{
  "id": 368447,
  "title": "score improvement G wave detection 20% data",
  "url": "/competitions/g2net-detecting-continuous-gravitational-waves/discussion/368447",
  "author_name": "Igor Litvin",
  "post_date": "2022-11-25T13:18:38.189000",
  "votes": 5,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Good day my Kaggle friend.</p>\n<p>I am new here and want to share something for you.</p>\n<p>I hope this  will help you to improve your score. Possible the idea is not new for you in this case please skip. I am sure that for some kaggle friends it will help.</p>\n<p>Check this notebook for my code:<br>\n<a href=\"https://www.kaggle.com/code/igorlitvin/l-and-h-distortion-of-g-wave-help\" target=\"_blank\">https://www.kaggle.com/code/igorlitvin/l-and-h-distortion-of-g-wave-help</a></p>\n<p>Idea:</p>\n<p>I figered out that aproximately 20% of the gravitation wave spectra are distorted. I think the distortion was made artificially because of it is exatly the same distortion for H and L shoulders of the interferometer.</p>\n<p>Possible, they multiplied by exactly the same function to H and exactly the same (but different from H) to L shoulder.</p>\n<p>I have identified this fumction by averaging 10 distorted L and 10 distorted H spectra. You can make it better of course and average more spectra.</p>\n<p>I have presented it here:<br>\n<a href=\"https://www.kaggle.com/code/igorlitvin/l-and-h-distortion-of-g-wave-help\" target=\"_blank\">https://www.kaggle.com/code/igorlitvin/l-and-h-distortion-of-g-wave-help</a></p>\n<p>How it can help?</p>\n<p>You can multiply (with some constant) to your generated date or train data by this distortion function and it will be close to 20 percent of the distorted test spectra and train you NN with better accuracy.</p>\n<p>Moreover you can train two NN for distorted and non distorted spectra.</p>\n<p>You just need to identify the distorted test spectrum you have or not.</p>\n<p>I can help you with it. Check my second code below to identify it.</p>\n<p>I hope it will help you.</p>\n<p>Please vote if the information is interesting for you.</p>\n<p>Regards</p>\n<p>Igor.</p>",
  "messages": [
    {
      "id": 2043233,
      "postDate": "2022-11-25T13:18:38.190Z",
      "content": "<p>Good day my Kaggle friend.</p>\n<p>I am new here and want to share something for you.</p>\n<p>I hope this  will help you to improve your score. Possible the idea is not new for you in this case please skip. I am sure that for some kaggle friends it will help.</p>\n<p>Check this notebook for my code:<br>\n<a href=\"https://www.kaggle.com/code/igorlitvin/l-and-h-distortion-of-g-wave-help\" target=\"_blank\">https://www.kaggle.com/code/igorlitvin/l-and-h-distortion-of-g-wave-help</a></p>\n<p>Idea:</p>\n<p>I figered out that aproximately 20% of the gravitation wave spectra are distorted. I think the distortion was made artificially because of it is exatly the same distortion for H and L shoulders of the interferometer.</p>\n<p>Possible, they multiplied by exactly the same function to H and exactly the same (but different from H) to L shoulder.</p>\n<p>I have identified this fumction by averaging 10 distorted L and 10 distorted H spectra. You can make it better of course and average more spectra.</p>\n<p>I have presented it here:<br>\n<a href=\"https://www.kaggle.com/code/igorlitvin/l-and-h-distortion-of-g-wave-help\" target=\"_blank\">https://www.kaggle.com/code/igorlitvin/l-and-h-distortion-of-g-wave-help</a></p>\n<p>How it can help?</p>\n<p>You can multiply (with some constant) to your generated date or train data by this distortion function and it will be close to 20 percent of the distorted test spectra and train you NN with better accuracy.</p>\n<p>Moreover you can train two NN for distorted and non distorted spectra.</p>\n<p>You just need to identify the distorted test spectrum you have or not.</p>\n<p>I can help you with it. Check my second code below to identify it.</p>\n<p>I hope it will help you.</p>\n<p>Please vote if the information is interesting for you.</p>\n<p>Regards</p>\n<p>Igor.</p>",
      "rawMarkdown": "Good day my Kaggle friend.\n\nI am new here and want to share something for you.\n\nI hope this  will help you to improve your score. Possible the idea is not new for you in this case please skip. I am sure that for some kaggle friends it will help.\n\nCheck this notebook for my code:\nhttps://www.kaggle.com/code/igorlitvin/l-and-h-distortion-of-g-wave-help\n\nIdea:\n\nI figered out that aproximately 20% of the gravitation wave spectra are distorted. I think the distortion was made artificially because of it is exatly the same distortion for H and L shoulders of the interferometer.\n\nPossible, they multiplied by exactly the same function to H and exactly the same (but different from H) to L shoulder.\n\nI have identified this fumction by averaging 10 distorted L and 10 distorted H spectra. You can make it better of course and average more spectra.\n\nI have presented it here:\nhttps://www.kaggle.com/code/igorlitvin/l-and-h-distortion-of-g-wave-help\n\nHow it can help?\n\nYou can multiply (with some constant) to your generated date or train data by this distortion function and it will be close to 20 percent of the distorted test spectra and train you NN with better accuracy.\n\nMoreover you can train two NN for distorted and non distorted spectra.\n\nYou just need to identify the distorted test spectrum you have or not.\n\nI can help you with it. Check my second code below to identify it.\n\nI hope it will help you.\n\nPlease vote if the information is interesting for you.\n\nRegards\n\nIgor.",
      "votes": 5
    },
    {
      "id": 2043881,
      "postDate": "2022-11-26T04:06:50.767Z",
      "content": "<p>thx for sharing. Could you share your dataset?</p>\n<p>two links same notebook?</p>",
      "rawMarkdown": "thx for sharing. Could you share your dataset?\n\ntwo links same notebook?",
      "votes": 1
    }
  ],
  "comments": [
    {
      "id": 2043881,
      "author_name": "dragon zhang",
      "author_url": "",
      "post_date": "2022-11-26T04:06:50.767000",
      "content": "<p>thx for sharing. Could you share your dataset?</p>\n<p>two links same notebook?</p>",
      "votes": 1,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2043233": "Good day my Kaggle friend.\n\nI am new here and want to share something for you.\n\nI hope this  will help you to improve your score. Possible the idea is not new for you in this case please skip. I am sure that for some kaggle friends it will help.\n\nCheck this notebook for my code:\nhttps://www.kaggle.com/code/igorlitvin/l-and-h-distortion-of-g-wave-help\n\nIdea:\n\nI figered out that aproximately 20% of the gravitation wave spectra are distorted. I think the distortion was made artificially because of it is exatly the same distortion for H and L shoulders of the interferometer.\n\nPossible, they multiplied by exactly the same function to H and exactly the same (but different from H) to L shoulder.\n\nI have identified this fumction by averaging 10 distorted L and 10 distorted H spectra. You can make it better of course and average more spectra.\n\nI have presented it here:\nhttps://www.kaggle.com/code/igorlitvin/l-and-h-distortion-of-g-wave-help\n\nHow it can help?\n\nYou can multiply (with some constant) to your generated date or train data by this distortion function and it will be close to 20 percent of the distorted test spectra and train you NN with better accuracy.\n\nMoreover you can train two NN for distorted and non distorted spectra.\n\nYou just need to identify the distorted test spectrum you have or not.\n\nI can help you with it. Check my second code below to identify it.\n\nI hope it will help you.\n\nPlease vote if the information is interesting for you.\n\nRegards\n\nIgor.",
    "2043881": "thx for sharing. Could you share your dataset?\n\ntwo links same notebook?"
  }
}