Alzheimer's disease is a common Neurodegeneration that can be clinically diagnosed on the basis of neuroimaging. Based on the deep convolution network, this paper analyzes the MRI images to identify and classify Alzheimer's disease. By establishing a depth network model, the accuracy of the training set and the test set, as well as the comparison images of the test values and the real values, therefore, it is of great significance to improve the clinical diagnostic efficiency and early prediction accuracy of Alzheimer's disease.
The acquisition of ballistocardiogram (BCG) signals during sleeping always presents all kinds of high-frequency noise, which causes the problem to extract effective signals. This article proposes a new method to extract heartbeat and respiration signals by combining the whale optimization algorithm (WOA) and variational mode decomposition (VMD). Firstly, the sample entropy and energy difference ratio are used as the fitness function of WOA to optimize the penalty factor in the variational mode decomposition a and the number of decomposition layers K;Then the original signal was decomposed into multiple modal components (IMF) by optimized VMD; Finally, respiration and heartbeat signals were reconstructed, and their frequencies got calculated. Compared with the experimental results of empirical mode decomposition (EMD) and ensemble empirical mode decomposition (EEMD), the average respiratory rate error obtained by this algorithm is 0.097 and 0.013 lower than EMD and EEMD respectively, and the average heart rate error is 0.03 and 0.006 lower than EMD and EEMD respectively, it is proved that the algorithm can extract breath and heartbeat signals more effectively and accurately.
In the field of substation operation and maintenance, recognizing the behaviors of substation operation and maintenance personnel is crucial for maintaining the safe operation of the power grid and ensuring the safety of workers. To enhance the accuracy of human behavior recognition in substation operation and maintenance, this paper proposes an ECA-MSG3D algorithm model for human behavior recognition of work apparatus based on the Multi-Scale Pointwise Convolutional Neural Network for 3D Object Detection (MSG3D) model. The MSG3D module, which utilizes a multi-scale aggregation scheme for unified spatiotemporal graph convolution, is used for feature learning across time and space. Then, channel features are learned through the efficient channel attention (ECA) module, and the final action is obtained through global average pooling with the softmax classifier. Results show that the ECA-MSG3D model with the ECA attention module outperforms the MSG3D model with other attention modules, achieving 89.06% and 89.26% accuracy and precision on the NTU RGB+D 60 Skeleton dataset. This model provides a highly accurate human behavior recognition method for substation operation and maintenance.
For the planning and control system of differential mobile robots, the traditional time elastic band (TEB) algorithm has a long obstacle detection time and cannot complete dynamic planning in complex environments. At the same time, the control quantity calculated by TEB based on the trajectory point sequence difference has a jump, which results in poor control effect and unstable steering. By simplifying complex obstacles with RANSAC (Random Sample Consensus) algorithm, the collision detection time can be reduced and the algorithm computation can be reduced. At the same time, based on the optimal preview strategy, a nonlinear proportional function of tracking error is defined to recalculate the robot control quantity, so as to reduce the jump and make the operation control more stable. Finally, a robot navigation system based on ROS is built for experiments. The experimental results verify the effectiveness of the method and improve the real-time performance and reliability of differential robot planning and control.
Nowadays, SUV is developing rapidly. This paper matches the drive motor, power battery and transmission system of a pure electric SUV according to the power and economic requirements of a traditional SUV. The vehicle is modeled by AVL Cruise software, and the power and economy of the vehicle are simulated to meet the requirements of power and economy. In order to further improve economy, a joint simulation model of Cruise and Isight is built and Multi Island Genetic Algorithm(MIGA) is chosen. The final ratio and the rolling radius of the tire are optimization parameters. The vehicle economy is calculated as the optimization target. The optimization results show that power consumption per 100 kilometers is reduced by 0.38kWh and the economy is increased by 2.60% under the optimized New European Driving Cycle(NEDC) cycle condition.
