Fuzzy Models for Teaching Assessment

Research Inventy: International Journal of Engineering And Science
Vol.5, Issue 8 (August 2015), PP -06-12
Issn (e): 2278-4721, Issn (p):2319-6483, www.researchinventy.com
6
Fuzzy Models for Teaching Assessment
1
N.Sarala , 2
R.Kavitha
1
Associate professor, A.D.M. college for women, Nagapattinam.
2
R.A. college for women, Tiruvarur.
ABSTRACT : The concept of teaching is the fundamental study of student’s cognitive action. In this paper a
Trapezoidal Fuzzy Assessment model (TFAM) is developed for teaching assessment. The TFAM is a new
variation of a special form, which is used in Fuzzy mathematics centre of gravity(COG) defuzzification
technique. The TFAM’s new idea is the replacement of the rectangles appearing in the graph of the COG
method by isosceles trapezoids sharing common parts, thus covering the ambiguous cases of teachers’ scores
being at the limits between two successive grades (e.g between A and B). A classroom application is also
presented in which the outcomes of the COG and TFAM methods are compared with those of other traditional
assessment methods (calculation of means and GPA index) and explanations are provided for the differences
appeared among these outcomes .
Keywords : Teaching assessment, GPA index, fuzzy sets, centre of gravity(COG) defuzzification technique,
trapezoidal fuzzy assessment model(TFAM).
I. Introduction
The concept of teaching is fundamental to the study of student cognitive action. But while everyone
knows in general what teaching is, to give the clear idea about complicated proofs. This basically happens
because it is very difficult for someone to understand the way in which the students’ mind works, and therefore
to describe the mechanisms of the acquisition of the knowledge by the individual. The problem is getting even
harder by taking into consideration the fact that these mechanism, although they appear to have some common
general characteristics, they actually differ in details from person to person.
From[1] A.H.Sequeira says that “Teaching is a set of events, outside the learners which are designed to
support internal process of learning. Teaching (instruction) is outside the learners. Learning is internal to
learners. You cannot motivate others if you are not self –motivated. Motives are not seen, but behavior are
seen. Teaching is a both motive and behavior.
There are many theories and models developed by psychologists and education researchers for the
description of the mechanisms of teaching. From [2] Dr.Graeme Aitken argued that teaching basically consists
of which focuses on how teacher teach and on student results. An alternative view of teaching effectiveness that
incorporates style and outcomes within an inquiry based frame work. The following statements illustrate the
view of teaching effectiveness.
1. Teaching effectiveness is determined by what student is achieve.
2. The comparative effectiveness of teachers is best determined by comparing the achievements of the
students they teach.
3. The comparative effectiveness of teachers is best determined by comparing the added value they
contribute to the achievements of the students they teach.
The knowledge that teachers have about various concepts is usually imperfect characterized by different
degree of depth. From the student’s point of view on the other hand there exists vagueness about the degree of
teachers’ success in each stage of the teaching process. All these gave us the impulsion in earlier papers to
introduce principles of fuzzy logic in order to achieve a better and more realistic representing of the process of
teaching. We used [3] fuzzy logic system for assessing teachers’ mathematics teaching skills. We applied [4] the
centroid defuzzification technique that would be enable us to compare the teaching skills of teacher groups at
the each stage of the teaching process. Later we also used [5] the Triangular fuzzy model for assessing the
teachers’ mathematics teaching skills.
In this paper is the expansion of an introduced [6],[7] Trapezoidal fuzzy model for teaching
assessment(TFAM). In section 2 we render a brief account of fuzzy logic in the teaching process. A particular
emphasis is given in this section to the description of a special form of the COG technique, which is actually the
basis for the development of the TFAM. In section 3 we describe in detail the TFAM., while in section 4 we
present a classroom application illustrating our results in practice. In this application, apart from the fuzzy, we
also use traditional methods for teaching assessment (calculation of means, GPA index) and we compare their
outcomes with those of the COG and the TFAM methods.
For general facts on fuzzy sets and logic we refer to the book[9],[10],[11].

Fuzzy Models For Teaching…
7
II.Fuzzy models for the learning process
Kuhs and Ball (1986) [8] developed a model for teaching mathematics. We used this model [3] to
apply the fuzzy system for assessing the teachers’ mathematics teaching skills using possibilities and
probabilities of teachers’ profile. Later we applied [4] total possibilistic uncertainty and centre of gravity(COG)
defuzzification technique to provide an alternative measure for the teaching assessment. According to the COG
technique the defuzzification of a fuzzy situation’s data is succeeded through the calculation of the coordinates
of the COG of the level’s area contained between the graph of the membership function associated with this
situation and the OX axis. In order to be able to design the graph of the membership function we correspond to
each an interval of values from a prefixed numerical distribution, which actually means that we replace
with a set of real intervals. A brief description of the special form of the COG method applied for the learning
assessment [3],[4] is the following:
Let be a set of linguistic characterizing for the faculties’ performance, when A
stands for excellent, B for very good, C for good, D for mediocre and F for unsatisfactory respectively.
Obviously, the above characterizations are fuzzy depending on the modeler’s personal criteria, which
however must be compatible to the common logic, in order to model the teaching situation in a worthy of credit
way. We have adopted Bhavika tailor et.al’s model [12] for marking the faculty performance. For example,
these criteria can be formed by marking the faculties’ performance in the corresponding students’ feedback and
questioners within a scale from 0 to 100 and by assigning to their scores the above characterizations as follows:
and less than 50. Assume now that we want to
assess the general performance of a group, say G, of n faculties, where n is an integer, . For this, we
represent G as a fuzzy subset of U. In fact, if , and denote the number of faculties that
demonstrated excellent, very good, good, mediocre and unsatisfactory performance respectively, we define the
in terms of the frequencies, i.e., by for each x in U. Then G
can be written as a fuzzy subset of U in the form:
Next we replace U with a set of real intervals as follows:
Consequently, we have that
for all x in for all lx in for all x in
for all x in for all x in Since the membership
values of the elements of U in G have been defined in terms of the corresponding frequencies, we obviously
have that
(1)
We are now in position to construct the graph of the membership function , which has the
form of the bar graph shown in ;Figure 1. From Figure 1 one can easily observe that the level’s area, say S,
contained between the bar graph of and the OX axis is equal to the sum of the areas of five rectangles
The one side of each one of these rectangles has length 1 unit and lies on the OX axis.
Figure 1 : Bar graphical data representation
It is well known (e.g. see[13]) that the coordinates of the COG, say of the level’s area S are
calculated by the formulas:
Taking into account the situation presented by figure 1 and equation (1) it is straightforward to check that in our
case formulas (2) can be transformed to the form:

8
(3)
In fact, is the area of S which is in our case is equal to
Also
Now using elementary algebraic inequalities it is easy to check that there is a unique minimum for
corresponding COG (an analogous process for TFAM is described in detail in section 3). Further, the
ideal case is when = Then from formulas (3) we get and
Therefore the COG in this case is the point On the other hand the worst case is when and
. Then from formulas (3) we find that the COG is the point . Therefore the
COG of the level’s section F lies in the area of the triangle
Then by elementary geometric observations (an analogous process for TFAM is described in detail in section
3) one can obtain the following criterion:
 Between two faculty groups the group with the bigger performs better.
 If the two groups have the same , then the group with the bigger performs better.
 If the two groups have the same , then the group with the lower performs better.
Recently we [5] developed a new variation of the COG method for teaching assessment, which they called
Triangular Fuzzy Model(TFM). The main idea of TFM is to replace the rectangles appearing in the graph of
the COG method (figure 1) by isosceles triangles sharing common parts, so that to cover the ambiguous cases
of faculty scores being at the limits between two successive grades.
III. The trapezoidal fuzzy assessment model(TFAM)
The TFAM is a new variation of the presented in the previous section COG method. The novelty of the
approach is in the replacement of the rectangles appearing in the graph of the membership function of the COG
method (figure1) by isosceles trapezoids sharing common parts, so that to cover the ambiguous cases of
faculties scores being at the limits between two successive grades. Here we shall present an enhanced version of
the TFAM. In the TFAM’s scheme (figure 2) we have five trapezoids, corresponding to the faculties’ grades
F,D,C,B and A respectively defined in the previous section. Without loss of generality and for making our
calculations easier we consider isosceles trapezoids with the bases of length 10 units lying on the OX axis. The
height of the each trapezoid is equal to the percentage of faculties who achieved the corresponding grade , while
the parallel to its base side is equal to 4 units. We allow for any two adjacent trapezoids to have 30% of their
bases (3 units) belonging to both of them. In this way we cover the ambiguous cases of faculties scores being at
the limits between two successive grades. It is a very common approach to divide the interval of the specific
grades in three parts and to assign the corresponding grade using + and -. For example, 75-77=B-, 78-81=B, 82-
84=B+. however, this consideration does not reflect the common situation, where the student is not sure about
the grading of the faculties whose performance could be assessed as marginal between and close to two adjacent
grades; for example, something like 84-85 being between B+ and A. The TFAM fits this situation.

9
Figure 2:The TFAM’s schemes
A faculty group can be represented, as in the COG method, as a fuzzy set bin U, whose membership
function has the graph the line of figure 2, which is the
union of the line segments However, in case of the TFAM the analytical form
of is not needed for calculating the COG of the resulting area. In fact, since the marginal cases of the
faculties scores are considered as common parts for any pair of the adjacent trapezoids, it is logical to count
these parts twice; e.g. placing the ambiguous cases B+ and A- in both regions B and A. In other words, the
COG methods, which calculates the coordinates of the COG of the area between the graph of the membership
function and the OX axis, thus considering the areas of the “common “ triangles
, only once, is not the proper one to be applied in the above
situation.
Instead , in this case we represent each one of the five trapezoids of figure 2 by its COG
and we consider the entire area, i.e. the sum of the areas of the five trapezoids, as the system of these points-
centers. More explicitly, the steps of the whole construction of the TFAM are the following:
1.Let be the percentage of the faculties whose performance was
characterized by the grades F,D,C, and A respectively; then
2. We consider the isosceles trapezoids with heights being equal to , in the way that has
been illustrated in figure 2.
3.We calculate the coordinates ( of the COG of each trapezoid as follows: It is well
known that the COG of a trapezoid lies along the line segment joining the midpoints of its parallel sides a and b
at a distance d from the longer side b given by , where h is the height (e.g. see[14]). Therefore in our
case we have = Also, since the abscissa of the COG of each trapezoid is equal to the abscissa
of the midpoint of its base, it is easy to observe that
4.We consider the system of COG’s i= 1, 2, 3, 4, 5 and we calculate the coordinates ( of the COG
of the whole area S considered in figure 2 by the following formulas ,derived from the commonly used in
such a cases definition(e.g. see [15]):
(4).
In formulas (4) ,I = 1, 2, 3, 4, 5 denote the areas of the corresponding trapezoids. Thus
and
Therefore, from formulas(4) we finally get that
(5)
5.We determine the area of COG lies as follows: For I j = 1, 2, 3, 4, 5, we have that
, therefore , with the equality holding if, and only if .
Therefore
+2
=5 (6),

10
with the equality holding if, and only if, = = In the case equality the first of
formulas (5) gives that .
Further, combining the inequality (6) with the second of formulas(5) one finds that . Therefore the
unique minimum for corresponds to COG . The ideal case is when =
= . Then from formulas (5) we get that and . Therefore the COG in
this case is the point (33, ). On the other hand, the worst case is when = 1 and = .
Then from formulas (3), we find that the COG is the point (5, ). Therefore the area where the COG lies
in the area of the triangle (see figure 3)
Figure 3: The area where the COG lies
6.We formulate our criterion for comparing the performances of two (or more) teacher groups’ as follows:
From elementary geometric observations (see figure 3) it follows that for two teacher groups the group having
the greater performs better. Further, if the two groups have the same , then the group having the
COG which is situated closer to is the group with the greater . Also, if the two groups have the same
, then the group having the COG which is situated the farther to is the group with the smaller .
Based on the above considerations it is logical to formulate our criterion for comparing the two groups’
performance in the following form:
 Between two teacher groups the group with the greater value of demonstrates the better
performance.
 If two teacher groups have the same , then the group with the greater value of
demonstrates the better performance.
 If two teacher groups have the same , then the group with the smaller value of
demonstrates the better performance.
IV. A class room application
The faculties of two different departments ( Business administration and Mathematics) of the R.A.
college for women, Thiruvarur, handled the classes for bachelor of business administration . Both of the faculty
members were taken the papers such as Business mathematics, Business Statistics, Operations research and
Quantitative techniques. We have adopted Bhavika Tailor et.al’s model [12], from that we got the marks for
both department faculty members which are given below:
Department 1(D1- Mathematics):
1/2 Fw Fi
F2' F2
1/10
F1' F1
Fm
0 ½ xc' 5/2 xc 9/2 x

11
85,85,75,77,79 ,60,61,63,51,51,50,40,42.
Department 2(D2- Business administration):
90,84,82,74,73,70,59,58,48,45,45.
The results of the faculties’ performance are summarized in table 1 below:
Table 1: Results of D1and D2
Grade D1 D2
A 2 1
B 3 2
C 3 3
D 3 2
F 2 3
Total 13 11
The evaluation of the above results will be performed below using both traditional methods, based on principles
of the classical (bivalent) logic, and fuzzy logic methods.
4.1 Traditional methods
i) Calculations of the means: A straightforward calculation gives that the means of the faculties’ scores
are approximately 63 and 66.18 for D1 and D2 respectively. This shows that the mean performance was good
(C) for the both department D1 and D2.
Comparing D1 and D2 ,D2 is better than D1.
ii) Calculation of the GPA index: We recall that the Great Point Average (GPA) index is a weighted
mean, where more importance is given to the higher scores by attaching greater coefficients (weights) to them
(e.g. see [16]). In other words, the GPA index focuses on the quality performance of a faculty group.
Let us denote by , , , and the numbers of faculties of a given group whose performance is
characterized by A, B, C, D and F respectively and by n the total number of faculties of the group. Then, the
GPA index is calculated by the formula
GPA = .
Obviously we that 0 . In our case the above formula can be written as GPA=
(7). Then, using the data of table 1 it is easy to check that the GPA for D1 is equal to
and for D2 is equal to . Therefore, since the values of the GPA index are less than the half of
its maximal possible value , which is equal to 4, the quality performance of D1 was satisfactory and D2 was
less than satisfactory. However, in contrast to their mean performances, the quality performance of both D1 and
D2 were good.
4.2 Fuzzy logic methods
In this paragraph we shall apply the fuzzy logic methods described in sections 2 and 3 of this paper
as follows:
iii) The COG method: Observing the coefficients of the s, i = 1, 2, 3, 4, 5 in the first of formulas (3) and
taking into account that, according to the criterion stated in section 2, the COG abscissa measures a faculty
group’ performance, it becomes evident that the COG method is also focused , as the GPA index does, on the
faculty groups’ quality performance.
In case of our classroom application taking into account the data of table 1 and using the first of
formulas (3) we find that for D1 and for D2. Since the above value of are
more than the half of its value in the ideal case, which is equal to (see section 2), the quality performance of
both department according was more than the satisfactory. Further, D1 demonstrated a better quality
performance than D2.
iv) Application of TFAM: Observing the coefficients of the s, i = 1, 2, 3, 4, 5 in the first of formulas (5)
it is easy to conclude that the COG method is also focused on the faculty groups’ quality performance.
In case of our classroom application taking into account the data of table 1 and using the first of
formulas (5) we find that for D1 and for D2. In this case the value of
are more than the half of its value in the ideal case, which is equal to 33 (see section 3), the quality performance
of both department according was more than the satisfactory. Further, D1 demonstrated a better quality
performance than D2.
4.3 Comparison of the assessment method used

12
In paragraphs 4.1 and 4.2 we have applied four in total methods for learning assessment. The
first of these methods measures the mean performances of a faculty group, while the other three methods (GPA,
COG, TFAM) measure its quality performance by assessing greater coefficients (weights) to the higher scores.
The coefficients attached to the ’s in these three methods – see formula(7) and the first of formulas (3) and (5)
respectively are present in the following table 2:
Table2: Weights coefficients of the ’s
GPA COG( ) TFAM( )
0 ½ 7
1 3/2 14
2 5/2 21
3 7/2 28
4 9/2 35
From table 2 becomes evident that TFAM assigns greater coefficients to the higher with respect to the
lower scores than COG and also COG does the same thing with respect to GPA. In other words TFAM is more
accurate than COG, and COG is more accurate than GPA for measuring the quality performance of a faculty
group. This explains why in our classroom application the quality performance of D1 and D2 were found to
be different. One should also mention that , while D1 demonstrated in all cases(GPA, COG, TFAM) a better
performance than D2, in contrast to the mean performance of D2 , which was found to be better than the
corresponding performance of D1.
In concluding , it is suggested to the user of the above four assessment methods to choose the one that
fits better to his/her personal goals.
V. Conclusion and discussion
The methods for assessing a group’s performance (for human activities) usually applied in practice are based
on principles of the bivalent logic (yes-no). However, fuzzy logic, due to its nature of characterizing a situation
with multiple values by using linguistic variables, offers a wider and richer field of resources for this purpose.
This gave us the impulsion to introduce in this paper principles of fuzzy logic for developing an expanded
version of the TFAM approach for teaching assessment. The TFAM is actually a more sensitive version of the
COG fitting better to the ambiguous cases of faculties’ scores lying at the limits between two different grades.
We also presented a classroom application in which we have compared the outcomes of TFAM approach with
the corresponding outcomes of the COG technique and of other traditional assessment methods(calculations
of the means and GPA index).
However, there is a need for more classroom applications to be performed in future for obtaining safer
statistical data. On the other hand, since the TFAM approach appears to have a potential of general assessment
method , our future research plans include also the effort to apply this approach for assessing the individuals’
performance in several other human activities.
References
[1] http://ssrn.com/abstract 2150166.
[2] http://www.tki.org.nz/r/governance/ftpp/module2/index_e.php., Gr.Aitken,s The inquiring teacher: clarifying the conceptof
teaching effectiveness
[3] N.Sarala, R.Kavitha, Model Of Mathematics Teaching: A Fuzzy Set Approach
[4] International organization of scientific research – journal of mathematics ,Jan-Feb 2015,Vol.11,Ver.1 Issue 1, 19-22.
N.Sarala, R.Kavitha, Application of centroid technique and fuzzy measure for measuring mathematics teaching
skill,International Journal ofSscience and Research , March 2015, Vol 4 Issue 3,1749-1755
[5] N.Sarala, R.Kavitha, A triangular fuzzy model for assessing teachers’ mathematics teaching skills, International journal of
mathematics trends and technology, June 2015, Vol 22, No 1,9-12.
[6] Subbotin, I.Ya. Trapezoidal Fuzzy logic model for learning assessment, ar XIV 1407.0823[Math .GM], submitted on July 2014.
[7] Subbotin, I.Ya, Michael Gr.k Voskoglou, fuzzy Models for learning assessment
[8] Models of mathematics teaching – CCSU www.math.ccsu.edu/.../ models of mathematics Tea.
[9] Klir. G.j & folger,t.a. (1988), Fuzzy sets and uncertainty and information, Prentice Hall London.
[10] Klir. G.j/bo yuan, Fuzzy sets and fuzzy logic, Theory and applications, Prentice Hall London.(2010)
[11] h.j. zimmermann, Fuzzy set theory and its applications, Fourth edition, Springer, New Delhi.
[12] Bhavika Tailor,Rasik shah, Dr.Jayesh Dhodiya, Dr.Dilip Joshi, An evalutation of faculty performance in teaching using fuzzy
modeling approach, International journal of advance engineering and research development, Volume 1, Issue 3, April 2014,1-6.
[13] Wikipedia, Center of mass: Definition, available in the Web at:http://en.wikipedia.org/wiki/center of mass#definition.
[14] Wikipedia, Trapezoid: Other properties, available in the Web at:http://en.wikipedia.org/wiki/trapezoid# other properties 15.
[15] Wikipedia, Center of mass: A system of particles, available in the Web at:http://en.wikipedia.org/wiki/center of mass#A system
of particles.
[16] Grade point average assessment, available in the web at: http://www.swinburne.edu.au/student-
[17] administration/assessment/gpa.html.

Fuzzy Models for Teaching Assessment

More Related Content

What's hot (20)

Similar to Fuzzy Models for Teaching Assessment (20)

More from inventy (20)

Recently uploaded (20)

Fuzzy Models for Teaching Assessment