13 Smart Learning Using Big and Small Data for Mobile and IOT e-Health
619
not been a technology-enabled education system in healthcare yet. Meanwhile,
the idea of building automated education systems already finds its application in
many other fields, such as student education. In this case study, we will discuss
the development of a hybrid smart learning framework that incorporates knowledge
symbiosis learning in the implementation of similar applications.
13.3.2 Background in Intelligent Tutoring Systems
The intelligent tutoring system (ITS) is a typical example for educational systems.
Here, teachers are supported by a computer system that can help structure a student’s
learning process. This sort of intelligent systems is expected to lend support to
personalized tutoring and in turn reduce the teacher-student ratio. This would help
grant easier access to quality education. ITS is different from computer-assisted
instruction, where computers are utilized for administering the delivery of content
with predetermined rules. Instead, ITS adapts the learning process individually for
each student and therefore is referred to as intelligent. Typical applications of ITS
include automated diagnosis of student weakness areas and automatic adjustment of
education content according to the degree of difficulty.
The current development of ITS benefits from the foundation set by learning
theories developed over the past few decades. For example, cognitivistic theories
help inform ITS design in knowledge provisioning in relation to a learner’s preexisting knowledge [75, 76], whereas constructivistic theories help ITS to provide
exercises in the learner’s realistic settings and select learning tasks relevant to the
learner’s living experiences [77]. (For a review of the major learning theories, please
refer to [78].)
A prerequisite of ITS is a lower barrier of access to technology. This was first
reached in the 1980s by the introduction of personal computers leading to a boom of
ITS. One example from that time is the LISPITS [79]. It was developed for teaching
the programming language LISP. The system was able to detect errors and provide
constructive feedback in real time [79, 80]. LISPITS has yielded positive evaluation,
reducing the required time for learners to complete their assigned exercises while
also improving on their scores [81].
The smart learning framework developed to support ITS consists of the following
four models:
• Domain model
• Student model
• Tutoring model
• User interface model
First, the domain model or expert model represents the domain knowledge of
an expert. More precisely as depicted in [82], it “contains the concepts, rules and
problem-solving strategies of the domain to be learned. It can fulfill several roles: as
a source of expert knowledge, a standard for evaluating the student’s performance
619
not been a technology-enabled education system in healthcare yet. Meanwhile,
the idea of building automated education systems already finds its application in
many other fields, such as student education. In this case study, we will discuss
the development of a hybrid smart learning framework that incorporates knowledge
symbiosis learning in the implementation of similar applications.
13.3.2 Background in Intelligent Tutoring Systems
The intelligent tutoring system (ITS) is a typical example for educational systems.
Here, teachers are supported by a computer system that can help structure a student’s
learning process. This sort of intelligent systems is expected to lend support to
personalized tutoring and in turn reduce the teacher-student ratio. This would help
grant easier access to quality education. ITS is different from computer-assisted
instruction, where computers are utilized for administering the delivery of content
with predetermined rules. Instead, ITS adapts the learning process individually for
each student and therefore is referred to as intelligent. Typical applications of ITS
include automated diagnosis of student weakness areas and automatic adjustment of
education content according to the degree of difficulty.
The current development of ITS benefits from the foundation set by learning
theories developed over the past few decades. For example, cognitivistic theories
help inform ITS design in knowledge provisioning in relation to a learner’s preexisting knowledge [75, 76], whereas constructivistic theories help ITS to provide
exercises in the learner’s realistic settings and select learning tasks relevant to the
learner’s living experiences [77]. (For a review of the major learning theories, please
refer to [78].)
A prerequisite of ITS is a lower barrier of access to technology. This was first
reached in the 1980s by the introduction of personal computers leading to a boom of
ITS. One example from that time is the LISPITS [79]. It was developed for teaching
the programming language LISP. The system was able to detect errors and provide
constructive feedback in real time [79, 80]. LISPITS has yielded positive evaluation,
reducing the required time for learners to complete their assigned exercises while
also improving on their scores [81].
The smart learning framework developed to support ITS consists of the following
four models:
• Domain model
• Student model
• Tutoring model
• User interface model
First, the domain model or expert model represents the domain knowledge of
an expert. More precisely as depicted in [82], it “contains the concepts, rules and
problem-solving strategies of the domain to be learned. It can fulfill several roles: as
a source of expert knowledge, a standard for evaluating the student’s performance