liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Gaussian Processes for Flow Modeling and Prediction of Positioned Trajectories Evaluated with Sports Data
Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, Faculty of Science & Engineering.
Department of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China.
Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, Faculty of Science & Engineering.
Ericsson AB, Sweden.
Show others and affiliations
2016 (English)In: 19th International Conference on  Information Fusion (FUSION), 2016, Institute of Electrical and Electronics Engineers (IEEE), 2016, 1461-1468 p.Conference paper, Published paper (Refereed)
Abstract [en]

Kernel-based machine learning methods are gaining increasing interest in flow modeling and prediction in recent years. Gaussian process (GP) is one example of such kernelbased methods, which can provide very good performance for nonlinear problems. In this work, we apply GP regression to flow modeling and prediction of athletes in ski races, but the proposed framework can be generally applied to other use cases with device trajectories of positioned data. Some specific aspects can be addressed when the data is periodic, like in sports where the event is split up over multiple laps along a specific track. Flow models of both the individual skier and a cluster of skiers are derived and analyzed. Performance has been evaluated using data from the Falun Nordic World Ski Championships 2015, in particular the Men’s cross country 4 × 10 km relay. The results show that the flow models vary spatially for different skiers and clusters. We further demonstrate that GP regression provides powerful and accurate models for flow prediction.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2016. 1461-1468 p.
National Category
Electrical Engineering, Electronic Engineering, Information Engineering Probability Theory and Statistics
Identifiers
URN: urn:nbn:se:liu:diva-129758ISBN: 9780996452748 (print)ISBN: 9781509020126 (print)OAI: oai:DiVA.org:liu-129758DiVA: diva2:943157
Conference
19th International Conference on Information Fusion, 5-8 July 2016, Heidelberg, Germany
Available from: 2016-06-27 Created: 2016-06-27 Last updated: 2017-09-13Bibliographically approved
In thesis
1. Position Estimation in Uncertain Radio Environments and Trajectory Learning
Open this publication in new window or tab >>Position Estimation in Uncertain Radio Environments and Trajectory Learning
2017 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

To infer the hidden states from the noisy observations and make predictions based on a set of input states and output observations are two challenging problems in many research areas. Examples of applications many include position estimation from various measurable radio signals in indoor environments, self-navigation for autonomous cars, modeling and predicting of the traffic flows, and flow pattern analysis for crowds of people. In this thesis, we mainly use the Bayesian inference framework for position estimation in an indoor environment, where the radio propagation is uncertain. In Bayesian inference framework, it is usually hard to get analytical solutions. In such cases, we resort to Monte Carlo methods to solve the problem numerically. In addition, we apply Bayesian nonparametric modeling for trajectory learning in sport analytics.

The main contribution of this thesis is to propose sequential Monte Carlo methods, namely particle filtering and smoothing, for a novel indoor positioning framework based on proximity reports. The experiment results have been further compared with theoretical bounds derived for this proximity based positioning system. To improve the performance, Bayesian non-parametric modeling, namely Gaussian process, has been applied to better indicate the radio propagation conditions. Then, the position estimates obtained sequentially using filtering and smoothing are further compared with a static solution, which is known as fingerprinting.

Moreover, we propose a trajectory learning framework for flow estimation in sport analytics based on Gaussian processes. To mitigate the computation deficiency of Gaussian process, a grid-based on-line algorithm has been adopted for real-time applications. The resulting trajectory modeling for individual athlete can be used for many purposes, such as performance prediction and analysis, health condition monitoring, etc. Furthermore, we aim at modeling the flow of groups of athletes, which could be potentially used for flow pattern recognition, strategy planning, etc.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2017. 45 p.
Series
Linköping Studies in Science and Technology. Thesis, ISSN 0280-7971 ; 1772
National Category
Control Engineering Signal Processing Probability Theory and Statistics Computer Vision and Robotics (Autonomous Systems) Computational Mathematics
Identifiers
urn:nbn:se:liu:diva-135425 (URN)10.3384/lic.diva-135425 (DOI)9789176855591 (ISBN)
Presentation
2017-03-29, Visionen, Hus B, Campus Valla, Linköping, 10:15 (English)
Opponent
Supervisors
Available from: 2017-03-14 Created: 2017-03-14 Last updated: 2017-03-14Bibliographically approved

Open Access in DiVA

Fusion 2016(504 kB)73 downloads
File information
File name FULLTEXT01.pdfFile size 504 kBChecksum SHA-512
8f12fce14cedfb959ac5d7eec5ddd9eaf980584bb5690d39e6b58bd03ed8f1bce5839733b2a60513d08103c59c22cd368789b05dde334bf9d85cc63c94cb17ae
Type fulltextMimetype application/pdf

Authority records BETA

Zhao, YuxinGunnarsson, Fredrik

Search in DiVA

By author/editor
Zhao, YuxinGunnarsson, Fredrik
By organisation
Automatic ControlFaculty of Science & Engineering
Electrical Engineering, Electronic Engineering, Information EngineeringProbability Theory and Statistics

Search outside of DiVA

GoogleGoogle Scholar
Total: 73 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 265 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf