.net 插件式开发——实现web框架中大数据算法嵌入(BP算法逼近)
- 关于算法的引入:插件式架构设计,可移植性强,利于算法的升级。
【插件式开发相关资料】https://www.cnblogs.com/lenic/p/4129096.html
- 以BP算法为例:
1、首先定义一个接口规范
/// <summary> /// //插件的统一入口 /// </summary> public interface IPluginPerfrom { /// <summary> /// 统一算法插件入口 /// </summary> /// <param name="argsOutNumber">输出参数的个数</param> /// <param name="argsOut">输出参数</param> /// <param name="argsIn">输入参数</param> /// <returns></returns> string ExcuteAlgorithmPlug(int argsOutNumber, ref string[,] argsOut, string[,] argsIn, string DBConnectionString = null); }
2、BP算法实现接口
// AForge Framework // Approximation using Mutli-Layer Neural Network // // Copyright ?Andrew Kirillov, 2006 // andrew.kirillov@gmail.com // using System; using System.Drawing; using System.Collections; using System.Collections.Generic; using System.ComponentModel; using System.Data; using System.Windows.Forms; using AForge; using AForge.Neuro; using AForge.Neuro.Learning; using AForge.Controls; using IPlugin; using Newtonsoft.Json; using System.Linq; using System.Text; namespace BP { /// <summary> /// Summary description for Form1. /// </summary> public class BP : IPluginPerfrom { //Chart chart = new Chart(); //实现统一接口 public string ExcuteAlgorithmPlug(int argsOutNumber, ref string[,] argsOut, string[,] argsIn, string DBConnectionString = null) { List<ResPreTemp> resLists = new List<ResPreTemp>(); string dataStr = argsIn[0, 0]; //Json格式的数据 List<dht11> dht11Lists = dataStr.ToList<dht11>(); double[,] arr = new double[dht11Lists.Count+1, 2]; for (int i = 0; i <dht11Lists.Count; i++) { TimeSpan t3 = dht11Lists[i].create_time - dht11Lists[0].create_time; // double getMillisecond = t3.TotalMilliseconds; ////将这个天数转换成毫秒, 返回值是double类型的 double dobleTime = t3.TotalSeconds; arr[i, 0] = dobleTime; arr[i, 1] = dht11Lists[i].temperature; } int outPutLength = 0; double[,] res = null; try { res = SearchSolution(arr); ResPreTemp resTemp = new ResPreTemp(dht11Lists[0].create_time, res[0, 1]); resLists.Add(resTemp); for (int i = 0; i <dht11Lists.Count; i++) { DateTime dataTimeX = dht11Lists[i].create_time.AddSeconds(res[i+1,0]); ResPreTemp resTemp1 = new ResPreTemp(dataTimeX, res[i + 1, 1]); resLists.Add(resTemp1); } } catch (Exception e) { throw e; } return Json.ToJson(resLists); } //返回的结果类 public class ResPreTemp { public DateTime create_time; public double temperature; public ResPreTemp(DateTime create_time, double temperature) { this.create_time = create_time; this.temperature = temperature; } } //private double learningRate = Convert.ToDouble( Config.learningRate); //private double momentum = Convert.ToDouble(Config.momentum); //private double sigmoidAlphaValue = Convert.ToDouble(Config.sigmoidAlphaValue); //private int neuronsInFirstLayer = Convert.ToInt32(Config.neuronsInFirstLayer); //private int iterations = 1000; private double learningRate =0.1; private double momentum = 0.0; private double sigmoidAlphaValue =2.0; private int neuronsInFirstLayer = 20; private int iterations = 1000; //private Thread workerThread = null; private bool needToStop = false; #region /// <summary> /// 开始预测 /// </summary> /// <param name="learningRateRow">学习速率</param> /// <param name="momentumRow"></param> /// <param name="alphaRaw">alpha值</param> /// <param name="neuronsRow">神经元的个数</param> /// <param name="iterationsRow">迭代次数</param> /// <returns></returns> private void startApproximation(string learningRateRow, string momentumRow, string alphaRaw, string neuronsRow, string iterationsRow) { // get learning rate #region 神经网络参数 try { learningRate = Math.Max(0.00001, Math.Min(1, double.Parse(learningRateRow))); } catch { learningRate = 0.1; } // get momentum try { momentum = Math.Max(0, Math.Min(0.5, double.Parse(momentumRow))); } catch { momentum = 0; } // get sigmoid's alpha value try { sigmoidAlphaValue = Math.Max(0.001, Math.Min(50, double.Parse(alphaRaw))); } catch { sigmoidAlphaValue = 2; } // get neurons count in first layer try { neuronsInFirstLayer = Math.Max(5, Math.Min(50, int.Parse(neuronsRow))); } catch { neuronsInFirstLayer = 20; } // iterations try { iterations = Math.Max(0, int.Parse(iterationsRow)); } catch { iterations = 1000; } #endregion needToStop = false; //double[,] solution = SearchSolution(); // return data; } #endregion public double[,] SearchSolution(double[,] data) { // number of learning samples int samples = data.GetLength(0); // data transformation factor double maxX = Caculate.getMax(data,0); double minX = Caculate.getMin(data, 0); double LengthX = maxX - minX; double maxY = Caculate.getMax(data, 1); double minY = Caculate.getMin(data, 1); double LengthY = maxY - minY; double yFactor = 1.7 / LengthY; //ymax-ymin double yMin = minY; double xFactor = 2.0 / LengthX; double xMin = minX; // prepare learning data double[][] input = new double[samples][]; double[][] output = new double[samples][]; for (int i = 0; i < samples; i++) { input[i] = new double[1]; output[i] = new double[1]; // set input input[i][0] = (data[i, 0] - xMin) * xFactor - 1.0; // set output output[i][0] = (data[i, 1] - yMin) * yFactor - 0.85; } // create multi-layer neural network ActivationNetwork network = new ActivationNetwork( new BipolarSigmoidFunction(sigmoidAlphaValue), 1, neuronsInFirstLayer, 1); // create teacher BackPropagationLearning teacher = new BackPropagationLearning(network); // set learning rate and momentum teacher.LearningRate = learningRate; teacher.Momentum = momentum; // iterations int iteration = 1; // solution array double[,] solution = new double[data.GetLength(0)+1, 2]; double[] networkInput = new double[1]; // calculate X values to be used with solution function for (int j = 0; j < data.GetLength(0) + 1; j++) { solution[j, 0] = minX + (double)j * LengthY / data.GetLength(0) + 1; } // loop while (!needToStop) { // run epoch of learning procedure:学习过程的运行过程 double error = teacher.RunEpoch(input, output) / samples; // calculate solution:预测 for (int j = 0; j < data.GetLength(0) + 1; j++) { networkInput[0] = (solution[j, 0] - xMin) * xFactor - 1.0; solution[j, 1] = (network.Compute(networkInput)[0] + 0.85) / yFactor + yMin; } // calculate error double learningError = 0.0; for (int j = 0, k = data.GetLength(0); j < k; j++) { networkInput[0] = input[j][0]; learningError += Math.Abs(data[j, 1] - ((network.Compute(networkInput)[0] + 0.85) / yFactor + yMin)); } // increase current iteration iteration++; // check if we need to stop if ((iterations != 0) && (iteration > iterations)) break; } return solution; } } }
注:以上的BP算法为BP算法的函数逼近,下一步是需要将BP的学习训练网络与预测过程分离,即实时进行学习训练,按任务的指定进行预测。
【BP通过反向传递误差来调整网络参数】
BP函数逼近算法通过最速下降法,通过反向传播不断调整网络的权值和阈值,不断地降低网络的误差,使得误差平方和最小。
BP神经网络模型包括输入层、隐含层和输出层。 输入层各神经网络负责接收来自外界的输入信息,并传递给中间层各神经元;中间层是内部信息处理层,负责信息变换,根据信息变化能力的需求。最后中间层可将信息传递到输出层。输出层输出期望值,经过一次迭代后,发现输出值与预期值的误差太大,则再次进入误差的反向传播过程。重复以上过程,调整各层的权值,知道BP网络的输出值的误差在可接受的范围内,则停止训练。网络学习过程结束。
【BP算法的具体步骤】
1、前馈计算
设置隐层的j个节点的输入和输出 I = f(Wij),O=f(Ij),其中f(Ij)为激励函数。
2、权值调整
设置误差函数Ep
调整输出层的权值
调整隐层的权值