Based on deep learning technology, this paper proposes a two-stage colorectal image feature mining and fast recognition model to achieve fully automatic medical image pathology discrimination. Drawing on the ideas of multi-factor Meta-regression analysis widely used in the medical field and the model aggregation framework based on Bayesian prior probability theory, a prognostic model of colorectal tumors suitable for various situations and scenarios is constructed. And using a combination of public data sets and real data sets, design two sets of experiments to verify these models from different angles. The algorithm was used to select one, four, and five related features from three sequences to construct three sets of prediction models. The application of the six algorithms failed to obtain a better predictive model (AUC value range 0.439 ~ 0.640). The algorithm (AUC value 0.750±0.137) and the algorithm (AUC value 0.764±0.128) can be used to obtain models with better predictive performance, and the four models are less effective (AUC value<0.7). In the joint model, the algorithm (AUC value 0.742± 0.101) and the algorithm (AUC value 0.718±0.069) can also be used to obtain a model with better prediction performance. Imagebased imaging histology tags can be used as a non-invasive auxiliary tool for preoperative evaluation of histological grading of CRAC, and are expected to be applied in clinical practice to assist in the development of individualized treatment plans. INDEX TERMS deep learning; colorectal imaging; feature mining; rapid identification.
This paper introduces an automatic feeding ship that applied in breeding crabs. For realizing autonomous navigation and making feed uniform on the surface of the aquaculture ponds, the GPS and automatic feeding machine are used on the ship. Bait scatters movement was analyzed by the method of physics and geometry which based on the structure and parameters of automatic feeding machine. For getting the mathematical model of bait distribution, the least square method is adopted to fit the experimental data. On this basis, the minimum variance of the bait thickness was selected as the objective function. An optimal trajectory was generated by using golden section method.
A device for measuring the depth of the borehole base on the magnetic grid during orthopedic surgery is proposed in this article. It consists of a magnetic grid, winding sleeve, two Hall sensors, and control circuitry. The magnetic grid comprises permanent magnets and coil windings. The device fixes on the electric hand drill and works during the surgical operation. An axial pressure keeps the shaft end of the magnetic grid in contact with the surface of the bone or the plate steadily during the electric handheld drilling of the bone. The pressure is an electromagnetic force generated by the interaction between the permanent magnets and the coil windings. The force should be large enough to support the weight of the magnetic grid and a low fluctuation is maintained. The larger the device, the higher the electromagnetic force will be generated. The electromagnetic force is simulated and obtained with the software of Maxwell. The factors that influence the force were the permanent magnet, and the others are the length of permanent magnet and the turns on the coil. The results of orthogonal simulation show that the primary factor is the diameter of the permanent magnet. The optimized parameters include the following: the diameter of the magnet is 7 mm, length of each permanent magnet is 5 mm, and the turns on the coil are 80. Then the pressure force range is approximately 0.485–0.716 N, and the variance of the force is 0.137.
Using the neural network to deal with complex data, because the pending sample with many variables, aiming at this nature of the pending sample and the structure properties of the BP neural network, in this paper, we propose the new BP neural network algorithm base on principal component analysis (PCA-BP algorithm). The new algorithm through PCA dimension reduction for complex data, got the low-dimensional data as the BP neural networks input, it will be beneficial to design the hidden layer of neural network, save a lot of storage space and computing time, and conductive to the convergence of the neural network. In order to verify the validity of the new algorithm, compared with the traditional BP algorithm, through the case analysis, the result show that the new algorithm improve the efficiency and recognition precise, worthy of further promotion.
In order to solve the traditional network monitor management system fault detection of slow problem,adaptive differential of high false alarm rate we built network monitor system model combined with the artificial immune principle.Through artificial immune "self" and "non-self" recognition ability network monitoring algorithm simulated the matching,negative selection,memory mechanism of artificial immune system detection of network fault.Throughout the design process,we studied the biological immune characteristics,antibody affinity and concentration of concepts the antibody selection probability algorithm was proposed.The algorithm enhanced new antibody generation mechanisms,memory mechanism the and tolerance of the system to establish the network monitoring system provides the theoretical model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.