Classification prediction | MATLAB implements GWO-BiLSTM-Attention multi-input classification prediction

Classification prediction | MATLAB implements GWO-BiLSTM-Attention multi-input classification prediction

predictive effect

basic introduction

1. GWO-BiLSTM-Attention data classification prediction program
2. Code description: Data classification prediction program based on Gray Wolf Optimization Algorithm (GWO), bidirectional long-term short-term memory network (BiLSTM) and attention mechanism.
Program platform: Matlab version 2023 and above are required.
Features:
1. Multi-line variable feature input.
2. GWO optimizes the learning rate, the number of neurons and other parameters, which is convenient for adding dimensions and optimizing other parameters. (If the accuracy of the first round is the highest, the fitness curve is a horizontal straight line)
3. It is suitable for the identification, diagnosis and classification of bearing faults, transformer oil and gas faults, power system transmission line fault areas, insulators, distribution networks and other fields.
4. The data can be directly replaced and imported using the EXCEL form without greatly modifying the program. There are detailed comments inside the code, which is easy to understand the operation of the program.

programming

• Complete program and data acquisition method 1: program exchange of equal value;
• Complete program and data acquisition method 2: private message bloggers reply to MATLAB to achieve GWO-BiLSTM-Attention multi-input classification prediction acquisition.

%%  划分训练集和测试集
P_train = res(1: num_train_s, 1: f_)';
T_train = res(1: num_train_s, f_ + 1: end)';
M = size(P_train, 2);

P_test = res(num_train_s + 1: end, 1: f_)';
T_test = res(num_train_s + 1: end, f_ + 1: end)';
N = size(P_test, 2);

%%  数据归一化
[p_train, ps_input] = mapminmax(P_train, 0, 1);
p_test = mapminmax('apply', P_test, ps_input);

[t_train, ps_output] = mapminmax(T_train, 0, 1);
t_test = mapminmax('apply', T_test, ps_output);
%%  个体极值和群体极值
[fitnesszbest, bestindex] = min(fitness);
zbest = pop(bestindex, :);     % 全局最佳
gbest = pop;                   % 个体最佳
fitnessgbest = fitness;        % 个体最佳适应度值
BestFit = fitnesszbest;        % 全局最佳适应度值

%%  迭代寻优
for i = 1 : maxgen
    for j = 1 : sizepop
        
        % 速度更新
        V(j, :) = V(j, :) + c1 * rand * (gbest(j, :) - pop(j, :)) + c2 * rand * (zbest - pop(j, :));
        V(j, (V(j, :) > Vmax)) = Vmax;
        V(j, (V(j, :) < Vmin)) = Vmin;
        
        % 种群更新
        pop(j, :) = pop(j, :) + 0.2 * V(j, :);
        pop(j, (pop(j, :) > popmax)) = popmax;
        pop(j, (pop(j, :) < popmin)) = popmin;
        
        % 自适应变异
        pos = unidrnd(numsum);
        if rand > 0.95
            pop(j, pos) = rands(1, 1);
        end
        
        % 适应度值
        fitness(j) = fun(pop(j, :), hiddennum, net, p_train, t_train);

    end
    
    for j = 1 : sizepop

        % 个体最优更新
        if fitness(j) < fitnessgbest(j)
            gbest(j, :) = pop(j, :);
            fitnessgbest(j) = fitness(j);
        end

        % 群体最优更新 
        if fitness(j) < fitnesszbest
            zbest = pop(j, :);
            fitnesszbest = fitness(j);
        end

    end

    BestFit = [BestFit, fitnesszbest];    
end
————————————————
版权声明：本文为CSDN博主「机器学习之心」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/kjm13182345320/article/details/130462492

References

[1] https://blog.csdn.net/kjm13182345320/article/details/129679476?spm=1001.2014.3001.5501
[2] https://blog.csdn.net/kjm13182345320/article/details/129659229?spm=1001.2014.3001.5501
[3] https://blog.csdn.net/kjm13182345320/article/details/129653829?spm=1001.2014.3001.5501