Radu Mariescu-Istodor

Postdoctoral Researcher
University of Eastern Finland



Address:
University of Eastern Finland
School of Computing
Office TB357, Science Park
Joensuu, Finland

Phone:
+358-(0)417517773

Email:


Machine Learning Group

Updated 12.1.2018

PhD


Because more and more users have mobile devices with GPS, the amount of location-based information is becoming difficult to manage. Such information includes geo-tagged photos, service locations and routes. In the Thesis we present efficient methods for storing, searching and visualizing large trajectory collections. All the methods were implemented and tested in Mopsi.

Interactive Applications













Publications

Journal Articles

  1. R. Mariescu-Istodor and P. Fränti, "Grid-based method for GPS route analysis for retrieval", ACM Trans. on Spatial Algorithms and Systems 3 (3), July 2017.

  2. P. Fränti, R. Mariescu-Istodor and L. Sengupta, "O-Mopsi: mobile orienteering game for sightseeing, exercising and education", ACM Trans. on Multimedia, Computing, Communications, and Applications 13 (4), 56:1-25, August 2017. IF=2.25

  3. N. Gali, R. Mariescu-Istodor and P. Fränti, "Using linguistic features to automatically extract web page title", Expert Systems with Applications, 79, 296-312, 2017. IF=2.98

  4. M. I. Malinen, R. Mariescu-Istodor and P. Fränti, "K-means*: Clustering by Gradual Data Transformation", Pattern Recognition, 47 (10), 3376-3386, October 2014. IF=2.63

Refereed Conference Papers

  1. R. Mariescu-Istodor and P. Fränti, "Detecting user actions in location-based systems", Conf. on Location-based Services (LBS), Zürich, Switzerland, January 2018.

  2. R. Mariescu-Istodor, P. Heng and P. Fränti, "Roundness measure for GPS routes", Conf. on Location-based Services (LBS), Zürich, Switzerland, January 2018.

  3. N. Gali, R. Mariescu-Istodor and P. Fränti, "Functional Classification of Websites", Int. Symposium on Information and Communication Technology (SoICT 2017), Nha Trang, Vietnam, 34-41, December 2017.

  4. N. Gali, R. Mariescu-Istodor, P. Fränti, "Similarity measures for title matching", IAPR Int. Conf. on Pattern Recognition, (ICPR'16), Cancun, Mexico, 1549-1554, December 2016.

  5. P. Fränti, R. Mariescu-Istodor, and C. Zhong, "XNN graph", Joint Int. Workshop on Structural, Syntactic, and Statistical Pattern Recognition (S+SSPR'16), Merida, Mexico, LNCS 10029, 207-217, November 2016.

  6. R. Mariescu-Istodor and P. Fränti, "Gesture input for GPS route search", Joint Int. Workshop on Structural, Syntactic, and Statistical Pattern Recognition (S+SSPR'16), Merida, Mexico, LNCS 10029, 439-449, November 2016.

  7. R. Mariescu-Istodor, A. Tabarcea, R. Saeidi and P. Fränti, "Low complexity spatial similarity measure of GPS trajectories", Int. Conf. on Web Information Systems & Technologies (WEBIST'14), Barcelona, Spain, April 2014.

  8. K. Waga, A. Tabarcea, R. Mariescu-Istodor and P. Fränti, "Real Time Access to Multiple GPS Tracks", Int. Conf. on Web Information Systems & Technologies (WEBIST'13), Aachen, Germany, May 2013.

  9. K. Waga, A. Tabarcea, R. Mariescu-Istodor and P. Fränti, "System for real time storage, retrieval and visualization of GPS tracks", Int. Conf. System Theory, Control and Computing (ICSTCC'12), Sinaia, Romania, Vol. 2, October 2012.

Submitted Manuscripts

  1. P. Fränti, R. Mariescu-Istodor and K. Waga, "Similarity of users based on sparce location history", Pattern Recognition Letters.

  2. R. Mariescu-Istodor and P. Fränti, "From Routes to Roads: Infer road network using GPS trajectories", ACM Trans. on Spatial Algorithms and Systems.

  3. N. Gali, R. Mariescu-Istodor, D. Hostettler and P. Fränti, "Similarity of titles", Journal of Information Retrieval.

Teaching

  1. Design and Analysis of Algorithms (exercises)
    University of Eastern Finland, 2014, 2015, 2016, 2017.

  2. Location-Aware Mobile Applications Development
    University of Eastern Finland, 2018.

  3. Here you can find some useful software development practices

Hobbies

  1. Long distance cycling and skiing
    • Skiing max (72 km / 9 h)
    • Cycling max (456 km / 20 h) Story

  2. Origami level*:
    Ancient Dragon by Satoshi Kamiya
    * = the most complicated model I tried