{
  "fetched_at": "2026-10-19T19:35:11Z",
  "source_url": "https://www.kaggle.com/competitions/gnss-urban-positioning/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Both training and testing dataset contain raw measurements from the f9p receiver. Please read and extract more features for your own machine learning training. The training data is collected in Tsim Sha Tsui (TST), Whampoa (WP), Mong Kok (MK). The data collection setup is as UrbanNav [1]. The testing data is collected in Kowloon Bay (KLB).\n\n## Files\n\n*   **GNSS_raw_train.csv** - the training set\n*   **GNSS_raw_test.csv** - the testing set\n*   **sample_submission.csv** - a sample submission file in the correct format, where the number in the \"ID\" column is the ID, following the testing dataset sequence, **East_error_base and North_error_base are the E and N based on the location [22.322101, 114.208885, 0]**\n\n## Columns\n\n*   `GPS_Time(s)` - GPS time\n*   `Satelite_code` - code of satellite\n*   `code_L1` - code measurement in L1\n*   `phase_L1` - phase measurement in L1\n*   `doppler_L1` - doppler in L1\n*   `cnr_L1` - signal strength in L1\n*   `code_L2` - code measurement in L2\n*   `phase_L2` - phase measurement in L2\n*   `doppler_L2` - doppler in L2\n*   `cnr_L2` - signal strength in L2\n*   `label` - LOS/NLOS label of the satellite, where 1 represents LOS, 0 represents NLOS. This is gained by 3D building model and the ground truth location.\n*   `Pr_Error` - Pseudorange error (assumed mostly contributed by multipath/NLOS). The value is calculated by double-difference using the closest ground station measurement and the highest elevation angle satellite as in [2] equation (17).\n*   `Latitude` - Latitude of the ground truth location\n*   `Longitude` - Longitude of the ground truth location\n*   `Height` - Ellipsoidal height of the ground truth location\n\n## Rows\n* **For GNSS_raw_train.csv**\n*   `2-10392` - Scenario Tsim Sha Tsui\n*   `10393-38144` - Scenario Whampo\n*   `38145-74086` - Scenario Mong Kok\n\n\n[1] L.-T. Hsu, Kubo, Nobuaki, Wen, Weisong, Chen, Wu, Liu, Zhizhao, Suzuki, Taro, Meguro, Junichi, \"UrbanNav:An Open-Sourced Multisensory Dataset for Benchmarking Positioning Algorithms Designed for Urban Areas,\" in Proceedings of the 34th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2021), St. Louis, Missouri, September 2021 2021, pp. 226-256, doi: https://doi.org/10.33012/2021.17895.\n[2] B. Xu, Q. Jia, Y. Luo, and L.-T. Hsu, \"Intelligent GPS L1 LOS/Multipath/NLOS Classifiers Based on Correlator-, RINEX- and NMEA-Level Measurements,\" Remote Sensing, vol. 11, no. 16, p. 1851, 2019. [Online]. Available: https://www.mdpi.com/2072-4292/11/16/1851.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "## Motivation\nGlobal navigation satellite system (GNSS) positioning accuracy is degraded in urban canyons due to signal blockages and reflections. This competition aims to foster the machine learning algorithms in GNSS multipath/NLOS problem. Totally there are three tasks for this problem, which is LOS/NLOS classification, Pseudorange Error Prediction, Positioning Prediction.\n\nThis is the page for GNSS position prediction. You can upload your prediction result to evaluate the performance of your model in a different scenario.\n\n## Acknowledgements\n\nWe thanks the fellows who contribute to the project:\nProf. Hsu, Mr. Huang, Mr. Zhang, Mr. Ivan, Mr. Zhong, Mr. Max, Mr. Xu",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "## Evaluation Metric\nThe evaluation metric for this competition is [RMSE](https://en.wikipedia.org/wiki/Root-mean-square_deviation). The RMSE is commonly used to measure the differences between values. The RMSE for this task is calculated for both E and N errors.\n\n\n## Benchmark\nThe benchmark result is from the conventional least-squares method. Because the ground truth of the testing set will not be provided, the E and N error is calculated based on the location near our data collection position. The location is  [22.322101, 114.208885, 0]. \n\n## Submission Format\n\n**For every GPS Time and Every Satellite in the dataset**, submission files should contain two columns: `ID`, `East_error_base`, and  `North_error_base`. `ID` follows the same sequence with the testing dataset, and within each GPS Time, the satellite sequence should also be the same as that in the testing set. Every `East_error_base` and  `North_error_base` are float values, which mean the E and N based on the above location and your position produced by your model. \n\n\nThe file should contain a header and have the following format:\n```\nID,East_error_base,North_error_base\n0,101,-10\n1,25\n2,0,-67\n3,367,87\n4,45,145\n5,120,123\n6,-261,68\n7,72,98\n8,49,81\n9,192,105\n10,238,-204\n11,-85,-20\n12,164,87\n13,175.-107\n```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Please use the training set to train your model. At the same time, do not forget to split a certain percentage of them to validate your model.\n\n - For this positioning competition, please use the information from this website ONLY. This limitation will be removed on the other positioning competition, where every input is welcomed, including IMU data from UrbanNAV, MAP and 3D building model information from the government website. \n(UrbanNAV: https://github.com/DarrenWong/UrbanNavDataset)\n(MAP and 3D model: https://www.landsd.gov.hk/tc/spatial-data/open-data.html)\n - Welcome to test the generalization performance of your model here!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}