Spatial and temporal considerations in next place predictions

Bhaskar Prabhala, Thomas F. La Porta

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

We present synthesized findings from a systematic study of user mobility based on a well grounded data set through mining attributes of place-to-place transitions. Next place predictions are the atomic units in constructing end-to-end user mobility trajectories based on historical trace data. These trajectories in turn form models for opportunistic networks to be utilized for providing location and communication services. We start with a baseline of the user's current place, start time, and end time to predict the next place. We demonstrate the efficiency of an algorithm called PeriodicaS through aggregated average prediction accuracies across all users over a large set of diverse participants. PeriodicaS mines periodicity intelligently in users' mobility traces and further improves prediction accuracies with additional classification rules. We derive these classification rules by applying explicit semantic annotations (home, work place and public transportation points associated with places visited), and accompanying group information. We propose novel ways of transforming bits of information in the mobility traces, defined to be inherent semantic annotations, as features for mobility modeling in PeriodicaS. Inherent semantic annotations are computed with temporal variations from visited places such as end time only, and measuring duration time. We deduce more inherent semantic annotations from place rankings by frequency of visits. By progressively employing these two types of semantic annotations, explicitly stated in the data set and deduced from the mobility traces, we improve next place prediction accuracies up to 54% compared to baseline predictions.

Original languageEnglish (US)
Title of host publication2015 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages390-395
Number of pages6
Volume2015-August
ISBN (Electronic)9781467371315
DOIs
StatePublished - Aug 4 2015
EventIEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2015 - Hong Kong, Hong Kong
Duration: Apr 26 2015May 1 2015

Other

OtherIEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2015
CountryHong Kong
CityHong Kong
Period4/26/155/1/15

Fingerprint

Semantics
Trajectories
Communication

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

Prabhala, B., & La Porta, T. F. (2015). Spatial and temporal considerations in next place predictions. In 2015 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2015 (Vol. 2015-August, pp. 390-395). [7179416] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/INFCOMW.2015.7179416
Prabhala, Bhaskar ; La Porta, Thomas F. / Spatial and temporal considerations in next place predictions. 2015 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2015. Vol. 2015-August Institute of Electrical and Electronics Engineers Inc., 2015. pp. 390-395
@inproceedings{43bb683d94f4468590e57f22c6656a73,
title = "Spatial and temporal considerations in next place predictions",
abstract = "We present synthesized findings from a systematic study of user mobility based on a well grounded data set through mining attributes of place-to-place transitions. Next place predictions are the atomic units in constructing end-to-end user mobility trajectories based on historical trace data. These trajectories in turn form models for opportunistic networks to be utilized for providing location and communication services. We start with a baseline of the user's current place, start time, and end time to predict the next place. We demonstrate the efficiency of an algorithm called PeriodicaS through aggregated average prediction accuracies across all users over a large set of diverse participants. PeriodicaS mines periodicity intelligently in users' mobility traces and further improves prediction accuracies with additional classification rules. We derive these classification rules by applying explicit semantic annotations (home, work place and public transportation points associated with places visited), and accompanying group information. We propose novel ways of transforming bits of information in the mobility traces, defined to be inherent semantic annotations, as features for mobility modeling in PeriodicaS. Inherent semantic annotations are computed with temporal variations from visited places such as end time only, and measuring duration time. We deduce more inherent semantic annotations from place rankings by frequency of visits. By progressively employing these two types of semantic annotations, explicitly stated in the data set and deduced from the mobility traces, we improve next place prediction accuracies up to 54{\%} compared to baseline predictions.",
author = "Bhaskar Prabhala and {La Porta}, {Thomas F.}",
year = "2015",
month = "8",
day = "4",
doi = "10.1109/INFCOMW.2015.7179416",
language = "English (US)",
volume = "2015-August",
pages = "390--395",
booktitle = "2015 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Prabhala, B & La Porta, TF 2015, Spatial and temporal considerations in next place predictions. in 2015 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2015. vol. 2015-August, 7179416, Institute of Electrical and Electronics Engineers Inc., pp. 390-395, IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2015, Hong Kong, Hong Kong, 4/26/15. https://doi.org/10.1109/INFCOMW.2015.7179416

Spatial and temporal considerations in next place predictions. / Prabhala, Bhaskar; La Porta, Thomas F.

2015 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2015. Vol. 2015-August Institute of Electrical and Electronics Engineers Inc., 2015. p. 390-395 7179416.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Spatial and temporal considerations in next place predictions

AU - Prabhala, Bhaskar

AU - La Porta, Thomas F.

PY - 2015/8/4

Y1 - 2015/8/4

N2 - We present synthesized findings from a systematic study of user mobility based on a well grounded data set through mining attributes of place-to-place transitions. Next place predictions are the atomic units in constructing end-to-end user mobility trajectories based on historical trace data. These trajectories in turn form models for opportunistic networks to be utilized for providing location and communication services. We start with a baseline of the user's current place, start time, and end time to predict the next place. We demonstrate the efficiency of an algorithm called PeriodicaS through aggregated average prediction accuracies across all users over a large set of diverse participants. PeriodicaS mines periodicity intelligently in users' mobility traces and further improves prediction accuracies with additional classification rules. We derive these classification rules by applying explicit semantic annotations (home, work place and public transportation points associated with places visited), and accompanying group information. We propose novel ways of transforming bits of information in the mobility traces, defined to be inherent semantic annotations, as features for mobility modeling in PeriodicaS. Inherent semantic annotations are computed with temporal variations from visited places such as end time only, and measuring duration time. We deduce more inherent semantic annotations from place rankings by frequency of visits. By progressively employing these two types of semantic annotations, explicitly stated in the data set and deduced from the mobility traces, we improve next place prediction accuracies up to 54% compared to baseline predictions.

AB - We present synthesized findings from a systematic study of user mobility based on a well grounded data set through mining attributes of place-to-place transitions. Next place predictions are the atomic units in constructing end-to-end user mobility trajectories based on historical trace data. These trajectories in turn form models for opportunistic networks to be utilized for providing location and communication services. We start with a baseline of the user's current place, start time, and end time to predict the next place. We demonstrate the efficiency of an algorithm called PeriodicaS through aggregated average prediction accuracies across all users over a large set of diverse participants. PeriodicaS mines periodicity intelligently in users' mobility traces and further improves prediction accuracies with additional classification rules. We derive these classification rules by applying explicit semantic annotations (home, work place and public transportation points associated with places visited), and accompanying group information. We propose novel ways of transforming bits of information in the mobility traces, defined to be inherent semantic annotations, as features for mobility modeling in PeriodicaS. Inherent semantic annotations are computed with temporal variations from visited places such as end time only, and measuring duration time. We deduce more inherent semantic annotations from place rankings by frequency of visits. By progressively employing these two types of semantic annotations, explicitly stated in the data set and deduced from the mobility traces, we improve next place prediction accuracies up to 54% compared to baseline predictions.

UR - http://www.scopus.com/inward/record.url?scp=84943273747&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943273747&partnerID=8YFLogxK

U2 - 10.1109/INFCOMW.2015.7179416

DO - 10.1109/INFCOMW.2015.7179416

M3 - Conference contribution

AN - SCOPUS:84943273747

VL - 2015-August

SP - 390

EP - 395

BT - 2015 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Prabhala B, La Porta TF. Spatial and temporal considerations in next place predictions. In 2015 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2015. Vol. 2015-August. Institute of Electrical and Electronics Engineers Inc. 2015. p. 390-395. 7179416 https://doi.org/10.1109/INFCOMW.2015.7179416