as well as designed a reasonable, efficient key distribution and management scheme. The result shows that the shortcomings of traditional solution are overcome, key storage and system overhead are reduced and real-time of security communication is improved.

To standardize and accelerate the encapsulation process of manufacturing resources, a novel encapsulation method of manufacturing resources was proposed based on service templates. The concept, structure and types of service templates were given according to the characteristics of manufacturing resources. Then the service template extraction procedure which utilized the existing programs of manufacturing services was proposed, and a service template extraction language was defined. The encapsulation procedure of manufacturing resources based on service templates was proposed, and the manufacturing resources were encapsulated to service-oriented architecture-based manufacturing services. At last the application case shows that the proposed method can standardize the development procedure of manufacturing services and accelerate the encapsulation process of manufacturing resources by fully utilizing existing programs of manufacturing services, so ordinary product developers can encapsulate manufacturing resources without special knowledge of software programming. This method can provide fundamental support for the sharing of manufacturing resources in the network environment.

Effective and timely Link Going Down (LGD) trigger mechanisms are critical to handover performance. Firstly, this paper introduced IEEE 802.21 MIH standard, and the required handover time was estimated using the information service provided by Media Independent Handover (MIH). Then, a LGD trigger mechanism based on grey prediction was proposed. It established grey prediction model by the required handover time, and the trigger time can be dynamically determined by the predictive Received Signal Strength (RSS) of mobile terminal. Furthermore, in order to reduce the prediction costs, a grey prediction modeling method based on signal decay detection was proposed. The simulation results show that this algorithm achieves the goal of effective and timely LGD trigger, and can reduce unnecessary prediction costs and avoid the waste of terminal resources.

The Finding and Extracting Community (FEC) algorithm has some disadvantages as the algorithm stability is not enough, and the quality of extracting community needs to be improved. To solve these problems, some improvements were made from the following aspects: Add the function of selecting target vertex before random walk; cancel the parameter of random walk steps of the original algorithm by using a method of detecting steps automatically; supplement the quality evaluation of the link between the communities on the base of the original community extraction; achieve the controllability of particle size of community by introducing the threshold parameter. The results show that the improved algorithm has some improvements at the aspects of stability, anti-jam performance and clustering analysis.