{
  "fetched_at": "2026-10-19T07:11:35Z",
  "source_url": "https://www.kaggle.com/competitions/dreem-automated-sleep-staging/data",
  "pages": [
    {
      "name": "data-description",
      "content": "We provide you the data from 9 labeled nights recorded with the Dreem Headband. 6 nights are used for training and 3 for evaluation.\n\n## Files\n\n*   **training_records** - raw data for the train set, each NumPy array is associated with a single record, more details in the following section.\n*   **test_records** - raw data for the test set, each NumPy array is associated with a single record, more details in the following section.\n*   **sample.csv** - a sample submission file in the correct format\n*   **targets_train.csv** - target for the training dataset\n        *   `record` -  record, target from record_0 will be indexed by 0\n        *   `index` - index of epoch within the record, if the index is 99, the target corresponds to the row 99 of the data from the corresponding record\n        *   `identifier` - Unique identifier for each row, computed as record * 10,000 + index\n        *   `target` - Sleep stage of the epoch 0: Wake, 1: N1, 2:N2, 3:N3, 4:REM \n\n## Content of the raw data.\nEach NumPy array is a table with N row and 42001 columns.\n- Column 0: index of the epoch in the record, the i-th epoch corresponds to the data from t=i * 30 seconds to t=(i+1) seconds.\n- Column 1:7501: First EEG (Frontal-occipital) channel sampled at 250Hz\n- Column 7501:15001: Second EEG (Frontal-occipital)  channel sampled at 250Hz\n- Column 15001:22501: Third EEG (Frontal-frontal)  channel sampled at 250Hz\n- Column 22501:30001: Fourth EEG (Frontal-occipital) channel sampled at 250Hz\n- Column 30001:37501: Fifth EEG (Frontal-occipital) channel sampled at 250Hz\n- Column 37501:39001: X-axis accelerometer channel sampled at 50Hz\n- Column 39001:40501: Y-axis accelerometer channel sampled at 50Hz\n- Column 40501:42001: Z-axis accelerometer channel sampled at 50Hz\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "## Problem Overview\n\nWe propose to use Dreem headband data to perform sleep stage scoring on 30 seconds epochs of physiological signals.\nContext\n\nSleep plays a vital role in an individual’s health and well-being. Sleep progresses in cycles that involve multiple sleep stages: wake, light sleep, deep sleep, and REM sleep. Different sleep stages are associated to di different physiological functions. Monitoring sleep stages is beneficial for diagnosing sleep disorders. The gold standard to monitor sleep stages relies on a polysomnography study conducted in a hospital or a sleep lab. Different physiological signals are recorded such as electroencephalogram, electrocardiogram  etc.\n\nSleep stage scoring is then performed visually by an expert on epochs of 30 seconds of signals recording. The resulting graph is called a hypnogram. It provides a compact description the night. \n\n![Hypnograms](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/7751170/bin/zsaa097_fig4.jpg)\nFig 1: Hypnograms scored by the Dreem Headband compared to hypnograms derived by a consensus of scorers\n\n##  The Dreem headband\n\nDreem headband allows doing polysomnography at home signal thanks to two kinds of sensors: electroencephalogram (EEG) and accelerometer signals.\n\nSince the Dreem headband records a lot of nights every day, we spent time developing the most accurate automatic sleep staging algorithms.\n\nIn this challenge, we provide you with labeled data. The idea is to develop an algorithm of sleep staging able to differentiate between Wake, N1, N2, N3 and REM on windows of 30 seconds of raw data. The raw data includes 5 EEG channels in frontal and occipital positions and 3 accelerometers channels (x, y and z).\n\n![Dreem headband](https://dreem.com/static/img/pharma/labs/headband.png)\nFig 1: The Dreem Headband\n\nYou can find a lot of information on Dreem at dreem.com",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}