Zhanchun Gao
ABSTRACT
This paper introduces a multi-radar track fusion method based on random forest regression and provides an accurate and stable fusion track. The increasing number of aircraft will lead to congested routes, further leading to safety issues. Therefore, an effective track fusion method can accurately locate the aircraft, thereby ensuring the safety of the aircraft in the case of crowded routes. The basic idea of the method proposed in this paper is to select the radar data of a certain track of a certain day to train the model, and predict the position of the aircraft on the next day of the track through the trained model. As a traditional track fusion algorithm, the Kalman filtering has the problem of requiring accurate error estimation, insensitivity to noise, and long calculation time in the case of large data volume. The neural network method that compensates for these shortcomings also has the disadvantage of poor generalization ability in the case of a large amount of noise.
The random forest regression model proposed in this paper can overcome the shortcomings of over-fitting in neural network, so it can achieve better prediction results. And through the real data test, the average error is 40m, compared with the neural network method, the result is increased by 50%.
- Liaw, M. Wiener (2002). Classification and regression by random forest. R News, 2(3), 18--22.Google Scholar
- Ali, B. Syd (2016). System specifications for developing an Automatic Dependent Surveillance-Broadcast (ADS-B) monitoring system. International Journal of Critical Infrastructure Protection, 15, 40--46.Google ScholarCross Ref
- D. Alexander, D. Zikic, J. Zhang, et al. Image Quality Transfer via Random Forest Regression: Applications in Diffusion MRI[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. 2014Google Scholar
- H. Yang, B. Yang, X. Wu, et al. 2018. Research and Prospect of Intellectualized Air Traffic Management Technology. Advanced Engineering Sciences, 50(4), 12--21.Google Scholar
- J. Ferrante. A Kalman filter-based radar track data fusion algorithm applied to a select ICBM case[C]// IEEE Radar Conference. IEEE, 2004.Google Scholar
- J.R. Quinlan (1986). Induction of Decision Trees. Machine Learning. 1(1), 81--106.Google ScholarDigital Library
- L. Breiman (2001), Random Forests, Machine Learning. 45(1), 5--32.Google ScholarDigital Library
- M.K. Iqbal, B. Anwer, S.M. Abbas. Multi-Radar Track Fusion: Making lives easier[M]. LAP Lambert Academic Publishing, 2012.Google Scholar
- N. El-Sheimy, K.W. Chiang, A. Noureldin (2006). The Utilization of Artificial Neural Networks for Multisensor System Integration in Navigation and Positioning Instruments[J]. IEEE Transactions on Instrumentation and Measurement, 55(5), 1606--1615.Google ScholarCross Ref
- N. Yadaiah, L. Singh, R.S. Bapi, et al. MultisensorData Fusion Using Neural Networks[C]// IEEE International Joint Conference on Neural Network. IEEE, 2006.Google Scholar
- O. Mutanga, E. Adam, M.A. Cho (2012). High density biomass estimation for wetland vegetation using WorldView-2 imagery and random forest regression algorithm. International Journal of Applied Earth Observation and Geoinformation. 18(1), 399--406.Google ScholarCross Ref
- P. Dubath, L. Rimoldini, M. Süveges, et al (2011). Random forest automated supervised classification of Hipparcos periodic variable stars. Monthly Notices of the Royal Astronomical Society. 414(3), 2602--2617.Google ScholarCross Ref
- P. Xu, F. Jelinek. Using Random Forests in the Structured Language Model.[C]// International Conference on Neural Information Processing Systems. MIT Press, 2004.Google Scholar
- P.F. Smith, S. Ganesh, P. Liu (2013). A comparison of random forest regression and multiple linear regression for prediction in neuroscience[J]. Journal of Neuroscience Methods. 220(1), 85--91.Google ScholarCross Ref
- R. Toledo, D. Gruyer, A. Lambert. A theoretical Analysis of the Extended Kalman Filter for Data Fusion in Vehicular Positioning[C]// International Conference on Its Telecommunications. IEEE, 2011.Google Scholar
- S. Adusumilli, D. Bhatt, H. Wang, et al (2013). A low-cost INS/GPS integration methodology based on random forest regression. Expert Systems with Applications. 40(11), 4653--4659.Google ScholarDigital Library
- S. Liu, S. Dissanayake, S. Patel, et al (2014). Learning accurate and interpretable models based on regularized random forests regression. BMC Systems Biology. 8(3 Supplement), S5.Google Scholar
- S.J. Julier, J.K. Uhlmann. New extension of the Kalman filter to nonlinear systems[C]// Signal Processing, Sensor Fusion, and Target Recognition VI. International Society for Optics and Photonics, 1997.Google Scholar
- V. Svetnik (2003). Random Forest: A Classification and Regression Tool for Compound Classification and QSAR Modeling. Journal of Chemical Information and Computer Sciences. 43(6), 1947--58.Google ScholarCross Ref
Index Terms
- A Multi-Radar Track Fusion Methodology Based on Random Forest Regression
Recommendations
Radar fusion to detect targets-Part II
In a previous paper [3] the Authors have described the concept of cueing a microwave radar by exploiting the detection of a low frequency radar; the target of interest was an aircraft. In this publication the study is extended to the case in which the ...
A Novel Data Fusion Method Applied in Radar Imaging Matching Position
ISDEA '12: Proceedings of the 2012 Second International Conference on Intelligent System Design and Engineering ApplicationHow to improve position precision via fusing radar multi-position data in radar imaging matching is one of research focus. In order to resolve the problem, a novel data fusion method called STCF (Space-Time Crossing Fusion) method is proposed. The ...
A Data Fusion Algorithm for Marine Radar Tracking
GCIS '09: Proceedings of the 2009 WRI Global Congress on Intelligent Systems - Volume 01Automatic Radar Plotting Aids (ARPA) and Automatic Identification System (AIS) are the most important navigational systems on board. ARPA is considered as the primary anti-collision system, but its detecting ability, tracking accuracy and reliability ...
Comments