{
  "id": 11377,
  "title": "1.3 seconds or more?",
  "url": "/competitions/inria-bci-challenge/discussion/11377",
  "author_name": "",
  "post_date": "2014-12-28T20:10:20.353Z",
  "votes": null,
  "comment_count": 2,
  "views": 1196,
  "content": "<p>I see that @phalaris&nbsp;used&nbsp;1.3 seconds in the GBM benchmark code and explained the rationale behind using that cutoff time.&nbsp;</p>\n<p>There is so much more data in the training files and I am wondering if anyone knows and could explain the value of using more data (i.e. beyond 1.3 seconds).</p>\n<p>Thanks</p>",
  "messages": [
    {
      "id": "61979",
      "postDate": "12/28/2014 20:10:20",
      "content": "<p>I see that @phalaris&nbsp;used&nbsp;1.3 seconds in the GBM benchmark code and explained the rationale behind using that cutoff time.&nbsp;</p>\n<p>There is so much more data in the training files and I am wondering if anyone knows and could explain the value of using more data (i.e. beyond 1.3 seconds).</p>\n<p>Thanks</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "61986",
      "postDate": "12/29/2014 03:37:26",
      "content": "<p>Check out the article; linked in description. The authors give some example vignettes for EEG&nbsp;response. The Cz channel is shown with a ~1 sec window. The Cz response signal-to-noise is very short (less than 1 sec). Gather&nbsp;all trajectories for your desired window length (per signal) and then simply compute the signal-to-noise for every time coordinate. This is like a cross-sectional s2n. (mean(x) - mean(y))/(std(x) + std(y)). where x is population for feedback=1 and y is population for feedback=0</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "61988",
      "postDate": "12/29/2014 04:00:23",
      "content": "<p>Thanks @Brian Geier</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 61986,
      "author_name": "bgeier",
      "author_url": "",
      "post_date": "12/29/2014 03:37:26",
      "content": "<p>Check out the article; linked in description. The authors give some example vignettes for EEG&nbsp;response. The Cz channel is shown with a ~1 sec window. The Cz response signal-to-noise is very short (less than 1 sec). Gather&nbsp;all trajectories for your desired window length (per signal) and then simply compute the signal-to-noise for every time coordinate. This is like a cross-sectional s2n. (mean(x) - mean(y))/(std(x) + std(y)). where x is population for feedback=1 and y is population for feedback=0</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 61988,
      "author_name": "",
      "author_url": "",
      "post_date": "12/29/2014 04:00:23",
      "content": "<p>Thanks @Brian Geier</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "61979": "",
    "61986": "",
    "61988": ""
  },
  "source": "meta"
}