Changes between Version 5 and Version 6 of ProjectSleep


Ignore:
Timestamp:
04/09/18 19:42:02 (7 years ago)
Author:
Monika Rizova
Comment:

--

Legend:

Unmodified
Added
Removed
Modified

  • ProjectSleep

    v5 v6  
    2222== '''Project Anatomy''' ==
    2323
    24 **Community**: !PyGaze community
     24**Community**: The lead developer and the contributors
    2525
    26 **Leadership**: Edwin Dalmaijer
     26**Leadership**: EtienneCmb - https://github.com/EtienneCmb
    2727
    28 **Forking**: Fork your own copy at this address https://github.com/esdalmaijer/PyGaze, for which you will need a !GitHub account.
     28**Forking**: Fork your own copy at this address https://github.com/EtienneCmb/visbrain/blob/master/docs/sleep.rst, for which you will need a !GitHub account.
    2929
    3030**Communication**: There are a couple of ways for communicating with !PyGaze developers, one is their support forum accessible from http://forum.cogsci.nl/index.php?p=/categories/pygaze and the other is a contact form found at http://www.pygaze.org/contact/ (in case you do not want to create a forum account)
    … …  
    3232**Roadmaps**:
    3333 
     34To do goals:
    3435
    35 ''Original goal:''
    36  
    37   - bundles of code for a large range of different eye trackers from different manufacturers into a single interface.
    38   - open-source based on excisting libraries
     36  - Run detections on non down-sampled signals
     37  - Improve detections integration (New detection axis?)
    3938
    40 ''Future goals:''
     39In progress:
    4140
    42   Short term:
    43   - better variable management and getting rid of some annoying bugs
    44   - an analysis suite to complement the existing experimental library
    45 
    46   Long term:
    47   - incorporate support for more eye trackers and support for even more obscure peripherals
    48   - support for electroencephalography
    49  
    50   Source: Interview with lead developer: https://opensource.com/life/15/12/pygaze-open-source-eye-tracking-toolkit
     41  - lazy loading and loading file improvements
     42  - Improve loading and specially down-sampling (data // hypnogram // save and load hypnogram data)
     43  - Automatic scoring based on machine learning :
     44    - Compute features
     45    - Trained the classifier
     46    - Provide an already trained classifier (channel problem?)
     47   ,based on the detections
     48    - Perform spindles / KCs / slow waves on a central electrodes
     49    - Perform REM on EOG electrode / MT on EMG
     50    - PerformPeaks on ECG
     51    - Compute frequency band power by epochs of 30 sec
     52    - Create a probability vector
    5153
    5254**Releases**: