{
  "id": 235926,
  "title": "Dataset of non-Wifi Data",
  "url": "/competitions/indoor-location-navigation/discussion/235926",
  "author_name": "Ravi Shah",
  "post_date": "2021-05-01T22:17:47.572000",
  "votes": 6,
  "comment_count": 0,
  "views": 0,
  "content": "<p><a href=\"https://www.kaggle.com/ravishah1/indoor-location-navigation-sensor-data\" target=\"_blank\">Link to Dataset</a><br>\n<a href=\"https://www.kaggle.com/ravishah1/indoor-loc-nav-sensor-dataset-generation\" target=\"_blank\">Link to code to make Dataset</a><br>\nI call this sensor data, but it is more like features computed with sensor data using the GitHub.</p>\n<p>It is pretty late in the competition to be posting a dataset, and I don’t expect it to improve results very much given that postprocessing uses similar functions. That being said hopefully someone can use it to improve their score. </p>\n<p>Things to note: this dataset is intended to not include WiFi Features but instead other types of features calculated from sensors such as acce and ahrs using the GitHub - <a href=\"https://www.kaggle.com/ravishah1/understanding-the-indoor-loc-github-data-eda\" target=\"_blank\">see my tutorial here</a> about using the GitHub for this competition. As a result, this is not a good starting dataset as something with wifi is better; however, it may still be useful for fine tuning your results. Also, you can probably get better results by using postprocessing rather than this dataset, I myself am still deciding if I want to use these features. I created and published this dataset just to help anyone who can find a good way to use it. </p>\n<p>Good Luck and if you end up using this dataset, comment your results.</p>",
  "messages": [
    {
      "id": 1290384,
      "postDate": "2021-05-01T22:17:47.573Z",
      "content": "<p><a href=\"https://www.kaggle.com/ravishah1/indoor-location-navigation-sensor-data\" target=\"_blank\">Link to Dataset</a><br>\n<a href=\"https://www.kaggle.com/ravishah1/indoor-loc-nav-sensor-dataset-generation\" target=\"_blank\">Link to code to make Dataset</a><br>\nI call this sensor data, but it is more like features computed with sensor data using the GitHub.</p>\n<p>It is pretty late in the competition to be posting a dataset, and I don’t expect it to improve results very much given that postprocessing uses similar functions. That being said hopefully someone can use it to improve their score. </p>\n<p>Things to note: this dataset is intended to not include WiFi Features but instead other types of features calculated from sensors such as acce and ahrs using the GitHub - <a href=\"https://www.kaggle.com/ravishah1/understanding-the-indoor-loc-github-data-eda\" target=\"_blank\">see my tutorial here</a> about using the GitHub for this competition. As a result, this is not a good starting dataset as something with wifi is better; however, it may still be useful for fine tuning your results. Also, you can probably get better results by using postprocessing rather than this dataset, I myself am still deciding if I want to use these features. I created and published this dataset just to help anyone who can find a good way to use it. </p>\n<p>Good Luck and if you end up using this dataset, comment your results.</p>",
      "rawMarkdown": "[Link to Dataset](https://www.kaggle.com/ravishah1/indoor-location-navigation-sensor-data)\n[Link to code to make Dataset](https://www.kaggle.com/ravishah1/indoor-loc-nav-sensor-dataset-generation)\nI call this sensor data, but it is more like features computed with sensor data using the GitHub.\n\nIt is pretty late in the competition to be posting a dataset, and I don’t expect it to improve results very much given that postprocessing uses similar functions. That being said hopefully someone can use it to improve their score. \n\nThings to note: this dataset is intended to not include WiFi Features but instead other types of features calculated from sensors such as acce and ahrs using the GitHub - [see my tutorial here](https://www.kaggle.com/ravishah1/understanding-the-indoor-loc-github-data-eda) about using the GitHub for this competition. As a result, this is not a good starting dataset as something with wifi is better; however, it may still be useful for fine tuning your results. Also, you can probably get better results by using postprocessing rather than this dataset, I myself am still deciding if I want to use these features. I created and published this dataset just to help anyone who can find a good way to use it. \n\nGood Luck and if you end up using this dataset, comment your results.",
      "votes": 6
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "1290384": "[Link to Dataset](https://www.kaggle.com/ravishah1/indoor-location-navigation-sensor-data)\n[Link to code to make Dataset](https://www.kaggle.com/ravishah1/indoor-loc-nav-sensor-dataset-generation)\nI call this sensor data, but it is more like features computed with sensor data using the GitHub.\n\nIt is pretty late in the competition to be posting a dataset, and I don’t expect it to improve results very much given that postprocessing uses similar functions. That being said hopefully someone can use it to improve their score. \n\nThings to note: this dataset is intended to not include WiFi Features but instead other types of features calculated from sensors such as acce and ahrs using the GitHub - [see my tutorial here](https://www.kaggle.com/ravishah1/understanding-the-indoor-loc-github-data-eda) about using the GitHub for this competition. As a result, this is not a good starting dataset as something with wifi is better; however, it may still be useful for fine tuning your results. Also, you can probably get better results by using postprocessing rather than this dataset, I myself am still deciding if I want to use these features. I created and published this dataset just to help anyone who can find a good way to use it. \n\nGood Luck and if you end up using this dataset, comment your results."
  }
}