International journal of advanced smart convergence

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

Design of a machine learning based mobile application with GPS, mobile sensors, public GIS: real time prediction on personal daily routes

  • Received : 2018.09.06
  • Accepted : 2018.09.17
  • Published : 2018.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Since the global positioning system (GPS) has been included in mobile devices (e.g., for car navigation, in smartphones, and in smart watches), the impact of personal GPS log data on daily life has been unprecedented. For example, such log data have been used to solve public problems, such as mass transit traffic patterns, finding optimum travelers' routes, and determining prospective business zones. However, a real-time analysis technique for GPS log data has been unattainable due to theoretical limitations. We introduced a machine learning model in order to resolve the limitation. In this paper presents a new, three-stage real-time prediction model for a person's daily route activity. In the first stage, a machine learning-based clustering algorithm is adopted for place detection. The training data set was a personal GPS tracking history. In the second stage, prediction of a new person's transient mode is studied. In the third stage, to represent the person's activity on those daily routes, inference rules are applied.

Keywords

OTNBCL_2018_v7n4_27_f0002.png 이미지

Figure 1. Example GPS log data near Washington Square Park, New York City. Courtesy of Open Street map [3].

OTNBCL_2018_v7n4_27_f0003.png 이미지

Figure 2. Example of motion sensor signals by behavioral pose. In this demonstrational graph, we captured signal from accelerator. In the graph, x- axis represents progressing time and y- axis does degree of angle.

OTNBCL_2018_v7n4_27_f0004.png 이미지

Figure 3. Flow chart of daily route prediction model

OTNBCL_2018_v7n4_27_f0005.png 이미지

Figure 4. Example of node clustering output. The blue circles are output of clustering algorithm on GPS points. Confer to Figure 1 for original GPS track

OTNBCL_2018_v7n4_27_f0007.png 이미지

Figure 6. Classification tree for transient mode. The original output is too big to draw (top), part of region was zoomed-in for readability.

OTNBCL_2018_v7n4_27_f0008.png 이미지

Figure 5 Cross validation for training transportation mode

Table 1. Cateogrization of type of places with examples

OTNBCL_2018_v7n4_27_t0001.png 이미지

Table 2. Object design: place definition

OTNBCL_2018_v7n4_27_t0002.png 이미지

Table 3. Object design: path definition

OTNBCL_2018_v7n4_27_t0003.png 이미지

Table 4. Object design: route definition

OTNBCL_2018_v7n4_27_t0004.png 이미지

Table 5. schema of personal knowledge database

OTNBCL_2018_v7n4_27_t0005.png 이미지

Table 6. R statements

OTNBCL_2018_v7n4_27_t0006.png 이미지

Table 7. list of activity ID for PAMAP2 data set

OTNBCL_2018_v7n4_27_t0007.png 이미지

References

  1. Jorge-L. Reyes-Ortiz, Luca Oneto, Albert SamA , Xavier Parra, Davide Anguita. "Transition-Aware Human Activity Recognition Using Smartphones", Neurocomputing. Springer, pp. 754, 2015.
  2. Ricardo Chavarriaga, Hesam Sagha, Alberto Calatroni, Sundaratejaswi Digumarti, Gerhard Troster, Jose del R. Millan, Daniel Roggen. "The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition", Pattern Recognition Letters, Vol 34, pp.1780-1788, 2013. https://doi.org/10.1016/j.patrec.2012.09.014
  3. OpenStreetMap. www.openstreetmap.org
  4. Manuel J. A. Eugster and Thomas Schlesinger. "osmar: OpenStrretMap and R", R Journal Vol 5. pp.1, 2013.
  5. Lin Lao, Dieter Fox, and H. Kauts. "Location based activity recognition", In Proc. NIPS, 2005.
  6. C. Zhou, N. Bhantnagar, S. Shekhar, and L. Terveen. "Mining Personally Important Places from GPS Tracks", ICDEW '07 Proc. 2007 IEEE 23rd ICDEW.
  7. M. Khalaf-Allah. "A Novel GPS-free Method for Mobile Unit Global Positioning in Outdoor Wireless Environments", Wireless Personal Communications, Vol. 44, No. 3, pp, 311-322, 2008. https://doi.org/10.1007/s11277-007-9374-0
  8. T. Theodoridis, A. Agapitos, H. Hu, and S. M. Lucas. "A QA-TSK Fuzzy Model versus Evolutionary Decision Trees Towards Nonlinear Action Pattern Recognition", IEEE International Conference in Information and Automation (ICIA-2010), pp. 1813-1818, 2010.
  9. Y. Zheng, L. Lie, L. Wang, X. Xie. "Learning Transportation Mode from Raw GPS data for Geographic Applications on the Web", Proc. WWW .08 of the 17 ICWWW, 2008.
  10. H. Azami, M. Mosavi, S. Sanei. "Classification of GPS Satellites Using Improved Back Propagation Training Algorithms", Wireless Personal Communications, Vol. 71, No. 2, pp. 789-803, 2013. https://doi.org/10.1007/s11277-012-0844-7
  11. Z. Salcic, E. Chan. "Mobile Station Positioning Using GSM Cellular Phone and Artificial Neural Networks" , Wireless Personal Communications Vol. 14, No.3, pp. 235-254, 2000. https://doi.org/10.1023/A:1008917401129
  12. D. Wang, M. Fattouche, F. Ghannouchi, D. Wang. "Geometry-Based Doppler Analysis for GPS Receivers", Wireless Personal Communications , Vol. 68, No. 1, pp. 1-13, 2013. https://doi.org/10.1007/s11277-011-0435-z
  13. K. Ellis, S. Godbole, S. Marshall, G. Lanckriet, J. Staudenmayer, and J. Kerr. "Identifying Active Travel Behaviors in Challenging Environments Using GPS, Accelerometers, and Machine Learning Algorithms", frontiers in Public Health, vol. 2., pp. 1-8, 2014.
  14. A. Reiss and D. Stricker. "Introducing a New Benchmarked Dataset for Activity Monitoring", The 16th IEEE International Symposium on Wearable Computers (ISWC), 2012.
  15. A. Reiss and D. Stricker. "Creating and Benchmarking a New Dataset for Activity Monitoring", The 5th Workshop on Affect and Behavior Related Assistance (ABRA), 2012.
  16. Davide Anguita, Alessandro Ghio, Luca Oneto, Xavier Parra and Jorge L. Reyes-Ortiz. "A Public Domain Dataset for Human Activity Recognition Using Smartphones". 21th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2013. Bruges, Belgium, 2013.