how to calculate classification accuracy

Question

Reen Blake-Carr 2020-10-3

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/604447-how-to-calculate-classification-accuracy

回答： Athul Prakash 2020-10-9

Hi i am using a fuzzy ifnerence system that i have built using matlab but i am looking to compare the classification accuracy to a deicision tree and i have no idea how tp calculate the classification accuracy of the fuzzy inference system i have the outout from the eval function use but where i have searched doesnt seem to provide me ith any answers to how to calculate the classification accuracy of the fuzzy inference system any help would be appreciated.

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Athul Prakash 2020-10-9

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/604447-how-to-calculate-classification-accuracy#answer_509461

在 MATLAB Online 中打开

Hi Reen,

I'm not sure which method you want to use for calculating an accuracy value, but here's one approach we may try:

% output= evalfis(fis, input);
pred = round(output);
acc_count = nnz(pred==input); 
acc = acc_count/length(input);

Essentially, I'm considering round values of the fuzzy system as the predictions obtained and then counting the number of correct predictions over the total number of inputs.

I think you could also use different functions, such as log or tanh, instead of rounding your predictions - that would be another kind of accuracy metric.

Hope it helps!