Low-cost and device-free activity recognition system with energy harvesting PIR and door sensors

Yukitoshi Kashimoto, Kyoji Hata, Hirohiko Suwa, Manato Fujimoto, Yutaka Arakawa, Takeya Shigezumi, Kunihiro Komiya, Kenta Konishi, Keiichi Yasumoto

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

3 Citations (Scopus)

Abstract

Progress of IoT and ubiquitous computing technologies has strong anticipation to realize smart services in households such as efficient energy-saving appliance control and elderly monitoring. In order to put those applications into practice, high-accuracy and low-cost in-home living activity recognition is essential. Many researches have tackled living activity recognition so far, but the following problems remain: (i)privacy exposure due to utilization of cameras and microphones; (ii) high deployment and maintenance costs due to many sensors used; (iii) burden to force the user to carry the device and (iv) wire installation to supply power and communication between sensor node and server; (v) few recognizable activities; (vi) low recognition accuracy. In this paper, we propose an in-home living activity recognition method to solve all the problems. To solve the problems (i){(iv), our method utilizes only energy harvesting PIR and door sensors with a home server for data collection and processing. The energy harvesting sensor has a solar cell to drive the sensor and wireless communication modules. To solve the problems (v) and (vi), we have tackled the following challenges: (a) determining appropriate features for training samples; and (b) determining the best machine learning algorithm to achieve high recognition accuracy; (c) complementing the dead zone of PIR sensor semipermanently. We have conducted experiments with the sensor by five subjects living in a home for 2{3 days each. As a result, the proposed method has achieved F-measure: 62.8% on average.

Original languageEnglish
Title of host publicationAdjunct Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems
Subtitle of host publicationComputing, Networking and Services, MobiQuitous 2016
PublisherAssociation for Computing Machinery
Pages6-11
Number of pages6
ISBN (Electronic)9781450347594
DOIs
Publication statusPublished - Nov 28 2016
Externally publishedYes
Event13th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2016 - Hiroshima, Japan
Duration: Nov 28 2016Dec 1 2016

Publication series

NameACM International Conference Proceeding Series
Volume28-November-2016

Conference

Conference13th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2016
CountryJapan
CityHiroshima
Period11/28/1612/1/16

Fingerprint

Energy harvesting
Sensors
Costs
Servers
Communication
Ubiquitous computing
Microphones
Sensor nodes
Learning algorithms
Learning systems
Solar cells
Energy conservation
Cameras
Wire
Monitoring
Processing
Experiments

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Kashimoto, Y., Hata, K., Suwa, H., Fujimoto, M., Arakawa, Y., Shigezumi, T., ... Yasumoto, K. (2016). Low-cost and device-free activity recognition system with energy harvesting PIR and door sensors. In Adjunct Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2016 (pp. 6-11). (ACM International Conference Proceeding Series; Vol. 28-November-2016). Association for Computing Machinery. https://doi.org/10.1145/3004010.3006378

Low-cost and device-free activity recognition system with energy harvesting PIR and door sensors. / Kashimoto, Yukitoshi; Hata, Kyoji; Suwa, Hirohiko; Fujimoto, Manato; Arakawa, Yutaka; Shigezumi, Takeya; Komiya, Kunihiro; Konishi, Kenta; Yasumoto, Keiichi.

Adjunct Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2016. Association for Computing Machinery, 2016. p. 6-11 (ACM International Conference Proceeding Series; Vol. 28-November-2016).

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

Kashimoto, Y, Hata, K, Suwa, H, Fujimoto, M, Arakawa, Y, Shigezumi, T, Komiya, K, Konishi, K & Yasumoto, K 2016, Low-cost and device-free activity recognition system with energy harvesting PIR and door sensors. in Adjunct Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2016. ACM International Conference Proceeding Series, vol. 28-November-2016, Association for Computing Machinery, pp. 6-11, 13th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2016, Hiroshima, Japan, 11/28/16. https://doi.org/10.1145/3004010.3006378
Kashimoto Y, Hata K, Suwa H, Fujimoto M, Arakawa Y, Shigezumi T et al. Low-cost and device-free activity recognition system with energy harvesting PIR and door sensors. In Adjunct Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2016. Association for Computing Machinery. 2016. p. 6-11. (ACM International Conference Proceeding Series). https://doi.org/10.1145/3004010.3006378
Kashimoto, Yukitoshi ; Hata, Kyoji ; Suwa, Hirohiko ; Fujimoto, Manato ; Arakawa, Yutaka ; Shigezumi, Takeya ; Komiya, Kunihiro ; Konishi, Kenta ; Yasumoto, Keiichi. / Low-cost and device-free activity recognition system with energy harvesting PIR and door sensors. Adjunct Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2016. Association for Computing Machinery, 2016. pp. 6-11 (ACM International Conference Proceeding Series).
@inproceedings{a226c925361e44cd85ba97b57ae0e440,
title = "Low-cost and device-free activity recognition system with energy harvesting PIR and door sensors",
abstract = "Progress of IoT and ubiquitous computing technologies has strong anticipation to realize smart services in households such as efficient energy-saving appliance control and elderly monitoring. In order to put those applications into practice, high-accuracy and low-cost in-home living activity recognition is essential. Many researches have tackled living activity recognition so far, but the following problems remain: (i)privacy exposure due to utilization of cameras and microphones; (ii) high deployment and maintenance costs due to many sensors used; (iii) burden to force the user to carry the device and (iv) wire installation to supply power and communication between sensor node and server; (v) few recognizable activities; (vi) low recognition accuracy. In this paper, we propose an in-home living activity recognition method to solve all the problems. To solve the problems (i){(iv), our method utilizes only energy harvesting PIR and door sensors with a home server for data collection and processing. The energy harvesting sensor has a solar cell to drive the sensor and wireless communication modules. To solve the problems (v) and (vi), we have tackled the following challenges: (a) determining appropriate features for training samples; and (b) determining the best machine learning algorithm to achieve high recognition accuracy; (c) complementing the dead zone of PIR sensor semipermanently. We have conducted experiments with the sensor by five subjects living in a home for 2{3 days each. As a result, the proposed method has achieved F-measure: 62.8{\%} on average.",
author = "Yukitoshi Kashimoto and Kyoji Hata and Hirohiko Suwa and Manato Fujimoto and Yutaka Arakawa and Takeya Shigezumi and Kunihiro Komiya and Kenta Konishi and Keiichi Yasumoto",
year = "2016",
month = "11",
day = "28",
doi = "10.1145/3004010.3006378",
language = "English",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
pages = "6--11",
booktitle = "Adjunct Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems",

}

TY - GEN

T1 - Low-cost and device-free activity recognition system with energy harvesting PIR and door sensors

AU - Kashimoto, Yukitoshi

AU - Hata, Kyoji

AU - Suwa, Hirohiko

AU - Fujimoto, Manato

AU - Arakawa, Yutaka

AU - Shigezumi, Takeya

AU - Komiya, Kunihiro

AU - Konishi, Kenta

AU - Yasumoto, Keiichi

PY - 2016/11/28

Y1 - 2016/11/28

N2 - Progress of IoT and ubiquitous computing technologies has strong anticipation to realize smart services in households such as efficient energy-saving appliance control and elderly monitoring. In order to put those applications into practice, high-accuracy and low-cost in-home living activity recognition is essential. Many researches have tackled living activity recognition so far, but the following problems remain: (i)privacy exposure due to utilization of cameras and microphones; (ii) high deployment and maintenance costs due to many sensors used; (iii) burden to force the user to carry the device and (iv) wire installation to supply power and communication between sensor node and server; (v) few recognizable activities; (vi) low recognition accuracy. In this paper, we propose an in-home living activity recognition method to solve all the problems. To solve the problems (i){(iv), our method utilizes only energy harvesting PIR and door sensors with a home server for data collection and processing. The energy harvesting sensor has a solar cell to drive the sensor and wireless communication modules. To solve the problems (v) and (vi), we have tackled the following challenges: (a) determining appropriate features for training samples; and (b) determining the best machine learning algorithm to achieve high recognition accuracy; (c) complementing the dead zone of PIR sensor semipermanently. We have conducted experiments with the sensor by five subjects living in a home for 2{3 days each. As a result, the proposed method has achieved F-measure: 62.8% on average.

AB - Progress of IoT and ubiquitous computing technologies has strong anticipation to realize smart services in households such as efficient energy-saving appliance control and elderly monitoring. In order to put those applications into practice, high-accuracy and low-cost in-home living activity recognition is essential. Many researches have tackled living activity recognition so far, but the following problems remain: (i)privacy exposure due to utilization of cameras and microphones; (ii) high deployment and maintenance costs due to many sensors used; (iii) burden to force the user to carry the device and (iv) wire installation to supply power and communication between sensor node and server; (v) few recognizable activities; (vi) low recognition accuracy. In this paper, we propose an in-home living activity recognition method to solve all the problems. To solve the problems (i){(iv), our method utilizes only energy harvesting PIR and door sensors with a home server for data collection and processing. The energy harvesting sensor has a solar cell to drive the sensor and wireless communication modules. To solve the problems (v) and (vi), we have tackled the following challenges: (a) determining appropriate features for training samples; and (b) determining the best machine learning algorithm to achieve high recognition accuracy; (c) complementing the dead zone of PIR sensor semipermanently. We have conducted experiments with the sensor by five subjects living in a home for 2{3 days each. As a result, the proposed method has achieved F-measure: 62.8% on average.

UR - http://www.scopus.com/inward/record.url?scp=85008196697&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85008196697&partnerID=8YFLogxK

U2 - 10.1145/3004010.3006378

DO - 10.1145/3004010.3006378

M3 - Conference contribution

T3 - ACM International Conference Proceeding Series

SP - 6

EP - 11

BT - Adjunct Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems

PB - Association for Computing Machinery

ER -