34results about How to "Meet actual application needs" patented technology

The invention discloses a multi-channel physiological signal somatosensory gesture recognition method based on PSO-PCA-SVM, Step1: collect the original sample of human physiological signal; Step2: extract the feature of the physiological signal; Step3: extract key features by principal component analysis; Step4: establish Multi-channel physiological signal somatosensory gesture SVM recognition model; Step5: PSO optimization training multi-channel physiological signal somatosensory gesture PCA and SVM recognition model. The invention provides a multi-channel physiological signal somatosensory gesture recognition method based on PSO-PCA-SVM. After using the method, the recognition accuracy is high, the real-time performance is good, and the recognition robustness is good.

A method for automatically classifying complexion in traditional Chinese medicine by applying a shallow neural network belongs to the field of computer vision. The designed shallow network has 5 layers in total, using three different layer structures, which are input layer, feature extraction layer, and output layer. The input layer consists of a convolutional layer and a rectified linear unit; the feature extraction layer consists of a 3-layer network, each of the first two layers consists of a convolutional layer and a ReLU activation function, between the convolutional layer and the ReLU A batch normalization, and add a pooling layer after the second ReLU of the feature extraction layer, the third layer of the feature extraction layer is a fully connected layer, followed by a corrected linear unit ReLU; the output layer consists of a fully connected layer , followed by a softmax classifier. The invention has obvious advantages in classification accuracy, is invariant to distortions such as zooming, translation, and rotation, has strong robustness, can effectively improve classification accuracy, and applies the theory of deep learning to the objectivity research of face-to-face diagnosis in traditional Chinese medicine. .

The invention relates to a method for manufacturing a two-phase heterogeneous strengthened non-welded box body, comprising: box body stamping forming, stress relief annealing treatment, installation of a reciprocating hydraulic deformation device, and reciprocating hydraulic deformation. It is characterized in that: Stamping forming technology, punching stainless steel sheet to obtain the main part of the box part; annealing stress relief treatment to eliminate the residual deformation structure in the part after stamping, and the deformation stress can be restored; reciprocating hydraulic deformation, the strain induces the box in the loaded area The martensite transformation of the austenite structure in some parts, the martensite structure increases the strength of the box, and retains the austenite structure in other parts, so that the box has good toughness at the same time.

The invention relates to a method for generating an automatic driving trajectory in a high-speed scene, comprising the steps of: constructing a two-dimensional coordinate system; obtaining original road data and original vehicle state data; obtaining optimal path data; obtaining several sampling points; generating candidate trajectories; calculating all sampling points Cost value between points; filter out the best path data and output; get the target trajectory and output it to the control system for execution. The invention adopts the third-order Bezier curve, so that the unmanned vehicle can reach the target point along a smooth trajectory when changing lanes, and the curvature of the curve is continuous; for the high-speed automatic driving scene, the Dijkstra algorithm is improved accordingly. On the basis of the path, the amount of calculation is greatly reduced, which meets the real-time requirements under high-speed conditions, and the results are continuous; the vehicle motion is constrained by the Cost function model, and the optimal solution is obtained; after considering the constraints in the actual motion of the vehicle Build road and motion models to better suit practical application needs.