Skip to content

Prediction of expertise level from BPMN models

Notifications You must be signed in to change notification settings

delas/ExpertisePredictor4BPMN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

36 Commits
 
 
 
 
 
 

Repository files navigation

Prediction of expertise level from BPMN models

Fully automatic, un-obtrusive, tool independent approach to predict the expertise level of modeler, based on the BPMN artifacts they draw.

Current implementation uses a feed-forward neural network, with one hidden layer comprising 50 neurons. The input layer contains 10 neurons, one for each feature of the vectorial representation of the model. The output layer contains 1 neuron, whose value distinguishes between the two classes (i.e., novice or expert).

The multilayer perceptron was trained with a learning rate of 0.3 and a learning momentum of 0.2. Additionally, we set the number of training epochs to 500.

About

Prediction of expertise level from BPMN models

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages