Fast subspace approach for mobile positioning with time-of-arrival measurements

2011 ◽  
Vol 5 (14) ◽  
pp. 2035-2039 ◽  
Author(s):  
S. Qin ◽  
Z.-X. Chen ◽  
Q. Wan
Keyword(s):  
Time Of Arrival ◽  
Mobile Positioning

A New Robust Tracking Approach in NLOS Environments

2013 ◽  
Vol 373-375 ◽  
pp. 382-387
Author(s):  
Cheng Dong Wu ◽  
Peng Da Liu ◽  
Yun Zhou Zhang ◽  
Long Cheng ◽  
Jing Yu Ru
Keyword(s):  
Kernel Method ◽  
Wireless Sensor ◽  
Time Of Arrival ◽  
Robust Tracking ◽  
Parametric Approach ◽  
Variable Kernel ◽  
Mobile Positioning ◽  
Noise Density ◽  
Position Estimate ◽  
Non Parametric

In wireless sensor networks, NLOS propagation often enlarges the errors of position estimates when time-of-arrival (TOA) measurements are used. To mitigate the effects caused by NLOS propagation, herein, an EKF-based robust non-parametric approach is proposed. In this paper, we utilize the variable kernel method to obtain an approximate noise density function, which is inexpensively computational and then used to improve the mobile positioning accuracy. Note that the standard EKF often works well when NLOS error is adequately low. This property could also be used to improve the accuracy of mobile positioning. In the proposed algorithm, a hard decision is employed to choose the rational position estimate which may come from the non-parametric approach or the standard EKF. Numerical simulations show a significant improvement over the standard EKF.

Analytical support to organization system of children transportation in long-distance trains

2018 ◽  
Vol 77 (6) ◽  
pp. 232-330
Author(s):  
A. V. Komissarov ◽  
E. A. Makarova ◽  
S. V. Muktepavel ◽  
I. A. Nestrakhov ◽  
I. N. Spesivtseva
Keyword(s):  
Time Of Arrival ◽  
Control Analysis ◽  
Social Significance ◽  
Passenger Cars ◽  
Long Distance ◽  
Number Of Children ◽  
Passenger Traffic ◽  
Destination Station ◽  
Increasing Demand ◽  
Management Functions

Abstract. In modern conditions for passenger complex of Russian Railways, important tasks include improvement of transportation quality, maintenance of stable positions in a competitive environment and increasing demand. To address these issues, a customer-oriented approach is applied based on the segmentation of transport market in relation to certain groups of passengers. Performance of children's transportation is of particular relevance and social significance. Railways are charged with a huge range of work, including sale of travel documents, preparation and equipping of passenger cars, provision of food during the trip, instructing workers, ensuring security during the embarkation/disembarkation of passengers, etc. Children can travel as individually with accompanying persons and as part of organized groups. Processes of planning, organizing, monitoring the transportation of this age category of passengers are associated with the analysis of a large amount of reference and regulatory and reporting documentation. On the basis of the ACS “Express-3”, a program-analytical complex “Children's transportation” was developed and implemented, which allows to receive data at the regional and network levels in the operational (train number, day) and statistical (period of dates, month) modes. This information technology provides analytical support for key transportation management functions — planning, control, analysis. Planning of transportation of organized children's groups is carried out on the basis of a study of the dynamics of data on the number of applications received and travel documents issued, determining the routes of trains, periods of the highest intensity of passenger traffic, obtaining information about the stations of embarkation and disembarkation. To perform the functions of monitoring the embarkation and disembarkation at the destination station of groups of children, the employees involved receive information on the train number, car number, date and time of arrival, number of children in the group using the Children's Transportation software. For the analysis of transportation of children's age categories, a functional has been developed that ensures the construction of aggregated reporting based on trains data that completed the trip. Users receive reporting information in table form, including “strict” (designed according to the approved layout) and “flexible” forms (construction is performed according to specified parameters). Software and analytical complex is designed for managers and specialists of the passenger unit of the JSC “Russian Railways”, has a modular principle of increasing functionality and provides a solution to current problems in the system of organizing children's transport service.

Prediction of aircraft estimated time of arrival using machine learning methods

2021 ◽  
pp. 1-15
Author(s):  
O. Basturk ◽  
C. Cetek
Keyword(s):  
Machine Learning ◽  
Web Application ◽  
Absolute Error ◽  
Machine Learning Algorithms ◽  
Weather Data ◽  
Time Of Arrival ◽  
Learning Models ◽  
Trajectory Data ◽  
Different Sources ◽  
Machine Learning Models

ABSTRACT In this study, prediction of aircraft Estimated Time of Arrival (ETA) is proposed using machine learning algorithms. Accurate prediction of ETA is important for management of delay and air traffic flow, runway assignment, gate assignment, collaborative decision making (CDM), coordination of ground personnel and equipment, and optimisation of arrival sequence etc. Machine learning is able to learn from experience and make predictions with weak assumptions or no assumptions at all. In the proposed approach, general flight information, trajectory data and weather data were obtained from different sources in various formats. Raw data were converted to tidy data and inserted into a relational database. To obtain the features for training the machine learning models, the data were explored, cleaned and transformed into convenient features. New features were also derived from the available data. Random forests and deep neural networks were used to train the machine learning models. Both models can predict the ETA with a mean absolute error (MAE) less than 6min after departure, and less than 3min after terminal manoeuvring area (TMA) entrance. Additionally, a web application was developed to dynamically predict the ETA using proposed models.

Sign in / Sign up

Export Citation Format

Share Document