Even though my histogram ratio attribute was a good classifier for kidnap activity, I struggled to train my neural net to identify the calculation. I wasn't doing much on the neural net's internal structure, however - I was letting Matlab handle most of it, and setting the initial layer to 15 neurons. I probably should have been more strategic about the neural net's layers if I wanted to improve my results.
I learned a valuable lesson by discussing my problem with my research advisor. The fact that I could perform a calculation on the histogram of the particle filter particle weights and label the results as 1 or 0 means that I'm imposing my own (unnecessary) limits on the problem (that the ratio of the tallest to 2nd tallest histograms is the solution). If I instead give the neural network the raw histogram bin data, the neural network will have more flexibility to find its own version of the relationship between the histogram bin heights that are assigned to "Kidnap" and "Normal" events.
Now, my dataset consists of 10 variables - the heights of each of the 10 histogram bins that correspond to the weights of the particles in the particle filter.
No comments:
Post a Comment