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).

## Files

*   **GNSS_raw_train.csv** - the training set
*   **GNSS_raw_test.csv** - the testing set
*   **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, and the number in the "Predict" column is the predicted pseudorange error

## Columns

*   `GPS_Time(s)` - GPS time
*   `Satelite_code` - code of satellite
*   `code_L1` - code measurement in L1
*   `phase_L1` - phase measurement in L1
*   `doppler_L1` - doppler in L1
*   `cnr_L1` - signal strength in L1
*   `code_L2` - code measurement in L2
*   `phase_L2` - phase measurement in L2
*   `doppler_L2` - doppler in L2
*   `cnr_L2` - signal strength in L2
*   `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.
*   `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).
*   `Latitude` - Latitude of the ground truth location
*   `Longitude` - Longitude of the ground truth location
*   `Height` - Ellipsoidal height of the ground truth location

## Rows
* **For GNSS_raw_train.csv**
*   `2-10392` - Scenario Tsim Sha Tsui
*   `10393-38144` - Scenario Whampo
*   `38145-74086` - Scenario Mong Kok


[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.
[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.