Intelligent Assistive System Using Real-Time Action Recognition for Stroke Survivors

Emilie Jean-Baptiste; Roozbeh Nabiei; Manish Parekh; Pia Rotshtein; Martin Russell; Peter Jancovic; Evangelia Fringi; B Drozdowska; Chris Baber

doi:10.1109/ICHI.2014.13

Intelligent Assistive System Using Real-Time Action Recognition for Stroke Survivors

Emilie Jean-Baptiste, Roozbeh Nabiei, Manish Parekh, Pia Rotshtein, Martin Russell, Peter Jancovic, Evangelia Fringi, B Drozdowska, Chris Baber

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

13 Citations (Scopus)

313 Downloads (Pure)

Abstract

Cog Watch is an EU project developing technologies for cognitive rehabilitation of stroke patients. The Cog Watch prototype is an automatic system to re-train patients with Apraxia or Action Disorganization Syndrome (AADS) to complete activities of daily living (ADLs). This paper describes the approach to automatic planning based on a Markov Decision Process, and real-time action recognition (AR) based on instrumented objects using Hidden Markov Models. The experimental results demonstrate the ability of a psychologically plausible planning system integrated in a Task Model (TM) to improve task performance via user simulation, and the viability of the approach to AR.

Original language	English
Title of host publication	2014 IEEE International Conference on Healthcare Informatics (ICHI)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	39-44
ISBN (Print)	978-1-4799-5701-9
DOIs	https://doi.org/10.1109/ICHI.2014.13
Publication status	Published - 2014
Event	IEEE International Conference on Healthcare Informatics 2014 (ICHI 2014) - Verona, Italy Duration: 15 Sept 2014 → 17 Sept 2014

Conference

Conference	IEEE International Conference on Healthcare Informatics 2014 (ICHI 2014)
Country/Territory	Italy
City	Verona
Period	15/09/14 → 17/09/14

Access to Document

10.1109/ICHI.2014.13

Jean-Baptiste_et_al_Intelligent_Assistive_System_Post-Print
(c) 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works. Checked June 2015
Accepted author manuscript, 2.13 MBLicence: Other (please specify with Rights Statement)

FP7 COLLAB: COGWATCH - Cognitive Rehabilitation of Apraxia and Action Disorganisation Syndrome
Wing, A., Baber, C., Russell, M., Humphreys, G. & Riddoch, J.
European Commission - Management Costs, European Commission
1/11/11 → 28/02/15
Project: Research

Cite this

Jean-Baptiste, E., Nabiei, R., Parekh, M., Rotshtein, P., Russell, M., Jancovic, P., Fringi, E., Drozdowska, B., & Baber, C. (2014). Intelligent Assistive System Using Real-Time Action Recognition for Stroke Survivors. In 2014 IEEE International Conference on Healthcare Informatics (ICHI) (pp. 39-44). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICHI.2014.13

@inproceedings{acac1687beb94075b499866d6fb2e1b5,

title = "Intelligent Assistive System Using Real-Time Action Recognition for Stroke Survivors",

abstract = "Cog Watch is an EU project developing technologies for cognitive rehabilitation of stroke patients. The Cog Watch prototype is an automatic system to re-train patients with Apraxia or Action Disorganization Syndrome (AADS) to complete activities of daily living (ADLs). This paper describes the approach to automatic planning based on a Markov Decision Process, and real-time action recognition (AR) based on instrumented objects using Hidden Markov Models. The experimental results demonstrate the ability of a psychologically plausible planning system integrated in a Task Model (TM) to improve task performance via user simulation, and the viability of the approach to AR.",

author = "Emilie Jean-Baptiste and Roozbeh Nabiei and Manish Parekh and Pia Rotshtein and Martin Russell and Peter Jancovic and Evangelia Fringi and B Drozdowska and Chris Baber",

year = "2014",

doi = "10.1109/ICHI.2014.13",

language = "English",

isbn = "978-1-4799-5701-9",

pages = "39--44",

booktitle = "2014 IEEE International Conference on Healthcare Informatics (ICHI)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

note = "IEEE International Conference on Healthcare Informatics 2014 (ICHI 2014) ; Conference date: 15-09-2014 Through 17-09-2014",

}

Jean-Baptiste, E, Nabiei, R, Parekh, M, Rotshtein, P, Russell, M, Jancovic, P, Fringi, E, Drozdowska, B & Baber, C 2014, Intelligent Assistive System Using Real-Time Action Recognition for Stroke Survivors. in 2014 IEEE International Conference on Healthcare Informatics (ICHI). Institute of Electrical and Electronics Engineers (IEEE), pp. 39-44, IEEE International Conference on Healthcare Informatics 2014 (ICHI 2014), Verona, Italy, 15/09/14. https://doi.org/10.1109/ICHI.2014.13

Intelligent Assistive System Using Real-Time Action Recognition for Stroke Survivors. / Jean-Baptiste, Emilie; Nabiei, Roozbeh; Parekh, Manish et al.
2014 IEEE International Conference on Healthcare Informatics (ICHI). Institute of Electrical and Electronics Engineers (IEEE), 2014. p. 39-44.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Intelligent Assistive System Using Real-Time Action Recognition for Stroke Survivors

AU - Jean-Baptiste, Emilie

AU - Nabiei, Roozbeh

AU - Parekh, Manish

AU - Rotshtein, Pia

AU - Russell, Martin

AU - Jancovic, Peter

AU - Fringi, Evangelia

AU - Drozdowska, B

AU - Baber, Chris

PY - 2014

Y1 - 2014

N2 - Cog Watch is an EU project developing technologies for cognitive rehabilitation of stroke patients. The Cog Watch prototype is an automatic system to re-train patients with Apraxia or Action Disorganization Syndrome (AADS) to complete activities of daily living (ADLs). This paper describes the approach to automatic planning based on a Markov Decision Process, and real-time action recognition (AR) based on instrumented objects using Hidden Markov Models. The experimental results demonstrate the ability of a psychologically plausible planning system integrated in a Task Model (TM) to improve task performance via user simulation, and the viability of the approach to AR.

AB - Cog Watch is an EU project developing technologies for cognitive rehabilitation of stroke patients. The Cog Watch prototype is an automatic system to re-train patients with Apraxia or Action Disorganization Syndrome (AADS) to complete activities of daily living (ADLs). This paper describes the approach to automatic planning based on a Markov Decision Process, and real-time action recognition (AR) based on instrumented objects using Hidden Markov Models. The experimental results demonstrate the ability of a psychologically plausible planning system integrated in a Task Model (TM) to improve task performance via user simulation, and the viability of the approach to AR.

U2 - 10.1109/ICHI.2014.13

DO - 10.1109/ICHI.2014.13

M3 - Conference contribution

SN - 978-1-4799-5701-9

SP - 39

EP - 44

BT - 2014 IEEE International Conference on Healthcare Informatics (ICHI)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - IEEE International Conference on Healthcare Informatics 2014 (ICHI 2014)

Y2 - 15 September 2014 through 17 September 2014

ER -

Intelligent Assistive System Using Real-Time Action Recognition for Stroke Survivors

Abstract

Conference

Access to Document

Fingerprint

Projects

FP7 COLLAB: COGWATCH - Cognitive Rehabilitation of Apraxia and Action Disorganisation Syndrome

Cite this