Activity recognition in WSN

A data-driven approach

Muhammad Arshad Awan, Zheng Guangbin, Shin-Dug Kim

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

3 Citations (Scopus)

Abstract

Activity recognition is a key component in identifying the context of a user for providing services based on the application. In this study, we propose a model that is based on the recognition of users' activities through wireless sensors network technologies. The model is composed of four components: set of sensors, set of activities, backend server with machine learning algorithms and a GUI application for the interaction with the user. New sensors can be added to the system based on the novel activities. In order to train the model, a sequence of steps involved in an activity need to be performed and then the model is applied for the identification of the same activity in future and visualize through GUI application. A prototype is developed to show the usability of the proposed model. As a pilot testing only accelerometer data of android phone is used to identify the activities of daily living (ADL); sitting, standing, walking and jogging. The model is trained by getting the sensors data while performing activities and tested on real data. A good accuracy of results i.e. about 96% on average is achieved in all activities.

Original languageEnglish
Title of host publicationProceedings - 2012 7th International Conference on Computing and Convergence Technology (ICCIT, ICEI and ICACT), ICCCT 2012
Pages15-20
Number of pages6
Publication statusPublished - 2012 Dec 1
Event2012 7th International Conference on Computing and Convergence Technology (ICCIT, ICEI and ICACT), ICCCT 2012 - Seoul, Korea, Republic of
Duration: 2012 Dec 32012 Dec 5

Other

Other2012 7th International Conference on Computing and Convergence Technology (ICCIT, ICEI and ICACT), ICCCT 2012
CountryKorea, Republic of
CitySeoul
Period12/12/312/12/5

Fingerprint

Graphical user interfaces
Sensors
Accelerometers
Learning algorithms
Learning systems
Wireless sensor networks
Identification (control systems)
Servers
Testing

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Software

Cite this

Awan, M. A., Guangbin, Z., & Kim, S-D. (2012). Activity recognition in WSN: A data-driven approach. In Proceedings - 2012 7th International Conference on Computing and Convergence Technology (ICCIT, ICEI and ICACT), ICCCT 2012 (pp. 15-20). [6530291]
Awan, Muhammad Arshad ; Guangbin, Zheng ; Kim, Shin-Dug. / Activity recognition in WSN : A data-driven approach. Proceedings - 2012 7th International Conference on Computing and Convergence Technology (ICCIT, ICEI and ICACT), ICCCT 2012. 2012. pp. 15-20
@inproceedings{4ac17f3707c84dfaa7c31c16253e9f3d,
title = "Activity recognition in WSN: A data-driven approach",
abstract = "Activity recognition is a key component in identifying the context of a user for providing services based on the application. In this study, we propose a model that is based on the recognition of users' activities through wireless sensors network technologies. The model is composed of four components: set of sensors, set of activities, backend server with machine learning algorithms and a GUI application for the interaction with the user. New sensors can be added to the system based on the novel activities. In order to train the model, a sequence of steps involved in an activity need to be performed and then the model is applied for the identification of the same activity in future and visualize through GUI application. A prototype is developed to show the usability of the proposed model. As a pilot testing only accelerometer data of android phone is used to identify the activities of daily living (ADL); sitting, standing, walking and jogging. The model is trained by getting the sensors data while performing activities and tested on real data. A good accuracy of results i.e. about 96{\%} on average is achieved in all activities.",
author = "Awan, {Muhammad Arshad} and Zheng Guangbin and Shin-Dug Kim",
year = "2012",
month = "12",
day = "1",
language = "English",
isbn = "9788994364216",
pages = "15--20",
booktitle = "Proceedings - 2012 7th International Conference on Computing and Convergence Technology (ICCIT, ICEI and ICACT), ICCCT 2012",

}

Awan, MA, Guangbin, Z & Kim, S-D 2012, Activity recognition in WSN: A data-driven approach. in Proceedings - 2012 7th International Conference on Computing and Convergence Technology (ICCIT, ICEI and ICACT), ICCCT 2012., 6530291, pp. 15-20, 2012 7th International Conference on Computing and Convergence Technology (ICCIT, ICEI and ICACT), ICCCT 2012, Seoul, Korea, Republic of, 12/12/3.

Activity recognition in WSN : A data-driven approach. / Awan, Muhammad Arshad; Guangbin, Zheng; Kim, Shin-Dug.

Proceedings - 2012 7th International Conference on Computing and Convergence Technology (ICCIT, ICEI and ICACT), ICCCT 2012. 2012. p. 15-20 6530291.

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

TY - GEN

T1 - Activity recognition in WSN

T2 - A data-driven approach

AU - Awan, Muhammad Arshad

AU - Guangbin, Zheng

AU - Kim, Shin-Dug

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Activity recognition is a key component in identifying the context of a user for providing services based on the application. In this study, we propose a model that is based on the recognition of users' activities through wireless sensors network technologies. The model is composed of four components: set of sensors, set of activities, backend server with machine learning algorithms and a GUI application for the interaction with the user. New sensors can be added to the system based on the novel activities. In order to train the model, a sequence of steps involved in an activity need to be performed and then the model is applied for the identification of the same activity in future and visualize through GUI application. A prototype is developed to show the usability of the proposed model. As a pilot testing only accelerometer data of android phone is used to identify the activities of daily living (ADL); sitting, standing, walking and jogging. The model is trained by getting the sensors data while performing activities and tested on real data. A good accuracy of results i.e. about 96% on average is achieved in all activities.

AB - Activity recognition is a key component in identifying the context of a user for providing services based on the application. In this study, we propose a model that is based on the recognition of users' activities through wireless sensors network technologies. The model is composed of four components: set of sensors, set of activities, backend server with machine learning algorithms and a GUI application for the interaction with the user. New sensors can be added to the system based on the novel activities. In order to train the model, a sequence of steps involved in an activity need to be performed and then the model is applied for the identification of the same activity in future and visualize through GUI application. A prototype is developed to show the usability of the proposed model. As a pilot testing only accelerometer data of android phone is used to identify the activities of daily living (ADL); sitting, standing, walking and jogging. The model is trained by getting the sensors data while performing activities and tested on real data. A good accuracy of results i.e. about 96% on average is achieved in all activities.

UR - http://www.scopus.com/inward/record.url?scp=84881147895&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881147895&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9788994364216

SP - 15

EP - 20

BT - Proceedings - 2012 7th International Conference on Computing and Convergence Technology (ICCIT, ICEI and ICACT), ICCCT 2012

ER -

Awan MA, Guangbin Z, Kim S-D. Activity recognition in WSN: A data-driven approach. In Proceedings - 2012 7th International Conference on Computing and Convergence Technology (ICCIT, ICEI and ICACT), ICCCT 2012. 2012. p. 15-20. 6530291