so I'm working on a Project where I want to predict the Vehicle Position from the Vehicle Data like speed, acceleration etc.. now the data that I have comes also with a timestamp for each sample ( I mean that I have also a timestamp feature).

at first I thought that I should get rid of that timestamp feature because it is not relevant to my Project, I mean logically, I will not need a timestamp feature to predict the vehicle position, that didn't make sense to me when I first took a look at the dataset. I thought other features like speed, acceleration, braking pressure etc.. are more important and I thought also that the solution for this Problem would be to use a normal Deep NN or RBFNN for making this Prediction. recently, I read some papers that shows how a Convolutional NN can be also used for regression and that confused me to choose the Architecture needed for my Project. this Week I also watched a Tutorial where a RNN/ LSTM was implemented for regression Tasks.

Now I'm very confused which architecture should I use for my Project. I also noticed that maybe if I used that timestamp feature, I can maybe use an RNN/LSTM Network for this Task but I don't know if my dataset can be seen as time-series dataset, actually the vehicle position doesn't depend on the time as far as I can tell.

Hopefully can someone answer me based on Experience. It would be also great to have some Papers or references where I can look for more.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.