ELECTROLAB: A NEW DATASET FOR EDUCATIONAL DATA MINING

Year 2018, Volume: 13 Issue: 4, 318 - 328, 13.10.2018

Bergen Karabulut , Şeyma Cihan , Halil Murat Ünver , Atilla Ergüzen

Abstract

Engineering
education prepares students for life by presenting theoretical and practical
knowledge together. A common method is applying laboratory experiments for
practicing theoretical knowledge by students. The objective of the laboratory
experiments is to gain student the ability of transferring theoretical
knowledge to practice and see the differences between theory and practice.
However; classical evaluation of laboratory courses has some difficulties in
terms of assessing complex input factors related to students. Educational data
mining, which has been widely used recently, allows evaluations for student
performance to be made easier. Implementing educational data mining for
laboratory lesson can be important contributions to the determination of the
factors affecting student performance and the structuring of training methods
accordingly. In this study, Electronic Circuits Laboratory Course, which is the
practice of Electronic Circuits Course as a basic course of Computer
Engineering education, were examined. A laboratory data set called ELECTROLAB was
created by collecting data from these courses. The first phases of CRISP, the
standard for data mining operations, have been implemented on this data set.
The data set was prepared and the attributes in the data set were analyzed
according to these phases. In the study, R programming language and Weka
program were used. The data set created by this study and the analysis process
will be the source of data mining methods to be applied in future studies. In
this way, it will be possible to determine the factors that affect the student
performance and to make studies to increase the success. 

Keywords

Data Mining, Educational Data Mining, Laboratory Dataset, Student Performance, CRISP-DM

ELECTROLAB: A NEW DATASET FOR EDUCATIONAL DATA MINING

Abstract

Engineering education prepares students for life by presenting theoretical and practical knowledge together. A common method is applying laboratory experiments for practicing theoretical knowledge by students. The objective of the laboratory experiments is to gain student the ability of transferring theoretical knowledge to practice and see the differences between theory and practice. However; classical evaluation of laboratory courses has some difficulties in terms of assessing complex input factors related to students. Educational data mining, which has been widely used recently, allows evaluations for student performance to be made easier. Implementing educational data mining for laboratory lesson can be important contributions to the determination of the factors affecting student performance and the structuring of training methods accordingly. In this study, Electronic Circuits Laboratory Course, which is the practice of Electronic Circuits Course as a basic course of Computer Engineering education, were examined. A laboratory data set called ELECTROLAB was created by collecting data from these courses. The first phases of CRISP, the standard for data mining operations, have been implemented on this data set. The data set was prepared and the attributes in the data set were analyzed according to these phases. In the study, R programming language and Weka program were used. The data set created by this study and the analysis process will be the source
of data mining methods to be applied in future studies. In this way, it will be possible to determine the factors that affect the student performance and to make studies to increase the success. 

Keywords

Data Mining, Educational Data Mining, Laboratory Dataset, Student Performance, CRISP-DM

References

• [1] Memon, J.A., Demirdöğen, R.E., and Chowdhry, B.S., (2009). Achievements, Outcomes and Proposal for Global Accreditation of Engineering Education in Developing Countries. Procedia-Social and Behavioral Sciences, Volume:1, Number:1, pp:2557-2561.
• [2] Shaleena, K.P. and Paul, S., (2015). Data mining Techniques for Predicting Student Performance. In Engineering and Technology (ICETECH), 2015 IEEE International Conference on, IEEE, pp:1-3.
• [3] Desai, A., Shah, N., and Dhodi, M., (2016). Student Profiling to Improve Teaching and Learning: A Data Mining Approach. In Data Science and Engineering (ICDSE), 2016 International Conference on.IEEE. pp:1-6.
• [4] Baradwaj, B.K. and Pal, S., (2012). Mining Educational Data to Analyze Students' Performance. arXiv preprint arXiv:1201.3417.
• [5] Yadav, S.K. and Pal, S., (2012). Data Mining: A Prediction for Performance Improvement of Engineering Students Using Classification. arXiv preprint arXiv:1203.3832.
• [6] Romero, C. and Ventura, S., (2010). Educational Data Mining: A Review of the State of the Art. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), Volume:40, Number:6, pp:601-618.
• [7] Kabra, R.R., and Bichkar, R.S., (2011). Performance Prediction of Engineering Students Using Decision Trees. International Journal of Computer Applications, Volume:36, Number:11, pp:8-12.
• [8] Wirth, R., and Hipp, J., (2000). CRISP-DM: Towards a Standard Process Model for Data Mining. In Proceedings of the 4th International Conference on the Practical Applications of Knowledge Discovery and Data Mining, pp:29-39.
• [9] Palaniappan, S. and Awang, R., (2008). Intelligent Heart Disease Prediction System Using Data Mining Techniques. In Computer Systems and Applications, 2008. AICCSA 2008. IEEE/ACS International Conference on, IEEE, pp:108-115.
• [10] Çınar, H. and Arslan, G., (2008). Veri Madenciliği ve CRISP-DM Yaklaşımı, XVII. İstatistik Araştırma Sempozyumu, Ankara, pp:304-314.
• [11] Al-Radaideh, Q.A., Al-Shawakfa, E.M., and Al-Najjar, M.I., (2006). Mining Student Data Using Decision Trees. In International Arab Conference on Information Technology (ACIT'2006), Yarmouk University, Jordan.
• [12] Hajizadeh, N. and Ahmadzadeh, M., (2014). Analysis of Factors That Affect the Students’ Academic Performance-Data Mining Approach. arXiv preprint arXiv:1409.2222.
• [13] Satyanarayana, A. and Nuckowski, M., (2016). Data Mining Using Ensemble Classifiers for Improved Prediction of Student Academic Performance.
• [14] Figueiredo, M., Esteves, L., Neves, J., and Vicente, H., (2016). A Data Mining Approach to Study the Impact of the Methodology Followed in Chemistry Lab Classes on the Weight Attributed by the Students to the lab Work on Learning and Motivation. Chemistry Education Research and Practice, Volume:17, No:1, pp:156-171.
• [15] Asif, R., Merceron, A., Ali, S.A., and Haider, N.G., (2017). Analyzing Undergraduate Students' Performance Using Educational Data Mining. Computers & Education.
• [16] Costa, E.B., Fonseca, B., Santana, M.A., de Araújo, F.F., and Rego, J., (2017). Evaluating the Effectiveness of Educational Data Mining Techniques for Early Prediction of Students' Academic Failure in Introductory Programming Courses. Computers in Human Behavior, Volume:73, pp:247-256.
• [17] Almarabeh, H., (2017). Analysis of Students' Performance by Using Different Data Mining Classifiers. International Journal of Modern Education and Computer Science, Volume:9, No:8.
• [18] Olaniyi, A.S., Kayode, S.Y., Abiola, H.M., Tosin, S.I.T., and Babatunde, A.N., (2017). Student’s Performance Analysis Using Decision Tree Algorithms. Annals. Computer Science Series, Volume:15, No:1.
• [19] Sarra, A., Fontanella, L., and Di Zio, S., (2018). Identifying Students at Risk of Academic Failure within the Educational Data Mining Framework. Social Indicators Research, pp:1-20.
• [20] Robbiano, C., Maciejewski, A.A., and Chong, E.K., (2018, June). Board 77: Work in Progress: An Analysis of Correlations in Student Performance in Core Technical Courses at a Large Public Research Institution’s Electrical and Computer Engineering Department. In 2018 ASEE Annual Conference & Exposition.
• [21] Khan, A. and Ghosh, S.K., (2018). Data Mining Based Analysis to Explore the Effect of Teaching on Student Performance. Education and Information Technologies, pp:1-21.