Activity recognition using conditional random field

Megha Agarwal; Peter Flach

doi:10.1145/2790044.2790045

Activity recognition using conditional random field

Megha Agarwal, Peter Flach

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

7 Citations (Scopus)

Abstract

Activity Recognition is an integral component of ubiquitous computing. Recognizing an activity is a challenging task since activities can be concurrent, interleaved or ambiguous and can consist of multiple actors (which would require parallel activity recognition). This paper investigates how the discriminative nature of Conditional Random Fields (CRF) can be exploited to enhance the accuracy of recognizing activities when compared to that achieved using generative models. It aims to apply CRF to recognize complex activities, analyze the model trained by CRF and evaluate the performance of CRF against existing models using Stochastic Gradient Descent (which is suitable for online learning).

Original language	English
Title of host publication	Proceedings of the 2nd international Workshop on Sensor-based Activity Recognition and Interaction
DOIs	https://doi.org/10.1145/2790044.2790045
Publication status	Published - 25 Jun 2015
Event	2nd International Workshop on Sensor-Based Activity Recognition and Interaction, iWOAR 2015 - Rostock, Germany Duration: 25 Jun 2015 → 26 Jun 2015

Conference

Conference	2nd International Workshop on Sensor-Based Activity Recognition and Interaction, iWOAR 2015
Country/Territory	Germany
City	Rostock
Period	25/06/15 → 26/06/15

Structured keywords

Jean Golding
SPHERE

Keywords

Activities of daily living
Conditional Random Fields
Online learning
Sensor based activity recognition
Supervised learning

Access to Document

10.1145/2790044.2790045

Handle.net

Persistent link

Cite this

@inproceedings{8ae6b5affcdb40508fef9d529c0fd44d,

title = "Activity recognition using conditional random field",

abstract = "Activity Recognition is an integral component of ubiquitous computing. Recognizing an activity is a challenging task since activities can be concurrent, interleaved or ambiguous and can consist of multiple actors (which would require parallel activity recognition). This paper investigates how the discriminative nature of Conditional Random Fields (CRF) can be exploited to enhance the accuracy of recognizing activities when compared to that achieved using generative models. It aims to apply CRF to recognize complex activities, analyze the model trained by CRF and evaluate the performance of CRF against existing models using Stochastic Gradient Descent (which is suitable for online learning).",

keywords = "Activities of daily living, Conditional Random Fields, Online learning, Sensor based activity recognition, Supervised learning",

author = "Megha Agarwal and Peter Flach",

year = "2015",

month = jun,

day = "25",

doi = "10.1145/2790044.2790045",

language = "English",

isbn = "9781450334549",

booktitle = "Proceedings of the 2nd international Workshop on Sensor-based Activity Recognition and Interaction",

note = "2nd International Workshop on Sensor-Based Activity Recognition and Interaction, iWOAR 2015 ; Conference date: 25-06-2015 Through 26-06-2015",

}

TY - GEN

T1 - Activity recognition using conditional random field

AU - Agarwal, Megha

AU - Flach, Peter

PY - 2015/6/25

Y1 - 2015/6/25

N2 - Activity Recognition is an integral component of ubiquitous computing. Recognizing an activity is a challenging task since activities can be concurrent, interleaved or ambiguous and can consist of multiple actors (which would require parallel activity recognition). This paper investigates how the discriminative nature of Conditional Random Fields (CRF) can be exploited to enhance the accuracy of recognizing activities when compared to that achieved using generative models. It aims to apply CRF to recognize complex activities, analyze the model trained by CRF and evaluate the performance of CRF against existing models using Stochastic Gradient Descent (which is suitable for online learning).

AB - Activity Recognition is an integral component of ubiquitous computing. Recognizing an activity is a challenging task since activities can be concurrent, interleaved or ambiguous and can consist of multiple actors (which would require parallel activity recognition). This paper investigates how the discriminative nature of Conditional Random Fields (CRF) can be exploited to enhance the accuracy of recognizing activities when compared to that achieved using generative models. It aims to apply CRF to recognize complex activities, analyze the model trained by CRF and evaluate the performance of CRF against existing models using Stochastic Gradient Descent (which is suitable for online learning).

KW - Activities of daily living

KW - Conditional Random Fields

KW - Online learning

KW - Sensor based activity recognition

KW - Supervised learning

UR - http://www.scopus.com/inward/record.url?scp=84958548405&partnerID=8YFLogxK

U2 - 10.1145/2790044.2790045

DO - 10.1145/2790044.2790045

M3 - Conference Contribution (Conference Proceeding)

AN - SCOPUS:84958548405

SN - 9781450334549

BT - Proceedings of the 2nd international Workshop on Sensor-based Activity Recognition and Interaction

T2 - 2nd International Workshop on Sensor-Based Activity Recognition and Interaction, iWOAR 2015

Y2 - 25 June 2015 through 26 June 2015

ER -

Activity recognition using conditional random field

Abstract

Conference

Structured keywords

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

SPHERE (EPSRC IRC)

Cite this

Activity recognition using conditional random field

Abstract

Conference

Structured keywords

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Projects

SPHERE (EPSRC IRC)

Cite this