Finding the optimal feature vector for detecting the environmental соnтtext from global navigation satellite systems datа

А. I. Bolkunov; Болкунов А. И.; V. V. Kulnev; Кульнев В. В.; Е. V. Kulnev; Кульнев Е. В.; E. O. Nakonechnyi; Наконечный Е. О.; V. I. Yaremchuk; Яремчук В. И.

doi:10.31857/S0002338824040118

Finding the optimal feature vector for detecting the environmental соnтtext from global navigation satellite systems datа

Авторлар: Bolkunov А.I.¹, Kulnev V.V.¹, Kulnev Е.V.¹, Nakonechnyi E.O.¹, Yaremchuk V.I.¹
Мекемелер:
1. JSC «TsNIImash»
Шығарылым: № 4 (2024)
Беттер: 154-166
Бөлім: НАВИГАЦИОННЫЕ СИСТЕМЫ
URL: https://journals.eco-vector.com/0002-3388/article/view/676407
DOI: https://doi.org/10.31857/S0002338824040118
EDN: https://elibrary.ru/UDUYPP
ID: 676407

Дәйексөз келтіру

Толық мәтін

Ашық рұқсат
Рұқсат жабық

Рұқсат берілді
Рұқсат жабық

Тек жазылушылар үшін

Аннотация
Толық мәтін
Авторлар туралы
Әдебиет тізімі
Қосымша файлдар
Статистика

Аннотация

In global navigation satellite systems, positioning quality indicators depend on both environmental conditions and user behaviour. The environment affects the reception quality of the radio signals that are available for positioning. An adaptive navigation solution is required to operate in different environmental conditions, which will detect the type of environment and apply different methods for navigation solution. The features formed from the received navigation signal data that can be used to determine the type of environment are discussed. This paper is devoted to finding an optimal feature vector for determining the type of environment from information from global navigation satellite systems. Experimental navigation data for different types of environment are collected. Criteria and methods for determining the optimal feature vector using algorithms from mathematical statistics are considered. The optimal feature vector that contributes the most to the determination of different types of environment is proposed.

Негізгі сөздер

GNSS, navigation signals, environmental context, feature vector

Толық мәтін

Әдебиет тізімі

Перов А.И. ГЛОНАСС. Модернизация и перспективы развития. Монография. М.: Радиотехника, 2020.
Кульнев В.В., Кульнев Е.В., Наконечный Е.О. Методы определения контекста по данным навигационной аппаратуры глобальных навигационных спутниковых систем // Космонавтика и ракетостроение. 2023. № 4. С. 43–53.
Groves P.D, Martin H., Voutsis K., Walter D., Wang L. Context Detection, Categorization and Connectivity for Advanced Adaptive Integrated Navigation. London UK: University College London, 2013.
Gao H., Groves P.D. Environmental Context Detection for Adaptive Navigation using GNSS Measurements from a Smartphone. London UK: University College London, 2018.
Wang Y., Liu P., Liu Q., Adeel M., Qian J., Jin X., Ying R. Urban Environment Recognition Based on the GNSS Signal Characteristics // Wiley ION. 2018. V. 66.
Liu H., Zhang M., Pei L., Wang W., L. Li, Pan C., Li Z. Environment Classification for Global Navigation Satellite Systems Using Attention // Shanghai Key Laboratory of Navigation and Location Based Services. Shanghai: Shanghai Jiao Tong University, 2021. February.
Feriol F., Watanabe Y., Vivet D. GNSS-based Environmental Context Detection for Navigation // IEEE Intelligent Vehicles Symposium (IV). Aachen. Germany, 2022. Jun.
U-blox M8 Receiver description. UBX-13003221. 2022. August.
Digital Cellular Telecommunications System (Phase 2+) (GSM) Location Services (LCS) Mobile Station (MS). Serving Mobile Location Centre (SMLC) Radio Resource LCS Protocol (RRLP) (3GPP TS 44.031 Version 17.0.0 Release 17). ETSI TS 144 031 V17.0.0. 2022.
BS ISO 5725-1. Accuracy (Trueness and Precision) of Measurement Methods and Results – Part 1: General Principles and Definitions. Geneva, 1994. P.1.
Cramer J.S. The Origins of Logistic Regression (PDF) // Tinbergen Institute. 2002. V. 119. P. 167–178.
Pearson K. Notes on Regression and Inheritance in the Case of Two parents. London: Proceedings of the Royal Society of London, 1895. June.
Székely G.J., Rizzo M.L., Bakirov N.K. Measuring and Testing Dependence by Correlation of Distances // The Annals of Statistics. 2007. V. 35. № 6. P. 2769–2794.
Никулин М.С. Критерий хи-квадрат для непрерывных распределений с параметрами сдвига и масштаба // Теория вероятностей и еe применение. 1973. Т. XVIII. Вып. 3.
Box G.E.P. Non-Normality and Tests on Variances // Biometrika. 1953. V. 40. P. 318–335.
Kraskov A., Stogbauer H., Grassberger P. Estimating Mutual Information // Physical Review E. 2004. V. 69.
Friedman J. Greedy Function Approximation: A Gradient Boosting // The Annals of Statistics. 2001. V. 29.
Hastie T., Tibshirani R., Friedman J. Chapter 15. Random Forests // The Elements of Statistical Learning. 2nd ed. Springer-Verlag, 2009.
Boyd S., Vandenberghe L. Convex Optimization. London UK: Cambridge University Press, 2004. 716 p.
Tipping M.E., Bishop C.M. Probabilistic Principal Component Analysis // J. Royal Statistical Society: Series B (Statistical Methodology). 1999. V. 61(3). P. 611–622.