On Enhancing Blended-Learning Scenarios through Fuzzy

Logic-based Modeling of Users’ LMS Quality of Interaction

The Rare & Contemporary Dance Paradigms

Sofia B. Dias

, Leontios J. Hadjileontiadis

and José A. Diniz

Faculty of Human Kinetics, Lisbon University, Estrada da Costa 1499-002 Cruz-Quebrada, Lisbon, Portugal

Department of Electrical & Computer Engineering, Aristotle University of Thessaloniki,

University Campus GR-54124, Thessaloniki, Greece

Keywords: Learning Scenarios, LMS Moodle, Quality of Interaction, Blended Learning, Fuzzy Logic-based Modelling,

Pedagogical Planning, Rare & Contemporary Dance, i-Treasures.

Abstract: The combination of the process of pedagogical planning within the Blended (b-)learning environment with

the users’ quality of interaction (QoI) with the Learning Management System (LMS), serving as an effective

feedback, is explored here. The required QoI (both for teachers and students) is estimated by adopting a

fuzzy logic-based modeling approach, namely FuzzyQoI, applied to LMS Moodle data from two academic

teaching of dance disciplines, including rare and contemporary dances, respectively. The latter are used as

paradigms that comply with the educational scenarios of the i-Treasures project (www.i-treasures.eu), which

refers to the intangible cultural heritage. Based on documental analysis, the pedagogical design strategies

per semester were transcribed to concept maps and the dynamically (per week) estimated QoIs were

presented as feedback to the teachers at the end of the first semester, so they could reflect and update their

pedagogical planning, anticipating more enhanced QoI at the second one. The results presented here show

the beneficial role of QoI to shift the educational scenarios and strategies towards a more dynamic design,

yet taking into consideration the inherent tendencies and attitudes of the users’ interaction within the b-

learning context.

1 INTRODUCTION

Quality of learning experience directly relates with

the amount and the quality of interaction (QoI) and

the sense of commitment to a community of inquiry

and learning. Those could be achieved through the

effective integration of technology, while at the

same time exploiting the advantages of a traditional

course that includes lectures and meetings (Garrison

and Kanuka, 2004). Towards this blending,

designing, developing and deploying programs that

are well organized, using multimedia to engage the

learner by employing various intelligences,

capturing the experiences and knowledge of the

learners, while incorporating and promoting

interactivity and training instructors to facilitate

online delivery, demand a strategic decision to be

made and adequate resources be made available.

Blended (b-)learning can address the potential

shortcomings of a purely e-learning approach, yet

only in the context of educators taking a strategic

approach and planning appropriately (Wall, 2012).

This suggests that education providers (e.g., Higher

Education Institutions-HEIs) should find the most

appropriate blend of conventional and digital

learning resources.

Determining learning behavior in electronic

media, however, is a complex problem. A difficulty

is that these environments are mostly used by

students away from the classroom and out of sight of

their educators. Without the informal monitoring

that occurs in F2F teaching it is difficult for

educators to know how their students are using and

responding to these environments. In this line,

educators have had to explore new ways of

obtaining information about the learning patterns of

their students. This clearly requires the development

of effective methods of determining and evaluating

learner's behavior in electronic environments (Hijón

and Velázquez, 2010), a role that is undertaken by

Learning Management Systems (LMSs).

765

B. Dias S., J. Hadjileontiadis L. and A. Diniz J..

On Enhancing Blended-Learning Scenarios through Fuzzy Logic-based Modeling of Users’ LMS Quality of Interaction - The Rare & Contemporary

Dance Paradigms.

DOI: 10.5220/0004861507650772

In Proceedings of the 9th International Conference on Computer Vision Theory and Applications (IAMICH-2014), pages 765-772

ISBN: 978-989-758-004-8

 2014 SCITEPRESS (Science and Technology Publications, Lda.)

The user's interaction with a LMS (e.g., Moodle)

is actually realized within Online Learning

Environments (OLEs), which are characterized by

fastness and immediacy, i.e., the ability to quickly

access a vast amount of information coupled with a

plurality of Web 2.0 tools (Redecker et al., 2009).

Apparently, the efficiency of the LMS depends on

how effectively the users can access its multi-faceted

benefits when interacting with it. According to

Wagner (1994), the interaction can be seen as the

occurrence of reciprocal events that require the

existence of at least two objects and two actions, and

when they influence each other. Chatteur et al.

(2008), also report that in OLEs is not uncommon

for individuals to interact spontaneously, i.e.,

without being motivated and/or encouraged through

interaction strategies and/or activities. In addition,

Herrington et al. (2007) argue that the (un)successful

learning is intrinsically dependent on the degree of

interaction that takes place in a specific educational

context. Collins and Berge (1996) highlighted that

learners tend to combine the new knowledge

acquired by interacting with content, with their prior

knowledge on that subject matter. Hence, interaction

can be synthesized as an active process, which

requires learners to do more than passively absorb

information.

The QoI between learner with online content is

one of the imperative factors in determining the

efficacy of Web-based teaching-learning towards the

creation and maintenance of sustainable learning

communities (Grant and Thornton, 2007).

Interaction with content is an internal dialogue of

reflective thought that occurs between learner and

the substance. Interaction is often triggered and

supported by events in the learning environment-on

how the learner interacts with what is to be learned.

A study carried out by McIsaac et al. (1999)

explored interactions of doctoral students with an

online environment and they concluded that student

interactions were goal-focused. In another study

(Hijón and Velázquez, 2006) it was shown that the

average connections to the LMS was over thirty

minutes. Analysis of learner's interactions may also

be used to compare learning behaviors of different

groups of students (Ramos and Yudko, 2008).

The aforementioned suggest the approach of

user's LMS interactions from the perspective that

reveals their quality, so the latter could be used to

unfold the true nature of the users' attitude when

interacting with the LMS within a b-learning

environment. So far, works focused on QoI usually

employ statistical analysis of LMS data, combined

with transcripts of the discussions and exchanges of

teacher and learners within the online forums,

specifically investigating the dimension, depth and

category of exchanges occurred (Ping et al., 2010).

Following an alternative pathway, here, the

FuzzyQoI model (Dias and Diniz, 2013) is adopted;

the latter takes into account the users' (professors'

and students') interactions, as expressed through the

LMS usage within a b-learning environment, and, by

translating the knowledge of the experts in the field

to fuzzy constructs, estimates, in a quantitative way,

a normalized index of the users’ QoI. In this way,

the estimated QoI could be used as effective

feedback to the teachers, in terms of reconstructing

their pedagogical planning and create updated

concept maps (Novak and Gowin, 1996) towards

more effective educational scenarios within b-

learning context. This process is exemplified here

with two dance paradigms, i.e., rare and

contemporary dance disciplines at a HEI, serving as

a bet-set for the realization of b-learning scenarios

within the i-Treasures project (www.i-treasures.eu),

related with the capture of the Intangible Cultural

Heritage (ICH) and learning the rare know-how of

living human treasures (FP7-ICT-2011-9-600676-i-

Treasures).

2 METHODOLOGY

2.1 The FuzzyQoI Model

In the effort to develop a successful evaluating

system of the user's interaction with the LMS

through the QoI, intelligent systems may play an

important role, i.e., provide a model of the domain

expert’s evaluating system, with the promise of

advanced features and adaptive functionality (Levy

and Weld 2000). Based on the latter, a Mamdani-

type (Tsoukalas and Uhrig 1996) fuzzy logic-based

QoI modelling, namely FuzzyQoI scheme, was

proposed by Dias and Diniz (2013). The FuzzyQoI

model constitutes a Fuzzy Inference System (FIS)

structure that is able to produce evaluative

inferences upon input data. In particular, the latter

correspond to the key-parameters and variables

(metrics) of LMS Moodle involved within a b-

learning environment concerning the user's

interaction with the system, whereas the outputted

inference forms a quantitative measure of the user's

overall QoI (Dias and Diniz, 2013).

The block diagram of the FuzzyQoI model is

depicted in Figure 1. As it is apparent from the

latter, the users (professors/students) interact with

the LMS and the available 110 LMS Moodle metrics

VISAPP2014-InternationalConferenceonComputerVisionTheoryandApplications

766

Figure 1: Block-diagram of the FuzzyQoI model (Dias and

Diniz, 2013).

are corresponded to 12 categories that serve as

inputs to the FIS structure. In an effort to efficiently

handle the 12 input variables, these are grouped in

three groups and a nested sequence of five FISs

(FIS1-FIS5) is used to form the proposed FuzzyQoI

scheme. The first level includes FIS1, FIS2 and

FIS3, which output the values of View (V), Addition

(AD) and Alteration (AL), respectively. In the

second level of inference, V, AD and AL are

considered as intermediate variables and are used as

inputs to the FIS4, which outputs the value of Action

(AC). Finally, in the third level of inference, the AC

is considered as intermediate variable and along with

Time Period (TP) and Engagement Time (ET) are

used as inputs to the FIS5, which outputs the

estimated QoI as the final output of the FuzzyQoI

scheme (Dias and Diniz, 2013).

For the construction of the knowledge base of the

FuzzyQoI scheme, an expert in the field of analyzing

LMS Moodle data within the context of b-learning

was used, for defining the structure of the

membership functions used for each FS and the

corresponding IF/THEN fuzzy rules.

In particular, a three-level of trapezoid

membership functions corresponding to Low,

Medium and High values, respectively, are used for

the FIS1-FIS4, whereas a five-level of trapezoid

membership functions corresponding to Very Low,

Low, Medium, High and Very High values were

adopted for the final FIS5, increasing, this way, the

resolution in the segmentation of the universe of

discourse of the AC, TP and ET inputs and QoI

output in the final FIS5. Analytical description of the

FuzzyQoI model can be found in Dias and Diniz

(2013).

2.2 C-Maps & Pedagogical Planning

Concept Maps (C-Maps) represent an eclectic range

of flexible tools in e/b-learning environments. In C-

Maps, in general, concepts are arranged

hierarchically, i.e., more general concepts are placed

higher on the map and specific concepts are located

lower (Novak and Gowin, 1996). C-Maps are largely

used in online environments that are able to be

presented as learning tools in all stages of the

learning process. The use of C-Maps as a way of

promoting discussion and negotiation processes

through communication tools can be really seen as a

valuable learning tool.

Here, the notion of C-Maps is placed within the

concept of pedagogical planning, so to facilitate the

organization of educational scenarios (Olimpo et al.,

2010). The realization of the latter is achieved by

adopting the MindMup tool from the i-Treasures

Pedagogical Planner (

Bottino et al., 2013), which is a

scalable cross-browser Web-based application

developed in PHP, MySQL and JavaScript. It is

conceived with the aim of supporting the design of

pedagogical activities/scenarios, namely the

descriptions, at different level of granularity, of the

playing out of a learning situation or a unit of

learning aimed at the acquisition of a precise body of

knowledge through the specification of roles and

activities. The Pedagogical Planner is essentially a

teacher-oriented online tool, yet in the way it is used

here, it could serve as a combinatory tool that

incorporates both designing and planning of the

educational interventions and feedback from the

realization of the b-learning delivered instruction. In

this way, causal relations between teachers’ and

students’ at the level of their LMS-based QoI could

be identified and teachers’ metacognitive processes

could be fired towards the enhancement of their

pedagogical planning and delivery.

The Pedagogical Planner comprises both

authoring and display capabilities, with specially

designed functions and interface features in both

cases. In particular, target population, learning

context, content domain, objectives and metrics,

along with available tools (such as MindMup), are

the core characteristics of the Pedagogical Planner

(see Figure 2).

OnEnhancingBlended-LearningScenariosthroughFuzzyLogic-basedModelingofUsers'LMSQualityofInteraction-

TheRare&ContemporaryDanceParadigms

767

Figure 2: The main page of the Pedagogical Planner within the i-Treasures project (http://i-treasures.itd.cnr.it/).

To exemplify the combination of the FuzzyQoI

model with the Pedagogical Planner two cases that

resemble the use-cases of the i-Treasure project, i.e.,

the rare and contemporary dances, are used as

paradigms and described in the subsequent section.

3 THE DANCE PARADIGMS

The data used for the dance paradigms were drawn

from the Faculty of Human Kinetics (FHK),

University of Lisbon, Portugal, where the

corresponding dance disciplines are realized within

the b-learning context.

The data were categorized into two types, that is,

the ones that relate with documental analysis

regarding the pedagogical instruction of the

disciplines (e.g., curriculum, teachers’ planning

strategies, online material) and the others coming

from the LMS Moodle platform. The former were

used to formulate transcribed C-Maps with the

MindMup software (see Section 2.2), whereas the

latter were used as input to the FuzzyQoI model for

the estimation of the QoI for each user

(teachers/students) per week. For each paradigm, the

data from two teachers (combined teaching) and 10

students were used and analyzed for the duration of

two academic semesters (S1: weeks 2-16, S2: weeks

23-38).

3.1 Rare Dances Planning

Rare dances at the FHK, actually, belong to the

Social Dances discipline, which aims to provide and

develop ways to dance, able to contribute to a

students’ education in a more complete,

comprehensive and multifaceted way, through the

diversity of approaches and multiplicity of

perspectives developed in each dance form.

Moreover, the social dimension and respect of

the act of dance are taken into account to enhance

the knowledge and extend the application domain

with multicultural approaches, revealing the nature

and specificity of their contents. For example,

dances from Greece (e.g., Tsamiko, Omonia),

Belgium (e.g., Schaatsenrijdersdans), Servia (e.g.,

Savila Se Bela Loza, Vlaški) and other folklore

expressions worldwide are approached and

examined.

The planning of this discipline aims to construct

Figure 3: The MindMup output of the pedagogical

planning of the rare dances context followed throughout

the S1.

VISAPP2014-InternationalConferenceonComputerVisionTheoryandApplications

768

a place of experience and experimentation with

different materials, choreographic and contextual,

along with specific techniques for analysis, leading

to “know-how” and the enlargement and

consolidation of formal and expressive repertoire of

the students.

To achieve the above goals within the b-learning

context, both F2F and online learning activities are

constructed. Figure 3 illustrates the pedagogical

planning of the S1 in the form of the MindMup

output, where the F2F and online components are

shown in the form of connected branches.

3.2 Contemporary Dances Planning

Contemporary dances at the FHK are included in the

Techniques of Theater Dances discipline, which

aims to promote the analysis and study of motor

vocabulary characteristic of modern and classical

dance forms. The pedagogical planning includes

practice of standardized modeling steps organized in

simple exercises with repetitions and chained in

sequence dances increasing complexity. Moreover,

training skills of observation in situations of mutual

learning, are also considered, being consistent with

the principles and quality of dance movements.

Under this discipline, it is intended that students

will be able to: know the fundamentals of the

techniques of theatrical dance; perform the basic

vocabulary of theater dance techniques addressed

with correction at the level of bodily vectors and

dynamic; play with fluency and accuracy through

demonstration sequences danced in technical

context; identify, characterize and describe the

specific motor skills techniques dance theater

addressed; cooperate with colleagues in group tasks;

interact with faculty and/or colleagues by actively

participating in the tasks; assess their technical

performance and that of others and their

participation in groups.

As in the case of rare dances, the above goals

within the b-learning context are achieved by

constructing both F2F and online learning activities,

within a corresponding pedagogical planning of the

S1, in the form of the MindMup output, depicted in

Figure 4.

3.3 Estimated QoI Feedback &

Pedagogical Planning Updating

The LMS Moodle users’ interaction data for S1 and

S2 were fed to the FuzzyQoI model that outputted

the corresponding estimated QoIs, i.e., 

,

/

,

Figure 4: The MindMup output of the pedagogical

planning of the contemporary dances context followed

throughout the S1.

Figure 5: The distribution of the estimated QoI of the rare

dances (left column) and contemporary dances (right

column) paradigms and corresponding users (professors:

top, students: bottom). The S1 and S2 are denoted on the

graphs with the vertical solid lines located at weeks 2 and

16 (S1) and weeks 23 and 38 (S2).

where the superscripts RD and CD indicate rare and

contemporary dances, respectively, and P and S refer

to professors and students, accordingly. The

analytically estimated QoIs for both semesters and

paradigms are holistically illustrated in Figure 5,

OnEnhancingBlended-LearningScenariosthroughFuzzyLogic-basedModelingofUsers'LMSQualityofInteraction-

TheRare&ContemporaryDanceParadigms

769

whereas the corresponding mean values are depicted

in Figure 6.

Although shown in Figures 5 and 6 in a sequential

way, the 



/

,

values were solely presented

to the corresponding teachers as a feedback at the

end of S1, so they could reflect on these and

readjust/update their pedagogical planning for the

S2, accordingly, resulting, hence, in the derived





/

,

values shown in Figures 5 and 6. This

updating process and its effect upon the

pedagogical planning is presented in Figures 7(a)

and 7(b) for the cases of rare and contemporary

dances, respectively. As it is apparent from Figure 7,

and in comparison with Figures 3 and 4, the

feedback from the estimated QoI has led to changes

in the pedagogical planning, particularly to the

online components, in an effort to increase and/or

sustain the users’ LMS QoI of S2 at higher levels

than those of S1.

Figure 6: The mean estimated QoI of the rare dances (top

panel) and contemporary dances (bottom panel) paradigms

and corresponding users (professors: black line, students:

gray line). The S1 and S2 are denoted on the graphs with

the vertical solid lines located at weeks 2 and 16 (S1) and

weeks 23 and 38 (S2).

4 DISCUSSION

From the Figure 5 (top panel) it is clear that the two

teachers incorporated in each discipline delivery had

a dissimilar behavior, regarding their QoI with the

LMS. In particular, for the case of rare dances

Professor #1-RD exhibited sparse interaction with

the LMS, located at the beginning of S2 and after it,

where as a significant change is noticed in the QoI

of Professor #2-RD, who just initiated the LMS-

based process at the beginning of S1 and after the

QoI feedback she notably increased her QoI. For the

case of contemporary dances, Professor #1-CD

showed a quasi-periodic interaction with LMS at the

beginning of S1, abandoned at the mid of S1 and

almost for the whole duration of S2, exhibiting an

increased QoI just before the end of S2. On the

contrary, Professor#2-CD, showed almost a constant

interaction with the LMS, exhibiting her high QoI

values almost across the whole S1 duration and

towards the end of S2. Regarding the students’ QoI

values, they were higher at S2 rather than in S1 for

the rare dances case, whereas the opposite effect was

noticed for the contemporary dance case.

Focusing at the mean estimated QoI of Figure 6,

it is clear that the effect of the professors’ QoI

feedback was higher in the case of the rare dances

(top panel) than the case of contemporary dances

(bottom panel). Clearly, in the case of the rare

dances, the sole peak of QoI at week 5 for the whole

S1 has been extended to more sustained QoI values

across S2, peaking also at the ~0.5 after the

beginning of S2. This change in professors’ QoI

probably can be connected with the noticeable

change in the students’ QoI. In fact, at the S1, a

hysteresis-like effect is noticed, as students’ QoI

starts growing only after professors’ peak at week 5,

peaks around the mid of S1 and tends to a decay

towards the end of S1. On the contrary, the

performance is totally different in S2, as the students

show a tendency to exhibit synchronized QoIs with

the ones of the professors, justifying the updated role

of the LMS part in the b-learning activities during

S2. In the case of contemporary dances, the

hysteresis-like effect is seen between the professors’

and students’ QoI during S1, where despite the high

QoI of the professors, the students QoI exhibits a

slow increase towards the end of S1, whereas the

updating of the pedagogical planning by the

professors for the S2 has contributed mostly to the

synchronization between the professors’ and

students’ QoIs. In both cases, the professors acted in

a reflective way by adjusting their pedagogical

planning for the S2 and exhibited increased QoI (in

both cases the QoI peaks are located within the S2).

Turning to pedagogical planning updating

process of Figure 7, the shift towards more

interactive and appealing online resources (e.g.,

VISAPP2014-InternationalConferenceonComputerVisionTheoryandApplications

770

(a)

(b)

Figure 7: A schematic representation of the way the estimated QoIs by the FuzzyQoI model from the S1 were used as

teachers’ feedback to update the pedagogical planning of S2, along with the updates of the MindMup outputs from the

initial version (followed throughout the S1-left) to the updated one (followed throughout the S2-right), for (a) the rare

dances and (b) contemporary dances paradigms.

quizzes, discussion forums, blogs, videos, e-

portfolios) has turned the interest to LMS

interaction, seeing the latter as a more enhanced

source of information, which could accompany the

F2F interaction and complement the effort towards

multifaceted way of learning.

From the paradigms presented here it is apparent

that the proposed approach could be extended to

OnEnhancingBlended-LearningScenariosthroughFuzzyLogic-basedModelingofUsers'LMSQualityofInteraction-

TheRare&ContemporaryDanceParadigms

771

various educational scenarios and use-cases (within

and outside the i-Treasures project), posing a

dynamic character to the role of LMS towards an

intelligent LMS (Dias et al., 2014), assisting both

teachers and students to enhance the quality of the

educational environment.

5 CONCLUSIONS

An effort to combine the process of pedagogical

planning within the b-learning context with the

users’ QoI with the LMS as an effective feedback

was presented here. A fuzzy logic-based modeling

approach, namely FuzzyQoI, was adopted to provide

reliable estimates of the QoI (both for teachers and

students) across two semesters of two academic

teaching of dance disciplines, including rare and

contemporary dances, respectively. The latter were

chosen as paradigms that comply with the

educational scenarios of the i-Treasures project

referring to the ICH, showing the potentiality to shift

towards a more dynamic design of the educational

scenarios and strategies, incorporating the inherent

tendencies and attitudes of the users within the b-

learning context.

ACKNOWLEDGEMENTS

This work has received funding from the EU

Seventh Framework Programme FP7-ICT-2011-9-

ICT-2011.8.2, under the grant agreement n° 600676:

"i-Treasures" Project (http://www.i-treasures.eu).

The authors would like to thank Mrs Francesca

Pozzi, Mrs Francesca Dagnino and ITD-CNR, Italy,

for providing access and support to the Pedagogical

Planning and MindMup software use.

REFERENCES

Bottino R., Earp J., Olimpo G., Ott M., Pozzi F., Tavella

M. (2008). Supporting the design of pilot learning

activities with the Pedagogical Plan Manager. In M.

Kendall & B. Samways (Eds.) Learning to live in the

Knowledge Society, (37-44), Springer.

Chatteur, F., Carvalho, L., Dong, A., 2008. Design for

Pedagogy Patterns for E-learning. In Proceedings of

the 8th IEEE International Conference on Advanced

Learning Technologies (pp. 341-343). DC: IEEE

Computer Society.

Collins, M., Berge, Z., 1996. Facilitating interaction in

computer mediated online courses. In Proceedings of

FSU/AECT Distance Education Conference. http://

penta.2.ufrgs.br/ edu/teleduc/wbi/flcc.htm.

Dias, S. B., Diniz, J. A., 2013. FuzzyQoI Model: A fuzzy

logic-based modelling of users' quality of interaction

with a learning management system under blended

learning, Computers & Education, 69, 38–59.

Dias, S. B., Diniz, J. A., Hadjileontiadis, L. J., 2014.

Towards an Intelligent Learning Management System

Under Blended Learning: Trends, Profiles and

Modelling Perspectives. Springer-Verlag. Berlin/

Heidelberg.

Garrison, D. R., Kanuka, H., 2004. Blended learning:

Uncovering its transformative potential in higher

education. The Internet and Higher Educ., 7, 95-105.

Grant, M. R., Thornton, H. R., 2007. Best Practices in

undergraduate adult-centered online learning:

mechanisms for course design and delivery. Journal of

Online Learning and Teaching, 3(4), 346-356.

Herrington, J., Reeves, T., Oliver, C., 2007. Immersive

Learning Technologies: Realism and Online Authentic

Learning. Journal of Computing in Higher Education,

19(1), 65-84.

Hijón, R. N., Velázquez, A. I., 2010. From the discovery

of students access patterns in e-learning including

Web 2.0 resources to the prediction and enhancement

of students outcome, e-learning experiences and

future. In S. Soomro (Ed.). E-learning Experiences

and Future, InTech (ch. 14, pp. 276-294).

Levy, Y. A., Weld, S. D., 2000. Intelligent internet

systems. Artificial Intelligence, 118, 1-14.

McIsaac, M. S., Blolcher, J. M., Mahes, V., Vrasidas, C.,

1999. Student and teacher perceptions of interaction in

online computer-mediated communication.

Educational Media International, 36(2), 121-131.

Novak, J. D., Gowin, D. B., 1996. Learning How To

Learn. Cambridge University Press. New York.

Olimpo, G., Bottino, R. M., Earp, J., Ott, M., Pozzi, F.,

Tavella, M., 2010. Pedagogical plans as

communication oriented objects. Computers &

Education, 55(2), 476-488.

Ping, T. A., Cheng., A. Y., Manoharan, K., 2010.

Students’ interaction in the online learning

management systems: A comparative study of

undergraduate and postgraduate courses. In Pro-

ceedings of the AAOU-2010 Annual Conf. (pp. 1-14).

Ramos, C., Yudko, E., 2008. “Hits” (not “Discussion

Posts”) predict student success in online courses: A

double cross-validation study. Computers &

Education, 50, 1174-1182.

Redecker, C., Ala-Mutka, K., Bacigalupo, M., Ferrari, A.,

Punie, Y., 2009. Learning 2.0: The impact of web 2.0

Innovations on Education and Training in Europe.

http://is.jrc.ec.europa.eu/pages/Learning-2.0.html.

Tsoukalas, H.L., Uhrig R.E., 1996. Fuzzy and neural

approaches in engineering. Wiley & Sons. New York.

Wagner, E. D., 1994. In support of a functional definition

of interaction. American Journal of Distance

Education, 8(2), 6-26.

Wall, J., 2012. Strategically integrating blended learning

to deliver lifelong learning. InTech, ch. 7, 133-148.

VISAPP2014-InternationalConferenceonComputerVisionTheoryandApplications

772