Preferred Learning Styles Among First Year Diploma Students Using Fuzzy Logic System \*\*double blind review, please do not include author information here\*\* \*\* Only include author information after the article has been reviewed \*\* Received Date: \*date Accepted Date: \*date Published Date: \*date **HIGHLIGHTS** - *Nine variables inputs were identified to obtain the VARK learning styles output.* - *Fuzzy logic system was used to determine preferred learning style based on VARK input.* - *Preferred students’ learning style was compared between male and female.* - *The Mamdani IF-THEN rules were used to determine the VARK learning styles output.* ABSTRACT *Every individual has his or her own natural or habitual pattern of gathering and processing information in learning situations. The different environments between school and university will pose a significant impact on the learning style of students. The objectives of this study are to analyse the most preferred learning style among first-year diploma students in Universiti Teknologi MARA (UiTM) Perlis Branch and to compare the preferred learning style by male and female students using Fuzzy Logic System.* *There were nine variables inputs in determining the fuzzy logic learning styles which are reading likeness, by nature, thinking time, speaking rate, activity level, activity enjoyment, visual distraction, auditory distraction and using instruction to obtain the VARK learning styles output. The result shows that 40% of the students preferred visual learning styles based on the VARK questionnaire while for fuzzy inferences system, 32% of the students preferred visual learning styles. Therefore, the visual learning style is chosen as the most preferred learning styles among the students in UiTM Perlis.* ***Keyword**s: Learning Styles, VARK, Fuzzy Logic, Fuzzy Inference System* # INTRODUCTION The different environments between school and university will have an impact on the learning style of students. The learning environment has changed in order to become more interconnected and centred on learners. First year can be difficult for some students because they have to adapt with the environment and different learning styles at the university level, which differs greatly from their school years. According to Singh, Govila and Rani (2015), learning styles are mental, emotional and psychological influences that serve as relatively stable markers of how the learner feels and communicates with and reacts to the learning environment. Study by Shuib, Zavareh and Abdullah (2014), VARK learning styles are preferable to other learning styles such as Honey and Mumford learning styles, Gardner Multiple Intelligence, Kolb learning styles and more. VARK is the short for Visual, Auditory, Read/Write and Kinaesthetic. Visual students, also known as a graphic learner, can retain information when confronted with images, charts, graphs, and displays just to name a couple. Auditory learners prefer to hear spoken information. These types of learners learn best from lectures, group discussion and even using mobile phones and emails. Auditory learners generally retain the best way to speak out loud when communicating with others. The read/write style prefers written and word details. Therefore, PowerPoints, written instructions and lists are preferred for these students. Kinaesthetic learning style is a perceptual preference related to the use of experience and practice. This includes demonstrations, stimulation, videos, and movies of 'real' material, as well as case studies, practice and application. According to Geetha and Praveena (2017), their previous study was to determine the relationship between learning style and interest in biological sciences among secondary school students. By using correlation analysis, the mean differences between the male and female are found to be 6.22. This value is tested for its significance using a t-test, which is the t-value 5.595, is found to be significant at 0.001 level of significance. Hence, there is a significance difference in the learning styles of male and female students. Besides that, by using the Fleming VARK learning styles, the findings of these studies showed that the most preferred learning styles among the secondary school are kinaesthetic learning styles which are 41.16% followed by visual 23.49%, auditory 19% and read/write 16.35%. Each student has a preferred learning style, but the four learning styles may be used to some degree, and some learners may use more than one style to an equal extent. There is a degree of uncertainty in determining the learning style (Alian & Shout, 2017). They use Fuzzy System in their previous study to measure the degree to which learners belong in relation to the four learning styles. This has inspired to conduct this research, in which a Fuzzy Logic system is formulated and implemented to measure the degree to which a learner belongs in relation to the four learning styles of male and female first year diploma students. # METHODOLOGY The population in this study are first year diploma students in UiTM Perlis Branch for semester September 2019 – January 2020 from six faculties. Online questionnaire was used to collect data from the students by using quota sampling method. Only 100 first year diploma students have answered the questionnaire. The survey has conducted through Google Form. There were nine variables inputs in determining the fuzzy logic learning styles which are Reading likeness, By nature, Thinking time, Speaking rate, Activity level, Activity Enjoyment, Visual Distraction, Auditory distraction and Using instruction. All the variables inputs in this study are based on the previous study by Alian and Shaout (2017). In this study, every variable input determines different learning styles output, however some inputs produced more than one output. For the Visual learning styles output; the reading likeness, visual distraction and auditory thinking time are used. While for the auditory learning styles output, the methods used are the auditory distraction, by nature, thinking time, speaking rate and activity level. For Read/Write output; thinking time, using instruction and read likeness are used. While thinking time, by nature, speaking rate, activity level and activity enjoyment are used for Kinesthetic output. There are three steps used in this study, which are fuzzification of input and output variables, evaluation of fuzzy inference and defuzzification using MATLAB software as shown in Figure 1. ![](171-1-501-1-2-20201224_media/media/image1.png)Figure 1: System of Fuzzy Logic **Fuzzification** Fuzzification is the first step in the fuzzy logic system. In this step, the linguistic variable such as ‘High’, ‘Moderate’, ‘Low’, ‘Fast’, ‘Moderate’ and ‘Slow’ will be used to obtain the result of the learning styles. These linguistic variables will be applied to represent the input and output variables such as read likeness, thinking time, speaking rate, activity level, activity enjoyment, by nature and VARK. The membership function for the variables is calculated based on triangular and trapezoidal functions. Table 1 shows the input and output variable with their linguistic terms. The linguistic term was provided from the previous study by (Alian & Shaout, 2017). Figure 2 shows the structure of the fuzzy inference system by using Mamdani. Table 1: Input and output variables and their linguistic terms
Function Variables Label Linguistic Term

Input

(Learning Features)

 By Nature ByNature {Outgoing, Quiet}
Read Likeness ReadLikeness {Low, Moderate, High}
Thinking Time ThinkingTime {Fast, Moderate, Slow}
Speaking Rate SpeakingRate {Slow, Medium, Fast}
Activity Level ActivityLevel {Mild, Moderate, Strenuous}
Activity Enjoyment ActivityEnjoyment {Worse, NoDiferrence, Better}
Visual Distraction VDistraction {Low, Moderate, High}
Auditory Distraction ADistraction {Low, Moderate, High}
Using Instruction UsingIntruction {NoInstruction, VerbalIntruction}

Output

(Learning Styles)

 Visual VLearningStyle {Mild, Strong, High}
Auditory ALearningStyle {Mild, Strong, High}
Kinaesthetic KLearningStyle {Mild, Strong, High}
Read/write RLearningStyle {Mild, Strong, High}
![](171-1-501-1-2-20201224_media/media/image2.png) > Figure 2: Fuzzy Inference System Editor **Table 2 - 11 show the parameters for each input while Figure 3 -13 show the membership functions for each input.** 1. **By nature** > Table 2: Fuzzy Number and Range for By Nature | **Fuzzy Number** | **Range** | | ---------------- | --------- | | Quiet | 0-5 | | Outgoing | 5.1-8 | > ![](171-1-501-1-2-20201224_media/media/image3.png) > > Figure 3: MATLAB - Membership Function for By Nature 2. **Read Likeness** > Table 3: Fuzzy Number and Range for Read Likeness | **Fuzzy Number** | **Range** | | ---------------- | --------- | | Low | 0-1 | | Moderate | 1.1-2 | | High | 2.1-4 | > ![](171-1-501-1-2-20201224_media/media/image4.png) > > Figure 4: MATLAB - Membership Function for Read Likeness 3. **Speaking Time** > Table 4: Fuzzy Number and Range for Speaking Time | **Fuzzy Number** | **Range** | | ---------------- | --------- | | Slow | 1-80 | | Medium | 80.1-120 | | Fast | 120.1-220 | ![](171-1-501-1-2-20201224_media/media/image5.png) > Figure 5: MATLAB - Membership Function for Speaking Time 4. **Thinking Time variables** > Table 5: Fuzzy Number and Range for Thinking Time | **Fuzzy Number** | **Range** | | ---------------- | --------- | | Fast | 1-80 | | Moderate | 80.1-120 | | Slow | 120.1-220 | > ![](171-1-501-1-2-20201224_media/media/image6.png) > > Figure 6: MATLAB - Membership Function for Thinking Time 5. **Level variables** > Table 6: Fuzzy Number and Range for Activity Level | **Fuzzy Number** | **Range** | | ---------------- | --------- | | Mild | 0-60 | | Moderate | 60.1-90 | | Strenuous | 90.1-120 | > ![](171-1-501-1-2-20201224_media/media/image7.png) > > Figure 7: MATLAB - Membership Function for Activity Level 6. **Activity Enjoyment** > Table 7: Fuzzy Number and Range for Activity Enjoyment | **Fuzzy Number** | **Range** | | ---------------- | --------- | | Worse | 0-3 | | No Difference | 3.1-5 | | Better | 5.1-7 | > ![](171-1-501-1-2-20201224_media/media/image8.png) > > Figure 8: MATLAB - Membership Function for Activity Enjoyment 7. > **Visual Distraction** > Table 8: Fuzzy Number and Range for Visual Distraction | **Fuzzy Number** | **Range** | | ---------------- | --------- | | Low | 0-12 | | Moderate | 12.1-15 | | High | 15.1-20 | > ![](171-1-501-1-2-20201224_media/media/image9.png) > > Figure 9: MATLAB - Membership Function for Visual Distraction 8. **Auditory Distraction** > Table 9: Fuzzy Number and Range for Auditory Distraction | **Fuzzy Number** | **Range** | | ---------------- | --------- | | Low | 0-10 | | Moderate | 10.1-15 | | High | 15.1-20 | > ![](171-1-501-1-2-20201224_media/media/image10.png) > > Figure 10: MATLAB - Membership Function for Auditory Distraction 9. **Using Instruction** Table 10: Fuzzy Number and Range for Using Instruction | **Fuzzy Number** | **Range** | | ------------------ | --------- | | No Instruction | 0-5 | | Verbal Instruction | 5.1-7 | > ![](171-1-501-1-2-20201224_media/media/image11.png) > > Figure 11: MATLAB - Membership Function for Using Instruction 10. **VARK Learning Styles** > Table 11: Fuzzy Number and Range for VARK Learning Styles | **Fuzzy Number** | **Range** | | ---------------- | --------- | | Mild | 0-13 | | Strong | 13.1-20 | | High | 20.1-25 | > ![](171-1-501-1-2-20201224_media/media/image12.png) Figure 12: MATLAB - Membership Function for VARK Learning Style **Evaluation of Fuzzy Inference** The input variables and output variables of the membership functions were applied in the Fuzzy Inference for the evaluation process. The output was generated by using IF-THEN rule with condition: "If *p* is *A* then *q* is *B*", where *A* and *B* are the linguistic values to formulate the conditional statement. This rule is a simplified representation of the behavior of a system that contains a condition and conclusion in order to help the user understand easily. The output membership function for each rule was determined based on Mamdani modelling. For Visual output there are 81 best rules are generated, for Auditory output there are 162 best rules are generated, for Read/Write output there 18 best rules and for Kinesthatics output there are 162 best rules are generated. The following is part of list of rules that was generated. 1. > If (ReadLikeness is low) and (ThinkingTime is fast) and (SpeakingRate is slow) and (VDistraction is low) then (VisualLearningStyle is mild) 2. > If (ReadLikeness is low) and (ThinkingTime is fast) and (SpeakingRate is slow) and (VDistraction is low) then (VisualLearningStyle is strong) 3. > If (ReadLikeness is low) and (ThinkingTime is fast) and (SpeakingRate is slow) and (VDistraction is low) then (VisualLearningStyle is high) 4. > If (ReadLikeness is moderate) and (ThinkingTime is fast) and (SpeakingRate is slow) and (VDistraction is low) then (VisualLearningStyle is mild) 5. > If (ReadLikeness is moderate) and (ThinkingTime is fast) and (SpeakingRate is slow) and (VDistraction is low) then (VisualLearningStyle is strong) 6. > If (ReadLikeness is moderate) and (ThinkingTime is fast) and (SpeakingRate is slow) and (VDistraction is low) then (VisualLearningStyle is high) 7. > If (ReadLikeness is high) and (ThinkingTime is fast) and (SpeakingRate is slow) and (VDistraction is low) then (VisualLearningStyle is mild) 8. > If (ReadLikeness is high) and (ThinkingTime is fast) and (SpeakingRate is slow) and (VDistraction is low) then (VisualLearningStyle is strong) 9. > If (ReadLikeness is high) and (ThinkingTime is fast) and (SpeakingRate is slow) and (VDistraction is low) then (VisualLearningStyle is high) 10. > If (ReadLikeness is low) and (ThinkingTime is moderate) and (SpeakingRate is slow) and (VDistraction is low) then (VisualLearningStyle is mild) The rules are then keyed in MATLAB software as shown in Figure 13. > ![](171-1-501-1-2-20201224_media/media/image13.png) > > Figure 13: MATLAB-Rules Editor for Visual Output **Defuzzification** The last step in fuzzy logic systems is defuzzification which is the process to convert value of the fuzzy membership into the single number or numerical values. Besides that, defuzzification is completed based on the membership function of the output variables. The most common in defuzzification is centroid method which is the method used to convert the linguistic terms to numerical values. Centroid Method is the centre of gravity of all defuzzification methods, the most appropriate and physically attractive. Formula for the centroid method in defuzzification: > (1) where, Defuzzied output Denoted to an algebraic integration \= Aggregated membership function output variables **FINDINGS AND DISCUSSIONS** Figure 14 shows the percentage of the preferred learning styles among the students in the datasets for each learning styles. From the VARK questionnaire, 32% preferred the Visual learning style and Auditory learning style, while for the Kinesthetic method, it is preferred with 25% and lastly the Read/Write was the least preferred learning styles with 11%. While, Figure 15 shows the preferred learning styles based on Fuzzy Inference System, which is Visual learning styles as the highest preferred learning styles with 40% and followed by the Read/Write with 27% preference. 18% of the students opted for the auditory mechanism, while the least preferred learning styles is Kinesthetic with 15%. Both of the results show that most of the students preferred Visual learning styles as their main learning styles. > \[CHART\] > > Figure 14: Preferred Percentage for VARK Questionnaire Learning Styles > > \[CHART\] > > Figure 15: Preferred Percentage for Fuzzy Inference System Figure 16 below shows the percentage of preferred learning styles by male and female students. Based on the figures, they show that 40% of male students preferred visual learning styles than other styles. This is followed by read/write and kinesthetic learning styles which are 20%. Apart from that, the female students also preferred visual learning styles, which is then followed by read/write learning styles comprising of 30% from the total female students. \[CHART\] **Figure 16: percentage of preferred learning styles by male and female students.** **CONCLUSION AND RECOMMENDATIONS** Fuzzy Logic System can be made useful in order to determine the preferred learning styles among the first-year diploma students in Universiti Teknologi MARA (UiTM) Perlis Branch. The input data were collected from an online questionnaire to obtain the inputs for the fuzzy inference system. The variables which were used as the providers for the input in this study are by nature, Reading Likeness, Visual Distraction, Auditory distraction, Using Instruction, Thinking Time, Activity Enjoyment and Speaking rate to determine the learning styles outputs which are Visual, Auditory, Read/Write and Kinesthetic. The Mamdani IF-THEN rules were used to determine the output. As a result, after inserting the first sample data into the Fuzzy Inference System, it shows that all the output variables come out 12.5 which is a strongly preferred learning style. The output obtained from the fuzzy inference system shows the same result with the actual data, which proved that the Visual learning style is the most preferred learning style by the students. Based on the fuzzy inference system, the result also exhibits that both male and female students choose Visual learning style as their approach in their education. For future work, several recommendations for improvement are proposed in order for coming researchers to better solve any problems that may arise. Besides that, the interactive system should be developed so that it can select the linguistic values for variables input for the fuzzy inference system. By doing this, the system can minimise or maximise the learning styles that the user possesses. Subsequently, lecturers or teachers should improve their techniques in teaching according to the learning styles that are preferred by their students. Lastly, students should understand their personal learning styles and improve their learning process so that it enables them to communicate with others. It also may be used to achieve excellent academic performance or in any other knowledge, skills or field. **REFERENCES** Alian, M., & Shaout, A. (2017). Predicting learners’ styles based on fuzzy model. *Education and Information Technologies*, *22*(5), 2217-2234. 8\. Geetha, M. C., & Praveena, K. B. (2017). Learning styles of secondary school students and their interest in biological science. *Learning*, *2*(5). Singh, L., Govil, P., & Rani, R. (2015). Learning style preferences among secondary school students. *International Journal of Recent Scientific Research*, *6*(5), 3924-3928. Shuib, L., Zavareh, A. A., & Abdullah, R. (2014). Fuzzy multi-criteria evaluation of research materials based on learning style. ARPN Journal of Engineering and Applied Sciences, 9(10), 1713-1717. (SCOPUS-Indexed)