Cognitive Load Persuade Attribute for Special Need Education System Using Data Mining

Integrated Intelligent Research (IIR) International Journal of Data Mining Techniques and Applications
Volume: 01 Issue: 01 June 2012 Page No.4-8
ISSN: 2278-2419
4
Cognitive Load Persuade Attribute for Special
Need Education System Using Data Mining
Sangita Babu1
, C.Jothi Venkateswaran2
1
Research scholar,Dept of computer Applications, Bharath university,Chennai
2
Research supervisor & Head,PG and research Dept of Computer Science Presidency College, Chennai
Abstract - Human learning system is highly sensitive to
responsive system according the processing, mapping, motion,
auditory and visualization system. Special education system is
implemented to overcome the demanded sense of the human
special care sensitive signals. This responsive system is
balanced and effectively instrumented with modern
technological learning pedagogy to bring the special need
learners into the normal learning system. In the learning
process, cognitive human sensors directly influence the
learning effectiveness. This paper attempted to observe the
cognitive load such as mental , physical , temporal
,performance , effort and frustration in the long term , short
term, working , instant , responsive, process, recollect ,
reference , instruction and action memory and classify the
observed values as per the generalized and specialized
properties. The six working loads are observed in the ten types
of learning system. The classification analysis aimed to
predicate the pattern for learning system for specific learning
challenges.
Key words - Special need education , Cognitive load,
Classification
I. INTRODUCTION
The educational right act aimed to provide education for all
irrespective of age, gender, region, community and challenges
of the human by birth. A Global Perspective on Right to
Education and Livelihoods clearly delineates the need for
capacity building through the inclusion of persons with
disabilities in the workplace and the larger community. The
statement affirms the importance of such things as (i)
improving educational opportunities, (ii) promoting sustainable
livelihood for persons with disabilities, (iii) capacity building
and institutional development for realization of effective
participation of persons with disabilities, (iv) promotion of the
rights and dignity of persons with disabilities, (v)
documentation of best practices and appropriate
technologies...research on education, (vi) strengthened teacher
training, development of inclusive curricula, and effective
involvement of families and communities for realization of
quality education for all children (United Nations Economic
and Social Commission for Asia and the Pacific, 2005).
Barriers to the provision of quality education for children with
disabilities are identified as lack of early identification and
intervention services, negative attitudes, exclusionary policies
and practices, inadequate teacher training, particularly training
of all regular teachers to teach children with diverse abilities,
inflexible curriculum and assessment procedures, inadequate
specialist support staff to assist teachers of special and regular
classes, lack of appropriate teaching equipment and devices,
and failure to make modifications to the school environment
to make it fully accessible (UNESCAP, 2003).however the
learner emotional approach overcome all above mentioned
barriers and provide the effective learning .the emotional
learning activities are balanced with cognitive load of the
special need learner.
This paper addresses the role of cognitive load and learning
system and its correlated factors. The analysis part attempted to
determine the associative relationship between the
performances of the learner as per their learning objective with
the minimal cognitive load.
II. THE PHYSIOLOGICAL LIMITATIONS TO
LEARNING
Researchers find that thinking processes happen serially,
resulting in delays caused by switching from one task to
another. The delays become more pronounced as the
complexity of the task increases.[1] Neuroscientists are
reporting new discoveries that provide insights into long-held
learning theories. For example, conjectures from decades ago
on the existence of short-term and long-term Memory[2] and
cognitive overload [3] now have supporting evidence from the
neurosciences. As per the research finding, the cognitive load
imposed on a person using a complex solving strategy such as
means –ends analysis may be an even more important factor in
interfering with learning during problem solving. Under most
circumstances, means-ends analysis will result in few dead-
ends being reached than any other general strategy which does
not rely on prior domain-specific knowledge for its operation.
In order to use the strategy, a problem solver must
simultaneously consider the current problem state, the goal
state, the relation between the current problem state and the
goal state, the relations between problem-solving operators and
lastly, if sub-goals have been used, a goal stack must be
,maintained. The cognitive processing capacity needed to
handle this information may be of such a magnitude as to leave
little for schema acquisition, even if the problem is solved.
This approach is adopted and experimented in the special need
educational learners around Chennai schools at the age
between from 13 to 18. Research indicates that the brain has
three types of memory: sensory memory, working memory,
and long-term memory.[4]

ISSN: 2278-2419
5
Figure 1. Memory Types
III. MEMORY RELATIONSHIP FOR LEARNING
PROCESS
A. Working memory
Working memory is where thinking gets done. While it is
represented as a box in the below Figure, it is actually more
brain function than location. The working memory is dual
coded with a buffer for storage of verbal/text elements, and a
second buffer for visual/spatial elements. This represents one
of the severe limitations of human thinking processes, for
short-term memory is thought to be limited to approximately
four objects that can be simultaneously stored in visual/spatial
memory and approximately seven objects that can be
simultaneously stored in verbal short-term memory. If those
buffers are full and the person shifts attention, new elements
may be introduced into working memory causing others to
disappear from thought/consciousness. Within working
memory, verbal/text memory and visual/spatial memory work
together, without interference, to augment understanding.
Overfilling either buffer can result in cognitive overload
[10].This includes buffers of visual/spatial memory traces and
verbal (auditory and text) memory traces. Recent studies
suggest that the brain is capable of multisensory convergence
of neurons provided the sensory input is received within the
same time frame [5]. Convergence in the creation of memory
traces has positive effects on memory retrieval. It creates
linked memories, so that the triggering of any aspect of the
experience will bring to consciousness the entire memory,
often with context.
B. Sensory memory
Experiencing any aspect of the world through the human
senses causes involuntary storage of sensory memory traces in
long-term memory as episodic knowledge. These degrade
relatively quickly[11]. It is only when the person pays attention
to elements of sensory memory that those experiences get
introduced into working memory. Once an experience is in
working memory, the person can then consciously hold it in
memory and think about it in context.
C. Long-term memory
The short-term memory acts in parallel with the long-term
memory. Long-term memory in humans is unlimited estimated
to store up to 109 to 1020 bits of information over a lifetime.
The brain has two types of long-term memory, episodic and
semantic. Episodic is sourced directly from sensory input and
is involuntary. Semantic memory stores memory traces from
working memory, including ideas, thoughts, schema, and
processes that result from the thinking accomplished in
working memory. The processing in working memory
automatically triggers storage in long-term memory. The
relationship between the memory and its associative maps
presented in the below diagram.
Figure 2. Physiological and cognitive functions
Students have preconceptions and prior experiences with many
of the areas of study included in the academic standards. These
are stored in long-term memory. Often some of those
preconceptions turn out to be misconceptions. Student learning
is greatly enhanced when each student’s prior knowledge is
made visible (that is, cued from long-term memory into
working memory).It is at that point the student has the
opportunity to correct misconceptions, build on prior
knowledge, and create schemas of understanding around a
topic. Learning is optimized when students can see where new
concepts build on prior knowledge. This is not acceptable and
adoptable to the learning challengers. The learning process of
the challenging learners and their cognitive load is observed
according to the NASA scaling and determined the persuade
factor among the load and its relation on the performance of
learning.
IV. COGNITIVE WORKLOAD CALCULATION
NASA task load index is a multidimensional rating procedure
that provides over all work load based on a weighted average
of rating on six subscales : mental demand , physical demand ,
temporal demand , Own performance ,Effort and
Frustration[6,7] This technique (referred to as the “NASA
Bipolar Rating Scale”) was quite successful in reducing
between-rater variability and provided diagnostic information
about the magnitudes of different sources of load from
subscale ratings [8,9]. However, its sensitivity to experimental
manipulations, while better than found for other popular
techniques and as a global one-dimensional workload
rating.Mental demand deals with mental and perceptual
activity was required for learning the concept and
implementation CPL. Physical demands focused physical
activity was required. Temporal demand deals with time
pressure of the students while learning the CPL. Performance

ISSN: 2278-2419
6
shows the accomplishment of goals of the task set by the
experimenter. Frustration level specifies the insecure,
discouraged, irritated, stressed and annoyed versus of the
learning. Effort measures the work to accomplish your level of
performance.
The NASA Task Load Index workload evaluation procedure is
a two-part procedure requiring the collection of both weights
and ratings from the subject and the manipulation of the
collected data to provide weighted subscale ratings and an
Overall Workload score. There are fifteen possible pair-wise
comparisons of the six scale elements. When Weights is
selected the load presents each pair to the subject one pair at a
time. The order in which the pairs are presented and the
position of the two elements (left or right) are completely
randomized and are different .Factor select which element they
felt contributed the most to the workload on the specific task.
When all fifteen possible pairs have been presented the second
part will be continue.
The learner’s performance is evaluated based on the multi-
dimensional rating procedure given by NASA TLX ( Task
Load index) based on the six subscales .The requirement is to
obtain numerical ratings for each scale element that reflect the
magnitude of that factor The subject responds between 0 to 20 .
The Weighted workload rating for each element in a task is
simply the Weight (tally) for that element a number between
zero and five, multiplied by the Magnitude of load, a number
between zero and one hundred. Therefore if the subject had
totaled 4 for the weight of Temporal Demand and indicated a
magnitude of Temporal Demand in a particular task to be 45,
the weighted workload due to Temporal Demand for that
particular task would be 90. OVERALL workload for a
particular task is determined by summing all of the weighted
workload ratings for an individual subject for the particular
task and dividing by 15.Using the above calculation the
different combinational learning and cognitive load are
observed and calculated.
Figure 3. Scaling method
Weighted rating determined from the sum of sum of adjusted
rating and divided with 15. As per the calculation the learners
observe the cognitive load such as mental , physical , temporal
,performance , effort and frustration in the long term , short
term, working , instructional , responsive, process, recollect ,
instruction and action memory .All the designed exercise and
its functional specifications are presented below The first
exercise is designed for testing long term memory or thinking,
where the SNE’s mental demand of thinking is tested. In this
exercise most of the student took great interest in replying the
questions, where they had to recall their long term memory , in
which they faced low physical , mental and temporal demand
whereas their performance was very high. The second exercise
is designed for testing short term memory, where SNE’s
Mental Demand of deciding is tested. In this exercise also most
of the students took great enthusiasm in replying where they
had to recall their short term memory and had to make decision
in which they faced low mental, physical and temporal demand
and took less effort and frustration level was also low
comparatively their performance was high.
The third exercise is designed for testing working (calculation)
memory where SNE’s Mental Demand for calculating is
tested. In this observation the student’s physical, mental and
temporal demand faced high effort and frustration and their
performance was very low. The forth exercise was designed for
instant memory, where SNE’s mental demand for remembering
is tested using remembering the objects on recent display. It is
also designed in play way activity where many of the students
faced low physical, mental and temporal demand however they
faced high performance with low effort and frustration and
vice-versa. The fifth exercise was designed for responsive
memory where SNE’s Mental Demand for looking was tested
which was designed in computer interactive activity, where the
students were able to recognize the day to days items whereas
found difficulty in identifying the colors, where their Mental,
Physical and temporal demand was average and performance
with any effort and frustration was also average.
The sixth exercise was designed for processing (search
content) memory where SNE’s Mental Demand for searching
was tested .It also designed as a computer interactive activity,
where the students were able to perform high and their physical
mental and temporal demand were average with less effort and
frustration. The seventh exercise was designed for recollecting
memory where SNE’s Physical Demand for Motor activity was
tested, here the students took great effort and faced high
frustration in facing the load, where as their physical mental
temporal demand was also average and performance was also
very low. The eight exercises was designed for reference
memory where SNE’s Physical demand for Interactive activity
was designed through computer interactive activity, Where
their physical mental and temporal demand was very high and
had to face high effort and frustration while doing this activity
and their performance level was very low.
The ninth exercise was designed for instruction memory where
SNE’s Physical demand for instructional activity was designed
through instructional activity. Here the students met high
physical, mental, temporal load, performed very low but it was
visa-versa for the comparatively low physical mental and
temporal students, they performed with lot of interest and
enthusiasm with low effort and frustration.The tenth exercise
was designed for action memory where the students observe
the instructor action and repeat the same where SNE’s
Physical activity replay demand was tested through repeating
Perf
orm
ance
Colle
ct 15
pair
value
s of
six
scale
eleme
nts
(Wei
ght)
Ratin
g of
Scale
d
eleme
nt 0-
20
(Raw
rating
)
Adjust
ed
Rating
=
Weigh
t x
Raw
rating

ISSN: 2278-2419
7
the instruction . The students mental , temporal and frustration
is less and the physical effort is high. All the observation which
made is presented the table and attempted to determine the
enforcing weightage for the influencing factor for learning
process. The learner’s activities are provided and observed
along with their cognitive load reactions. These loads are
increasing the efficiency of the learning with the minimal load
for the special need learns. While these exercises are a carried
out ; the observation measures are collected from the students
through the NASA scaling system . The NASA scales and the
working loads are converted using the neural network approach
the obtained a result pattern which presented below.
V. CONSTRUCTION OF NEURAL NETWORK
MODEL
As per the adopted back propagation neural network model, the
observed data is mapped and the model is constructed. All
external observation attributes are considered for the input. I1
to I10 represents the input variable which presents the score of
the each exercise which carried out different memory learning
process such as long term, short term, working , instant ,
responsive, process, recollect , reference , instruction and
action memory. The cognitive loads are treated as process
neuron of hidden layer. The H1 to H6 presents the mental,
physical, temporal, performance, effort and frustration
cognitive loads. According to the observed values, the neural
network process is made. The student exercise values are
presented 5, 7, 10, 7,10, 6, 8,10,10 and 8. The process values
weightage is presented as a matrix. Initially Assigned Input to
Hidden layer values are
0.1159 0.7452 0.7667 0.3303 0.5616 0.0683
0.6439 0.4698 0.0191 0.2963 0.8009 0.6156
0.2143 0.5475 0.2102 0.3169 0.1742 0.4353
0.9549 0.5177 0.1248 0.0150 0.7018 0.2846
0.4923 0.1257 0.9708 0.0489 0.7574 0.9536
0.0792 0.3202 0.8221 0.3629 0.9702 0.0913
0.1030 0.4678 0.0615 0.0294 0.1558 0.3777
0.6844 0.4638 0.3015 0.5345 0.3129 0.2956
0.8698 0.8769 0.1957 0.9274 0.4688 0.0399
0.1469 0.6540 0.3309 0.5981 0.0100 0.3490
Table 1: Initial assignment I->
Figure 4. neural network model
Initially Assigned Input to Hidden layer values are
0.1159 0.7452 0.7667 0.3303 0.5616 0.0683
0.6439 0.4698 0.0191 0.2963 0.8009 0.6156
0.2143 0.5475 0.2102 0.3169 0.1742 0.4353
0.9549 0.5177 0.1248 0.0150 0.7018 0.2846
0.4923 0.1257 0.9708 0.0489 0.7574 0.9536
0.0792 0.3202 0.8221 0.3629 0.9702 0.0913
0.1030 0.4678 0.0615 0.0294 0.1558 0.3777
0.6844 0.4638 0.3015 0.5345 0.3129 0.2956
0.8698 0.8769 0.1957 0.9274 0.4688 0.0399
0.1469 0.6540 0.3309 0.5981 0.0100 0.3490
Initially Assigned Hidden layer to Output values are
Table 2: Initial Assignment H-> O
0.9532 0.4718
0.0451 0.0943
0.1912 0.4462
0.5433 0.1154
0.6347 0.8885
0.8214 0.0804
From the initial values, each level obtained output is
recalculated and assigned as a input and reduced the error
level. Initially the output is estimated for 81 for the learning
cognitive and 95 for the learning performance. The initial
assigned neuron process produced 96 for the cognitive load
and 89 for the learner performance. While obtaining this
process , -62.048 error is produced. The iterative process
implemented and obtained the final value in zero level error.
The final weightage values are presented below
Final Input to Hidden layer values are
0.2318 1.4905 1.5335 0.6605 1.1232 0.1366
1.2879 0.9397 0.0382 0.5926 1.6019 1.2313
0.4286 1.0950 0.4204 0.6338 0.3484 0.8705
1.9099 1.0355 0.2495 0.0300 1.4036 0.5692
0.9846 0.2514 1.9416 0.0979 1.5147 1.9072
0.1583 0.6403 1.6442 0.7259 1.9405 0.1825
0.2060 0.9356 0.1229 0.0587 0.3116 0.7554
1.3687 0.9276 0.6030 1.0690 0.6258 0.5912
1.7397 1.7538 0.3913 1.8548 0.9375 0.0799
0.2938 1.3080 0.6618 1.1962 0.0200 0.6980
Table 1: Obtained weight I-> H
Final Hidden to output layer values are
0.9532 0.4718
0.0451 0.0943
0.1912 0.4462
0.5433 0.1154
0.6347 0.8885
0.8214 0.0804
Table 1: Obtained weight H->O
While processing the network model, the high value of mental
effort is influenced at the maximum level of 95.32 percentages

International Journal of Data Mining Techniques Volume: 01 No: 01 January – June 2012
8
and least level of physical at 4.51 percentage. The learning
performance is inclined to performance factor of the cognitive
load to obtained expected result. All the model is presented
according to the load along with the learning performance.
Figure 5. cognitive loads
The load is differ one with another according to the different
learning process. Mental, physical, temporal, effort, frustration
is less while performance is high. The learning process and its
corresponding variation is presented as a graph.
VI. CONCLUSION
As per the model which is designed and implemented neuron
system identified the influencing factor of the cognitive load
and the learning performance of the special need education
learners. According to the obtained result learner cognitive
load is high for mental and the performance factor is high for
the learner result. While processing this model the special need
learners basic factors such as nature of the need, gender, type
of school and the deficiency based pattern is attempted to
generate for generalize the process. The pattern generation and
the factor determination process continue as part of the
research work.
REFERENCES
[1] Miyake, A., & Shah, P. (Eds.) (1999). Models of working memory:
Mechanisms of active maintenance and executive control. Cambridge
University Press: New York.
[2] Rubinstein, J.S., Meyer, D.E., & Evans, J.E. (2001). Executive Control of
Cognitive Processes in Task Switching. University of Michigan, Ann
Arbor, Mich., Journal of Experimental Psychology -Human Perception
and Performance, Vol 27. No.4.
[3] Baddeley, A.D. (1992). Working Memory. Science; 255-256.
[4] Sweller, J. (1988). Cognitive load during problem solving, Cognitive
Science 12: 257–285.Marois, R. & Ivanoff, J. (2005). Capacity limits of
information processing in the brain. Trends in Cognitive Sciences, 9(6),
296-305. Baddeley, A. D. (1997). Human Memory: Theory and Practice:
Psychology Press.Beyers, J.C., Bittner, Jr, A. and Hills, S.G. Traditional
and raw task load index (TLX) correlations: are paired comparisons
necessary. Advances in Industrial Ergonomics and Safety I. London:
Taylor and Francis, 1989.
[5] Hart, S. G., & Staveland, L. E. (1988). Development of a multi-
dimensional workload rating scale: Results of empirical and theoretical
research. NASA
[6] Hitt II, J.M., Kring, J.P., Daskarolis, E., Morris, C., & Mouloua, M.
(1999). Assessing mental workload with subjective measures: An
analytical review of the NASA-TLX index
[7] Wierwille, W.W. & Eggemeier, F.T. (1993). Recommendation for mental
workload measurement in a test and evaluation environment. Human
Factors, 35, 263-281.
[8] Sweller, J. (1999). Instructional Design in Technical Areas. Melbourne,
Australia: ACER Press.

Cognitive Load Persuade Attribute for Special Need Education System Using Data Mining

More Related Content

What's hot (19)

Similar to Cognitive Load Persuade Attribute for Special Need Education System Using Data Mining (20)

More from ijdmtaiir (20)

Recently uploaded (20)

Cognitive Load Persuade Attribute for Special Need Education System Using Data Mining