Research on a Fog Computing Architecture and BP Algorithm Application for Medical Big Data

Although the Internet of Things has been widely applied,the problems of cloud computing in the application of digital smart medical Big Data collection,processing,analysis,and storage remain,especially the low efficiency of medical diagnosis.And with the wide application of the Internet of Things and Big Data in the medical field,medical Big Data is increasing in geometric magnitude resulting in cloud service overload,insufficient storage,communication delay,and network congestion.In order to solve these medical and network problems,a medical big-data-oriented fog computing architec-ture and BP algorithm application are proposed,and its structural advantages and characteristics are studied.This architecture enables the medical Big Data generated by medical edge devices and the existing data in the cloud service center to calculate,compare and analyze the fog node through the Internet of Things.The diagnosis results are designed to reduce the business processing delay and improve the diagnosis effect.Considering the weak computing of each edge device,the artificial intelligence BP neural network algorithm is used in the core computing model of the medical diagnosis system to improve the system computing power,enhance the medical intelligence-aided decision-making,and improve the clinical diagnosis and treatment efficiency.In the application process,combined with the characteristics of medical Big Data technology,through fog architecture design and Big Data technology integration,we could research the processing and analysis of heterogeneous data of the medical diagnosis system in the context of the Internet of Things.The results are promising:The medical platform network is smooth,the data storage space is sufficient,the data processing and analysis speed is fast,the diagnosis effect is remarkable,and it is a good assistant to doctors’treatment effect.It not only effectively solves the problem of low clinical diagnosis,treatment efficiency and quality,but also reduces the waiting time of patients,effectively solves the contradiction between doctors and patients,and improves the medical service quality and management level.

MENDED GENETIC BP NETWORK AND APPLICATION TO ROLLING FORCE PREDICTION OF 4-STAND TANDEM COLD STRIP MILL

In order to make good use of the ability to approach any function of BP (backpropagation) network and overcome its local astringency, and also make good use of the overallsearch ability of GA (genetic algorithms), a proposal to regulate the network's weights using bothGA and BP algorithms is suggested. An integrated network system of MGA (mended genetic algorithms)and BP algorithms has been established. The MGA-BP network's functions consist of optimizing GAperformance parameters, the network's structural parameters, performance parameters, and regulatingthe network's weights using both GA and BP algorithms. Rolling forces of 4-stand tandem cold stripmill are predicted by the MGA-BP network, and good results are obtained.

Neural network fault diagnosis method optimization with rough set and genetic algorithms

Aiming at the disadvantages of BP model in artificial neural networks applied to intelligent fault diagnosis, neural network fault diagnosis optimization method with rough sets and genetic algorithms are presented. The neural network nodes of the input layer can be calculated and simplified through rough sets theory; The neural network nodes of the middle layer are designed through genetic algorithms training; the neural network bottom-up weights and bias are obtained finally through the combination of genetic algorithms and BP algorithms. The analysis in this paper illustrates that the optimization method can improve the performance of the neural network fault diagnosis method greatly.

STUDY ON INJECTION AND IGNITION CONTROL OF GASOLINE ENGINE BASED ON BP NEURAL NETWORK

According to advantages of neural network and characteristics of operatingprocedures of engine, a new strategy is represented on the control of fuel injection and ignitiontiming of gasoline engine based on improved BP network algorithm. The optimum ignition advance angleand fuel injection pulse band of engine under different speed and load are tested for the samplestraining network, focusing on the study of the design method and procedure of BP neural network inengine injection and ignition control. The results show that artificial neural network technique canmeet the requirement of engine injection and ignition control. The method is feasible for improvingpower performance, economy and emission performances of gasoline engine.

The Application of BP Networks to Land Suitability Evaluation

The back propagation (BP) model of artificial neural networks (ANN) has many good qualities comparing with ordinary methods in land suitability evaluation.Through analyzing ordinary methods’ limitations,some sticking points of BP model used in land evaluation,such as network structure,learning algorithm,etc.,are discussed in detail,The land evaluation of Qionghai city is used as a case study.Fuzzy comprehensive assessment method was also employed in this evaluation for validating and comparing.

Establishment of constitutive relationship model for 2519 aluminum alloy based on BP artificial neural network

An isothermal compressive experiment using Gleeble 1500 thermal simulator was studied to acquire flow stress at different deformation temperatures, strains and strain rates. The artificial neural networks with the error back propagation(BP) algorithm was used to establish constitutive model of 2519 aluminum alloy based on the experiment data. The model results show that the systematical error is small(δ=3.3%) when the value of objective function is 0.2, the number of nodes in the hidden layer is 5 and the learning rate is 0.1. Flow stresses of the material under various thermodynamic conditions are predicted by the neural network model, and the predicted results correspond with the experimental results. A knowledge-based constitutive relation model is developed.

An Improved BP Algorithm and Its Application in Classification of Surface Defects of Steel Plate

Artificial neural network is a new approach to pattern recognition and classification. The model of multilayer perceptron （MLP） and back-propagation （BP） is used to train the algorithm in the artificial neural network. An improved fast algorithm of the BP network was presented, which adopts a singular value decomposition （SVD） and a generalized inverse matrix. It not only increases the speed of network learning but also achieves a satisfying precision. The simulation and experiment results show the effect of improvement of BP algorithm on the classification of the surface defects of steel plate.

Motion Control of Underwater Vehicle Based on Least Disturbance BP Algorithm

Up to now, some technology of neural networks are developed to solve the non-linearity of researched objects and to implement the adaptive control in many engineering fields, and some good results were achieved. Though it puts some questions over to design application structure with neural networks, it is really unknowable about the study mechanism of those. But, the importance of study ratio is widely realized by many scientists now, and some methods on the modification of that are provided. The main subject is how to improve the stability and how to increase the convergent rate of networks by defining a good form of the study ratio. Here a new algorithm named LDBP (least disturbance BP algorithm) is proposed to calculate the ratio online according to the output errors, the weights of network and the input values. The algorithm is applied to the control of an autonomous underwater vehicle designed by HEU. The experimental results show that the algorithm has good performance and the controller designed based on it is fine.

Coal mine safety production forewarning based on improved BP neural network

Firstly, the early warning index system of coal mine safety production was given from four aspects as per- sonnel, environment, equipment and management. Then, improvement measures which are additional momentum method, adaptive learning rate, particle swarm optimization algorithm, variable weight method and asynchronous learning factor, are used to optimize BP neural network models. Further, the models are applied to a comparative study on coal mine safety warning instance. Results show that the identification precision of MPSO-BP network model is higher than GBP and PSO-BP model, and MPSO- BP model can not only effectively reduce the possibility of the network falling into a local minimum point, but also has fast convergence and high precision, which will provide the scientific basis for the forewarnin~ management of coal mine safetv production.

Accelerating BP-Based Iterative Low-Density Parity-Check Decoding by Modified Vertical and Horizontal Processes

Two modified BP algorithms related to vertical and horizontal processes are proposed to accelerate iterative low-density parity- check （LDPC） decoding over an additive white Gaussian noise （AWGN） channel, where the newly updated extrinsic information is immediately used in the current decoding round. Theoretical analysis and simulation results demonstrate that both the modified approaches provide significant performance improvements over the traditional BP algorithm with almost no additional decoding complexity. The proposed algorithm with modified horizontal process offers even better performance than another algorithm with the modified horizontal process. The two modified BP algorithms are very promising in practical communications since both can achieve an excellent trade-off between the performance and decoding complexity.

Modeling of mechanical properties of as-cast Mg-Li-Al alloys based on PSO-BP algorithm

Artificial neural networks have been widely used to predict the mechanical properties of alloys in material research. This study aims to investigate the implicit relationship between the compositions and mechanical properties of as-cast Mg-Li-AI alloys. Based on the experimental collection of the tensile strength and the elongation of representative Mg-Li-AI alloys, a momentum back-propagation （BP） neural network with a single hidden layer was established. Particle swarm optimization （PSO） was applied to optimize the BP model. In the neural network, the input variables were the contents of Mg, Li and AI, and the output variables were the tensile strength and the elongation. The results show that the proposed PSO-BP model can describe the quantitative relationship between the Mg-Li-AI alloy＇s composition and its mechanical properties. It is possible that the mechanical properties to be predicted without experiment by inputting the alloy composition into the trained network model. The prediction of the influence of AI addition on the mechanical properties of as-cast Mg-Li-AI alloys is consistent with the related research results.

Fast Quantification of the Mixture of Polycyclic Aromatic Hydrocarbons Using Surface-Enhanced Raman Spectroscopy Combined with PLS-GA-BP Network

To realize the fast and accurate quantitative analysis of the mixture of polycyclic aromatic hydrocarbons(PAHs),surface-enhanced Raman spectroscopy(SERS)coupled with multivariate calibrations were employed.In this study,three kinds of calibration algorithms were used to quantitative analysis of the mixture of naphthalene(Nap),phenanthrene(Phe),and pyrene(Pyr).Firstly,partial least squares(PLS)algorithm was used to select characteristic variables,then the global search capability of genetic algorithm(GA)was used for the determining of the initial weights and thresholds of back propagation(BP)neural network so that local minima was avoided.The PLS-GA-BP model exhibited superiority to quantify PAHs mixture,which achieved R2=0.9975,0.9710,0.9643,ARE=10.07%,19.28%,16.72%and RMSE=13.10,5.40,5.10 nmol L−1 for Nap,Phe,Pyr(in the PAHs mixture)concentration prediction respectively.The forecast error,ARE and RMSE have been reduced more than 50%and 60%respectively compared with the whole spectral BP model.The study indicates that accurate quantitative spectroscopic analysis of the mixture of PAHs samples can be achieved through the combination of SERS technique and PLS-GA-BP algorithm.

Circle BP Algorithm for MLP Neural Network

A simple new BP algorithm named circle BP algorithm is introduced.With this algorithm,local minimums can be completely got rid of and learning speed can improve dramatically.It can be easily designed into the circuitry and advance further the application of MLP neural network .

Sub-pixel mapping method based on BP neural network

A new sub-pixel mapping method based on BP neural network is proposed in order to determine the spatial distribution of class components in each mixed pixel.The network was used to train a model that describes the relationship between spatial distribution of target components in mixed pixel and its neighboring information.Then the sub-pixel scaled target could be predicted by the trained model.In order to improve the performance of BP network,BP learning algorithm with momentum was employed.The experiments were conducted both on synthetic images and on hyperspectral imagery(HSI).The results prove that this method is capable of estimating land covers fairly accurately and has a great superiority over some other sub-pixel mapping methods in terms of computational complexity.

Application of genetic BP network to discriminating earthquakes and explosions

We developed a GA-BP algorithm by combining the genetic algorithm (GA) with the back propagation (BP) algorithm and established a genetic BP neural network. We also applied the BP neural network based on the BP algorithm and the genetic BP neural network based on the GA-BP algorithm to discriminate earthquakes and explosions. The obtained result shows that the discriminating performance of the genetic BP network is slightly better than that of the BP network.

Demarcation of potential seismic sources on integration of genetic algorithm and BP algorithm

In this paper potential seismic sources in coastal region of South China are identified by integration of genetic algorithm (GA) and back propagation (BP algorithm). GA is used for finding the best parameter combination rapidly in an infinite solution space for artificial neural networks (ANN). The results show that the distribution of potential seismic sources with different upper magnitude demarcated by this classifier is mostly satisfied the intrinsic relationship between seismic environment and earthquake occurrence, with less effect from subjective judgment of human being.

Sedimentary Micro-phase Automatic Recognition Based on BP Neural Network

In the process of geologic prospecting and development, it is important to forecast the distribution of gritstone, master the regulation of physical parameter in the reserves mass level. Especially, it is more important to recognize to rock phase and sedimentary circumstance. In the land level, the study of sedimentary phase and micro-phase is important to prospect and develop. In this paper, an automatic approach based on ANN (Artificial Neural Networks) is proposed to recognize sedimentary phase, the corresponding system is designed after the character of well general curves is considered. Different from the approach extracting feature parameters, the proposed approach can directly process the input curves. The proposed method consists of two steps: The first step is called learning. In this step, the system creates automatically sedimentary micro-phase features by learning from the standard sedimentary micro-phase patterns such as standard electric current phase curves of the well and standard resistance rate curves of the well. The second step is called recognition. In this step, based the results of the learning step, the system classifies automatically by comparing the standard pattern curves of the well to unknown pattern curves of the well. The experiment has demonstrated that the proposed approach is more effective than those approaches used previously.

The tool for building an NN based on improved BP algorithm

Back propagation (BP) algorithm is a very useful algorithm in many areas, but its leaning process is a very complicated non linear convergence process, in which, chaos often happens, and slow convergence speed and local least often make it difficult for the non experts to use it widely, and an improved BP (IBP) algorithm is therefore suggested to expedite the convergence speed. The algorithm can judge local least and take some steps automatically to jump out from the local least. Furthermore, this algorithm introduces the expert knowledge base. An IBP based agile and current neural network (NN) constructed tool is designed. An initial NN can be constructed automatically using an expert knowledge base. And an Aitken’s Δ 2 process method is used to expedite the convergent speed for NN. Besides, the method of changing the parameter of Sigmoid function and increasing the hidden node is used to bring surge for NN to jump out from the local

A Quantitative Seismic Topographic Effect Prediction Method Based upon BP Neural Network Algorithm and FEM Simulation

Topography can strongly affect ground motion,and studies of the quantification of hill surfaces’topographic effect are relatively rare.In this paper,a new quantitative seismic topographic effect prediction method based upon the BP neural network algorithm and three-dimensional finite element method(FEM)was developed.The FEM simulation results were compared with seismic records and the results show that the PGA and response spectra have a tendency to increase with increasing elevation,but the correlation between PGA amplification factors and slope is not obvious for low hills.New BP neural network models were established for the prediction of amplification factors of PGA and response spectra.Two kinds of input variables’combinations which are convenient to achieve are proposed in this paper for the prediction of amplification factors of PGA and response spectra,respectively.The absolute values of prediction errors can be mostly within 0.1 for PGA amplification factors,and they can be mostly within 0.2 for response spectra’s amplification factors.One input variables’combination can achieve better prediction performance while the other one has better expandability of the predictive region.Particularly,the BP models only employ one hidden layer with about a hundred nodes,which makes it efficient for training.

Neural network based method for compensating model error

Two traditional methods for compensating function model errors, the method of adding systematic parameters and the least-squares collection method, are introduced. A proposed method based on a BP neural network （called the H-BP algorithm） for compensating function model errors is put forward. The function model is assumed as y =f（x1, x2,… ,xn）, and the special structure of the H-BP algorithm is determined as （ n ＋ 1） ×p × 1, where （n ＋ 1） is the element number of the input layer, and the elements are xl, x2,…, xn and y＇ （ y＇ is the value calculated by the function model）; p is the element number of the hidden layer, and it is usually determined after many tests; 1 is the dement number of the output layer, and the element is △y = y0-y＇（y0 is the known value of the sample）. The calculation steps of the H-BP algorithm are introduced in detail. And then, the results of three methods for compensating function model errors from one engineering project are compared with each other. After being compensated, the accuracy of the traditional methods is about ± 19 mm, and the accuracy of the H-BP algorithm is ± 4. 3 mm. It shows that the proposed method based on a neural network is more effective than traditional methods for compensating function model errors.