Skip to content
/ LSTM Public

Using LSTM and Informer to train AI models with stoke therapist and patient's data

Notifications You must be signed in to change notification settings

zeyangz2/LSTM

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

28 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LSTM for therapist trajectory prediction

train LSTM with stroke therapist and patient data

We collected some sample data in data file to train the network.

Feel free to change the hyperparameters in config_1.json. Recommand to directly use config_2.json, since the hyperparameters are fine-tuned by Zeyang.

Uncomment the lines in run.py to save your predicted results.

Use this jupyter notebook to get a 3D graph of predicted trajectory. You can use the results I got from file: saved test&predict results Open In Colab

Since LSTM is good for point by point prediction but not good for long sequence prediction, we use another model called Informer to do long sequence prediction. Open In Colab

To use Informer, you must need to add a date column and put the feaeture that you want to predict to the rightmost column in your data file(.scv file). Right now, Informer gives proper predicted results but still not good enough.

Make sure to edit the sample data in trial2.csv before using Informer to train the network.

Architecture of new LSTM model

(the number of inputs given to the model could change depending on the number of inputs we want to use to train the model):

4360afb28290abd2a1b6080a8f3a115

results from trial2.csv:

red line for ground truth and green line for our prediction

3D result

z_axis:

result_z

z_axis model loss:

Model Loss z

y_axis:

results_y

y_axis model loss:

Model Loss y

x_axis:

results_x

x_axis model loss:

Model Loss x

results from srikar and zeyang_1.csv:

red line for ground truth and green line for our prediction

37598975822b4d1736266b1c8c183d3

z_axis:

new result z

z_axis model loss:

new Model Loss z

y_axis:

new result y

y_axis model loss:

new Model Loss y

x_axis:

new result x

x_axis model loss:

new Model Loss x

more updates later...

About

Using LSTM and Informer to train AI models with stoke therapist and patient's data

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published