I am passionate about aerospace and computer science. I like challenges and enjoy meeting people from different backgrounds. I was born in China and completed my bachelor's degree there as well. Since then I have studied and worked in six different countries. Thought I have held various positions, I am first and foremost an engineer. Currently, I am completing my PhD research at TuDelft, in the Netherlands.
#Computing, #Aircraft, #Coding, #Python, #Java, #PHP, #Cloud, #DataMining, #WebApp
Research and Education
2015 - Present: PhD at TuDelft. Research topic: "Developing Aircraft Performance Models Using Data Mining"
2007-2010: MSc of Aerospace Science and Technology, Technical University of Catalonia (UPC) Master Thesis
2003-2007: BSc of Electronic Information Technology, Beijing University of Post and Telecommunication
2009 Jun-Aug: Space Studies Program, International Space University
Sun, J., Ellerbroek, J., & Hoekstra, J. (2017). Aircraft initial mass estimation using Bayesian inference method . Transportation Research. Part C: Emerging Technologies.
Sun, J., Ellerbroek, J., & Hoekstra, J. (2017). Flight Extraction and Phase Identification for Large Automatic Dependent Surveillance-Broadcast Datasets . Journal of Aerospace Information Systems.
Sun, J., Ellerbroek, J., & Hoekstra, J. (2017). Modeling Aircraft Performance Parameters with Open ADS-B Data. In Proceedings of the 12th USA/Europe Air Traffic Management Research and Development Seminar. FAA/EUROCONTROL.
Sun, J., Ellerbroek, J., & Hoekstra, J. (2017). Bayesian Inference of Aircraft Initial Mass . In Proceedings of the 12th USA/Europe Air Traffic Management Research and Development Seminar. FAA/EUROCONTROL.
Verbraak, T. L., Ellerbroek, J., Sun, J., & Hoekstra, J. M. Large-Scale ADS-B Data and Signal Quality Analysis In Proceedings of the 12th USA/Europe Air Traffic Management Research and Development Seminar. FAA/EUROCONTROL.
Sun, J., Ellerbroek, J., & Hoekstra, J. (2016). Large-Scale Flight Phase Identification from ADS-B Data Using Machine Learning Methods. In 7th International Conference on Research in Air Transportation.
Sun, J., Ellerbroek, J., & Hoekstra, J. (2016). Modeling and Inferring Aircraft Takeoff Mass from Runway ADS-B Data. In 7th International Conference on Research in Air Transportation.
Sun, J., & Xhafa, F. (2011, June). A genetic algorithm for ground station scheduling. In Complex, Intelligent and Software Intensive Systems (CISIS), 2011 International Conference on (pp. 138-145). IEEE.
2015 - Present: PhD, TuDelft, Netherlands
2012-2015: Academic Coordination of SSP, International Space University, France
2011-2012: Researcher in Positioning Technology, Ascamm Technology Centre, Spain
2007-2011: Aerospace Engineer / IT Manager, Barcelona Aerospace Technology Centre, Spain
Some Fun Projects
Open Aircraft Performance Database
As part of Open Aircraft Performance model, the OFE database provides operational and limitation values of aircraft performance parameters. Common aircraft types are included. ADS-B data are use for model construction. Each parameters are constructed based on at least 5000 flight of same aircraft type.
The ADS-B decoder has evolved into a fully powered Mode-S decoder with contributions from the community. It decodes ADS-B messages (DF17, DF18) and Enhanced Mode-S (DF20, DF21) messages. Many more aircraft states can now be discovered through Mode-S, in addition to ADS-B.
GitHub and PIP
A database to search for aircraft IDs (such as ICAO address, registrations ID, etc) and related information. It is built in Python / Flask and data is from Flight Radar 24.
Aircraft Database and GitHub
ADS-B / EHS Decoding Guide
A guide to decode the ADS-B messages. Part of my PhD research involves using ADS-B data to assist aircraft performance modeling. This is the first project that I worked here at TuDelft.
BlueSky is the open source Air Traffic Simulation we are building in my group. I am only a part of the coding team, contributing to the development of the tool.
Creating an internet MEME is easy, but it is difficult for a computer to understand the accompanying text. We developed a machine learning system that can extract and understand the text within an internet MEME. The accuracy of the text recognition exceeds 95%.