this is for holding javascript data
Daniel Stanley Tan edited We_experimented_on_training_a__.tex
over 8 years ago
Commit id: de4cff418698e34bc5a5cc2636cbe9a5efcda76c
deletions | additions
diff --git a/We_experimented_on_training_a__.tex b/We_experimented_on_training_a__.tex
index 7e8403c..6e35322 100644
--- a/We_experimented_on_training_a__.tex
+++ b/We_experimented_on_training_a__.tex
...
We experimented on training a Support Vector Machine (SVM) classifier on the different values of $k$. Table \ref{tab:svmTable} shows the performance of the SVM classifier.
The values were computed from a 10-fold cross validation. At $k=2$, the SVM classifier had a low accuracy. Poor segmentation of the images during the clustering step affected the classifier leading to a low accuracy. Increasing $k$ to 3 and 4 significantly improved the results, having up to 82.2\% and 85.8\% accuracy respectively. We tried to see how much the classifier would improve by having more clusters, but even after doubling the value of $k$ the accuracy only increased by 1.3\%. Figure \ref{fig:accuracyxk} plots the accuracy as a function of $k$. It shows that increasing $k$ further would have minimal effect on the accuracy of the classifier.
Since the infected part of the cacao pods tend to be colored dark red to brown, the SVM classifier confuses the healthy reddish colors as infected. ...