Application of Advanced BP Neural Network in Image Recognition

The Back Propagation (BP) neural network genetic algorithm was used to identify alphabet, and the new algorithm combine the advantages of both genetic algorithm and the BP neural network. Genetic learning algorithm was used for the global optimization and BP training algorithm to accurately optimize the neural network weights and training the neural network to learn letter recognition algorithm. Add-noise alphabet of MATLAB simulation results show that the new network error recognition rate reduced by 10% compared to BP neural network and the recognition speed is also faster than the traditional BP neural network with accuracy and fast convergence.

Based on safety assessment factors determined by operation characteristics of a certain tailing ,genetic BP neural network evaluation model is established. To overcome such problems of BP neural network as slow convergence ,poor generalization ability and easy to fall into local minimum value,this paper proposes to use genetic algorithm to optimize threshold value,weights and structure of neural network. Thus,by taking advantage of extensive mapping ability of neural network and global search ability of genetic algorithm,neural network and genetic algorithm will have complementary advantages and the learning speed of network will be accelerated. The application of the described method shows optimized fitting precision,improved accuracy and efficiency ,and enhanced generalization ability of BP neural network. In conclusion,this model can effectively reflect and accurately evaluate non-linear relations between security levels and evaluation factors in tailing.

Aiming at the problems of the classic convolutional neural network with fewer convolutional layers, fixed convolution kernel size, and fewer features extracted, this paper proposes an improved deep convolutional neural network model, which different convolution kernels can be assigned to perform convolution operations according to the different amount of information in the image area, so it can better extract the effective information of the image and is more suitable for the recognition of complex images. Experiment shows that a higher recognition rate can be obtained.

In order to improve the efficiency and accuracy of thermal and moisture comfort prediction of underwear, a new prediction model is designed by using principal component analysis method to reduce the dimension of related variables and eliminate the multi-collinearity relationship between variables, and then inputting the converted variables into genetic algorithm (GA) and BP neural network. In order to avoid the problems of slow convergence speed and easy falling into local minimum of Back Propagation (BP) neural network, this paper adopted GA to optimize the weights and thresholds of BP neural network, and utilized MATLAB software to program, and established the prediction models of BP neural network and GA–BP neural network. To verify the superiority of the model, the predicted result of GA–BP, PCA–BP and BP are compared with GA–BP neural network. The results show that PCA could improve the accuracy and adaptability of GA–BP neural network for thermal and moisture comfort prediction. PCA–GA–BP model is obviously superior to GA–BP, PCA–BP, BP, SVM and K-means prediction models, which could accurately predict thermal and moisture comfort of underwear. The model has better accuracy prediction and simpler structure.

In this paper, an improved neural network enterprise credit rating model, which is grounded on a genetic algorithm, is suggested. With the characteristics of self-adaptiveness and self-learning, the genetic algorithm is utilized to adjust and enhance the thresholds and weights of the neural network connections. The potential problems of the backpropagation (BP) neural network with slothful speed of convergence and the possibility of falling into the local minimum point are solved to a convinced degree using the genetic algorithm in combination. The hybrid technique of the genetic BP neural network is applied to a credit rating system. Using commercial banks’ datasets, our experimental evaluations suggest that, using a combination of the BP neural network and the genetic algorithm, the proposed model has high accuracy in enterprise credit rating and has good application value. Moreover, the proposed model is approximately 15.9% more accurate than the classical BP neural network approach.

According to such defects as that BP neural network is easy to fall into the local minimum values and is sensitive to the initial values of weights and thresholds, genetic algorithm was combined with BP neural network to improve the initial values of weights and thresholds. According to the fault diagnosis of complex system, based on cognitive science, its structure was decomposed; the fault diagnostic sub-model using genetic BP neural network was established to the different parts of the structure; D-S evidence theory was used to different sub-models for the global information fusion. GNN-DS diagnostic model was established for the fault diagnosis of complex system, this model reduced the uncertainty of fault diagnosis of complex system.

To recognize the abnormal heating of cable terminal, Radon and Fourier-Mellin transform is used to extract the feature in the paper. First, processing the original image by Radon transform and Fourier-Mellin transform successively and then extracting the four feature quantities of the transformed image based on invariant function. Finally, feature vectors will be input to the BP neural network for image recognition. It can be concluded from the result that the method proposed in the paper can reflect features of the infrared image more effectively. Infrared image with Pepper and salt noise and white Gaussian noise is recognized based on the method which proves its strong robusticity on noise disturbance.

With the Belt and Road strategy deeply rooted in people's hearts, it is an inevitable choice for China and countries (or regions) along the Belt and Road strategy to build a science and technology innovation community. In this study, the high-tech industries of major provinces and cities in China are taken as the research object, and the collaborative innovation process and mechanism of each innovation subject are taken as the research purpose. By introducing the collaborative innovation concept of the innovation community, we construct the innovation performance evaluation index system to optimize the model of the innovation community performance evaluation via using neural networks. The neural network is one of the most widely used algorithms among deep learning algorithms, and this paper mainly analyzes the characteristics of Back Propagation (BP) neural network in the performance evaluation, which has strong local optimization but slow convergence speed. We build a BP neural network based on the genetic algorithm, and this neural network makes the performance evaluation model has the characteristics of strong global optimization and fast convergence speed. However, at the same time, it also has the risk of early convergence and lacks the ability of the global search. On this basis, we propose an improved genetic BP neural network based on simulated annealing in this paper. The improved simulated annealing algorithm not only can reduce error but also has a stronger local convergence and a faster evolution speed, which can obtain a satisfying global optimal solution. When we apply the improved simulated annealing genetic BP neural network in the performance evaluation of the science and technology innovation community, the simulation results show that this algorithm can be a reliable performance evaluation method and easier to obtain the optimal solution than other algorithms. Besides, the feasibility of the evaluation system and method is verified.

In order to solve insufficient data features utilization efficiency and improve the performance of the deep neural network in image recognition, we propose a cross partial path weighted feature fusion (CPP) algorithm based on the Yolo framework. Firstly, CPP deepens the down-sampling depth of the backbone framework; then two weighted sampling partial paths are built in the feature fusion network, and the corresponding FPN layers are weighted and fused to form an output feature maps; finally, the output feature maps of different sizes are used to obtain more accurate bounding box position and category information. The experimental analysis results show that the advantage of our algorithm is to extend the network depth of the model as well as the network width. Our model be able to fuse more feature information so that it improves the recognition accuracy of object detection.

Based on the wide application of neural network in image recognition and character recognition, this paper introduces three kinds of neural network models, compares and analyzes the performance of different neural network models in practical application. This paper first introduces the development of neural networks, especially the convolutional neural network, and the principles of the three neural network models in detail. Then building and training the three models that are based on the analysis. Finally, through experimental simulation, it shows that convolutional neural network has an outstanding advantage in handwritten digital image recognition.

An electronic nose (E-nose) was developed to distinguish different stored eggs by using principal component analysis (PCA),linear discriminant analysis (LDA),BP neural network (BPNN) and the combination of a genetic algorithm and BP neural network (GANN). Results showed that the E-nose can distinguish eggs of different storage time under cool and room-temperature storage by LDA and PCA. LDA preceded PCA. Better prediction values were obtained by GANN than by BPNN. Relationships were established between the E-nose signal and egg quality indices by quadratic polynomial step regression (QPSR). The prediction models indicated good prediction performance with correlation coefficient between predicted and measured values greater than 0.90.

Tool wear conditions monitoring is an important mechanical processing system that can improve the processing quality of wood plastic composite furniture and reduce industrial energy consumption. An appropriate signal, feature extraction method, and model establishment method can effectively improve the accuracy of tool wear monitoring. In this work, an effective method based on discrete wavelet transformation (DWT) and genetic algorithm (GA) – back propagation (BP) neural network was proposed to monitor the tool wear conditions. The spindle power signals under different spindle speeds, depths of milling, and tool wear conditions were collected by power sensors connected to the machine tool control box. Based on the feature extraction method, the approximate coefficients of spindle power signal were extracted by DWT. Then, the extracted approximate coefficients, spindle speeds, depths of milling, and tool wear conditions were taken as samples to train the monitoring model. Threshold and weight of BP neural network were optimized by GA, and the accuracy of monitoring model established by the GA – BP neural network can reach 100%. Thus, the proposed monitoring method can accurately monitor tool wear conditions with different milling parameters, which can achieve the purpose of improving the processing quality of wood plastic composite furniture and reducing energy consumption.

飞机驾驶舱系统自动化水平提高的关键在于科学合理地进行人机功能分配。为了提高飞机驾驶舱人机功能分配的可靠性，本文通过对遗传算法和BP神经网络这两种智能算法进行分析研究，提出了基于遗传BP神经网络的飞机驾驶舱人机功能分配方法。将机组成员飞行时的生理指标HRV2和TLI2作为网络的输入变量，使用遗传算法优化BP神经网络权值和阀值，输出飞行任务自动化等级，进而得到相应的人机功能分配方案。仿真结果表明，相比于传统的BP神经网络，该方法确定的人机功能分配方案可靠性更高。 The key to improve the automation level of the aircraft cockpit system is getting on man-machine function allocation scientifically and reasonably. In order to improve the reliability of man-machine function allocation for cockpit, based on the study of genetic algorithm and BP neural network, we propose a method of using genetic BP neural network in this paper. The input variables of the network are HRV2 and TLI2 which are the physiological indexes of the crew. Geneticalgorithm was used to optimize the weights and bias of BP neural network. The output variable of the network is the levels of automation. In this way, we can get corresponding man-machine function allocation scheme. Compared with the traditional BP neural network, the simulation result shows that this method is more reliable for the man-machine function allocation.

In order to scientifically and accurately evaluate power information system, the new power information risk evaluation method based on the genetic algorithm and BP neural network is presented. The method combining the genetic algorithm and BP algorithm can be used to train the feedforward neural network , namely, first , to use the genetic algorithm to do the global training, then ,to use BP algorithm to do local precise training ,which not only overcomes the drawbacks of the traditional BP network (the training time is long, and the network is easy to fall to local extremum),but also improves the global convergence efficiency. The method was adopted to evaluate the power information system. And findings identify that the new method has distinctive convergence speed and high predicition accuracy, which provides a new concept for power information system risk assessment.

BP neural network is a multilayer feedforward network trained by error back-propagation algorithm, which is one of the most widely used neural network models. However, BP neural network has exposed more and more shortcomings and deficiencies with the expansion of the application scope. In the prediction of ore quantity, BP neural network has the characteristics of slow convergence and easy to fall into local minimum point. In order to obtain the global optimal solution, and to improve the defects of BP neural network, this paper proposes combination optimization algorithm of genetic algorithm (GA) and BP neural network to improve the speed and accuracy of forecasting the main design flow chart and the analysis of the sort distinguish algorithm are offered, and then some problem in the design and debugging of the algorithm are discussed. On this basis, the GA-BP neural network model is constructed and applied to optimize the initial weights and threshold value of BP neural network. This model choices the floating point coding method to encode the connection weights and thresholds, and divides subjects into several populations. Through the introduction of selection, mutation, crossover, initial weight and other operators, making operational synergies between the various groups. This study selects 30 geological units, 8 quantitative variables (Pb, Zn, Cu, Mo, Si, Ni, Co, V) and 12 qualitative variables to carry out empirical analysis. Then the simulation of the algorithm is carried out in MATLAB and the parameters are analysed. By normalizing the input samples, 22 groups of observation data are used as the training data for prediction, and the latter 8 groups of observation data are used as the test data to be verified. The results show that when the ore quantity characteristics are not very significant, the model will produce prediction bias. But the improvement of the algorithm increases the efficiency of the function approach capacity of BP neural network and conquer the BP neural network system’s instability. It provides an auxiliary guide for ore prediction, which have higher reference value.