Skip to content

Latest commit

 

History

History
21 lines (14 loc) · 956 Bytes

File metadata and controls

21 lines (14 loc) · 956 Bytes

Prediction-using-Bayesian-Neural-Network

Prediction of continuous signals data and object tracking data using dynamic Bayesian neural network. Compared with other network architectures aswell.

Software Required

  • Matlab 2016a and above

Data used

Two types of data were used and code for them is slightly different

  • Firstly tested network on continous time series data (Wave Signals)
  • Second data set was Object tracking data from a webcam

Running Code

Run the Matlab (.m) file from the algorithm folder you wish to see. Free to change the parameters for training and testing data, change the amount of hidden activation units in a neural network depending on your system performance.

It generates Error performance files and the Network interface generates the results.

Credits

Salam Ismaeel for helpful tips.

Jason for providing the Object Tracking Data on our NSERC Project.