Application of the back-error propagation artificial neural network(BPANN) on genetic variants in the PPAR-γ and RXR-α gene and risk of metabolic syndrome in a Chinese Han population

This study was aimed to explore the associations between the combined effects of several polymorphisms in the PPAR-γ and RXR-α gene and environmental factors with the risk of metabolic syndrome by back-error propaga- tion artificial neural network （BPANN）. We established the model based on data gathered from metabolic syndrome patients （n = 1012） and normal controls （n = 1069） by BPANN. Mean impact value （MIV） for each input variable was calculated and the sequence of factors was sorted according to their absolute MIVs. Generalized multifactor dimensionality reduction （GMDR） confirmed a joint effect of PPAR-9＂ and RXR-a based on the results from BPANN. By BPANN analysis, the sequences according to the importance of metabolic syndrome risk fac- tors were in the order of body mass index （BMI）, serum adiponectin, rs4240711, gender, rs4842194, family history of type 2 diabetes, rs2920502, physical activity, alcohol drinking, rs3856806, family history of hypertension, rs1045570, rs6537944, age, rs17817276, family history of hyperlipidemia, smoking, rs1801282 and rs3132291. However, no polymorphism was statistically significant in multiple logistic regression analysis. After controlling for environmental factors, A1, A2, B1 and B2 （rs4240711, rs4842194, rs2920502 and rs3856806） models were the best models （cross-validation consistency 10/10, P = 0.0107） with the GMDR method. In conclusion, the interaction of the PPAR-γ and RXR-α gene could play a role in susceptibility to metabolic syndrome. A more realistic model is obtained by using BPANN to screen out determinants of diseases of multiple etiologies like metabolic syndrome.

A Review on Back-Propagation Neural Networks in the Application of Remote Sensing Image Classification

ANNs （Artificial neural networks） are used extensively in remote sensing image processing. It has been proven that BPNNs （back-propagation neural networks） have high attainable classification accuracy. However, there is a noticeable variation in the achieved accuracies due to different network designs and implementations. Hence, researchers usually need to conduct several experimental trials before they can finalize the network design. This is a time consuming process which significantly reduces the effectiveness of using BPNNs and the final design may still not be optimal. Therefore, there is a need to see whether there are some common guidelines for effective design and implementation of BPNNs. With this aim in mind, this paper attempts to find and summarize the common guidelines suggested by different authors through literature review and discussion of the findings. To provide readers with background and contextual information, some ANN fundamentals are also introduced.

DAMAGE DETECTION IN STRUCTURES USING MODIFIED BACK-PROPAGATION NEURAL NETWORKS

A nonparametric structural damage detection methodology based on neuralnetworks method is presented for health monitoring of structure-unknown systems. In this approachappropriate neural networks are trained by use of the modal test data from a 'healthy' structure.The trained networks which are subsequently fed with vibration measurements from the same structurein different stages have the capability of recognizing the location and the content of structuraldamage and thereby can monitor the health of the structure. A modified back-propagation neuralnetwork is proposed to solve the two practical problems encountered by the traditionalback-propagation method, i.e., slow learning progress and convergence to a false local minimum.Various training algorithms, types of the input layer and numbers of the nodes in the input layerare considered. Numerical example results from a 5-degree-of-freedom spring-mass structure andanalyses on the experimental data of an actual 5-storey-steel-frame demonstrate thatneural-networks-based method is a robust procedure and a practical tool for the detection ofstructural damage, and that the modified back-propagation algorithm could improve the computationalefficiency as well as the accuracy of detection.

Analysis of Factors Related to Vasovagal Response in Apheresis Blood Donors and the Establishment of Prediction Model Based on BP Neural Network Algorithm

Objective:To analyze the factors related to vessel vasovagal reaction(VVR)in apheresis donors,establish a mathematical model for predicting the correlation factors and occurrence risk,and use the prediction model to intervene in high-risk VVR blood donors,improve the blood donation experience,and retain blood donors.Methods:A total of 316 blood donors from the Xi'an Central Blood Bank from June to September 2022 were selected to statistically analyze VVR-related factors.A BP neural network prediction model is established with relevant factors as input and DRVR risk as output.Results:First-time blood donors had a high risk of VVR,female risk was high,and sex difference was significant(P value<0.05).The blood pressure before donation and intergroup differences were also significant(P value<0.05).After training,the established BP neural network model has a minimum RMS error of o.116,a correlation coefficient R=0.75,and a test model accuracy of 66.7%.Conclusion:First-time blood donors,women,and relatively low blood pressure are all high-risk groups for VVR.The BP neural network prediction model established in this paper has certain prediction accuracy and can be used as a means to evaluate the risk degree of clinical blood donors.

FORCE RIPPLE SUPPRESSION TECHNOLOGY FOR LINEAR MOTORS BASED ON BACK PROPAGATION NEURAL NETWORK

Various force disturbances influence the thrust force of linear motors when a linear motor （LM） is running. Among all of force disturbances, the force ripple is the dominant while a linear motor runs in low speed. In order to suppress the force ripple, back propagation（BP） neural network is proposed to learn the function of the force ripple of linear motors, and the acquisition method of training samples is proposed based on a disturbance observer. An off-line BP neural network is used mainly because of its high running efficiency and the real-time requirement of the servo control system of a linear motor. By using the function, the force ripple is on-line compensated according to the position of the LM. The experimental results show that the force ripple is effectively suppressed by the compensation of the BP neural network.

A Human Body Posture Recognition Algorithm Based on BP Neural Network for Wireless Body Area Networks

Human body posture recognition has attracted considerable attention in recent years in wireless body area networks(WBAN). In order to precisely recognize human body posture,many recognition algorithms have been proposed.However, the recognition rate is relatively low. In this paper, we apply back propagation(BP) neural network as a classifier to recognizing human body posture, where signals are collected from VG350 acceleration sensor and a posture signal collection system based on WBAN is designed. Human body signal vector magnitude(SVM) and tri-axial acceleration sensor data are used to describe the human body postures. We are able to recognize 4postures: Walk, Run, Squat and Sit. Our posture recognition rate is up to 91.67%. Furthermore, we find an implied relationship between hidden layer neurons and the posture recognition rate. The proposed human body posture recognition algorithm lays the foundation for the subsequent applications.

BP neural networks and random forest models to detect damage by Dendrolimus punctatus Walker

The construction of a pest detection algorithm is an important step to couple"ground-space"characteristics,which is also the basis for rapid and accurate monitoring and detection of pest damage.In four experimental areas in Sanming City,Jiangle County,Sha County and Yanping District in Fujian Province,sample data on pest damage in 182 sets of Dendrolimus punctatus were collected.The data were randomly divided into a training set and testing set,and five duplicate tests and one eliminating-indicator test were done.Based on the characterization analysis of the host for D.punctatus damage,seven characteristic indicators of ground and remote sensing including leaf area index,standard error of leaf area index(SEL)of pine forest,normalized difference vegetation index(NDVI),wetness from tasseled cap transformation(WET),green band(B2),red band(B3),near-infrared band(B4)of remote sensing image are obtained to construct BP neural networks and random forest models of pest levels.The detection results of these two algorithms were comprehensively compared from the aspects of detection precision,kappa coefficient,receiver operating characteristic curve,and a paired t test.The results showed that the seven indicators all were responsive to pest damage,and NDVI was relatively weak;the average pest damage detection precision of six tests by BP neural networks was 77.29%,the kappa coefficient was 0.6869 and after the RF algorithm,the respective values were 79.30%and 0.7151,showing that the latter is more optimized,but there was no significant difference(p>0.05);the detection precision,kappa coefficient and AUC of the RF algorithm was higher than the BP neural networks for three pest levels(no damage,moderate damage and severe damage).The detection precision and AUC of BP neural networks were a little higher for mild damage,but the difference was not significant(p>0.05)except for the kappa coefficient for the no damage level(p<0.05).An"over-fitting"phenomenon tends to occur in BP neural networks,while RF method is more robust,providing a detection effect that is better than the BP neural networks.Thus,the application of the random forest algorithm for pest damage and multilevel dispersed variables is thus feasible and suggests that attention to the proportionality of sample data from various categories is needed when collecting data.

Determination of Gamma point source efficiency based on a backpropagation neural network

Efficiency is an important factor in quantitative and qualitative analysis of radionuclides, and the gamma point source efficiency is related to the radial angle,detection distance, and gamma-ray energy. In this work, on the basis of a back-propagation(BP) neural network model,a method to determine the gamma point source efficiency is developed and validated. The efficiency of the point sources ^(137)Cs and ^(60)Co at discrete radial angles, detection distances, and gamma-ray energies is measured, and the BP neural network prediction model is constructed using MATLAB. The gamma point source efficiencies at different radial angles, detection distances, and gamma-ray energies are predicted quickly and accurately using this nonlinear prediction model. The results show that the maximum error between the predicted and experimental values is 3.732% at 661.661 keV, 11π/24, and 35 cm, and those under other conditions are less than 3%. The gamma point source efficiencies obtained using the BP neural network model are in good agreement with experimental data.

A Short-Range Quantitative Precipitation Forecast Algorithm Using Back-Propagation Neural Network Approach

A back-propagation neural network （BPNN） was used to establish relationships between the shortrange （0-3-h） rainfall and the predictors ranging from extrapolative forecasts of radar reflectivity, satelliteestimated cloud-top temperature, lightning strike rates, and Nested Grid Model （NGM） outputs. Quan- titative precipitation forecasts （QPF） and the probabilities of categorical precipitation were obtained. Results of the BPNN algorithm were compared to the results obtained from the multiple linear regression algorithm for an independent dataset from the 1999 warm season over the continental United States. A sample forecast was made over the southeastern United States. Results showed that the BPNN categorical rainfall forecasts agreed well with Stage Ⅲ observations in terms of the size and shape of the area of rainfall. The BPNN tended to over-forecast the spatial extent of heavier rainfall amounts, but the positioning of the areas with rainfall ≥25.4 mm was still generally accurate. It appeared that the BPNN and linear regression approaches produce forecasts of very similar quality, although in some respects BPNN slightly outperformed the regression.

Load Reduction Test Method of Similarity Theory and BP Neural Networks of Large Cranes

Static load tests are an important means of supervising and detecting a crane＇s lift capacity. Due to space restrictions, however, there are difficulties and potential danger when testing large bridge cranes. To solve the loading problems of large-tonnage cranes during testing, an equivalency test is proposed based on the similarity theory and BP neural networks. The maximum stress and displacement of a large bridge crane is tested in small loads, combined with the training neural network of a similar structure crane through stress and displacement data which is collected by a physics simulation progressively loaded to a static load test load within the material scope of work. The maximum stress and displacement of a crane under a static load test load can be predicted through the relationship of stress, displacement, and load. By measuring the stress and displacement of small tonnage weights, the stress and displacement of large loads can be predicted, such as the maximum load capacity, which is 1.25 times the rated capacity. Experimental study shows that the load reduction test method can reflect the lift capacity of large bridge cranes. The load shedding predictive analysis for Sanxia 1200 t bridge crane test data indicates that when the load is 1.25 times the rated lifting capacity, the predicted displacement and actual displacement error is zero. The method solves the problem that lifting capacities are difficult to obtain and testing accidents are easily possible when 1.25 times related weight loads are tested for large tonnage cranes.

Study on analytical noise propagation in convolutional neural network methods used in computed tomography imaging

Neural network methods have recently emerged as a hot topic in computed tomography(CT) imaging owing to their powerful fitting ability;however, their potential applications still need to be carefully studied because their results are often difficult to interpret and are ambiguous in generalizability. Thus, quality assessments of the results obtained from a neural network are necessary to evaluate the neural network. Assessing the image quality of neural networks using traditional objective measurements is not appropriate because neural networks are nonstationary and nonlinear. In contrast, subjective assessments are trustworthy, although they are time-and energy-consuming for radiologists. Model observers that mimic subjective assessment require the mean and covariance of images, which are calculated from numerous image samples;however, this has not yet been applied to the evaluation of neural networks. In this study, we propose an analytical method for noise propagation from a single projection to efficiently evaluate convolutional neural networks(CNNs) in the CT imaging field. We propagate noise through nonlinear layers in a CNN using the Taylor expansion. Nesting of the linear and nonlinear layer noise propagation constitutes the covariance estimation of the CNN. A commonly used U-net structure is adopted for validation. The results reveal that the covariance estimation obtained from the proposed analytical method agrees well with that obtained from the image samples for different phantoms, noise levels, and activation functions, demonstrating that propagating noise from only a single projection is feasible for CNN methods in CT reconstruction. In addition, we use covariance estimation to provide three measurements for the qualitative and quantitative performance evaluation of U-net. The results indicate that the network cannot be applied to projections with high noise levels and possesses limitations in terms of efficiency for processing low-noise projections. U-net is more effective in improving the image quality of smooth regions compared with that of the edge. LeakyReLU outperforms Swish in terms of noise reduction.

Linearization Learning Method of BP Neural Networks

Feedforward multi layer neural networks have very strong mapping capability that is based on the non linearity of the activation function, however, the non linearity of the activation function can cause the multiple local minima on the learning error surfaces, which affect the learning rate and solving optimal weights. This paper proposes a learning method linearizing non linearity of the activation function and discusses its merits and demerits theoretically.

HCl emission characteristics and BP neural networks prediction in MSW/coal co-fired fluidized beds

The HCl emission characteristics of typical municipal solid waste(MSW) components and their mixtures have been investigated in a Φ150 mm fluidized bed. Some influencing factors of HCl emission in MSW fluidized bed incinerator was found in this study. The HCl emission is increasing with the growth of bed temperature, while it is decreasing with the increment of oxygen concentration at furnace exit. When the weight percentage of auxiliary coal is increased, the conversion rate of Cl to HCl is increasing. The HCl emission is decreased, if the sorbent(CaO) is added during the incineration process. Based on these experimental results, a 14×6×1 three-layer BP neural networks prediction model of HCl emission in MSW/coal co-fired fluidized bed incinerator was built. The numbers of input nodes and hidden nodes were fixed on by canonical correlation analysis technique and dynamic construction method respectively. The prediction results of this model gave good agreement with the experimental results, which indicates that the model has relatively high accuracy and good generalization ability. It was found that BP neural network is an effectual method used to predict the HCl emission of MSW/coal co-fired fluidized bed incinerator.

Distributed Resource Allocation in Ultra-Dense Networks via Belief Propagation

Ultra-dense networking is widely accepted as a promising enabling technology to realize high power and spectrum efficient communications in future 5G communication systems. Although joint resource allocation schemes promise huge performance improvement at the cost of cooperation among base stations,the large numbers of user equipment and base station make jointly optimizing the available resource very challenging and even prohibitive. How to decompose the resource allocation problem is a critical issue. In this paper,we exploit factor graphs to design a distributed resource allocation algorithm for ultra dense networks,which consists of power allocation,subcarrier allocation and cell association. The proposed factor graph based distributed algorithm can decompose the joint optimization problem of resource allocation into a series of low complexity subproblems with much lower dimensionality,and the original optimization problem can be efficiently solved via solving these subproblems iteratively. In addition,based on the proposed algorithm the amounts of exchanging information overhead between the resulting subprob-lems are also reduced. The proposed distributed algorithm can be understood as solving largely dimensional optimization problem in a soft manner,which is much preferred in practical scenarios. Finally,the performance of the proposed low complexity distributed algorithm is evaluated by several numerical results.

Fashion Color Forecasting by Applying an Improved Back Propagation Neural Network

Fashion color forecasting is one of the most important factors for fashion marketing and manufacturing. Several models have been applied by previous researchers to conduct fashion color forecasting. However, few convincing forecasting systems have been established. A prediction model for fashion color forecasting was established by applying an improved back propagation neural network (BPNN) model in this paper. Successive six-year fashion color palettes, released by INTERCOLOR, were used as learning information for the neural network to develop a reliable prediction model. Colors in the palettes were quantified by PANTONE color system. Additionally, performance of the established model was compared with other GM(1, 1) models. Results show that the improved BPNN model is suitable to predict future fashion color trend.

Surface Quality Evaluation of Fluff Fabric Based on Particle Swarm Optimization Back Propagation Neural Network

Aiming at the problem that back propagation(BP)neural network predicts the low accuracy rate of fluff fabric after fluffing process,a BP neural network model optimized by particle swarm optimization(PSO)algorithm is proposed.The sliced image is obtained by the principle of light-cutting imaging.The fluffy region of the adaptive image segmentation is extracted by the Freeman chain code principle.The upper edge coordinate information of the fabric is subjected to one-dimensional discrete wavelet decomposition to obtain high frequency information and low frequency information.After comparison and analysis,the BP neural network was trained by high frequency information,and the PSO algorithm was used to optimize the BP neural network.The optimized BP neural network has better weights and thresholds.The experimental results show that the accuracy of the optimized BP neural network after applying high-frequency information training is 97.96%,which is 3.79%higher than that of the unoptimized BP neural network,and has higher detection accuracy.

Backpropagation neural network method in data processing of ultrasonic imaging logging-while-drilling

The existing methods for extracting the arrival time and amplitude of ultrasonic echo cannot eff ectively avoid the local interference of ultrasonic signals while drilling,which leads to poor accuracy of the echo arrival time and amplitude extracted by an ultrasonic imaging logging-while-drilling tool.In this study,a demodulation algorithm is used to preprocess the ultrasonic simulation signals while drilling,and we design a backpropagation neural network model to fit the relationship between the waveform data and time and amplitude.An ultrasonic imaging logging model is established,and the finite element simulation software is used for forward modeling.The response under diff erent measurement conditions is simulated by changing the model parameters,which are used as the input layer of the neural network model;The ultrasonic echo signal is considered as a low-frequency signal modulated by a high-frequency carrier signal,and a low-pass fi lter is designed to remove the high-frequency signal and obtain the low-frequency envelope signal.Then the amplitude of the envelope signal and its corresponding time are extracted as an output layer of the neural network model.By comparing the application eff ects of the various training methods,we fi nd that the conjugate gradient descent method is the most suitable method for solving the neural network model.The performance of the neural network model is tested using 11 groups of simulation test data,which verify the eff ectiveness of the model and lay the foundation for further practical application.

Combinatorial Optimization Based Analog Circuit Fault Diagnosis with Back Propagation Neural Network

Electronic components' reliability has become the key of the complex system mission execution. Analog circuit is an important part of electronic components. Its fault diagnosis is far more challenging than that of digital circuit. Simulations and applications have shown that the methods based on BP neural network are effective in analog circuit fault diagnosis. Aiming at the tolerance of analog circuit,a combinatorial optimization diagnosis scheme was proposed with back propagation( BP) neural network( BPNN).The main contributions of this scheme included two parts:( 1) the random tolerance samples were added into the nominal training samples to establish new training samples,which were used to train the BP neural network based diagnosis model;( 2) the initial weights of the BP neural network were optimized by genetic algorithm( GA) to avoid local minima,and the BP neural network was tuned with Levenberg-Marquardt algorithm( LMA) in the local solution space to look for the optimum solution or approximate optimal solutions. The experimental results show preliminarily that the scheme substantially improves the whole learning process approximation and generalization ability,and effectively promotes analog circuit fault diagnosis performance based on BPNN.

Designing of Commercial Bank Loans Risk Early Warning System Based on BP Neural Networks

According to the index early warning method, a commercial bank loans risk early warning system based on BP neural networks is proposed. The warning signal is mainly involved with the financial situation signal of loaning corporation. Except the structure description of the system structure the demonstration of attemptive designing is also elaborated.