{
  "id": 588872,
  "title": "Do you pay more attention to the IMU than other features?",
  "url": "/competitions/cmi-detect-behavior-with-sensor-data/discussion/588872",
  "author_name": "Stas Kolchin",
  "post_date": "2025-07-08T19:33:00.422000",
  "votes": 2,
  "comment_count": 0,
  "views": 0,
  "content": "<p>From data describtion: \"Expect approximately 3,500 sequences in the hidden test set.<br>\nHalf of the hidden-test sequences are recorded with IMU only; the thermopile (thm_) and time-of-flight (tof__v*) columns are still present but contain null values for those sequences.\"</p>\n<p>So I wonder if it is a good tactic to continually improve the performance of the model based on IMU features, rather than the IMU+TOF? Has anyone done any tests/comparisons?</p>",
  "messages": [
    {
      "id": 3245035,
      "postDate": "2025-07-08T19:33:00.423Z",
      "content": "<p>From data describtion: \"Expect approximately 3,500 sequences in the hidden test set.<br>\nHalf of the hidden-test sequences are recorded with IMU only; the thermopile (thm_) and time-of-flight (tof__v*) columns are still present but contain null values for those sequences.\"</p>\n<p>So I wonder if it is a good tactic to continually improve the performance of the model based on IMU features, rather than the IMU+TOF? Has anyone done any tests/comparisons?</p>",
      "rawMarkdown": "From data describtion: \"Expect approximately 3,500 sequences in the hidden test set.\nHalf of the hidden-test sequences are recorded with IMU only; the thermopile (thm_) and time-of-flight (tof__v*) columns are still present but contain null values for those sequences.\"\n\nSo I wonder if it is a good tactic to continually improve the performance of the model based on IMU features, rather than the IMU+TOF? Has anyone done any tests/comparisons?",
      "votes": 2
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "3245035": "From data describtion: \"Expect approximately 3,500 sequences in the hidden test set.\nHalf of the hidden-test sequences are recorded with IMU only; the thermopile (thm_) and time-of-flight (tof__v*) columns are still present but contain null values for those sequences.\"\n\nSo I wonder if it is a good tactic to continually improve the performance of the model based on IMU features, rather than the IMU+TOF? Has anyone done any tests/comparisons?"
  }
}