1 簡介
為實作精準施肥"減施增效"的數字化農業施肥技術,本文基于并運用了麻雀搜索演算法,對廣義回歸神經網路(GRNN)進行了結合與改進,并構建作物廣義回歸神經網路(GRNN)結合麻雀搜索演算法的預測施肥量模型.通過采集得到的資料樣本會被用來輸入MATLAB進行仿真和實驗驗證.仿真和實驗結果表明,基于麻雀搜索演算法的GRNN神經網路模型比BP神經網路具有更少的輸入引數,能更好地反映施肥量與諸多影響因素之間的關系,具有實用價值.且基于麻雀搜索演算法改進的GRNN神經網路演算法模型人為設定量更少,更為客觀,預測值與實際值之間的誤差更小,預測結果更加準確.
2 部分代碼
%_________________________________________________________________________%
% 麻雀優化演算法 %
%_________________________________________________________________________%
function [Best_pos,Best_score,curve]=SSA(pop,Max_iter,lb,ub,dim,fobj)
ST = 0.6;%預警值
PD = 0.7;%發現者的比列，剩下的是加入者
SD = 0.1;%意識到有危險麻雀的比重
PDNumber = round(pop*PD); %發現者數量
SDNumber = round(pop*SD);%意識到有危險麻雀數量
if(max(size(ub)) == 1)
ub = ub.*ones(1,dim);
lb = lb.*ones(1,dim);
end
%種群初始化
X0=initialization(pop,dim,ub,lb);
X = X0;
%計算初始適應度值
fitness = zeros(1,pop);
for i = 1:pop
fitness(i) = fobj(X(i,:));
end
[fitness, index]= sort(fitness);%排序
BestF = fitness(1);
WorstF = fitness(end);
GBestF = fitness(1);%全域最優適應度值
for i = 1:pop
X(i,:) = X0(index(i),:);
end
curve=zeros(1,Max_iter);
GBestX = X(1,:);%全域最優位置
X_new = X;
for i = 1: Max_iter
BestF = fitness(1);
WorstF = fitness(end);
R2 = rand(1);
for j = 1:PDNumber
if(R2<ST)
X_new(j,:) = X(j,:).*exp(-j/(rand(1)*Max_iter));
else
X_new(j,:) = X(j,:) + randn()*ones(1,dim);
end
end
for j = PDNumber+1:pop
% if(j>(pop/2))
if(j>(pop - PDNumber)/2 + PDNumber)
X_new(j,:)= randn().*exp((X(end,:) - X(j,:))/j^2);
else
%產生-1，1的亂數
A = ones(1,dim);
for a = 1:dim
if(rand()>0.5)
A(a) = -1;
end
end
AA = A'*inv(A*A');
X_new(j,:)= X(1,:) + abs(X(j,:) - X(1,:)).*AA';
end
end
Temp = randperm(pop);
SDchooseIndex = Temp(1:SDNumber);
for j = 1:SDNumber
if(fitness(SDchooseIndex(j))>BestF)
X_new(SDchooseIndex(j),:) = X(1,:) + randn().*abs(X(SDchooseIndex(j),:) - X(1,:));
elseif(fitness(SDchooseIndex(j))== BestF)
K = 2*rand() -1;
X_new(SDchooseIndex(j),:) = X(SDchooseIndex(j),:) + K.*(abs( X(SDchooseIndex(j),:) - X(end,:))./(fitness(SDchooseIndex(j)) - fitness(end) + 10^-8));
end
end
%邊界控制
for j = 1:pop
for a = 1: dim
if(X_new(j,a)>ub(a))
X_new(j,a) =ub(a);
end
if(X_new(j,a)<lb(a))
X_new(j,a) =lb(a);
end
end
end
%更新位置
for j=1:pop
fitness_new(j) = fobj(X_new(j,:));
end
for j = 1:pop
if(fitness_new(j) < GBestF)
GBestF = fitness_new(j);
GBestX = X_new(j,:);
end
end
X = X_new;
fitness = fitness_new;
%排序更新
[fitness, index]= sort(fitness);%排序
BestF = fitness(1);
WorstF = fitness(end);
for j = 1:pop
X(j,:) = X(index(j),:);
end
curve(i) = GBestF;
end
Best_pos =GBestX;
Best_score = curve(end);
end
3 仿真結果
4 參考文獻
[1]倪賢達, 楊得航, 左桐,等. 基于遺傳演算法改進GRNN神經網路的施肥量預測研究[J]. 2020.
[2]印雷, 顧德, & 劉飛. (2021). 基于改進麻雀搜索演算法優化的dv-hop定位演算法. 傳感技術學報, 34(5), 6.
部分理論參考網路文獻，若有侵權聯系博主洗掉，
轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/395015.html
標籤：AI
上一篇：自學Seurat的一點記錄