Abstract
The observation data is the basis for the global navigation satellite system (GNSS) to provide positioning, navigation and timing (PNT) service, and the observation quality directly determines the performance level of the PNT service. At present, the analysis of GNSS observations quality is partial and can only be based on a single index assessment. GNSS observation quality is difficult to analyze comprehensively by fusing multiple indicators. To solve the above problem, the supervised and unsupervised machine learning algorithms are applied, and a new comprehensive and classification method of GNSS observations quality based on the k-means clustering algorithm (k-means) and K-nearest neighbor algorithm (KNN) was proposed. The four core index features of GNSS observations, including data integrity rate, carrier-to-noise-density ratio (CNR), pseudorange multipath and the number of observations per slip, were selected to construct the sample dataset. The sample set was unsupervised clustered based on the k-means algorithm, and the classification label of GNSS observations quality was obtained. Then KNN algorithm was used to construct a comprehensive classification and evaluation model for GNSS observations quality. The data from 30 MGEX stations in the Asia–Pacific region in 2019 were selected for modeling analysis. The experiment results show that: (1) a strong correlation has been revealed between pseudorange multipath, CNR and the number of observations per slip. (2) The average classification correctness rate of the new model was over 90% by \(n\)-fold cross-validation. (3) The new model can effectively realize the automatic evaluation and classification of GNSS observations quality and easily distinguish the superiority and inferiority of the station observations. The relevant results provide a new idea for the automatic classification and assessment of GNSS observation quality.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10291-023-01557-8/MediaObjects/10291_2023_1557_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10291-023-01557-8/MediaObjects/10291_2023_1557_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10291-023-01557-8/MediaObjects/10291_2023_1557_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10291-023-01557-8/MediaObjects/10291_2023_1557_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10291-023-01557-8/MediaObjects/10291_2023_1557_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10291-023-01557-8/MediaObjects/10291_2023_1557_Fig6a_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10291-023-01557-8/MediaObjects/10291_2023_1557_Fig6b_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10291-023-01557-8/MediaObjects/10291_2023_1557_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10291-023-01557-8/MediaObjects/10291_2023_1557_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10291-023-01557-8/MediaObjects/10291_2023_1557_Fig9_HTML.png)
Similar content being viewed by others
Data availability
The GNSS observations are available in the IGS repository: ftp://cddis.gsfc.nasa.gov/pub/gps/data/campaign/mgex/daily/rinex3. The satellite orbit, clock offset, ERP and DCB products from CODE MGEX center: http://ftp.aiub.unibe.ch/CODE_MGEX/. The multi-GNSS DCB products from CAS: ftp://ftp.gipp.org.cn/product/dcb/.
References
Blewitt G (1998) GPS data processing methodology: from theory to applications. GPS for Geodesy. Springer, Berlin, pp 231–270
Cai C, He C, Santerre R, Pan L, Cui X, Zhu J (2016) A comparative analysis of measurement noise and multipath for four constellations: GPS, BeiDou. GLONASS Galileo Surv Rev 48(349):287–295
Chang G, Xu T, Yao Y, Wang Q (2018) Adaptive Kalman filter based on variance component estimation for the prediction of ionospheric delay in aiding the cycle slip repair of GNSS triple-frequency signals. J Geod 92:1241–1253
Chen Z, Cui Y, Li L, Zhang Q, Lu Z, Li X, Kuang Y, Yang K, Rong F (2020) GDP: an open-source GNSS data preprocessing toolkit. GPS Solut 24:87
Cover T, Hart P, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13(1):21–27
Deng Z, Zhu X, Cheng D, Ming Z, Zhang S (2016) Efficient knn classification algorithm for big data. Neurocomputing 195:143–148
Estey L, Meertens C (1999) TEQC: the multi-purpose toolkit for GPS/GLONASS data. GPS Solut 3:42–49
Gao Y (2017) Research on comprehensive quality evaluation method of BDS tri-band observations. Chang’an University.
Guo L (2017) Development and applications of GNSS data quality assessment software. PLA Information Engineering University.
Hamerly G, Elkan C (2003) Learning the K in K-means. Advances in Neural Information Processing Systems.
Han C, Liu L, Cai Z, Lin Y (2021) The space-time references of BeiDou navigation satellite system. Satell Navig 2:18
Haringer H (1999) Bpunner F (1999) Variances of GPS phase observations: SINMA model. GPS Solut 4(2):35–43
Hatch R (1982) The synergism of GPS code and carrier measurements. In: Proceedings of the third international symposium on satellite doppler positioning. Las Cruces, pp 1213–1231
Hein G (2020) Status, perspectives and trends of satellite navigation. Satell Navig 1:22
Hu G, Dawson J (2020) Overview of legal traceability of GPS positioning in Australia. Satell Navig 1:25
Huang P, Rizos C, Roberts C (2018) Satellite selection with an end-to-end deep learning network. GPS Solut 22(4):108
Jain A, Murty M, Flynn P (1999) Data clustering: a review. ACM Comput Surv 31(3):264–323
Kim M, Seo J, Lee J (2014) A comprehensive method for GNSS data quality determination to improve ionospheric data analysis. Sensors 14:14971–14993
Kouba J, Héroux P (2001) Precise point positioning using IGS orbit and clock products. GPS Solut 5(2):12–28
Kumirek W, Szmuro A, Wiewiórka M, Nowak R, Gambin T (2019) Comparison of knn and k-means optimization methods of reference set selection for improved cnv callers performance. BMC Bioinf 20:1–10
Li B, Liu T, Nie L, Qin Y (2019) Single-frequency GNSS cycle slip estimation with positional polynomial constraint. J Geod 93:1781–1803
Li M, Huang G, Wang L, **e W, Yue F (2022) Performance of Multi-GNSS in the Asia-Pacific region: signal quality, broadcast ephemeris and precise point positioning (PPP). Remote Sens 14(13):3028
Li L, Elhajj M, Feng Y, Ochieng W (2023) Machine learning based GNSS signal classification and weighting scheme design in the built environment: a comparative experiment. Satell Navig 4:12
Li Z, Huang J (2013) GPS Surveying and Data Processing. Wuhan University press,pp 79–81
Li J, et al. (2019) Observation data quality assessment methods for BDS/GNSS geodetic receiver. BD 420022–2019.
Liu C, Yao Z, Wang D, Gao W, Liu T, Rao Y, Li D, Su C (2022) Multiplexing modulation design optimization and quality evaluation of BDS-3 PPP service signal. Satell Navig 3:1
MacQueen J (1965) Some methods for classification and analysis of multivariate observations. In: Proceedings of Berkeley symposium on mathematical statistics and probability, pp 281–297
Su M, Yang Y, Qiao L, Teng X, Song H (2020) Enhanced multipath mitigation method based on multi-resolution CNR model and adaptive statistical test strategy for real-time kinematic PPP. Adv Space Res 67(2):868–882
Su M, Feng W, Qiao L, Qiu Z, Zhang H, Zheng J, Yang Y (2022) An improved time-domain multipath mitigation method based on the constraint of satellite elevation for low-cost single frequency receiver. Adv Space Res 69(10):3597–3608
Wei Y, Li J, Guo L, Wei L (2016) Research on GNSS data quality evaluation based on TOPSIS. J Geod Geodyn 36(10):892–896
Wen H, Pan S, Gao W, Zhao Q, Wang Y (2020) Real-time single-frequency GPS/BDS code multipath mitigation method based on C/N0 normalization. Measurement 164:108075
Xu R, Wunsch D (2005) Survey of clustering algorithms. IEEE Trans Neural Netw 16(3):645–678
Xu H, Angrisano A, Gaglione S, Hsu L (2020) Machine learning based LOS/NLOS classifier and robust estimator for GNSS shadow matching. Satell Navig 1:15
Yan X, Huang G, Zhang Q, Liu C, Wang L, Qin Z (2018) Early analysis of precise orbit and clock offset determination for the satellites of the global BeiDou-3 system. Adv Space Res 63(3):1270–1279
Yang Y, Mao Y, Sun B (2020) Basic performance and future developments of BeiDou global navigation satellite system. Satell Navig 1:1
Yao Y, Wang S (2020) Effect of selection of combined observations on cycle-slip repair success rate for BDS triple-frequency signals. Adv Space Res 66(12):2914–2925
Yuan H, Zhang Z, He X, Li G, Wang S (2021) Stochastic model assessment of low-cost devices considering the impacts of multipath effects and atmospheric delays. Measurement 188:110619
Zhang X, Ding L (2013) Quality analysis of the second generation compass observables and stochastic model refining. Geomat Inf Sci Wuhan Univ 38(7):832–836
Zhang S, Li J, Guo L, Wei Y, Wang S (2016) Station selection strategy of ionospheric modeling based on data quality assessment and global grid model. GNSS World of China 41(3):1–5
Zhao D, Hu X, **ong S, Tian J, Li H (2021) K-means clustering and knn classification based on negative databases. Appl Soft Comput 110(1):107732
Zumberge J, Heflin M, Jefferson D, Watkins M, Webb F (1997) Precise point positioning for the efficient and robust analysis of GPS data from large networks. J Geophys Res-Sol Ea 102(B3):5005–5017
Acknowledgments
The IGS, CODE, WHU and CAS are greatly acknowledged for providing the Multi-GNSS tracking data, SINEX coordinates, satellite orbit, ERP, clock offset and DCB products. We would also like to thank Zhongyang Zhao, an employee of **’an Honor Device Co., Ltd. for his suggestions on this paper.
Funding
This work was supported by the Programs of the National Natural Science Foundation of China (42127802), the Key R&D Program of Shaanxi Province (2022ZDLSF07-12), the Special Fund for Basic Scientific Research of Central Colleges (Grant No. CHD300102269305, CHD300102268305, CHD300102263401, Chang’an University).
Author information
Authors and Affiliations
Contributions
ML conducted the experiments, prepared figures, and wrote the manuscript. GH developed the methodology and reviewed the manuscript. LW proposed this study and developed the methodology, and reviewed the manuscript. WX conducted the experiments and reviewed the manuscript. All authors were involved in discussions throughout the development.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Li, M., Huang, G., Wang, L. et al. Comprehensive classification assessment of GNSS observation data quality by fusing k-means and KNN algorithms. GPS Solut 28, 21 (2024). https://doi.org/10.1007/s10291-023-01557-8
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10291-023-01557-8