Distributed Activity Recognition with Fuzzy-Enabled Wireless Sensor Networks

Mihai Marin Perianu; C. Lombriser; O. Amft; Paul J.M. Havinga; G. Troster

doi:10.1007/978-3-540-69170-9_20

Distributed Activity Recognition with Fuzzy-Enabled Wireless Sensor Networks

Mihai Marin Perianu, C. Lombriser, O. Amft, Paul J.M. Havinga, G. Troster

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

25 Citations (Scopus)

19 Downloads (Pure)

Abstract

Wireless sensor nodes can act as distributed detectors for recognizing activities online, with the final goal of assisting the users in their working environment. We propose an activity recognition architecture based on fuzzy logic, through which multiple nodes collaborate to produce a reliable recognition result from unreliable sensor data. As an extension to the regular fuzzy inference, we incorporate temporal order knowledge of the sequences of operations involved in the activities. The performance evaluation is based on experimental data from a car assembly trial. The system achieves an overall recognition performance of 0.81 recall and 0.79 precision with regular fuzzy inference, and 0.85 recall and 0.85 precision when considering temporal order knowledge. We also present early experiences with implementing the recognition system on sensor nodes. The results show that the algorithms can run online, with execution times in the order of 40ms, for the whole recognition chain, and memory overhead in the order of 1.5kB RAM.

Original language	Undefined
Title of host publication	Distributed Computing in Sensor Systems
Publisher	Springer
Pages	296-313
Number of pages	18
ISBN (Print)	978-3-540-69169-3
DOIs	https://doi.org/10.1007/978-3-540-69170-9_20
Publication status	Published - Jun 2008
Event	4th IEEE International Conference on Distributed Computing in Sensor Systems, DCOSS 2008 - Santorini, Greece Duration: 11 Jun 2008 → 14 Jun 2008 Conference number: 4 http://www.dcoss.org/dcoss08/index.php

Publication series

Name
Publisher	Springer Verlag
Number	274

Conference

Conference	4th IEEE International Conference on Distributed Computing in Sensor Systems, DCOSS 2008
Abbreviated title	DCOSS 2008
Country/Territory	Greece
City	Santorini
Period	11/06/08 → 14/06/08
Internet address	http://www.dcoss.org/dcoss08/index.php

Keywords

IR-62358
EWI-12875
EC Grant Agreement nr.: FP7/215923
METIS-251006

Access to Document

10.1007/978-3-540-69170-9_20

http://eprints.eemcs.utwente.nl/secure2/12875/01/DWARF.pdf

Cite this

@inproceedings{b3d8a8bffd2240c8ba38cc7f89b93c5f,

title = "Distributed Activity Recognition with Fuzzy-Enabled Wireless Sensor Networks",

abstract = "Wireless sensor nodes can act as distributed detectors for recognizing activities online, with the final goal of assisting the users in their working environment. We propose an activity recognition architecture based on fuzzy logic, through which multiple nodes collaborate to produce a reliable recognition result from unreliable sensor data. As an extension to the regular fuzzy inference, we incorporate temporal order knowledge of the sequences of operations involved in the activities. The performance evaluation is based on experimental data from a car assembly trial. The system achieves an overall recognition performance of 0.81 recall and 0.79 precision with regular fuzzy inference, and 0.85 recall and 0.85 precision when considering temporal order knowledge. We also present early experiences with implementing the recognition system on sensor nodes. The results show that the algorithms can run online, with execution times in the order of 40ms, for the whole recognition chain, and memory overhead in the order of 1.5kB RAM.",

keywords = "IR-62358, EWI-12875, EC Grant Agreement nr.: FP7/215923, METIS-251006",

author = "{Marin Perianu}, Mihai and C. Lombriser and O. Amft and Havinga, {Paul J.M.} and G. Troster",

note = "10.1007/978-3-540-69170-9_20 ; 4th IEEE International Conference on Distributed Computing in Sensor Systems, DCOSS 2008 ; Conference date: 11-06-2008 Through 14-06-2008",

year = "2008",

month = jun,

doi = "10.1007/978-3-540-69170-9_20",

language = "Undefined",

isbn = "978-3-540-69169-3",

publisher = "Springer",

number = "274",

pages = "296--313",

booktitle = "Distributed Computing in Sensor Systems",

address = "Germany",

url = "http://www.dcoss.org/dcoss08/index.php",

}

Marin Perianu, M, Lombriser, C, Amft, O, Havinga, PJM & Troster, G 2008, Distributed Activity Recognition with Fuzzy-Enabled Wireless Sensor Networks. in Distributed Computing in Sensor Systems., 10.1007/978-3-540-69170-9_20, Springer, pp. 296-313, 4th IEEE International Conference on Distributed Computing in Sensor Systems, DCOSS 2008, Santorini, Greece, 11/06/08. https://doi.org/10.1007/978-3-540-69170-9_20

TY - GEN

T1 - Distributed Activity Recognition with Fuzzy-Enabled Wireless Sensor Networks

AU - Marin Perianu, Mihai

AU - Lombriser, C.

AU - Amft, O.

AU - Havinga, Paul J.M.

AU - Troster, G.

N1 - Conference code: 4

PY - 2008/6

Y1 - 2008/6

N2 - Wireless sensor nodes can act as distributed detectors for recognizing activities online, with the final goal of assisting the users in their working environment. We propose an activity recognition architecture based on fuzzy logic, through which multiple nodes collaborate to produce a reliable recognition result from unreliable sensor data. As an extension to the regular fuzzy inference, we incorporate temporal order knowledge of the sequences of operations involved in the activities. The performance evaluation is based on experimental data from a car assembly trial. The system achieves an overall recognition performance of 0.81 recall and 0.79 precision with regular fuzzy inference, and 0.85 recall and 0.85 precision when considering temporal order knowledge. We also present early experiences with implementing the recognition system on sensor nodes. The results show that the algorithms can run online, with execution times in the order of 40ms, for the whole recognition chain, and memory overhead in the order of 1.5kB RAM.

AB - Wireless sensor nodes can act as distributed detectors for recognizing activities online, with the final goal of assisting the users in their working environment. We propose an activity recognition architecture based on fuzzy logic, through which multiple nodes collaborate to produce a reliable recognition result from unreliable sensor data. As an extension to the regular fuzzy inference, we incorporate temporal order knowledge of the sequences of operations involved in the activities. The performance evaluation is based on experimental data from a car assembly trial. The system achieves an overall recognition performance of 0.81 recall and 0.79 precision with regular fuzzy inference, and 0.85 recall and 0.85 precision when considering temporal order knowledge. We also present early experiences with implementing the recognition system on sensor nodes. The results show that the algorithms can run online, with execution times in the order of 40ms, for the whole recognition chain, and memory overhead in the order of 1.5kB RAM.

KW - IR-62358

KW - EWI-12875

KW - EC Grant Agreement nr.: FP7/215923

KW - METIS-251006

U2 - 10.1007/978-3-540-69170-9_20

DO - 10.1007/978-3-540-69170-9_20

M3 - Conference contribution

SN - 978-3-540-69169-3

SP - 296

EP - 313

BT - Distributed Computing in Sensor Systems

PB - Springer

T2 - 4th IEEE International Conference on Distributed Computing in Sensor Systems, DCOSS 2008

Y2 - 11 June 2008 through 14 June 2008

ER -