4results about How to "Reduce expertise" patented technology

The invention provides a neonatal acute respiratory distress syndrome antenatal prediction model, which is characterized in that 15 key variables for predicting neonatal acute respiratory distress syndrome are screened out by using an LASSO regression algorithm according to perinatal high-risk factors; and taking the key variables as input, taking the neonatal acute respiratory distress syndrome as output, and training by using a BP neural network to obtain the neonatal acute respiratory distress syndrome antenatal prediction model. According to the method, personalized early prediction of the NARDS can be realized, and the possibility of occurrence of the neonatal acute respiratory distress syndrome can be predicted before a fetus is born; in the prediction process, the examination result can be obtained only by inputting various existing examination data into the prediction model, the method is simple and easy to operate, visual, reliable and rapid, evaluation can be conducted at any time, and the requirements for professional knowledge of medical staff and hospital instruments and equipment are low.

The utility model discloses an electronic sphygmomanometer with cuff wearing state detection function belongs to electronic medical instrument technical field, and the sphygmomanometer aims at solving the problem of inaccurate measurement result caused by improper wearing position or unsuitable tightness of user's cuff in prior art. The utility model discloses a sphygmomanometer main part, cuff, the position sensor for detecting wearing position set on the cuff, the tightness sensor for detecting wearing tightness, the microcontroller for analyzing signal and judging wearing state with sensor connection, and the prompt unit for sending prompt information when wearing improperly with microcontroller connection. The utility model discloses through real -time detection the position and tightness of wearing cuff, and timely provides adjustment guidance to the user, can effectively improve the accuracy and reliability of blood pressure measurement, and promotes user experience.

The invention belongs to the technical field of foundation treatment, and discloses a dynamic compaction effective reinforcement depth calculation method and method.The method comprises the steps that the dry density of soil layers every preset depth before dynamic compaction construction of a construction site is obtained; obtaining an actual measurement result of the effective reinforcement depth of dynamic compaction after trial compaction and dry density of soil layers at intervals of preset depth after trial compaction; determining the average dry density of the soil layers before dynamic compaction construction and the average dry density of the soil layers after the dynamic compaction according to the dry density of the soil layers every preset depth before the dynamic compaction construction of the construction site and the dry density of the soil layers every preset depth after the dynamic compaction test on the basis of the actual measurement result of the effective reinforcement depth of the dynamic compaction after the dynamic compaction test; the compaction settlement after formal dynamic compaction construction is obtained; according to the average dry density of the soil layer before dynamic compaction construction, the average dry density of the soil layer after compaction and the compaction settlement after formal dynamic compaction construction, the calculation result of the dynamic compaction effective reinforcement depth of the construction site is obtained through calculation; the calculation process is simple, and the randomness and deviation of the calculation result of the dynamic compaction effective reinforcement depth are reduced.

This invention proposes a reconfigurable metasurface beamforming design method based on CGAN and Gumbel-Sinkhorn. This method constructs a conditional generative adversarial network (GAN) as the inverse design network. The generator takes the target beam pattern as a conditional input to generate the corresponding encoding matrix. The Gumbel-Sinkhorn operator is introduced to discretize this continuous matrix, transforming it into an approximately doubly random permutation matrix. The encoding is sorted and selected by multiplying this permutation matrix with a predefined structure vector (SV), outputting a discrete 0 / 1 metasurface encoding array. A noisy forward prediction network is trained to predict the beam pattern corresponding to a given encoding array. In the training of the inverse design network, the discretized encoding matrix output by the generator is input into the noisy-trained forward prediction network. The mean square error between the predicted beam pattern and the target beam pattern is calculated as the target loss term to optimize the network parameters and accurately learn the complex mapping relationship from the beam pattern to the encoding array.