SVM to detect the presence of visitors in a smart home environment

Johanna Petersen, Nicole Larimer, Jeffrey A. Kaye, Misha Pavel, Tamara L. Hayes

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

Abstract

With the rising age of the population, there is increased need to help elderly maintain their independence. Smart homes, employing passive sensor networks and pervasive computing techniques, enable the unobtrusive assessment of activities and behaviors of the elderly which can be useful for health state assessment and intervention. Due to the multiple health benefits associated with socializing, accurately tracking whether an individual has visitors to their home is one of the more important aspects of elders' behaviors that could be assessed with smart home technology. With this goal, we have developed a preliminary SVM model to identify periods where untagged visitors are present in the home. Using the dwell time, number of sensor firings, and number of transitions between major living spaces (living room, dining room, kitchen and bathroom) as features in the model, and self report from two subjects as ground truth, we were able to accurately detect the presence of visitors in the home with a sensitivity and specificity of 0.90 and 0.89 for subject 1, and of 0.67 and 0.78 for subject 2, respectively. These preliminary data demonstrate the feasibility of detecting visitors with in-home sensor data, but highlight the need for more advanced modeling techniques so the model performs well for all subjects and all types of visitors.

Original languageEnglish (US)
Title of host publicationProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Pages5850-5853
Number of pages4
DOIs
StatePublished - 2012
Event34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2012 - San Diego, CA, United States
Duration: Aug 28 2012Sep 1 2012

Other

Other34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2012
CountryUnited States
CitySan Diego, CA
Period8/28/129/1/12

Fingerprint

Toilet Facilities
Insurance Benefits
Health
Self Report
Kitchens
Sensors
Ubiquitous computing
Technology
Sensitivity and Specificity
Sensor networks
Population

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Cite this

Petersen, J., Larimer, N., Kaye, J. A., Pavel, M., & Hayes, T. L. (2012). SVM to detect the presence of visitors in a smart home environment. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS (pp. 5850-5853). [6347324] https://doi.org/10.1109/EMBC.2012.6347324

SVM to detect the presence of visitors in a smart home environment. / Petersen, Johanna; Larimer, Nicole; Kaye, Jeffrey A.; Pavel, Misha; Hayes, Tamara L.

Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2012. p. 5850-5853 6347324.

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

Petersen, J, Larimer, N, Kaye, JA, Pavel, M & Hayes, TL 2012, SVM to detect the presence of visitors in a smart home environment. in Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS., 6347324, pp. 5850-5853, 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2012, San Diego, CA, United States, 8/28/12. https://doi.org/10.1109/EMBC.2012.6347324
Petersen J, Larimer N, Kaye JA, Pavel M, Hayes TL. SVM to detect the presence of visitors in a smart home environment. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2012. p. 5850-5853. 6347324 https://doi.org/10.1109/EMBC.2012.6347324
Petersen, Johanna ; Larimer, Nicole ; Kaye, Jeffrey A. ; Pavel, Misha ; Hayes, Tamara L. / SVM to detect the presence of visitors in a smart home environment. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2012. pp. 5850-5853
@inproceedings{e54c69b66f754f3d851c63e8224af778,
title = "SVM to detect the presence of visitors in a smart home environment",
abstract = "With the rising age of the population, there is increased need to help elderly maintain their independence. Smart homes, employing passive sensor networks and pervasive computing techniques, enable the unobtrusive assessment of activities and behaviors of the elderly which can be useful for health state assessment and intervention. Due to the multiple health benefits associated with socializing, accurately tracking whether an individual has visitors to their home is one of the more important aspects of elders' behaviors that could be assessed with smart home technology. With this goal, we have developed a preliminary SVM model to identify periods where untagged visitors are present in the home. Using the dwell time, number of sensor firings, and number of transitions between major living spaces (living room, dining room, kitchen and bathroom) as features in the model, and self report from two subjects as ground truth, we were able to accurately detect the presence of visitors in the home with a sensitivity and specificity of 0.90 and 0.89 for subject 1, and of 0.67 and 0.78 for subject 2, respectively. These preliminary data demonstrate the feasibility of detecting visitors with in-home sensor data, but highlight the need for more advanced modeling techniques so the model performs well for all subjects and all types of visitors.",
author = "Johanna Petersen and Nicole Larimer and Kaye, {Jeffrey A.} and Misha Pavel and Hayes, {Tamara L.}",
year = "2012",
doi = "10.1109/EMBC.2012.6347324",
language = "English (US)",
isbn = "9781424441198",
pages = "5850--5853",
booktitle = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",

}

TY - GEN

T1 - SVM to detect the presence of visitors in a smart home environment

AU - Petersen, Johanna

AU - Larimer, Nicole

AU - Kaye, Jeffrey A.

AU - Pavel, Misha

AU - Hayes, Tamara L.

PY - 2012

Y1 - 2012

N2 - With the rising age of the population, there is increased need to help elderly maintain their independence. Smart homes, employing passive sensor networks and pervasive computing techniques, enable the unobtrusive assessment of activities and behaviors of the elderly which can be useful for health state assessment and intervention. Due to the multiple health benefits associated with socializing, accurately tracking whether an individual has visitors to their home is one of the more important aspects of elders' behaviors that could be assessed with smart home technology. With this goal, we have developed a preliminary SVM model to identify periods where untagged visitors are present in the home. Using the dwell time, number of sensor firings, and number of transitions between major living spaces (living room, dining room, kitchen and bathroom) as features in the model, and self report from two subjects as ground truth, we were able to accurately detect the presence of visitors in the home with a sensitivity and specificity of 0.90 and 0.89 for subject 1, and of 0.67 and 0.78 for subject 2, respectively. These preliminary data demonstrate the feasibility of detecting visitors with in-home sensor data, but highlight the need for more advanced modeling techniques so the model performs well for all subjects and all types of visitors.

AB - With the rising age of the population, there is increased need to help elderly maintain their independence. Smart homes, employing passive sensor networks and pervasive computing techniques, enable the unobtrusive assessment of activities and behaviors of the elderly which can be useful for health state assessment and intervention. Due to the multiple health benefits associated with socializing, accurately tracking whether an individual has visitors to their home is one of the more important aspects of elders' behaviors that could be assessed with smart home technology. With this goal, we have developed a preliminary SVM model to identify periods where untagged visitors are present in the home. Using the dwell time, number of sensor firings, and number of transitions between major living spaces (living room, dining room, kitchen and bathroom) as features in the model, and self report from two subjects as ground truth, we were able to accurately detect the presence of visitors in the home with a sensitivity and specificity of 0.90 and 0.89 for subject 1, and of 0.67 and 0.78 for subject 2, respectively. These preliminary data demonstrate the feasibility of detecting visitors with in-home sensor data, but highlight the need for more advanced modeling techniques so the model performs well for all subjects and all types of visitors.

UR - http://www.scopus.com/inward/record.url?scp=84870844101&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870844101&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2012.6347324

DO - 10.1109/EMBC.2012.6347324

M3 - Conference contribution

C2 - 23367259

SN - 9781424441198

SP - 5850

EP - 5853

BT - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

ER -