Information Technology Reference
In-Depth Information
Artificial Intelligence Model
of an Smartphone-Based Virtual Companion
Elham Saadatian
, Thoriq Salafi, Hooman Samani,
Yu De Lim, and Ryohei Nakatsu
Keio-NUS CUTE Center, NUS
elham@nus.edu.sg
Abstract.
This paper introduces an Artificial Intelligence (AI) model
of a virtual companion system on smartphone. The proposed AI model is
composed of two modules of Probabilistic Mood Estimation (PME) and
Behavior Network. The PME is designed for the purpose of automatic
estimation of the mood, under uncertain and dynamic smartphone con-
text. The model combines Support Vector Machine (SVM) and Dynamic
Bayesian Networks (DBNs) to estimate the probabilistic mood state of
the user. The behavior network contorts the behavior of the interactive
and intelligent virtual companion, considering the detected mood and ex-
ternal factors. In order to make the virtual companion more believable,
the system consists of an internal mood state structure. The mood of the
agent, could also be inferred from another real human such as a remote
partner. The fitness of the artificial companion behavior in relation to
the users mood state was evaluated by user study and effectiveness of
the system was confirmed.
Keywords:
Artificial Intelligence, Entertaining Virtual Companion, Af-
fective Computing.
1
Introduction
The aim of this research is to employ various sensors integrated in the mod-
ern smartphones to observe the behavior of users and develop smart systems
to enrich communications and interactions. Emerging field of mediated affective
communication relates to the technologies that aim to mediate personal com-
munication across distance. Contemporary lifestyle changes have led to design
and adoption of technologies in support of modern lifestyle. In our earlier work,
a comprehensive study of existing prototypical systems and related conceptual
studies was investigated [9].
Intelligent virtual agents are human-like embodied characters [5]. These au-
tonomous artificial characters have applications in many fields, such as computer
game [11], conversational agents [1], and affective robotics systems [10] and many
more. In this study, we have proposed and AI system for intelligent affective vir-
tual companion on smartphone. In this respect, a model is proposed to detect
Keio-NUS CUTE Center, National University of Singapore, Singapore.
