2014 IEEE International Conference on Healthcare Informatics 2014
DOI: 10.1109/ichi.2014.13
|View full text |Cite
|
Sign up to set email alerts
|

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

Abstract: Link to publication on Research at Birmingham portal General rightsWhen referring to this publication, please cite the published version. Copyright and associated moral rights for publications accessible in the public portal are retained by the authors and/or other copyright owners. It is a condition of accessing this publication that users abide by the legal requirements associated with these rights.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
18
0

Year Published

2015
2015
2019
2019

Publication Types

Select...
3
2
2

Relationship

3
4

Authors

Journals

citations
Cited by 16 publications
(18 citation statements)
references
References 24 publications
0
18
0
Order By: Relevance
“…This has been recognized to be an obstacle to adoption especially for children and the idea of instrumenting objects of everyday life has been recently pursued. In CogWatch project [50] objects of everyday life (e.g., coffee machines, mugs) have been instrumented with inertial and contact wireless sensors to gather data that can be used to assess the correct sequence of gestures (e.g., preparing a coffee) to early detect cognitive decline. Sen.se [51] has pushed this approach further providing motion sensors that can be attached to any daily life object.…”
Section: Related Researchmentioning
confidence: 99%
“…This has been recognized to be an obstacle to adoption especially for children and the idea of instrumenting objects of everyday life has been recently pursued. In CogWatch project [50] objects of everyday life (e.g., coffee machines, mugs) have been instrumented with inertial and contact wireless sensors to gather data that can be used to assess the correct sequence of gestures (e.g., preparing a coffee) to early detect cognitive decline. Sen.se [51] has pushed this approach further providing motion sensors that can be attached to any daily life object.…”
Section: Related Researchmentioning
confidence: 99%
“…The results that will be presented in section 7.1 show that when the cost function (i) is combined with relevant knowledge from users and clinicians (i.e., cost function (ii)), it allows the AIPS to generate more meaningful and efficient strategies during the task. In the rest of this paper, note that when using the cost function (i) only, the AIPS strategies will be referred as Non-Psychologically Plausible; when using the combination (i) and (ii), the AIPS strategies will be referred as Psychologically Plausible [38].…”
Section: Mdp Overview and Adaptationmentioning
confidence: 99%
“…Since many trials are necessary to robustly estimate the Q values, it is common practice that a simulated user is used to interact with the system during policy optimization [40,41,42,43,44,45,46]. Hence, a Simulated User (SimU ) based on real patients' data was implemented in order to generate actions [38]. This SimU is composed of 5 main modules ( Figure 5).…”
Section: Offline Training and Mdp Solvingmentioning
confidence: 99%
“…where c(s, a) is the cost for taking action a when in state s. As explained in [3], c(s, a) is a mechanism to incorporate human judgment about the importance of different types of behaviour into the MDP.…”
Section: Pomdp's Adaptationmentioning
confidence: 99%
“…Mihailidis et al [2] implemented the COACH system that helps patients with Alzheimer's during hand-washing. Jean-Baptiste et al [3] engineered an assistive system named CogWatch, which guides apraxic people during tea-making. The notion of task can also be understood as a daily plan composed of different Activities of Daily Living (ADLs).…”
Section: Introductionmentioning
confidence: 99%