search

nalmadi / EMIP-Toolkit

EMIP Toolkit (EMTK): A Python Library for Processing Eye Movement in Programming Data
16 stars 22 forks source link

Add more fixation detection methodS #45

Open hatran22 opened 2 years ago

hatran22 commented 2 years ago

Hi @nalmadi, Ideally we want to provide users with more fixation detection methods. Other than the dispersion-based, we can, for example, use the 10 methods benchmarked in this paper https://link.springer.com/content/pdf/10.3758/s13428-016-0738-9.pdf. Also it would be useful if we can add more documents for this one.

nalmadi commented 2 years ago

Great suggestion, Tran! Here are more documents and resources for this one: Python implementation: https://github.com/dcnieho/I2MC_Python

paper: https://link.springer.com/article/10.3758/s13428-016-0822-1

@hatran22 do you want to port I2MC to EMIP Toolkit? This would be a great extension! :)

hatran22 commented 2 years ago

Sounds great! I will try to implement this

nalmadi commented 2 years ago

Great! It is already implemented, it just needs to be ported to EMTK (make sure you add a comment referencing the original implementation)

hatran22 commented 2 years ago

We will add 5 more fixation-saccade detection methods and refactoring those. For extension I will port the I2MC. Hope these will be useful!

nalmadi commented 2 years ago

That would be great! Thanks!

hatran22 commented 2 years ago

62 Here is our implementation. There is still room for improvement, so please let me know what else we can do!

Thank you so much

nalmadi commented 2 years ago

Excellent work! The code looks great, can you make a Jupyter notebook to run/test the different classifiers and show how they perform?

Also, I think you are 4 commits behind main, can you pull from main again?

Let's put all the code for classifiers in a new directory called "classifiers." We have plans to split the code up, and that would make it easier for us.

Also, let's meet on Zoom for 20 minutes this week or the next to discuss your work. I think you guys did an excellent job, we just need to clean it up a bit, test it, then merge it.

Thanks for your hard work!

hatran22 commented 2 years ago

I am glad that you like it! We can definitely meet this week - I am available on the 29th, and we can meet whenever is convenient for you . In the meantime, I will add a Jupyter notebook for the sake of demonstration.

hatran22 commented 2 years ago

@nalmadi I am also available on the 28th, before noon!