{
  "id": 459999,
  "title": "Sleep detection",
  "url": "/competitions/child-mind-institute-detect-sleep-states/discussion/459999",
  "author_name": "Reza.mm79",
  "post_date": "2023-12-07T11:29:29.867000",
  "votes": 0,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Hi, everybody. It was a nice job from a nice team. I encountered a problem on sleep detection and would love to hear your solutions. I am attempting to do almost the same thing with the same data, but there are some differences. My data is much noisier due to 1-minute intervals and low accuracy.</p>\n<p>I am working on a web-based solution, so it needs to be very CPU-friendly. I came up with the idea of implementing a score-based system. First, I normalize the heart rate, step, and activity data, then multiply each by a related weight, and finally, add up scores for each point. I then define a threshold score to classify as sleep or wake. However, all the weight parameters and the threshold are defined manually.</p>\n<p>Does anyone have an idea on how to improve this or how to use ML to find the best parameters for this score-based system? I am generating my own data and labeling it, so I have a hard time accessing large data as well.</p>",
  "messages": [
    {
      "id": 2552321,
      "postDate": "2023-12-07T11:29:29.867Z",
      "content": "<p>Hi, everybody. It was a nice job from a nice team. I encountered a problem on sleep detection and would love to hear your solutions. I am attempting to do almost the same thing with the same data, but there are some differences. My data is much noisier due to 1-minute intervals and low accuracy.</p>\n<p>I am working on a web-based solution, so it needs to be very CPU-friendly. I came up with the idea of implementing a score-based system. First, I normalize the heart rate, step, and activity data, then multiply each by a related weight, and finally, add up scores for each point. I then define a threshold score to classify as sleep or wake. However, all the weight parameters and the threshold are defined manually.</p>\n<p>Does anyone have an idea on how to improve this or how to use ML to find the best parameters for this score-based system? I am generating my own data and labeling it, so I have a hard time accessing large data as well.</p>",
      "rawMarkdown": "Hi, everybody. It was a nice job from a nice team. I encountered a problem on sleep detection and would love to hear your solutions. I am attempting to do almost the same thing with the same data, but there are some differences. My data is much noisier due to 1-minute intervals and low accuracy.\n\nI am working on a web-based solution, so it needs to be very CPU-friendly. I came up with the idea of implementing a score-based system. First, I normalize the heart rate, step, and activity data, then multiply each by a related weight, and finally, add up scores for each point. I then define a threshold score to classify as sleep or wake. However, all the weight parameters and the threshold are defined manually.\n\nDoes anyone have an idea on how to improve this or how to use ML to find the best parameters for this score-based system? I am generating my own data and labeling it, so I have a hard time accessing large data as well."
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "2552321": "Hi, everybody. It was a nice job from a nice team. I encountered a problem on sleep detection and would love to hear your solutions. I am attempting to do almost the same thing with the same data, but there are some differences. My data is much noisier due to 1-minute intervals and low accuracy.\n\nI am working on a web-based solution, so it needs to be very CPU-friendly. I came up with the idea of implementing a score-based system. First, I normalize the heart rate, step, and activity data, then multiply each by a related weight, and finally, add up scores for each point. I then define a threshold score to classify as sleep or wake. However, all the weight parameters and the threshold are defined manually.\n\nDoes anyone have an idea on how to improve this or how to use ML to find the best parameters for this score-based system? I am generating my own data and labeling it, so I have a hard time accessing large data as well."
  }
}