The three-dimensional RGB-D image contains not only the color and texture information of the two-dimensional image, but also contains the surface geometry information of the target. This article analyzes the RGB-D image recognition methods, including stereo vision technology, structured light technology, etc. By studying the application points of RGB-D image recognition technology under the background of feature fusion and machine learning, the purpose is to improve the richness of image recognition content and provide reference for the smooth development of the follow-up work.

Recently, single image super-resolution (SISR) based on deep convolutional neural networks (CNNs) has been widely studied and achieved remarkable results. However, most of these methods mainly widen or deepen the network to get better results, ignoring the self-similarity in natural images. Some works have successfully leveraged this self-similarity by exploring non-local attention modules, but they only use non-local attention modules at one scale or two scales. And they need to calculate the self-similarity in each residual module, which makes the network more complex and takes a long time to train. We propose a multiple-scale self-similarity module (MSSS) that can be flexibly inserted into existing various super-resolution networks. MSSS uses convolution with different kernels and the trailing dilated convolution to obtain feature maps at different scales, and then calculates the correlation between multiple feature maps at different scales through two-head region-level recurrent criss-cross attention modules (TRRCCA), finally gets fusion output through channel attention. So MSSS can mine multiple-scale self-similarities. We only insert a MSSS module into the basic residual SISR network, and the result is significantly improved.

The high grades in postgraduates entrance examination are the stepping stone to improve the professional competition in China, which makes the critical influence factors to the initial examination of postgraduates as a hot topic. In order to measure the correlation between the academic performance of undergraduate students and the probability of successful postgraduate entrance examination, and find some effective ways to improve the success rate in the postgraduate entrance examination, we design regression discontinuity model to search the causal correlation between the preliminary entrance exam and CET-6 scores of candidates. Global parameter estimation and local non-parameter estimation were estimated respectively to improve the accuracy of model fitting. In addition, the validity and robustness of the experiment were tested by sensitivity analysis. The results show that the students who get better grades in college are more likely to have a positive effect in the preliminary entrance examination, and make the success rate of postgraduate entrance examination higher.

This work takes this Asian Hornet’s invasion of Washington in 2020 as an example to build an auxiliary identification system for Destructive Pests to help the government’s rescue work. To help the government to prioritize the resource to the most possible reports and improve the investigation efficiency, we built a binary classification model to classify the report that contains images and text. For image classification, we design a VGG16-based convolutional neural network pretraining with ImageNet, which achieved superior performance with a high F1 score (95.08%) on our dataset. For text classification, we use the Latent Dirichlet Allocation (LDA) model to cluster words into different themes and adopt cosine similarity to calculate the similarity between the new report and the benchmark positive/negative sets. The results demonstrated that our approach can identify target pests efficiently and help the government to prioritize the resource to the most possible reports, improving the investigation efficiency.

Improving the methodological apparatus for monitoring and analyzing the potential of technological processes of industrial enterprises, based on the identification of the level of maturity of processes, is the primary task of achieving a competitive state. The article describes ways to verify the processes of the main activities of the organization, using fuzzy logic models and criteria for achieving the required level of automation.

A program that implements a simple Markov homogeneous random search algorithm of an extremum with normal distributions is presented. This program allows solving a fairly wide class of problems of finding the global extremum of an objective function with a high accuracy.