01-09-2012, 05:09 PM
Task Prediction in cooking activities using Hierarchical state space Markov Chain and Object based Task Grouping
Task Prediction.pdf (Size: 733.23 KB / Downloads: 23)
Abstract
Cooking activities are complex activities consisting
of multiple steps or tasks. These tasks can be associated with
one another based on two properties - the temporal structure
that defines the sequence of occurrence of tasks and the objects
that are used in the activity. This paper develops cooking
activity models for the purpose of task prediction based on
these two properties. The temporal structure of the sequence of
tasks is captured by the novel hierarchical state space markov
chain (HMC) and the object usage is represented using the
object based task group (OTG) models. A probabilistic task
prediction algorithm that fuses the HMC and OTG models
has been developed to predict the next most probable task,
given that a sequence of tasks has been completed. The
proposed models and algorithms have been evaluated on two
complex cooking activities - making brownies and making
eggs, achieving a subject independent accuracy of 68.5% for
predicting tasks, which is an improvement by an average of
6% in comparison to a Markov chain.
INTRODUCTION
Cooking activities are complex activities and typically
contain several sub-activities (which we call tasks) within
itself. When a person starts a cooking activity, he or she
accomplishes it by following a particular order of doing its
constituent tasks. This is illustrated in Figure 1, where fews
tasks that are involved in the activity of making brownie
are shown. There exists a lot of variability in the order of
occurrence of these tasks across individuals and contexts,
which makes the problem of learning activity models for
these complex activities challenging. Furthermore, for applications
such as a prompting system for individuals with
Alzheimer’s disease (AD) or dementia, the activity models
must also be capable of predicting the task the individual
will perform even before its occurrence.