Jyotish: Constructive approach for context predictions of people movement from joint Wifi/Bluetooth trace

Long Vu, Quang Do, Klara Nahrstedt

Research output: Contribution to journalArticle

Abstract

It is well known that people movement exhibits a high degree of repetition since people visit regular places and make regular contacts for their daily activities. This paper1 presents a novel framework named Jyotish,2 which constructs a predictive model by exploiting the regularity of people movement found in the real joint Wifi/Bluetooth trace. The constructed model is able to answer three fundamental questions: (1) where the person will stay, (2) how long she will stay at the location, and (3) who she will meet. In order to construct the predictive model, Jyotish includes an efficient clustering algorithm to cluster Wifi access point information in the Wifi trace into locations. Then, we construct a Naive Bayesian classifier to assign these locations to records in the Bluetooth trace and obtain a fine granularity of people movement. Next, the fine grain movement trace is used to construct the predictive model including location predictor, stay duration predictor, and contact predictor to provide answers for three questions above. Finally, we evaluate the constructed predictive model over the real Wifi/Bluetooth trace collected by 50 participants in University of Illinois campus from March to August 2010. Evaluation results show that Jyotish successfully constructs a predictive model, which provides a considerably high prediction accuracy of people movement.

Original languageEnglish (US)
Pages (from-to)690-704
Number of pages15
JournalPervasive and Mobile Computing
Volume7
Issue number6
DOIs
StatePublished - Dec 2011

Fingerprint

Bluetooth
Wi-Fi
Predictive Model
Trace
Prediction
Predictors
Contact
Bayesian Classifier
Granularity
Clustering Algorithm
Assign
Person
Clustering algorithms
Efficient Algorithms
Regularity
Context
Movement
Classifiers
Evaluate
Evaluation

Keywords

  • Bluetooth trace
  • People movement prediction
  • People movement trace
  • Wifi trace

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Software
  • Information Systems
  • Hardware and Architecture
  • Computer Science Applications
  • Computer Networks and Communications
  • Applied Mathematics

Cite this

Jyotish : Constructive approach for context predictions of people movement from joint Wifi/Bluetooth trace. / Vu, Long; Do, Quang; Nahrstedt, Klara.

In: Pervasive and Mobile Computing, Vol. 7, No. 6, 12.2011, p. 690-704.

Research output: Contribution to journalArticle

@article{992760ddea314758beb1ecc218b4b745,
title = "Jyotish: Constructive approach for context predictions of people movement from joint Wifi/Bluetooth trace",
abstract = "It is well known that people movement exhibits a high degree of repetition since people visit regular places and make regular contacts for their daily activities. This paper1 presents a novel framework named Jyotish,2 which constructs a predictive model by exploiting the regularity of people movement found in the real joint Wifi/Bluetooth trace. The constructed model is able to answer three fundamental questions: (1) where the person will stay, (2) how long she will stay at the location, and (3) who she will meet. In order to construct the predictive model, Jyotish includes an efficient clustering algorithm to cluster Wifi access point information in the Wifi trace into locations. Then, we construct a Naive Bayesian classifier to assign these locations to records in the Bluetooth trace and obtain a fine granularity of people movement. Next, the fine grain movement trace is used to construct the predictive model including location predictor, stay duration predictor, and contact predictor to provide answers for three questions above. Finally, we evaluate the constructed predictive model over the real Wifi/Bluetooth trace collected by 50 participants in University of Illinois campus from March to August 2010. Evaluation results show that Jyotish successfully constructs a predictive model, which provides a considerably high prediction accuracy of people movement.",
keywords = "Bluetooth trace, People movement prediction, People movement trace, Wifi trace",
author = "Long Vu and Quang Do and Klara Nahrstedt",
year = "2011",
month = "12",
doi = "10.1016/j.pmcj.2011.07.004",
language = "English (US)",
volume = "7",
pages = "690--704",
journal = "Pervasive and Mobile Computing",
issn = "1574-1192",
publisher = "Elsevier",
number = "6",

}

TY - JOUR

T1 - Jyotish

T2 - Constructive approach for context predictions of people movement from joint Wifi/Bluetooth trace

AU - Vu, Long

AU - Do, Quang

AU - Nahrstedt, Klara

PY - 2011/12

Y1 - 2011/12

N2 - It is well known that people movement exhibits a high degree of repetition since people visit regular places and make regular contacts for their daily activities. This paper1 presents a novel framework named Jyotish,2 which constructs a predictive model by exploiting the regularity of people movement found in the real joint Wifi/Bluetooth trace. The constructed model is able to answer three fundamental questions: (1) where the person will stay, (2) how long she will stay at the location, and (3) who she will meet. In order to construct the predictive model, Jyotish includes an efficient clustering algorithm to cluster Wifi access point information in the Wifi trace into locations. Then, we construct a Naive Bayesian classifier to assign these locations to records in the Bluetooth trace and obtain a fine granularity of people movement. Next, the fine grain movement trace is used to construct the predictive model including location predictor, stay duration predictor, and contact predictor to provide answers for three questions above. Finally, we evaluate the constructed predictive model over the real Wifi/Bluetooth trace collected by 50 participants in University of Illinois campus from March to August 2010. Evaluation results show that Jyotish successfully constructs a predictive model, which provides a considerably high prediction accuracy of people movement.

AB - It is well known that people movement exhibits a high degree of repetition since people visit regular places and make regular contacts for their daily activities. This paper1 presents a novel framework named Jyotish,2 which constructs a predictive model by exploiting the regularity of people movement found in the real joint Wifi/Bluetooth trace. The constructed model is able to answer three fundamental questions: (1) where the person will stay, (2) how long she will stay at the location, and (3) who she will meet. In order to construct the predictive model, Jyotish includes an efficient clustering algorithm to cluster Wifi access point information in the Wifi trace into locations. Then, we construct a Naive Bayesian classifier to assign these locations to records in the Bluetooth trace and obtain a fine granularity of people movement. Next, the fine grain movement trace is used to construct the predictive model including location predictor, stay duration predictor, and contact predictor to provide answers for three questions above. Finally, we evaluate the constructed predictive model over the real Wifi/Bluetooth trace collected by 50 participants in University of Illinois campus from March to August 2010. Evaluation results show that Jyotish successfully constructs a predictive model, which provides a considerably high prediction accuracy of people movement.

KW - Bluetooth trace

KW - People movement prediction

KW - People movement trace

KW - Wifi trace

UR - http://www.scopus.com/inward/record.url?scp=81855218655&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=81855218655&partnerID=8YFLogxK

U2 - 10.1016/j.pmcj.2011.07.004

DO - 10.1016/j.pmcj.2011.07.004

M3 - Article

AN - SCOPUS:81855218655

VL - 7

SP - 690

EP - 704

JO - Pervasive and Mobile Computing

JF - Pervasive and Mobile Computing

SN - 1574-1192

IS - 6

ER -