Transcript Learning styles - Department of Computer Science

Intelligent technologies:
basics, review, research and
real-life application examples
Assoc. Prof. Dr. Eugenijus Kurilovas
Vilnius Gediminas Technical University, Lithuania
EPL202-EPL463, UCY, Erasmus+, 17 Sept. 2015
Abstract
The lecture aims at presenting basics, review, and real-life
application examples of intelligent (smart) technologies.
What are intelligent (smart) technologies?
What are intelligent technologies for?
Literature review on Web 3.0, ontologies, artificial intelligence,
intelligent agents, recommender systems and decision support
systems.
Some author’s research results
and real-life application
examples of Web 3.0, semantic search, ontologies,
recommender systems and decision support systems in
education.
1. Basics and
applications
What are intelligent technologies?
Intelligent technologies explore the fundamental roles and practical impacts of
artificial intelligence and knowledge management in various paradigms.
A main factor of intelligence is the ability to create new ideas and correlate
them with existing knowledge. Technology is good at accomplishing one of
these tasks, but the "creative thinking" aspect is more than just coming up
with something new or uncommon / random.
It means that one draws upon past experiences, feelings, questions, and
answers, and contemplates unique ways of interchanging them. The
difference is that the resulting ideas are understood based on more than the
parts that lead to their inception.
Intelligent technology should, therefore, lead to a method of self-actualization
where the technology would be able to improve itself through "creative
thought".
What are intelligent technologies for? Applications
“Smart” is electronic device or system that can be connected to the Internet,
used interactively, as is for some extent intelligent.
Examples:
–
–
–
–
–
–
–
–
–
–
–
–
–
–
Smart TV
Smart home devices (e.g. smart washing machine, fridge)
Smart phone
Smart watch
Smart glasses
Smart table
Smart board
Smart buildings
Smart traffic light
Smart farming
Smart connected vehicles (automatically calls the emergency services in
the event of an accident)
Smart surveillance (a security systems based on face recognition)
Smart education
Tablet devices
2. Literature review
Semantic Web
Semantic Web (or Web 3.0) is an extension of the Web through standards by
the World Wide Web Consortium (W3C). The standards promote common
data formats and exchange protocols on the Web, most fundamentally the
Resource Description Framework (RDF).
In addition to the classic “Web of documents” W3C is helping to build a
technology stack to support a “Web of data,” the sort of data you find in
databases. The ultimate goal of the Web of data is to enable computers to do
more useful work and to develop systems that can support trusted interactions
over the network. The term “Semantic Web” refers to W3C’s vision of the Web
of linked data. Semantic Web technologies enable people to create data
stores on the Web, build vocabularies, and write rules for handling data.
According to the W3C, "The Semantic Web provides a common framework
that allows data to be shared and reused across application, enterprise, and
community boundaries". The term was coined by Tim Berners-Lee in 2001 for
a web of data that can be processed by machines.
Ontologies
In computer science and information science, an ontology is a formal naming
and definition of the types, properties, and interrelationships of the entities
that really or fundamentally exist for a particular domain of discourse. It is thus
a practical application of philosophical ontology, with a taxonomy. An ontology
compartmentalizes the variables needed for some set of computations and
establishes the relationships between them.
What many ontologies have in common in both computer science and in
philosophy is the representation of entities, ideas, and events, along with their
properties and relations, according to a system of categories. In both fields,
there is considerable work on problems of ontological relativity. Computer
scientists are more concerned with establishing fixed, controlled vocabularies,
while philosophers are more concerned with first principles, such as whether
there are such things as fixed essences or whether entities must be
ontologically more primary than processes.
The fields of artificial intelligence, the Semantic Web, systems engineering,
software engineering, biomedical informatics, library science, enterprise
bookmarking, and information architecture all create ontologies to limit
complexity and to organize information. The ontology can then be applied to
problem solving.
Artificial intelligence
Artificial intelligence (AI) is the intelligence exhibited by machines or software.
It is also the name of the academic field of study which studies how to create
computers and computer software that are capable of intelligent behavior.
Researchers and textbooks define this field as "the study and design of
intelligent agents", in which an intelligent agent is a system that perceives its
environment and takes actions that maximize its chances of success. AI is
also "the science and engineering of making intelligent machines".
The central problems (or goals) of AI research include reasoning, knowledge,
planning, learning, natural language processing (communication), perception
and the ability to move and manipulate objects. General intelligence is still
among the field's long-term goals. Currently popular approaches include
statistical methods, computational intelligence and traditional symbolic AI.
There are a large number of tools used in AI, including versions of search and
mathematical optimization, logic, methods based on probability and
economics, and many others.
The AI field is interdisciplinary, in which a number of sciences and professions
converge, including computer science, mathematics, psychology, linguistics,
philosophy and neuroscience, as well as other specialized fields such as
artificial psychology.
Intelligent agents
In artificial intelligence, an intelligent agent (IA) is an autonomous entity which
observes through sensors and acts upon an environment using actuators and
directs its activity towards achieving goals (i.e. it is "rational"). IAs may also
learn or use knowledge to achieve their goals.
IAs are often described schematically as an abstract functional system similar
to a computer program. For this reason, IAs are sometimes called abstract
intelligent agents to distinguish them from their real world implementations as
computer systems, biological systems, or organizations. Some definitions of
intelligent agents emphasize their autonomy, and so prefer the term
autonomous IAs. Still others considered goal-directed behavior as the
essence of intelligence and so prefer a term borrowed from economics,
"rational agent".
IAs are also closely related to software agents (an autonomous computer
program that carries out tasks on behalf of users). In computer science, the
term IA may be used to refer to a software agent that has some intelligence,
regardless if it is not a rational agent. For example, autonomous programs
used for operator assistance or data mining are also called "intelligent
agents".
Recommender systems
Recommender systems (or recommendation systems) are a subclass of
information filtering system that seek to predict the 'rating' or 'preference' that
a user would give to an item.
Recommender systems have become extremely common in recent years, and
are applied in a variety of applications. The most popular ones are movies,
music, news, books, research articles, search queries, social tags, and
products in general.
Recommender systems typically produce a list of recommendations in one of
two ways - through collaborative or content-based filtering. Collaborative
filtering approaches building a model from a user's past behavior (items
previously purchased or selected and/or numerical ratings given to those
items) as well as similar decisions made by other users. This model is then
used to predict items (or ratings for items) that the user may have an interest
in. Content-based filtering approaches utilize a series of discrete
characteristics of an item in order to recommend additional items with similar
properties. These approaches are often combined (Hybrid Recommender
Systems).
Decision support systems
A Decision Support System (DSS) is a computer-based information system that
supports business or organizational decision-making activities. DSSs serve the
management, operations, and planning levels of an organization (usually mid and
higher management) and help people make decisions about problems that may be
rapidly changing and not easily specified in advance (i.e. Unstructured and SemiStructured decision problems).
Decision support systems can be either fully computerized, human-powered or a
combination of both.
While academics have perceived DSS as a tool to support decision making process,
DSS users see DSS as a tool to facilitate organizational processes. Some authors
have extended the definition of DSS to include any system that might support decision
making.
DSSs include knowledge-based systems. A properly designed DSS is an interactive
software-based system intended to help decision makers compile useful information
from a combination of raw data, documents, and personal knowledge, or business
models to identify and solve problems and make decisions.
3. Research and
real-life application
examples
Introduction
What learning content, methods and technologies are the most suitable to
achieve better learning quality and efficiency? In Lithuania, we believe that
there is no correct answer to this question if we don’t apply personalised
learning approach. We strongly believe that “one size fits all” approach
doesn’t longer work in education.
It means that, first of all, before starting any learning activities, we should
identify students’ personal needs: their preferred learning styles, knowledge,
interests, goals etc.
After that, teachers should help students to find their suitable (optimal)
learning paths: learning methods, activities, content, tools, mobile applications
etc. according to their needs.
But, in real schools practice, we can’t assign personal teacher for each
student. This should be done by intelligent technologies. Therefore, we
believe that future school means personalisation plus intelligence.
In this presentation, Lithuanian Intelligent Future School (IFS) project is
presented aimed at implementing both learning personalisation and
educational intelligence.
IFS concept
5: Empower
Redefinition
& innovative
use
1.
4: Extend
Network
redesign &
embedding
1.
2.
3.
2.
3.
3: Enhance
Process
redesign
1.
2.
3.
Technology supports new learning services that go beyond
institutional boundaries.
Mobile and locative ICT support ‘agile’ teaching and learning.
The learner as a ‘co-designer’ of the learning journey, supported by
intelligent content and analytics.
Ubiquitous, integrated, seamlessly connected ICT support learner
choice and personalisation beyond the classroom.
Teaching and learning are distributed, connected and organised
around the learner.
Learners take control of learning using ICT to manage their own
learning
Teaching and learning redesigned to incorporate ICT, building on
research in learning and cognition.
Institutionally embedded ICT supports the flow of content and data,
providing an integrated approach to teaching, learning and
assessment.
The learner as a ‘producer’ using networked ICT to model and
make.
___________________________________________
2: Enrich
Internal
Coordination
1.
2.
3.
1: Exchange 1.
Localised use 2.
3.
ICT used interactively to make differentiated provision within the
classroom.
ICT supports a variety of routes to learning.
The learner as a ‘user’ of ICT tools and resources
ICT is used within current teaching approaches.
Learning is teacher-directed and classroom-located.
The learner as a ‘consumer’ of learning content and resources
Future school means personalisation plus intelligence
IFS implementation stages
(based on iTEC schools innovation maturity model):
(1) Creating learners’ models (profiles) based on their learning
styles and other particular needs
(2) Interconnecting learners’ models with relevant learning
components (learning content, methods, activities, tools,
apps etc.) and creating corresponding ontologies
(4) Creating intelligent agents and recommender systems
(5) Creating and implementing personalised learning scenarios
(e.g. in STEM – Science, Technology, Engineering and
Mathematics – subjects)
(6) Creating educational multiple criteria decision making
models and methods
Personalisation
Personalisation: creating students’ profiles
(1) Selecting good taxonomies (models) of learning styles, e.g.,
(Felder & Silverman, 1988), (Honey & Mumford, 2000), the
VARK style (Fleming, 1995)
(2) Creating integrated learning style model which integrates
characteristics from several models. Dedicated psychological
questionnaire(s)
(3) Creating open learning style model
(4) Using implicit (dynamic) learning style modelling method
(5) Integrating the rest features in the student profile
(knowledge, interests, goals)
Personalisation: identifying learning styles
Personalisation: identifying learning styles
VARK inventory was designed by Fleming in 1987 and is an acronym made from
Visual, Aural, Read/write and Kinaesthetic. These modalities are used for
preferable ways of learning (taking and giving out) information:

Visual learners prefer to receive information from depictions in figures: in
charts, graphs, maps, diagrams, flow charts, circles, hierarchies, and others.
It does not include pictures, movies and animated websites that belong to
Kinaesthetic.

The aural perceptual mode describes a preference for spoken or heart
information. Aural learners learn best by discussing, oral feedback, email,
chat, discussion boards, and oral presentations.

Read/write learners prefer information displayed as words: quotes, lists,
texts, books, and manuals.

The kinaesthetic perceptual mode describes a preference for reality and
concrete situations. They prefer videos, teaching others, pictures of real
things, examples of principles, practical sessions, and others.
Multimodals are those learners who have preferences in more than one mode.
Creating recommender system
Learning styles
(Honey and
Mumford, 1992)
Activists are
those people
who learn by
doing. Have an
open-minded
approach to
learning,
involving
themselves
fully and
without bias in
new
experiences
Preferred
learning
activities
Brainstorming,
problem
solving, group
discussion,
puzzles,
competitions,
and role-play
Suitable teaching / learning
methods
(iCOPER D3.1, 2009))
Suitable LO
types
(LRE AP v4.7,
2011)
Active Learning, Blogging,
Brainstorming and Reflection,
Competitive Simulation, EPortfolio, Creation of
Personalised Learning
Environments, Creative
Workshops, Exercise Unit,
Games Genre, Presenting
Homework, Image Sharing, Inclass Online Discussion, Mini
Conference, Modelling, Online
Reaction Sheets, Online Training,
Peer Assessment, Processbased Assessment, Process
Documentation, Project-based
Learning, Resource-based
Analysis, Role Play, Student Wiki
Collaboration, World Café, Web
Quest
Application,
Assessment,
Broadcast,
Case study, Drill
and practice,
Educational
game, Enquiryoriented activity,
Experiment,
Exploration,
Glossary, Open
activity,
Presentation,
Project,
Reference, Role
play, Simulation,
Tool, Website
Creating recommender system
Creating recommender system
Creating recommender system
iOS (Apple iPad)
Android (Samsung)
iOS / Android
Suitable LO
types
Idea Sketch – lets
you easily draw a
diagram – mind map,
concept map, or flow
chart - and convert it
to a text outline, and
vice versa. You can
use Idea Sketch for
anything, such as
brainstorming new
ideas, illustrating
concepts, making
lists and outlines,
planning
presentations,
creating
organizational charts,
and more
Mindjet for Android
– rated as one of
the best mind
mapping apps for
Android. Create
nodes and notes,
add images of your
own or icons
provided, and add
attachments and
hyperlinks. Sync to
your Dropbox
Mind Mapping – lets you
create, view and edit
mind maps online or
offline and lets the app
synch with your online
account whenever
connected. You can
share mind maps
directly from the device,
inviting users via email.
You can add icons,
colours and styles, view
notes, links and tasks
and apply map themes,
drag and drop and
zoom
Application,
Broadcast,
Enquiry-oriented
activity,
Glossary, Open
activity,
Presentation,
Reference, Role
play, Simulation,
Tool, Website
Interconnection of Activists Brainstorming learning activity with suitable apps and LOs types
Creating recommender system
Example: Integrating
Web 2.0 tools into
learning activities
Recommender systems (as a kind of services in the e-learning environment) can
provide personalised learning recommendations to learners.
Recommender systems are information processing systems that gather various
kinds of data in order to create their recommendations.
The data are primarily about the items (objects that are recommended) to be
suggested and the users who will receive these recommendations.
The data can be formalised in domain ontology, thus the knowledge about a user
and items becomes reusable for people and software agents. Also, the
ontology could contain a useful knowledge that can be used to infer more
interests than can be seen by just an observation.
The aim of TEL is to improve learning. It is therefore an application domain that
generally covers technologies that support all forms of learning activities. An
important activity in TEL is search-ability relevant learning resources and
services as well as their better finding. Recommender systems support such
an information retrieval.
There are different types of recommender systems based on the recommendation
approaches: content-based, collaborative filtering, demographic, knowledgebased, community-based, utility-based, hybrid, and semantic.
In this research, knowledge-based recommender system using rules-based
reasoning is used. Knowledge-based systems recommend items based on
the specific domain knowledge about how certain item features satisfy users’
needs and preferences as well as how the item is useful for the user.
Knowledge-based recommender systems can be rule-based or case-based. The
form of data collected by the knowledge-based system about user’s
preferences can be statements, rules, or ontologies.
The knowledge base of the rule-based system comprises the knowledge that is
specific to the domain of the application.
The rule-based reasoning system represents knowledge of the system in terms of
a bunch of rules (facts). These rules are in the form of IF THEN rules such
as “IF some condition THEN some action”. If the ‘condition’ is satisfied, the
rule will take the ‘action’.
The proposed method for Web 2.0 tools integration into learning activities is
based on the ontology developed.
With the view to find a particular Web 2.0 tool suitable for the accomplishment of
the learning activity, a link between the tool and the learning activity must be
identified. This relationship can be established by interconnections between
the defined tool and activity elements.
The learning activity is defined as consisting of the following elements:
(1) Learning Activity (what action a learner performs);
(2) Content (which object a learner manages);
(3) Interaction (with whom a learner interacts); and
(4) Synchronicity (at what time a learner performs the intended action).
Web 2.0 tool is defined as set of universal functions. This universal function is
defined as consisting of the following elements:
(1) Function (what action can be performed by using a tool);
(2) Artefact (which object can be managed by using a tool);
(3) Interaction (what kind of interaction the tool enables); and
(4) Synchronicity (at what time the intended action is enabled by a tool to take
place).
The Learning activities and Functions of tools are classified mostly based on the
[Conole, 05] media taxonomy. These types and particular elements are
presented in Table 2:
Type
Learning
activities
Subtype (1-8)
Web 2.0 tool function
Narrative
Revise
1: View
Explore ( Read, view, listen)
Information
management
Find
2: Search
Search
Collect
3: Host
Host (Store), Syndicate
Productive
Prepare
4: Create
Create (draw, write, record, edit)
Communicative
Present
5: Share
Share, publicise
Dispute
6: Discuss
Communicate
Role play
7: Imitate
Simulate (Game simulation)
Observation
8: Model
Model (Phenomenon modelling)
Imitative
Table 2: Learning activities and Web 2.0 tools functions types
Thus, Web 2.0 tools could be divided based on their usage possibilities, managed
objects, communication form, and sort of imitation process into three groups
as follows:
(1) Artefacts management, (2) Communication, and (3) Imitation tools.
We have defined the following components in the domain ontology visualised with
Protégé 4.3 ontology editor:
Concepts (Main Classes) (Figure 1), and
Relationships between Concepts (Properties) (Figure 2):
The stages of the method of integrating Web 2.0 tools into learning activities are
as follows:
1.
Identification of learner’s learning style (i.e. preferences of the learning
content and communication modes)
2.
Selection of the learning objective and the learning method
3.
Determination of the elements of chosen learning method activities
4.
Determination of universal function elements of each Web 2.0 tool
5.
Finding of the link between tool and learning activity elements
6.
Selection of a suitable tool based on specified elements: Action, Interaction,
Synchronicity. Artefact is determined based on individual learning style.
Description of each stage and the detailed presentation of the method are
provided in [Juskeviciene, Kurilovas, 14].
In order to ascertain the suitability of this approach, the recommender system
prototype was developed. This prototype was developed following the
working principles of the knowledge-based recommender system. The
domain knowledge was conceptualised in the ontology.
The prototype of the knowledge-based recommender system implements this
method completely:
Scheme of the recommender system
Recommender system prototype operation
Example: educational
multiple criteria
decision making
Multiple Criteria Decision Making
Scalarisation method:
the experts’ additive utility function
Literature review has shown that fuzzy numbers and scalarisation methods are applicable for
e-textbooks and other LOs quality and reusability evaluation in terms of its simplicity and
effectiveness. Scalarisation method is referred here as the experts’ additive utility function
represented by the formula (1). According to this method, a possible decision here could be to
transform a multi-criteria task into one-criterion task obtained by adding all the criteria ratings
(values) together with their weights (Kurilovas & Serikoviene, 2012):
m
f ( X )   ai f i ( X ) ,
i 1
m
 ai  1 , a  0 .
i
i 1
Here fi(X) is the rating (i.e. non-fuzzy value) of the criterion i for the each of the examined etextbooks and other LOs alternatives Xj, and ai are the weights of the quality criteria
The major is the meaning of the utility function the better LOs meet the
quality requirements in comparison with the ideal (100%) quality
According to scalarisation method, we need LOs evaluation criteria ratings
(values) and weights
(1)
Linguistic variables conversion
into triangle non-fuzzy values and weights:
Linguistic variables
Non-fuzzy values
Excellent / Extremely valuable
Good / Very valuable
Fair / Valuable
Poor / Marginally valuable
Bad / Not valuable
0.850
0.675
0.500
0.325
0.150
In identifying quality criteria for the decision making, the
following considerations are relevant to all multiple
criteria decision making approaches:
•
•
•
•
•
•
•
•
Value relevance
Understandability
Measurability
Non-redundancy
Judgmental independence
Balancing completeness and conciseness
Operationality
Simplicity versus complexity
E-textbooks and other learning objects quality model
Criteria group
Nr.
Technological criteria
‘Internal’ quality 1
2
3
Quality ‘in use’
4
Quality criteria
Interoperability
Architecture
Interactivity
Design and usability: aesthetics, navigation, userfriendly interface and information
structure,
personalisation
Pedagogical criteria
E-textbook and other LO relevance to educate basic subject competences
criteria:
5
E-textbook and other LO textual and visual material are
suitable to acquire knowledge, and to educate
understanding, skills and values defined in the
curriculum
Assignments provided in e-textbook and other LO are
6
suitable to acquire knowledge, and to educate
understanding, skills and values defined in the
curriculum
E-textbook and other LO methodological structure is
7
suitable to acquire knowledge, and to educate
understanding, skills and values defined in the
curriculum
Criterion of E-textbook and other LO material suitability to educate general
competences defined in the curriculum:
E-textbook and other LO textual and visual material,
8
assignments and methodological structure suitability to
educate general competences
IPR criterion
9
Clear license: e-textbook and other LO is open, free to
use, and cost-effective
IFS concept
implementation vision
1. Collaboration agreements between Vilnius University and
(20 pilot) schools on IFS implementation
2. Joint expert group on creating interconnections and
intelligent agents
3. R&D, creation of technologies and scenarios, and
validation at schools
4. Feedback, questionnaires, interviews, data mining
5. Return to (3) based on (4)
Papers 2015

Kurilovas, E.; Juskeviciene, A.; Bireniene, V. (2015). Research on Mobile Learning
Activities Using Tablets. In: Proceedings of the 11th International Conference on
Mobile Learning (ML 2015). Madeira, Portugal, March 14–16, 2015, pp. 94–98.

Kurilovas, E.; Zilinskiene, I.; Dagiene, V. (2015). Recommending Suitable Learning
Paths According to Learners’ Preferences: Experimental Research Results.
Computers in Human Behavior, Vol. 51, 2015, pp. 945–951.

Kurilovas, E.; Juskeviciene, A. (2015). Creation of Web 2.0 Tools Ontology to
Improve Learning. Computers in Human Behavior, Vol. 51, 2015, pp. 1380–1386.

Kurilovas, E.; Vinogradova, I.; Kubilinskiene, S. (2015). New MCEQLS Fuzzy AHP
Methodology for Evaluating Learning Repositories: A Tool for Technological
Development of Economy. Technological and Economic Development of Economy
– in press, DOI: 10.3846/20294913.2015.1074950

Kurilovas, E. (2015). Future School: Personalisation plus Intelligence. Chapter in:
“Handbook of Research on Information Technology Integration for Socio-Economic
Development”. IGI Global – in print
Papers 2014

Kurilovas, E.; Juskeviciene, A.; Kubilinskiene, S.; Serikoviene, S. (2014). Several
Semantic Web Approaches to Improving the Adaptation Quality of Virtual Learning
Environments. Journal of Universal Computer Science, Vol. 20 (10), 2014, pp.
1418–1432.

Kurilovas, E.; Kubilinskiene, S.; Dagiene, V. (2014). Web 3.0 – Based
Personalisation of Learning Objects in Virtual Learning Environments. Computers
in Human Behavior, Vol. 30, 2014, pp. 654–662. [Q1]

Kurilovas, E.; Zilinskiene, I.; Dagiene, V. (2014). Recommending Suitable Learning
Scenarios According to Learners’ Preferences: An Improved Swarm Based
Approach. Computers in Human Behavior, Vol. 30, 2014, pp. 550–557. [Q1]

Kurilovas, E.; Serikoviene, S.; Vuorikari, R. (2014). Expert Centred vs Learner
Centred Approach for Evaluating Quality and Reusability of Learning Objects.
Computers in Human Behavior, Vol. 30, 2014, pp. 526–534. [Q1]

Juskeviciene, A.; Kurilovas, E. (2014). On Recommending Web 2.0 Tools to
Personalise Learning. Informatics in Education, Vol. 13 (1), 2014, pp. 17–30.

Kurilovas, E. (2014). Research on Tablets Applications for Mobile Learning
Activities. Journal of Mobile Multimedia, Vol. 10 (3&4), 2014, pp. 182–193.
Papers 2013

Kurilovas, E.; Serikoviene, S. (2013). New MCEQLS TFN Method for Evaluating
Quality and Reusability of Learning Objects. Technological and Economic
Development of Economy, Vol. 19 (4), 2013, pp. 706–723. [Q1]

Kurilovas, E.; Zilinskiene, I. (2013). New MCEQLS AHP Method for Evaluating Quality
of Learning Scenarios. Technological and Economic Development of Economy, Vol. 19
(1), 2013, pp. 78–92. [Q1]

Kurilovas, E. (2013). MCEQLS Approach in Multi-Criteria Evaluation of Quality of
Learning Repositories. Chapter 6 in the book: José Carlos Ramalho, Alberto Simões,
and Ricardo Queirós (Ed.) “Innovations in XML Applications and Metadata
Management: Advancing Technologies”. IGI Publishing, USA, 2013, pp. 96–117.

Kurilovas, E.; Serikoviene, S. (2013). On E-Textbooks Quality Model and Evaluation
Methodology. International Journal of Knowledge Society Research, Vol. 4 (3), 2013,
pp. 66–78.
Papers 2012

Kurilovas, E.; Zilinskiene, I. (2012). Evaluation of Quality of Personalised Learning
Scenarios: An Improved MCEQLS AHP Method. International Journal of Engineering
Education, Vol. 28 (6), 2012, pp. 1309–1315.

Kurilovas, E.; Serikoviene, S. (2012). New TFN Based Method for Evaluating Quality
and Reusability of Learning Objects. International Journal of Engineering Education,
Vol. 28 (6), 2012, pp. 1288–1293.

Zilinskiene, I.; Dagiene, V.; Kurilovas, E. (2012). A Swarm-based Approach to Adaptive
Learning: Selection of a Dynamic Learning Scenario. In: Proceedings of the 11th
European Conference on e-Learning (ECEL 2012). Groningen, the Netherlands,
October 26–27, 2012, pp. 583–593.
Conclusion

Future school means personalisation + intelligence

Learning personalisation means creating and implementing
personalised learning paths based on recommender systems
and personal intelligent agents suitable for particular learners
according to their personal needs

Educational intelligence means application of intelligent
technologies and methods enabling personalised learning to
improve learning quality and efficiency

Lithuanian IFS project is aimed at implementing both learning
personalisation and educational intelligence
Thank you for your attention.
Questions?
Dr. Eugenijus Kurilovas
http://eugenijuskurilovas.wix.com/my_site