Java实现的隐马尔科夫模型中前向、后项和维特比算法.docx

packagecom.HMM.test;public class HMM {protected int N;//状态数protected int M;//观察符号数protected double[][] A;//状态转移概率protected double[][] B;//符号观测概率protected double[] PI;//初始状态概率分布public HMM(){};//参数1 状态数目；参数2 观察符号数目public HMM(intstateNum,intobservationSymbolNum){N=stateNum;M=observationSymbolNum;A=new double[N][N];B=new double[N][M];PI=new double[N];}}//前向算法packagecom.HMM.test;public class Forward extends HMM{public Forward(intstateNum,intobservationSymbolNum){super(stateNum,observationSymbolNum);}//ob是已知的观察序列；返回结果是观察序列的概率public double forward(int[] ob){double[][] alpha = null;return forward(ob,alpha);}//ob:已知的观察序列；alpha：输出中间结果，局部概率；返回观察序列的概率public double forward(int[] ob,double[][] alpha){alpha=new double[ob.length][N];//1.初始化，计算初始时刻所有状态的局部概率System.out.println(1.初始化：);for(inti=0;iN;i++){alpha[0][i]=PI[i]*B[i][ob[0]];System.out.println(alpha[0][+i+]:+alpha[0][i]);}//2.归纳，递归计算每个时间点的局部概率System.out.println(2.归纳：);for (inti = 1; i ob.length; i++)//从第一个观测值开始循环， { for (int j = 0; j N; j++)//对于每个状态 {double sum = 0;for (int k = 0; k N; k++) {sum += alpha[i - 1][k] * A[k][j]; }alpha[i][j] = sum * B[j][ob[i]];System.out.println(alpha[+i+][+j+]:+alpha[i][j]); } }//3.终止，观察序列的概率等于最终时刻所有局部概率之和String s=P(red,yellow,blue)=;System.out.println(3.终止，求和：);double probability = 0;for (inti = 0; i N; i++) {probability += alpha[ob.length - 1][i];s+=alpha[+(ob.length - 1)+][+i+];if(i!=N-1)s+=+; }System.out.println(s+=+probability);return probability;}}//后项算法packagecom.HMM.test;public class Backward extends HMM{public Backward(intstateNum,intobservationSymbolNum){super(stateNum,observationSymbolNum);}//ob已知的观察序列public double backward(int[] ob) { double[][] beta = null; // 只声明，不定义return backward(ob, beta); }//ob已知的观察序列；beta 后向变量；返回观测序列的概率public double backward(int[] ob,double[][] beta) { beta = new double[ob.length][N]; // 初始化System.out.println(1.初始化：);for (inti =