فصلنامه علمی

نوع مقاله: مقاله پژوهشی

نویسندگان

1 باشگاه پژوهشگران و نخبگان جوان دانشگاه آزاد اسلامی واحد دهاقان، اصفهان. ایران

2 گروه مهندسی کامپیوتر و فناوری اطلاعات دانشگاه پیام نور، اصفهان، ایران

3 گروه مهندسی کامپیوتر، اصفهان، ایران

10.22061/tej.2015.377

چکیده

هدف این پژوهش ارائه الگویی جهت پیش­بینی عملکرد و افزایش کارایی و موفقیت یادگیری دانشجویان در یک محیط آموزشی با استفاده از داده­کاوی است. با تکیه به روش­های کتابخانه­ای و پرسشنامه­ای و مشاوره با افراد خبره تعدادی از وﯾﮋﮔﯽﻫﺎی ﺗأﺛﯿﺮﮔﺬار در ﯾﺎدﮔﯿﺮی داﻧﺸﺠﻮﯾﺎن شناسایی شد و ﺑﺎ اﺳﺘﻔﺎده از روش اﻧﺘﺨﺎب وﯾﮋﮔﯽ، مؤثرترین آنها اﻧﺘﺨﺎب ﺷﺪﻧﺪ و برای روشن­تر شدن روابط بین ویژگی­های انتخاب شده، ﺧﻮﺷﻪﺑﻨﺪی ﻓﺎزی ﺑﺮ روی آﻧﻬﺎ اﻧﺠﺎم ﮔﺮﻓﺖ. در فاز دوم پژوهش ﺑﺎ اﺳﺘﻔﺎده از ﺗﮑﻨﯿﮏﻫﺎی دادهﮐﺎوی ﺑﻪ ﭘﯿﺶ­ﺑﯿﻨﯽ ﻧﻤﺮات دانشجویان محیط آموزشی مورد مطالعه ﭘﺮداخته شد. ﻓﯿﻠﺪﻫﺎﯾﯽ ﮐﻪ ﺑﻪ ﻋﻨﻮان ﻣﺘﻐﯿﺮ در ﻧﻈﺮ ﮔﺮﻓﺘﻪ ﺷﺪ، ﻧﻤﺮه ﻣﯿﺎنﺗﺮم، ﭘﺎﯾﺎنﺗﺮم و ﻧﻤﺮه ﻧﻬﺎﯾﯽ (معدل) دروس اخذ شده در یک ترم توسط دانشجویان ورودی 1385 تا 1391 داﻧﺸﮕﺎه اﺳﺖ.
ﺑﺮ ﻣﺒﻨﺎی اﻟﮕﻮﻫﺎی ﺑﻪ دﺳﺖ آﻣﺪه ﻣﯽﺗﻮان ﻫﺮ داﻧﺸﺠﻮ را در راستای ویژگی­های تأثیرگذار بر روی آنها (دانشجویان) از اﺑﺘﺪای ﺗﺮم راﻫﻨﻤﺎﯾﯽ و ﺑﺎ ﺗﻮﺟﻪ ﺑﻪ ﻧﻤﺮاﺗﯽ ﮐﻪ در ﻃﻮل ﺗﺮم ﮐﺴﺐ ﻣﯽ­ﮐﻨﺪ، او را از ﻣﺤﺪوده ﻧﻤﺮه ﻧﻬﺎﯾﯽ ﺧﻮد آﮔﺎه ﮐﺮد و ﺑﺮ ﻃﺒﻖ ﺗﻮاﻧﺎﯾﯽﻫﺎﯾﺶ ﺑﺮﻧﺎﻣﻪرﯾﺰی ﻣﻨﺎﺳﺐ ﺗﺤﺼﯿﻠﯽ ﻧﻤﻮد. اﯾﻦ اﻟﮕﻮﻫﺎ ﻣﯽﺗﻮاﻧﻨﺪ ﺑﺮای ﮐﺎرآﻣﺪﺗﺮ ﺳﺎﺧﺘﻦ ﻓﺮآﯾﻨﺪ ﯾﺎدﮔﯿﺮی در ﺳﯿﺴﺘﻢ ﻣﺆﺛﺮ ﺑﺎﺷﻨد. نتایج آزمایش­ها حاکی از دقت مطلوب روش پیشنهادی 939/0 نسبت به روش­های قبلی (کشف قوانین همبستگی،کلاس‌بندی و تشخیص ناهمگونی).

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Applying fuzzy clustering to assess and anticipate students' educational progress in learning environments

نویسندگان [English]

  • M. Rostami 1
  • S.S. Ayat 2
  • F. Saghari 3
  • F. Yaghoobi 3

1 Young Researchers Club, Islamic Azad University, Dehaghan Branch, Isfahan, Iran,

2 Department of Computer Engineering and Information Technology, Payame Noor University. Isfahan, Iran

3 Software Engineering Department. Isfahan, Iran

چکیده [English]

The purpose of this paper is to propose a method to anticipate students' proceed and to enhance their learning efficiency and success in a learning environment, using data mining. Based on library and survey searching methods, as well as consulting with experts, some effective features in students' learning are identified and then using feature selection method, the most efficient ones are chosen. To clarify the relation between selected features, fuzzy clustering is applied to them. In the second phase of the research, scores of the students of Educational environment study, are predicted, using data mining. Variables taken are midterm and final scores and the average score of selected units in one semester by students studying there between 2006 (1385) and 2012 (1391).
According to the achieved methods we can guide each student from the beginning of the semester in line with their effective features, and based on scores gained during the semester we can inform the student about his range of final score to receive an educational plan based on his/her abilities. These methods can be effective in streamlining learning procedure in a system. Test results show the desired accuracy (0.939) of the proposed method than previous methods (discovery of association rules, classification, and identifying the inconsistencies).

کلیدواژه‌ها [English]

  • Electronic education
  • Feature selection
  • Fuzzy clustering
  • Data mining
  • Detection of integrity rules

[1] Cabena, P., Hadjinian, P., Stadler, R., Verhees, J., Zanasi, A., “Discovering Data Mining: From Concepts to Implementation”, Upper Saddle River, NJ: Prentice Hall, (1998). [2] Ranjan, J & Malik, K. “Effective educational process: a data mining approach”. VINE: The journal of information and knowledge management systems, Vol. 37, No. 4, (2007), pp. 502-515. [3] Shafiepoor, F. Nazari, H.,“Designing an Adjusted Model for Evaluating Electronic Learning Strategies’ Efficiency on Students’ Academic Achievement”, jte.srttu.edu, pp. 93- 101, (2014). [In Persian] محمد رستمی و همکاران 93 نشریه علمی پژوهشی فناوری آموزش، جلد 01 ،شماره 0 ،پاییز 0931 [4] Romero, C. Ventura, S. and Garcia, E. “Data mining in course management systems: Moodle case study and tutorial”, Computers & Education, Vol. 51, (2008), pp. 368-384. [5] Han Binglan “Student Modeling and Adaptively in Web Based Learning Systems” Ms. c. Thesis, Massey University, New Zealand. [6] Zarghami, E. and Azamati, S., “Considering the Desirability of Campus in Students Viewpoint”, Journal of technology of education, pp. 287-296, (2013). [In Persian] [7] Paulo Cortez, Alice Silva, “Using data minig to predict secondraycshool student performance”, (2007). [8] Romero, C., Espejo, G, Zafra, A, Romero and Ventura, J. R., “Web usage mining for predicting final marks of students that use Moodle courses. Computer Applications in Engineering Education”. Doi 10.1002/ cae. 20456, (2010). [9] Hung, J., & Zhang, K. “Revealing online learning behaviors and activity patterns and making predictions with data mining techniques in online teaching”. MERLOT Journal of Online Learning and Teaching, 2008. [10] Félix Castro, Alfredo Vellido, ÀngelaNebot, and Francisco Mugica, “Applying Data Mining Techniques to e-Learning Problems”.Studies in Computational Intelligence (SCI), (2007), pp. 183-221. [11] Mehdi, S. “Feature Selection using combination of GA and ACO”, Islamic Azad University of Tehran, (2009). [In Persian] [12] Romero, S. Ventura, “Educational data mining: A survey from 1995 to (2005), in Expert Systems with Applications”, (2007). [13] http://ceit.aut.ac.ir/~shiry/lecture/mac hinelearning/tutorial/fuzzy%20clusteri ng/introduction/introduction.htm [Accessed June 18, 2014]. [14] Seraji, F., Movahedi, R. M., and Siyahatkhah, “An Investigation of Iranian Virtual Universities Teachers’ Skills in Teaching These Courses”, jte.srttu.edu, pp. 25-37, (2015). [In Persian]