Classification performance metrics:

You developed a classification model that uses images of damaged vehicles at accident sites to

estimate the location of the initial impact on the vehicle. The images are combined with infor$-$

mation from the vehicle $-$ speed and direction of the vehicle before the initial impact to classify

each damaged vehicle by location of initial impact. This classification will be used in determining

the cause of the accident. The classes are $\{$head$-$on$,$ rear$-$end, left$-$front, right$-$front, right$-$rear,

and left$-$rear$\}.$ Your model was validated by crash engineers with video footage from intersec$-$

tion traffic cameras. In total, $817$ vehicle crash cases were classified by your model. The follow$-$

ing are the results from your validated classification model:Classification performance metrics:

You developed a classification model that uses images of damaged vehicles at accident sites to

estimate the location of the initial impact on the vehicle. The images are combined with infor$-$

mation from the vehicle $-$ speed and direction of the vehicle before the initial impact to classify

each damaged vehicle by location of initial impact. This classification will be used in determining

the cause of the accident. The classes are head$-$on$,$ rear$-$end, left$-$front, right$-$front, right$-$rear,

and left$-$rear$\}.$ Your model was validated by crash engineers with video footage from intersec$-$

tion traffic cameras. In total, $817$ vehicle crash cases were classified by your model. The follow$-$

ing are the results from your validated classification model:

AME

$($a$)$ Create a confusion matrix for your classifier results:

$($b$)$ Compute the mean accuracy of your classification $($show your work$)$:

Mean Accuracy $=\frac{TP}{\text{T}\text{o}\text{t}\text{a}\text{l}}=$