Back Propagation Neural Network Theory Research Articles

Application of business intelligence under deep neural network in credit scoring of bank users

This paper aims to improve the level of social credit system and the accuracy and efficiency of bank users’ credit scoring by using business intelligence technology based on deep neural network (DNN). Firstly, based on the theory of personal credit evaluation factors, a comprehensive credit evaluation factor system is constructed, taking into account social and economic background, consumption habits, behavior patterns and other factors. Meanwhile, back propagation neural network (BPNN) theory is introduced as the core method of modeling to cope with the nonlinear relationship in the credit scoring task and the demand of large-scale data processing. Secondly, by analyzing the operation process of BPNN in detail, the specific application in credit scoring model is emphasized. Finally, on the basis of theory and operation, this paper implements a credit scoring model for bank users based on BPNN theory. The experimental results show that the model realized in this paper can automatically discover the key attributes and internal rules in the sampled data, and adjust the weight and threshold of the network by modifying the parameters and network structure to meet the expected requirements. The accuracy of the credit score of the predicted sample data reaches 99.5%, and the prediction error is very small, which has a good prediction effect. This paper provides a feasible solution for business intelligence and DNN in the field of credit scoring, and also provides strong empirical support for improving the level of social credit system.

The moving load identification method on asphalt roads based on the BP neural network and FBG sensor monitoring

This study to accurately identify the load information of vehicles on asphalt roads is based on the measured data of the fiber Bragg grating (FBG) sensor and the Back Propagation (BP) neural network. First, the input parameters were determined by the BP neural network and FBG sensor theory. Second, the internal mechanical response of asphalt roads under different working conditions was calculated by using finite element software and by using the results of numerical simulation trained in the neural network. Third, the accuracy of the BP neural network used to identify the moving load on asphalt roads was verified by the field-measured data of the FBG sensor. Fourth, the influential factors of moving load identification accuracy were analyzed. The main conclusions are as follows: (a) the sensitive factors of moving load identification on asphalt roads include vehicle speed, asphalt layer temperature, the longitudinal strain between asphalt layers, the number of wheels, and load position; (b) the average absolute error of moving load identification is about 4.11kN, and the average recognition accuracy is up to 90.57%; (c) the measurement accuracy is sensitive to the speed of the vehicle. When vehicle speed exceeds 60 km/h, recognition accuracy may decrease to less than 90%; and (d) the loads at different locations have a significant influence on moving load identification.

A Model for Resolving Images of Similar Quality Based on Data Application

Different remote sensing image applications require different quality remote sensing images, and selecting the best quality remote sensing image from multiple remote sensing images with similar quality directly determines the application effect of the image. According to the different applications of remote sensing images, the Rough Set Theory, Fuzzy Set Theory and Back Propagation Neural Network theory (BP Neural Network) are used to establish a remote sensing image quality evaluation model. Combining the basic influencing factors of remote sensing image quality and the influencing factors of specific applications as evaluation indicators, the remote sensing image quality evaluation model is imported, and the best quality remote sensing images are selected in specific applications for remote sensing images of special quality. Finally, this paper proves the feasibility of the model in the selection of the best image quality for specific applications of three different experiments.

Time series prediction based on deep confidence network

The timing deep belief network model (T-DBN) is proposed to solve the problems of gradient dispersion, local minimum, poor long-term prediction performance of nonlinear time series prediction and high complexity of high-dimensional sequence data in traditional computer neural networks. In the pre-training stage, the improved greedy pre-training algorithm is adopted. In the pre-training process, the gradient fixing parallel tempering (GFPT) algorithm is used to determine the depth of network by reconstruction error. In the stage of reverse adjustment, the quasi-newton method (BFGS) is adopted to obtain more accurate prediction performance. Combined with the theory of phase space reconstruction and BP (back propagation) neural network, the total power of agricultural machinery in Jiangxi province of China from 2016 to 2020 is predicted. For the highly nonlinear stock data, the characteristics of the Shanghai stock exchange index from 1990-12-20 to 2018-03-30 are extracted from the stock data of Tonghuashun software. T-DBN, DBN and long short-term memory (LSTM) models areused for stock forecasting with the prediction accuracy of 79.3%, 77.9% and 74.6%, respectively. The experimental results demonstrate the better prediction performance of T-DBN model in comparison with DBN and LSTM models.

Research on Detection and Defense Mechanisms of DoS Attacks Based on BP Neural Network and Game Theory

DoS (Denial of Service) attacks are becoming one of the most serious security threats to global networks. We analyze the existing DoS detection methods and defense mechanisms in depth. In this paper, BP (back propagation) neural networks and game theory are introduced to design detection methods and defense mechanisms for the DoS attacks. The BP neural network DoS attacks detection model uses KDDCUP99 as the dataset and selects multiple feature vectors from the dataset that can efficiently identify DoS attacks by large-scale training, which improves the accuracy of detecting DoS attacks to 99.977%. Furthermore, we use game theory to perform secondary analysis on DoS attacks that are not recognized by the neural network model, so that the detection rate of Dos attacks increases from 99.97% to 99.998%. Finally, we propose a DoS attacks defense strategy based on game theory. The simulation results show that the proposed detection method and defense strategy are effective for DoS attacks.

Constitution Identification System for Traditional Chinese Medicine (TCM) Based on Correlation Between TCM Constitution and Physical Examination Indices

ABSTRACT Objective Identification of one’s constitution based on a combination of features and back propagation neural network theory is needed in modern medicine and traditional Chinese medicine (TCM). We describe a method to identify one’s constitution based on TCM constitution classification and a physical index model. Methods We created a constitution identification system based on neural network using Visio Studio development tool. We report the initial implementation of the system, the accuracy of which was verified using actual data. Results We found a relatively strong correlation between TCM constitution and physical indicators. Conclusion Finally, our report describes a possible application of the proposed system.

A Hybrid NIDS Model Using Artificial Neural Network and D-S Evidence

Artificial Neural Networks (ANNs), especially back-propagation (BP) neural network, can improve the performance of intrusion detection systems. However, for the current network intrusion detection methods, the detection precision, especially for low-frequent attacks, detection stability and training time are still needed to be enhanced. In this paper, a new model which based on optimized BP neural network and Dempster-Shafer theory to solve the above problems and help NIDS to achieve higher detection rate, less false positive rate and stronger stability. The general process of the authors' model is as follows: firstly dividing the main extracted feature into several different feature subsets. Then, based on different feature subsets, different ANN models are trained to build the detection engine. Finally, the D-S evidence theory is employed to integration these results, and obtain the final result. The effectiveness of this method is verified by experimental simulation utilizing KDD Cup1999 dataset.

Performance and Modeling of a Pilot-Scale Up-Flow Anaerobic Sludge Blanket (UASB) Treating Pharmaceutical Wastewater Containing Berberine

A pilot-scale test was conducted with an up-flow anaerobic sludge blanket (UASB) treating pharmaceutical wastewater containing berberine. The aim of this study was to investigate the performance of UASB in the condition of a high chemical oxygen demand (COD) loading rate from 4.64 to 8.68 kg/m3d and a wide berberine concentration from 254 to 536 mg/L, in order to provide a reference for treating the similar pharmaceutical wastewater containing berberine. The results demonstrated that the UASB average percentage reduction in COD and berberine 68.14% and 57.39%, respectively. Granular sludge was formed during this process. In addition, a model, built on the back propagation neural network (BPNN) theory and linear regression techniques was developed for the simulation of the UASB system performance in the biodegradation of pharmaceutical wastewater containing berberine. The average errors of COD and berberine were -0.55% and 0.24%, respectively. The results indicated that this model built on the BPNN theory was well-fitted to the detected data, and was able to simulate and predict the removal of COD and berberine by UASB reactor.

An Improved Prediction Model based on Fuzzy-rough Set Neural Network

After the brief review of the basic principles and characteristics of BP (back-propagation) neural network and rough set theory, a novel artificial neural network model based on fuzzy-rough set is proposed in this paper, which is suitable for nonlinear regression to achieve the precise prediction result by introducing improved rough set to obtain minimal attribute set to solve the optimized problem of input layer. Compared to the normal prediction model, the feasibility and effectiveness of the proposed model is verified by a practical case study of the mine gas emission prediction.

Performance and model of a full-scale up-flow anaerobic sludge blanket (UASB) to treat the pharmaceutical wastewater containing 6-APA and amoxicillin

A full-scale test was conducted with an up-flow anaerobic sludge blanket (UASB) pre-treating pharmaceutical wastewater containing 6-aminopenicillanic acid (6-APA) and amoxicillin. The aim of the study is to investigate the performance of UASB in the condition of a high chemical oxygen demand (COD) loading rate from 12.57 to 21.02 kg m −3 d −1 and a wide pH from 5.57 to 8.26, in order to provide a reference for treating the similar chemical synthetic pharmaceutical wastewater containing 6-APA and amoxicillin. The results demonstrated that the UASB average percentage reduction in COD, 6-APA and amoxicillin were 52.2%, 26.3% and 21.6%, respectively. In addition, three models, built on the back propagation neural network (BPNN) theory and linear regression techniques were developed for the simulation of the UASB system performance in the biodegradation of pharmaceutical wastewater containing 6-APA and amoxicillin. The average error of COD, 6-APA and amoxicillin were −0.63%, 2.19% and 5.40%, respectively. The results indicated that these models built on the BPNN theory were well-fitted to the detected data, and were able to simulate and predict the removal of COD, 6-APA and amoxicillin by UASB.