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

Author

Jean-Baptiste, Emilie M. D. ; Nabiei, Roozbeh ; Parekh, Manish ; Fringi, Evangelia ; Drozdowska, Bogna ; Baber, Chris ; Jancovic, Peter ; Rotshein, Pia ; Russell, Martin

Author_Institution

Sch. of Electron. Electr. & Comput. Eng., Univ. of Birmingham, Birmingham, UK

fYear

2014

Firstpage

39

Lastpage

44

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.

Keywords

cognition; decision theory; hidden Markov models; medical computing; patient rehabilitation; AADS; ADLs; AR; Cog Watch; Markov decision process; TM; action disorganization syndrome; activities of daily living; apraxia; automatic planning; cognitive rehabilitation; hidden Markov models; intelligent assistive system; patient retraining; real-time action recognition; stroke survivors; task model; task performance improvement; user simulation; Artificial intelligence; Dairy products; Detectors; Hidden Markov models; Psychology; Sugar; Action Recognition; HMM; MDP; Rehabilitation System; Task Model;

fLanguage

English

Publisher

ieee

Conference_Titel

Healthcare Informatics (ICHI), 2014 IEEE International Conference on

Type

conf

DOI

10.1109/ICHI.2014.13

Filename

7052468