Structure Of BP Neural Network Research Articles

Research on the application of neural networks in macroeconomic forecasting and strategic management decision-making

Abstract Traditional macroeconomic forecasting models have some limitations in utilizing large-scale variables, screening appropriate variables, and forecasting accuracy. Based on the theories of economic fluctuation and New Keynes, this paper uses monetary policy, investment behavior, and consumption behavior as predictors of macroeconomic fluctuation. Then, it explores the principles and steps of the BP network applied to forecasting, the design of BP neural network structure, the selection of training algorithm and training parameters, and finally establishes a reasonable BP network structure model. Finally, using the prediction of GDP growth rate as an example, an empirical comparative analysis of model prediction accuracy is carried out. The empirical results of the model in the training set and the test set show that the structure of the BP neural network model is 3-48-1, and the model obtains the optimal learning error (6.207×10−5) at 500 iterations. In the experimental set, the root-mean-square prediction error between the output predicted value and the actual value is less than ±0.2 . The model accurately predicts the GDP growth rate, which can provide a theoretical basis for proposing macroeconomic strategic management decisions.

Application of power electronic circuit design based on BP artificial neural network in environmental monitoring

Abstract Our natural resources have played an important role in building our economy. In addition to the number one energy resource, oil, electric energy is also the best quality and much in demand by society in the history of human civilization. It is because electrical energy can be fully developed and applied by society that the construction of human spiritual civilization has entered industrialization and high-tech information technology. The transmission and application of electric energy has been recognized by society, but how can we make it more reasonable and efficient for easy utilization. In order to solve the problem of how complex power electronic circuit devices can be more widely used with improved technology. This paper establishes the error estimation model of intelligent circuit from data collection and data prediction preprocessing, then proposes to optimize the number of nodes in the hidden layer by using particle swarm optimization algorithm to address the limitations of the traditional BP neural network, and uses the optimized number of nodes in the hidden layer to build a BP neural network structure to train the training sample data, and calculates the error data of the intelligent circuit based on the trained BP neural network to test the sample data. The method established in this paper is used to perform the evaluation of intelligent circuit operation errors. The simulation example shows that the established model can effectively evaluate the smart circuit operation error, and the evaluation accuracy is significantly improved compared with the traditional evaluation method.

Neural network-based robot nonlinear output feedback control method

In order to improve the accuracy of robot terminal pose tracking and the anti-interference performance of robot nonlinear motion path control, a nonlinear output feedback control method based on neural network is proposed. Construct the coordinate transformation matrix of the connecting rod, calculate the linear and angular velocity of the nonlinear motion of the robot, then calculate the sum of the kinetic energy of each connecting rod of the robot, and establish the motion equation of the robot. The structure of BP neural network is analyzed, and the motion equation is solved by BP neural network. Finally, a Fractional Order PID controller is designed and BP neural network is constructed to control the nonlinear motion equation of the robot to complete the output feedback control of the robot. The experimental results show that the end attitude tracking error of this method is the smallest, and it best fits the actual nonlinear trajectory of the robot. It shows that this method can accurately track the end posture of the robot, and can still effectively control the trajectory of the robot in the interference environment.

A Study on the Identification of Glass Artefacts Based on Multiple Logistic Regression

In this paper, traditional glass artefacts are classified into four categories, and the common factors obtained from factor analysis are used to solve a multivariate logistic regression model to avoid the 'pseudo-regression' caused by multiple covariance, and then predict the unknown types of glass artefacts. The BP neural network structure was also constructed based on the data, and the optimal solution was obtained after 1000 iterations using Bayesian regularization to minimize the sum of squares of the errors, provided that 10 neurons were used. The glass samples were identified to belong to the categories of unweathered high potassium, weathered lead barium, unweathered lead barium, unweathered lead barium, weathered lead barium, weathered high potassium, weathered high potassium and unweathered lead barium.

Prediction Model of Car Ownership Based on Back Propagation Neural Network Optimized by Particle Swarm Optimization

Aiming to address the problems of traditional BP neural networks, which include their slow convergence speed and low accuracy, a vehicle ownership prediction model based on a BP neural network with particle swarm optimization is proposed. The weights and thresholds of the BP neural network are optimized by PSO to make the prediction results more accurate. Based on the current literature regarding BP neural networks’ ability to predict car ownership, a 9-10-1 BP neural network structure model is established. A traditional BP neural network and a PSO-optimized BP neural network are used to predict car ownership at the same time. In order to compare their prediction accuracy, a genetic algorithm (GA) and whale optimization algorithm (WOA) are additionally selected to optimize the BP neural network as a control group to predict car ownership. The data on China’s car ownership from 2005 to 2021 were collected as experimental data. The data from 2005 to 2016 were used as training data, and the remaining data were used as validation data for model prediction. The results show that the PSO-optimized neural network only undergoes three iterations of training, and the convergence accuracy reaches 1.41 × 10−8. The relative error between the predicted value of car ownership and the corresponding real value is between 0.023 and 0.083, and the decisive coefficient R2 is 0.96002, indicating that the neural network has better prediction ability and higher prediction accuracy for car ownership. The particle swarm optimization algorithm is used to optimize the weights and thresholds of the BP neural network, which solves the problems of the traditional BP neural network, including the ease with which it falls into the local minimum value and its slow convergence speed, and improves its prediction accuracy of car ownership. Compared with the results optimized by the genetic algorithm and whale optimization algorithm, the error of the BP neural network optimized by PSO is the smallest, and the prediction accuracy is the highest. Through the comparative analysis of training results, it can be seen that the PSO-BP prediction model has the best stability and accuracy.

Intelligent Evaluation Method of Engineering Cost Feasibility Model Based on Internet of Things

In order to solve the problem of low accuracy of high-rise building cost evaluation, the author proposes an intelligent evaluation method of engineering cost feasibility model based on the Internet of Things. According to the overall investment composition of the construction project, this paper classifies the cost index, determines the overall cost correction coefficient, and uses the gray correlation analysis method to build the evaluation index system; according to the structure of BP neural network, the network error is calculated, and the error signals of output layer and hidden layer are defined by gradient descent method to obtain the network weight adjustment formula; finally, this paper uses the adaptive learning rate adjustment formula to set the network parameters, introduces the key parameters in the construction project to the input layer, and establishes the final cost evaluation model. Experimental results show that the error rate of this system is controlled within 10%, which meets the requirements of investment estimation. Conclusion. The proposed method can accurately and quickly evaluate the best solution for the cost of high-rise buildings with less information and has strong nonlinear information processing capabilities.

Multiple health indicators fusion-based health prognostic for lithium-ion battery using transfer learning and hybrid deep learning method

Accurate state of health (SOH) estimation of lithium-ion battery provides a guarantee for the safe driving of electric vehicles. Most SOH estimation methods based on the machine learning assume that the training and testing data follow the uniform distribution. However, the distribution of the datasets obtained at the different working conditions has discrepancy, which also increases its inherently large computational burden. Therefore, a novel SOH estimation method based on multiple health indicators (HIs) fusion using transfer learning and deep belief network (DBN)-long short-term memory (LSTM) hybrid network is proposed. Transfer learning is used to learn the shared features in the source domain and the target domain. Then, aiming at the insufficiency of shallow network in mining data features, DBN is utilized for SOH estimation. And considering the influence of historical information on future prediction, LSTM cell is used to replace the traditional BP neural network structure. Comparative study is conducted by applying deep and shallow network on the measured data for monitoring SOH of the battery in applications. The experimental results show that the method proposed in this paper is effective, and the performance of knowledge transferring under single domain and cross domain is also verified.

Accuracy Analysis of Sports Performance Prediction Based on BP Neural Network Intelligent Algorithm

With the increasing attention and popularity of competitive sports, the continuous progress of artificial intelligence, and deep learning theory, people’s sports performance prediction technology for professional athletes or sports students is also developing. Accurate and effective prediction can help athletes and students to carry out more targeted training, so as to further improve their performance. BP neural network (BPNN) is a multilayer feedforward neural network (NN). Therefore, based on the BPNN algorithm, this work conducts a deep research on the prediction of sports performance. First of all, this work uses the three-layer structure of BPNN to design the algorithm and then selects the weight, oxygen saturation, systolic and diastolic blood pressure, the previous best score, the worst score in the past period, and the average score of one week before the examination as the feature vector of the input sample. The students’ scores of two classes of physical education major in a university are selected as the prediction objects, and the time period of students’ relevant information data is selected from September 2018 to December 2018. The quantity of hidden units is calculated to be 15 by training. After the successful construction of BPNN sports performance estimation method, the PSO search approach is utilized to enhance the BPNN sports performance prediction model. Finally, the relationship between the two classes’ performance and the students’ performance is analyzed. 49% of the total number of times the error of class A was predicted to be 0, and the number of times that the error of class B was 0 was 50%, 58%, and 75%, respectively. There is no strong linear correlation between sports performance and body weight, but a high correlation systolic, pulse pressure, and plasma oxygen levels. This shows that the BPNN sports prediction model established in this work has high accuracy in predicting sports performance.

Design and Application of Anti-Liquid Sweat Suit Based on Polyvinyl Butyral SiO2 Nanocomposite

Since the changes in the content of potassium chloride and urea in sweat are related to the normal working conditions of the internal organs, and people have low sensitivity to daily food, therefore, the research on the content of potassium chloride and urea in sweat can help determine the physiological condition of the human body. This article aims to explore the design and application of anti-liquid sweat suits based on polyvinyl butyral SiO2 nanocomposites. This article first analyzes the performance of polyethylene and introduces the advantages of polyethylene. At the same time, it proposes the infrared spectroscopy analysis method of sweat multi-component, introduces the structure of BP neural network, and the flow chart of sweat single-component sample analysis. Then a comprehensive analysis of the SiO2 nanocomposite was carried out, and the properties of the polyvinyl butyral (PVB) material were explored. It provides a theoretical basis and reference value for the design and application of anti-liquid sweat suits based on polyvinyl butyral SiO2 nanocomposites. The experimental results in this paper show that the use of polyvinyl butyral (PVB) materials and SiO2 nanocomposite materials to prepare spinning sweat suits can increase the performance of anti-sweat and sweat by 60%, and at the same time, the firmness will also be increased.

Evaluation Model of Urban Smart Energy System Based on Improved Genetic Algorithm-Bp Neural Network

There are many problems such as strong subjectivity, complex calculations, and lack of intelligence in most of the current energy system evaluation models, so a design of an evaluation system for urban smart energy systems based on an improved genetic algorithm-back propagation (BP) neural network is proposed. First of all, the hierarchical structure of the indicator evaluation system for energy system was established, analytic hierarchy process (AHP) was used to assign weights to each indicator, and data samples were classified. Then, SeqGAN was used to expand the data set, which solved the difficult problem of data acquisition. Finally, the genetic algorithm was used to determine the best initial values of the weights and thresholds of the BP neural network structure parameters designed for this research. The simulation experiment results showed that the method in this paper has higher classification accuracy than the traditional method, and comprehensive evaluation model proposed can effectively evaluate the urban smart energy system.

Observation on Application Effect of Arterial Puncture and Catheterization under Guidance of Intelligent Medical Care Ultrasound in Clinical Anesthesia.

In clinical anesthesia and the rescue of critically ill patients, arterial puncture and catheterization are the most commonly chosen ways to establish central arterial access for patients. Invasive arterial puncture and catheterization facilitate the grasp of real-time vital sign information of patients during surgery, which strengthens patient monitoring during surgery and improves safety. However, the traditional method of arterial puncture and cannulation through palpation of the radial artery is often prone to complications related to mechanical injury, such as hemorrhage, hematoma, and accidental perforation of the artery. Studies have shown that ultrasound-guided radial artery puncture and cannulation can shorten the puncture cannulation time, reduce the incidence of complications related to puncture cannulation, and improve the success rate of puncture cannulation. In order to verify it, this paper uses the experimental group and the control group to conduct comparative experiments and uses the neural network method to evaluate the effects of the two methods. As a more mature method of artificial intelligence, BP neural network is widely used in a wide range of applications and has the characteristics of strong generalization ability and fast convergence, so we choose it as the base model. The specific work of this paper is as follows: (1) in-depth study of the relevant theory of BP neural network (BPNN), focusing on the structure of BPNN and the working principle of algorithm; the problems to be solved in the clinical anesthesia effect evaluation have laid a theoretical foundation for the establishment of an improved BPNN evaluation model in the following chapters. (2) introduce the basic principle of genetic neural network, analyze the benefits of combining genetic neural network and BPNN; introduce in detail the process of genetic algorithm to optimize the weights and thresholds of BPNN, and establish a GA-BP evaluation model. The test proves the feasibility and superiority of the model.

Research on Piano Informatization Teaching Strategy Based on Deep Learning

Applying information technology to piano teaching can effectively avoid these problems. The application of information teaching means can not only enrich teaching methods but also enhance students’ interest in learning. Deep learning (DL) focuses on immersing students in knowledge and learning situations, emphasizing critical thinking, and realizing the intrinsic value of knowledge. Understanding DL theory is of great significance to deepening the teaching reform in China. BP algorithm is a very effective algorithm for prediction and evaluation. In this paper, the complex factors affecting the quality of piano information teaching are comprehensively considered, and the improved BP neural network (BPNN) algorithm is used to evaluate and predict the quality of piano information teaching. The model structure of BPNN for evaluating and predicting the quality of piano information teaching is given and simulated in MATLAB. The results show that the evaluation and prediction method overcomes the subjective factors of expert evaluation and obtains reasonable results. Compared with the traditional BPNN algorithm, it has good applicability.

A Novel GA-BP Neural Network for Wireless Diagnosis of Rolling Bearing

Rolling bearings are pivotal components in industrial rotating equipment and the issue of fault will occur inevitably due to long-term abrasion. This study proposes a novel GA-BP neural network (GA-BPNN) algorithm to improve the accuracy of fault diagnosis of industrial rolling bearings. The genetic algorithm (GA) is employed to optimize the structure, initial weight and threshold of BP neural network, which can improve the ability of diagnosis and reduce the time of network training. At first, the structure of network is determined so that the optimal parameters of GA can be given, then the population of GA will be encoded. At second, the individual fitness function is calculated based on the test error norm of the BP neural network, as a criterion for distinguishing the individual from individual. The optimal weight and threshold are obtained by means of the corresponding selection, cross and variation, etc. Finally, the simulation experiment is carried out in Matlab and massive vibration experimental data of industrial rolling bearing are utilized. To verify the ability of the proposed novel GA-BPNN, compared with BP neural network algorithm (BPNN), the convergence speed and accuracy of GA-BPNN are better. The results of experiment illustrate that the optimized GA-BPNN method can identify the fault-type quicker, and has higher feasibility, which can be used to assist diagnosis of industrial bearing and improve efficiency.

Rapid detection method of Pleurotus eryngii mycelium based on near infrared spectral characteristics

Edible fungus is a large fungus with edible and medicinal value. Rapid detection of mycelium phenotypic characteristics is of great significance for edible fungus breeding and intelligent cultivation. Traditional method based on experienced observation easily led to make mistakes on distinguishing the growth stages, which impacted on the yield and quality of edible fungus. Therefore, in view of the lack of accurate and efficient detection technology during the growth stages of Pleurotus eryngii mycelium, a rapid detection method of Pleurotus eryngii mycelium at different growth stages is proposed based on the characteristics of near-infrared spectroscopy. First, the spectral data of mycelium of Pleurotus eryngii at six different growth stages were scanned. Second, the multivariate scattering correction method (MSC) was used to pre-process the raw spectral data, and then the competitive adaptive reweighted sampling algorithm (CARS) was adopted to detect the characteristic wave number of the effective variables for Pleurotus eryngii mycelium. In addition, the mathematical model between the mycelium of Pleurotus eryngii and the characteristic wave number of near-infrared spectrum was established by using feed forward neural network (BP). Finally, and the coding vector output by the network was used to detect to the growth stages. The results showed that the BP neural network structure of MSC-CARS-BP detection model was 86–85-85–95-6, and the accuracy of identifying different growth stages of Pleurotus eryngii mycelium was 99.67%. The research results could provide a new idea and technical support for the rapid detection of Pleurotus eryngii mycelium at different growth stages.

Music emotion recognition algorithm based on BP neural network

Music plays a very important role in animation production. Because it could better express the emotion of the character, this paper uses BP neural network to identify the music emotion. This paper first introduced the structure of BP neural network. Then, the parameters and structure of the network were designed according to the category of music emotion. Finally, a three-layer BP neural network with 5 input nodes, 13 hidden layer nodes and 4 output nodes was constructed and applied to music emotion recognition. The recognition accuracy was 85.02%, which basically met the requirements of music emotion recognition and achieves the expected effect.

Study on Quantitative Prediction of Anticancer Compound Activity Based on Neural Network Model

Breast cancer poses a serious threat to global women's health. Around this problem, a quantitative prediction model of biological activity based on neural network and a quantitative prediction model of multiple linear regression are established in this paper. 20 kinds of molecular descriptor data with the most significant effect on biological activity of 1974 compounds were selected as input layer and 1 biological activity data as output layer, and a quantitative prediction model of biological activity based on neural network was established. Based on the quantitative prediction model based on parameter setting, the single hidden layer BP neural network structure is used to test the model, and the fitting error R values of the training set and test set of the model are close to 1, and the trend in the scatter diagram is obvious, which shows that the prediction value of the model is more accurate.

Research on the Estimation of Gaze Location for Head-eye Coordination Movement

Abstract Sight is the main source for humans to obtain information from the outside world. Due to the structure of the human eye [1], the range of human sight is limited. For this reason, people need to constantly move their line of sight when observing the surrounding environment and the target, and the movement of the sight is based on the coordinated movement of the head and the eye[2]. Therefore, the key issue for gaze research is how to correctly establish the relationship between head-eye movement and gaze movement. Taking the simulated flight environment as the research background, this paper collects a large number of head-eye images through the designed “three-camera and eight-light source” head-eye data acquisition platform, and proposes a gaze estimation method based on the combination of appearance and features, which effectively combines The relationship of head-eye coordination movement. Then, the ResNet-18 deep residual network structure and the traditional BP neural network structure are used to complete the effective fusion of the head pose and human eye features in the process of capturing the sight target, so as to realize the accurate estimation of the sight drop point, and its average accuracy up to 89.9%.

Strength Prediction of Coal-Based Solid Waste Filler Based on BP Neural Network

The compressive strength of filling body is an important index to characterize the filling and mining effect of coal mine. In order to accurately predict the strength of coal-based solid waste filler (CBSWF) to guide the safe, efficient, and green mining of coal mine, coal gangue is used as coarse material; fly ash, desulfurization gypsum, gasification slag, and furnace bottom slag are used as fine materials; and cement is used as gelling agent. The compressive strength and bleeding rate of CBSWF are tested through orthogonal test, and the strength of CBSWF at different curing ages is predicted by using a 4-11-3 three-layer BP neural network structure. The results show that the correlation coefficient r of strength prediction of CBSWF is 0.99987, which can accurately predict the strength of CBSWF. Orthogonal test combined with the BP neural network can reduce the number of tests without losing generality, make full use of the advantages of adaptive nonlinear optimization of the BP neural network, and improve the operation efficiency of the model, fast prediction speed, and high accuracy.

Research on Catalyst Combination for Ethanol Coupling Preparation of C4 Olefins Based on BP Neural Network

In this paper, a grey correlation analysis model based on BP neural network is established for the preparation of C4 olefins by ethanol coupling. Firstly, the grey correlation analysis of ethanol conversion, C4 olefin selectivity and its influencing factors was carried out, and the correlation degree of 5 factors in the catalyst combination was obtained. Then, the BP neural network structure is constructed to predict the obtained correlation degree. It is concluded that the average relative error between the calculated correlation degree and the predicted correlation degree is 1.7%, which verifies the rationality of the model. Finally, the residual analysis of the results shows that the absolute error is 5.3%.

Research on vehicle adaptive cruise control based on BP neural network working condition recognition

To solve the problems of the vehicle following model mismatch under different driving conditions and poor vehicle following performance, this paper proposes an adaptive cruise control system based on BP neural network to identify different driving conditions. Firstly, eight typical driving cycles are selected as samples, which are redivided into low-speed mode and medium high-speed mode. According to the selected characteristic parameters and re-division of driving mode, a new BP neural network structure is designed. Secondly, the characteristic parameter values are calculated by using the characteristic parameters, and the characteristic parameters are normalized. The working condition recognition model is obtained by training the normalized data values. Finally, according to the classification of working conditions, the fuzzy control upper control algorithm and the MPC upper control algorithm for medium-high speed conditions are designed respectively. Based on the above control algorithms, the joint simulation is carried out with Car-Sim and MATLAB/Simulink. The simulation results show that the low-speed fuzzy logic algorithm and the medium high-speed MPC algorithm proposed in this paper can make the vehicle have a better following performance and comfort.