# Appraise testees' behavior in the individual tests using fuzzy logic.

INTRODUCTION

One of the most important principles of individual tests is observe the testees' behavior in the test session. With this observation is that results interpretations of other factors are meaningful. In other words, testees' behavior observation is the most important advantage of individual tests than the group tests. Individual tests that have many strengths, weaknesses, too. One of those cases, entering subjective judgment to the measurement process. Human behavior, according to human nature, with vast complexity and uncertainty. In addition, in the behavioral assessments, classifications' criteria are qualitative and mismatch, the proofer is faced with a wide variety of irregular data. Certainly this makes the conclusions difficult and unreliable.

The importance of behavior observation, ambiguities and complexities of the target group and uncertainty in the results requires systematic process in the measurement. The attributes are expressed; fuzzy logic can be useful and indispensible role to play in this area. Not only in this particular subject, but in all areas of behavioral science that deals with the ambiguities and complexities of human behavior, the fuzzy system is available a powerful tool for researchers.

2. Related work:

Fuzzy logic, which was developed in 1965 by Professor Nasser Lotfi Zadeh, in 1970, entered the field of psychology [1]. Lot, but not enough research has been done in behavioral science by using fuzzy logic. Kushwaha in [5] described the role of fuzzy systems in psychological research and investigated the relationship between anxiety and stimulus. khademi in [4] assessed Educational performance of students with collaborative management and integration of fuzzy systems. Mssaro in [6] for speech perception contrasted the traditional model and fuzzy model. Hamam in [3] offered a fuzzy logic system for evaluating quality of experience of haptic-Based Applications. Haghani in [2] modeling the academic achievement with fuzzy system.

3. Fuzzification of appraise process:

3.1 Classification:

Dr H. Pasha Sharifi in [7] introduced following 14-fold criteria for appraise the testee's behavior in the test session.

1. Tests' comprehension

2. Compatibility with the Location

3. Amount of interest

4. Amount of cooperation

5. Diction

6. Power of Expression

7. Attentive and careful

8. Esteem

9. Attempt

10. Insist on doing task

11. Flexibility

12. Reaction to encouragement

13. The lack of reaction to the defeat

14. Perceptions and self-assessment

Classification criteria for the systematic measurement are mismatch. For example the classification of two criteria is as follows:

* Tests' comprehension

a) The purpose of testing is to fully understand

b) The purpose of testing is to some extent understand

c) The purpose of testing does not understand

* Power of Expression

a) Excellent

b) Good

c) Medium

d) Weak

e) Very weak

Thus, we considered scores range from 0 to 100 for quantifying and classification.

3.2 Fuzzification:

Fuzzy sets for all criteria defined as follow:

VL: Very Low, L: Low, M: Moderate, H: High, VH: Very High

For more flexible we used trapezoidal fuzzy sets. Draw a diagram and define the membership functions.

[MATHEMATICAL EXPRESSION NOT REPRODUCIBLE IN ASCII]

3.2.1 Intersection of fuzzy sets:

[[mu].sub.c](x) = min [[[mu].sub.A](x), [[mu].sub.B](x)]

3.3 Defuzzification:

[MATHEMATICAL EXPRESSION NOT REPRODUCIBLE IN ASCII]

Example::

Suppose obtained scores of behavior Appraisal a sample, accordance with the table 1. First characterized the membership functions of fuzzy sets, then with Intersection of fuzzy sets, [[mu].sub.c](x) are determine.

Calculations are done for defuzzification. How to calculate the fuzzy scores with a sample (x=73) explain:

[MATHEMATICAL EXPRESSION NOT REPRODUCIBLE IN ASCII]

All traditional scores convert into fuzzy scores. The results are shown in table2. t-test using for evaluated the significance differences between traditional scores and fuzzy scores. Null hypothesis is no significant difference. The data of table2 are used.

[MATHEMATICAL EXPRESSION NOT REPRODUCIBLE IN ASCII]

t table with degrees of freedom N=14-1=13 and a=0.01 is t=3.012. So the calculated t is less than t table, therefore the null hypothesis is true. Thus the two scoring methods have not significance differences.

Conclusions:

Using the systematic classification, definition of membership functions and selection centroid model for defazzification, a method offered that minimizes the proofer subjective judgment; this method is also covered uncertainty in the behavioral observing. t-test are shown that is no significant difference in the scoring of both traditional and fuzzy methods. Therefore this method is useful and can be used in individual tests.

ARTICLE INFO

Article history:

Received 11 June 2014

Received in revised form 21 September 2014

Accepted 25 November 2014

Available online 29 December 2014

REFERENCES

[1] Belohlavek, R., J.K. George., W.L. Harold, L. Lewis, C.W. Eileen, 2009. Concepts and fuzzy sets: Misunderstandings, misconceptions, and oversights. International Journal of Approximate Reasoning, 51: 23-34.

[2] Haghani, M., 2007. Application of fuzzy logic in the evaluation of academic progress. Qurterly Journal of Education, 50: 53-68.

[3] Hamam, A., M. Eid, A. Saddik, 2008. A Fuzzy Logic System for Evaluating Quality of Experience of Haptic-Based Applications. EuroHaptics, 5024: 129-138.

[4] Khademi, H., 2013. Collaborative management and integration of fuzzy system for evaluating students' academic performance. Qurterly Journal of Research and Planing in Higher Education, 69: 23-40.

[5] Kushwaha, G.S., S. Kumar, 2009. Role of the Fuzzy System in Psychological Research. Europe's Journal of Psychology, 2: 123-134.

[6] Massaro, W.D., 1989. Testing between the TRACE Model and the Fuzzy Logical Model of Speech Perception. Cognitive Psychology, 21: 398-421.

[7] Sharifi, H., 1998. Psychometric and Psychological testing, Tehran, Roshd Publications, 5: 273-276.

(1) Mir Abolfazl Nourani and (2) Somayeh Shoja Garebagh

(1) Department of Psychology, College of Humanity and Educational Sciences, Tabriz branch, Islamic Azad University, Tabriz, Iran .

(2) Tuberculosis and lung disease research center, Tabriz University of medical sciences, Tabriz, Iran.

Corresponding Author: Mir Abolfazl Nourani, Department of Psychology, College of Humanity and Educational Sciences, Tabriz branch Islamic Azad University, Tabriz, Iran.

E-mail: Nourani2008@gmail.com

One of the most important principles of individual tests is observe the testees' behavior in the test session. With this observation is that results interpretations of other factors are meaningful. In other words, testees' behavior observation is the most important advantage of individual tests than the group tests. Individual tests that have many strengths, weaknesses, too. One of those cases, entering subjective judgment to the measurement process. Human behavior, according to human nature, with vast complexity and uncertainty. In addition, in the behavioral assessments, classifications' criteria are qualitative and mismatch, the proofer is faced with a wide variety of irregular data. Certainly this makes the conclusions difficult and unreliable.

The importance of behavior observation, ambiguities and complexities of the target group and uncertainty in the results requires systematic process in the measurement. The attributes are expressed; fuzzy logic can be useful and indispensible role to play in this area. Not only in this particular subject, but in all areas of behavioral science that deals with the ambiguities and complexities of human behavior, the fuzzy system is available a powerful tool for researchers.

2. Related work:

Fuzzy logic, which was developed in 1965 by Professor Nasser Lotfi Zadeh, in 1970, entered the field of psychology [1]. Lot, but not enough research has been done in behavioral science by using fuzzy logic. Kushwaha in [5] described the role of fuzzy systems in psychological research and investigated the relationship between anxiety and stimulus. khademi in [4] assessed Educational performance of students with collaborative management and integration of fuzzy systems. Mssaro in [6] for speech perception contrasted the traditional model and fuzzy model. Hamam in [3] offered a fuzzy logic system for evaluating quality of experience of haptic-Based Applications. Haghani in [2] modeling the academic achievement with fuzzy system.

3. Fuzzification of appraise process:

3.1 Classification:

Dr H. Pasha Sharifi in [7] introduced following 14-fold criteria for appraise the testee's behavior in the test session.

1. Tests' comprehension

2. Compatibility with the Location

3. Amount of interest

4. Amount of cooperation

5. Diction

6. Power of Expression

7. Attentive and careful

8. Esteem

9. Attempt

10. Insist on doing task

11. Flexibility

12. Reaction to encouragement

13. The lack of reaction to the defeat

14. Perceptions and self-assessment

Classification criteria for the systematic measurement are mismatch. For example the classification of two criteria is as follows:

* Tests' comprehension

a) The purpose of testing is to fully understand

b) The purpose of testing is to some extent understand

c) The purpose of testing does not understand

* Power of Expression

a) Excellent

b) Good

c) Medium

d) Weak

e) Very weak

Thus, we considered scores range from 0 to 100 for quantifying and classification.

3.2 Fuzzification:

Fuzzy sets for all criteria defined as follow:

VL: Very Low, L: Low, M: Moderate, H: High, VH: Very High

For more flexible we used trapezoidal fuzzy sets. Draw a diagram and define the membership functions.

[MATHEMATICAL EXPRESSION NOT REPRODUCIBLE IN ASCII]

3.2.1 Intersection of fuzzy sets:

[[mu].sub.c](x) = min [[[mu].sub.A](x), [[mu].sub.B](x)]

3.3 Defuzzification:

[MATHEMATICAL EXPRESSION NOT REPRODUCIBLE IN ASCII]

Example::

Suppose obtained scores of behavior Appraisal a sample, accordance with the table 1. First characterized the membership functions of fuzzy sets, then with Intersection of fuzzy sets, [[mu].sub.c](x) are determine.

Calculations are done for defuzzification. How to calculate the fuzzy scores with a sample (x=73) explain:

[MATHEMATICAL EXPRESSION NOT REPRODUCIBLE IN ASCII]

All traditional scores convert into fuzzy scores. The results are shown in table2. t-test using for evaluated the significance differences between traditional scores and fuzzy scores. Null hypothesis is no significant difference. The data of table2 are used.

[MATHEMATICAL EXPRESSION NOT REPRODUCIBLE IN ASCII]

t table with degrees of freedom N=14-1=13 and a=0.01 is t=3.012. So the calculated t is less than t table, therefore the null hypothesis is true. Thus the two scoring methods have not significance differences.

Conclusions:

Using the systematic classification, definition of membership functions and selection centroid model for defazzification, a method offered that minimizes the proofer subjective judgment; this method is also covered uncertainty in the behavioral observing. t-test are shown that is no significant difference in the scoring of both traditional and fuzzy methods. Therefore this method is useful and can be used in individual tests.

ARTICLE INFO

Article history:

Received 11 June 2014

Received in revised form 21 September 2014

Accepted 25 November 2014

Available online 29 December 2014

REFERENCES

[1] Belohlavek, R., J.K. George., W.L. Harold, L. Lewis, C.W. Eileen, 2009. Concepts and fuzzy sets: Misunderstandings, misconceptions, and oversights. International Journal of Approximate Reasoning, 51: 23-34.

[2] Haghani, M., 2007. Application of fuzzy logic in the evaluation of academic progress. Qurterly Journal of Education, 50: 53-68.

[3] Hamam, A., M. Eid, A. Saddik, 2008. A Fuzzy Logic System for Evaluating Quality of Experience of Haptic-Based Applications. EuroHaptics, 5024: 129-138.

[4] Khademi, H., 2013. Collaborative management and integration of fuzzy system for evaluating students' academic performance. Qurterly Journal of Research and Planing in Higher Education, 69: 23-40.

[5] Kushwaha, G.S., S. Kumar, 2009. Role of the Fuzzy System in Psychological Research. Europe's Journal of Psychology, 2: 123-134.

[6] Massaro, W.D., 1989. Testing between the TRACE Model and the Fuzzy Logical Model of Speech Perception. Cognitive Psychology, 21: 398-421.

[7] Sharifi, H., 1998. Psychometric and Psychological testing, Tehran, Roshd Publications, 5: 273-276.

(1) Mir Abolfazl Nourani and (2) Somayeh Shoja Garebagh

(1) Department of Psychology, College of Humanity and Educational Sciences, Tabriz branch, Islamic Azad University, Tabriz, Iran .

(2) Tuberculosis and lung disease research center, Tabriz University of medical sciences, Tabriz, Iran.

Corresponding Author: Mir Abolfazl Nourani, Department of Psychology, College of Humanity and Educational Sciences, Tabriz branch Islamic Azad University, Tabriz, Iran.

E-mail: Nourani2008@gmail.com

Table 1: Scores of behavior Appraisal of sample [[mu].sub.c](x) membership functions [[mu]sub.VH](x) [[mu].sub.H] (x) [[mu].sub.M](x) 1 0 0 0 0.3 0 0 0.3 1 0 0 0 0.4 0 0 0 0.7 0 0 0.7 1 0 0 0 0.2 0 0 0 1 0 0 1 0.7 0 0 0.7 0.1 0 0.8 0.1 1 0 1 0 1 1 0 0 0.9 0 0.9 0 1 1 0 0 [[mu].sub.c](x) membership functions traditional [[mu].sub.L](x) [[mu].sub.VL](x) scores 1 1 0 43 0.3 0.4 0 48 1 1 0 30 0.4 0.4 0.6 22 0.7 0 0 52 1 0 1 12 0.2 0.8 0.2 24 1 0 0 65 0.7 0 0 73 0.1 0 0 79 1 0 0 80 1 0 0 95 0.9 0 0 86 1 0 0 98 [[mu].sub.c](x) Criteria row 1 tests' comprehension 1 0.3 Compatibility with the Location 2 1 amount of interest 3 0.4 amount of cooperation 4 0.7 Diction 5 1 Power of Expression 6 0.2 attentive and careful 7 1 esteem 8 0.7 attempt 9 0.1 insist on doing task 10 1 flexibility 11 1 reaction to encouragement 12 0.9 The lack of reaction to the defeat 13 1 perceptions and self-assessment 14 Table 2: Fuzzy scores [D.sup.2] D Fuzzy scores 64.00 8.00 35 210.25 -14.50 62.5 25.00 -5.00 35 169.00 -13.00 35 110.25 -10.50 62.5 0.03 0.18 11.82 148.35 12.18 11.82 6.25 2.50 62.5 110.25 10.50 62.5 272.25 16.50 62.5 16.00 -4.00 84 1.23 -1.11 96.11 4.00 2.00 84 3.57 1.89 96.11 [summation][D.sup.2] [absolute value of [bar.X] = 57,24 = 1140,44 ([summation]D)] = 5.64 [sigma] = 26.01 [D.sup.2] traditional scores 64.00 43 210.25 48 25.00 30 169.00 22 110.25 52 0.03 12 148.35 24 6.25 65 110.25 73 272.25 79 16.00 80 1.23 95 4.00 86 3.57 98 [summation][D.sup.2] [bar.X] = 57,64 = 1140,44 [sigma] = 23.64 [D.sup.2] Criteria 64.00 tests' comprehension 210.25 Compatibility with the Location 25.00 amount of interest 169.00 amount of cooperation 110.25 Diction 0.03 Power of Expression 148.35 attentive and careful 6.25 esteem 110.25 attempt 272.25 insist on doing task 16.00 flexibility 1.23 reaction to encouragement 4.00 The lack of reaction to the defeat 3.57 perceptions and self-assessment [summation][D.sup.2] = 1140,44

Printer friendly Cite/link Email Feedback | |

Author: | Nourani, Mir Abolfazl; Garebagh, Somayeh Shoja |
---|---|

Publication: | Advances in Environmental Biology |

Article Type: | Report |

Date: | Oct 1, 2014 |

Words: | 1480 |

Previous Article: | The relationship between leadership styles (transformational and transactional) and time traps in directors-general and heads of government agencies... |

Next Article: | A study of the relationship between ethical intelligence and organizational health in the high schools of 5th educational zone. |

Topics: |