Detecting Wandering Behavior Based on GPS Traces for Elders with Dementia

Qiang Lin; Daqing Zhang; Xiaodi Huang; Hongbo Ni; Xingshe Zhou

doi:10.1109/ICARCV.2012.6485238

Detecting Wandering Behavior Based on GPS Traces for Elders with Dementia

Qiang Lin, Daqing Zhang, Xiaodi Huang, Hongbo Ni, Xingshe Zhou

Research output: Book chapter/Published conference paper › Conference paper › peer-review

58 Citations (Scopus)

4 Downloads (Pure)

Abstract

Wandering is among the most frequent problematic, and dangerous behaviors for elders with dementia. Frequent wanderers likely suffer falls and fractures, which affect the safety and quality of their lives. In order to monitor outdoor wandering of elderly people with dementia, this paper proposes a real-time method for wandering detection based on individuals’ GPS traces. By representing wandering traces as loops, the problem of wandering detection is transformed into detecting loops in elders’ mobility trajectories. Specifically, the raw GPS data is first preprocessed to remove noisy and crowded points by performing an online mean shift clustering. A novel method called 0_WD is then presented that is able to detect loop-like traces on the fly. The experimental results on the GPS datasets of several elders have show that the 0_WD method is effective and efficient in detecting wandering behaviors, in terms of detection performance (AUC > 0.99, and 90% detection rate with less than 5% of the false alarm rate), as well as time complexity.

Original language	English
Title of host publication	Proceedings of the 12th International Conference on Control, Automation, Robotics and Vision
Subtitle of host publication	ICARCV 2012
Place of Publication	United States
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	672-677
Number of pages	6
ISBN (Electronic)	9781467318723
ISBN (Print)	9781467318716
DOIs	https://doi.org/10.1109/ICARCV.2012.6485238
Publication status	Published - 2012
Event	12th International Conference on Control, Automation, Robotics and Vision: ICARCV 2012 - Guangzhou Baiyun International Convention Center, Guangzhou, China Duration: 05 Dec 2012 → 07 Dec 2012 https://web.archive.org/web/20121104092339/http://icarcv.org/2012/ (Conference website)

Conference

Conference	12th International Conference on Control, Automation, Robotics and Vision
Country/Territory	China
City	Guangzhou
Period	05/12/12 → 07/12/12
Other	Inaugurated in 1990, ICARCV is a biennial event and has proven to be a premium forum where researchers, professionals and engineers in the area of Control, Automation, Robotics and Vision meet to interact and exchange the latest theoretical and experimental results in these four areas. The future ICARCV will strive to serve the same purpose. To help delegates to be in touch with us, a permanent email address (secretariat@icarcv.org) and website (http://www.icarcv.org) have been set up.
Internet address	https://web.archive.org/web/20121104092339/http://icarcv.org/2012/ (Conference website)

Access to Document

10.1109/ICARCV.2012.6485238

Cite this

@inproceedings{381257425b1a407d9fc0544509015b20,

title = "Detecting Wandering Behavior Based on GPS Traces for Elders with Dementia",

abstract = "Wandering is among the most frequent problematic, and dangerous behaviors for elders with dementia. Frequent wanderers likely suffer falls and fractures, which affect the safety and quality of their lives. In order to monitor outdoor wandering of elderly people with dementia, this paper proposes a real-time method for wandering detection based on individuals{\textquoteright} GPS traces. By representing wandering traces as loops, the problem of wandering detection is transformed into detecting loops in elders{\textquoteright} mobility trajectories. Specifically, the raw GPS data is first preprocessed to remove noisy and crowded points by performing an online mean shift clustering. A novel method called 0_WD is then presented that is able to detect loop-like traces on the fly. The experimental results on the GPS datasets of several elders have show that the 0_WD method is effective and efficient in detecting wandering behaviors, in terms of detection performance (AUC > 0.99, and 90% detection rate with less than 5% of the false alarm rate), as well as time complexity. ",

keywords = "Dementia, Elderly care, GPS trace, Wandering behavior, Wandering detection",

author = "Qiang Lin and Daqing Zhang and Xiaodi Huang and Hongbo Ni and Xingshe Zhou",

note = "Imported on 03 May 2017 - DigiTool details were: publisher = United States: Institute of Electrical and Electronics Engineers, 2012. Event dates (773o) = 5-7 December, 2012; Parent title (773t) = International Conference on Control, Automation, Robotics and Vision.; 12th International Conference on Control, Automation, Robotics and Vision : ICARCV 2012 ; Conference date: 05-12-2012 Through 07-12-2012",

year = "2012",

doi = "10.1109/ICARCV.2012.6485238",

language = "English",

isbn = "9781467318716",

pages = "672--677",

booktitle = "Proceedings of the 12th International Conference on Control, Automation, Robotics and Vision",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

url = "https://web.archive.org/web/20121104092339/http://icarcv.org/2012/",

}

Lin, Q, Zhang, D, Huang, X, Ni, H & Zhou, X 2012, Detecting Wandering Behavior Based on GPS Traces for Elders with Dementia. in Proceedings of the 12th International Conference on Control, Automation, Robotics and Vision: ICARCV 2012. IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 672-677, 12th International Conference on Control, Automation, Robotics and Vision, Guangzhou, China, 05/12/12. https://doi.org/10.1109/ICARCV.2012.6485238

Detecting Wandering Behavior Based on GPS Traces for Elders with Dementia. / Lin, Qiang; Zhang, Daqing; Huang, Xiaodi et al.

Proceedings of the 12th International Conference on Control, Automation, Robotics and Vision: ICARCV 2012. United States : IEEE, Institute of Electrical and Electronics Engineers, 2012. p. 672-677.

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - Detecting Wandering Behavior Based on GPS Traces for Elders with Dementia

AU - Lin, Qiang

AU - Zhang, Daqing

AU - Huang, Xiaodi

AU - Ni, Hongbo

AU - Zhou, Xingshe

N1 - Imported on 03 May 2017 - DigiTool details were: publisher = United States: Institute of Electrical and Electronics Engineers, 2012. Event dates (773o) = 5-7 December, 2012; Parent title (773t) = International Conference on Control, Automation, Robotics and Vision.

PY - 2012

Y1 - 2012

N2 - Wandering is among the most frequent problematic, and dangerous behaviors for elders with dementia. Frequent wanderers likely suffer falls and fractures, which affect the safety and quality of their lives. In order to monitor outdoor wandering of elderly people with dementia, this paper proposes a real-time method for wandering detection based on individuals’ GPS traces. By representing wandering traces as loops, the problem of wandering detection is transformed into detecting loops in elders’ mobility trajectories. Specifically, the raw GPS data is first preprocessed to remove noisy and crowded points by performing an online mean shift clustering. A novel method called 0_WD is then presented that is able to detect loop-like traces on the fly. The experimental results on the GPS datasets of several elders have show that the 0_WD method is effective and efficient in detecting wandering behaviors, in terms of detection performance (AUC > 0.99, and 90% detection rate with less than 5% of the false alarm rate), as well as time complexity.

AB - Wandering is among the most frequent problematic, and dangerous behaviors for elders with dementia. Frequent wanderers likely suffer falls and fractures, which affect the safety and quality of their lives. In order to monitor outdoor wandering of elderly people with dementia, this paper proposes a real-time method for wandering detection based on individuals’ GPS traces. By representing wandering traces as loops, the problem of wandering detection is transformed into detecting loops in elders’ mobility trajectories. Specifically, the raw GPS data is first preprocessed to remove noisy and crowded points by performing an online mean shift clustering. A novel method called 0_WD is then presented that is able to detect loop-like traces on the fly. The experimental results on the GPS datasets of several elders have show that the 0_WD method is effective and efficient in detecting wandering behaviors, in terms of detection performance (AUC > 0.99, and 90% detection rate with less than 5% of the false alarm rate), as well as time complexity.

KW - Dementia

KW - Elderly care

KW - GPS trace

KW - Wandering behavior

KW - Wandering detection

U2 - 10.1109/ICARCV.2012.6485238

DO - 10.1109/ICARCV.2012.6485238

M3 - Conference paper

SN - 9781467318716

SP - 672

EP - 677

BT - Proceedings of the 12th International Conference on Control, Automation, Robotics and Vision

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - United States

T2 - 12th International Conference on Control, Automation, Robotics and Vision

Y2 - 5 December 2012 through 7 December 2012

ER -

Detecting Wandering Behavior Based on GPS Traces for Elders with Dementia

Abstract

Conference

Access to Document

Fingerprint

Cite this