Learning Techniques

Question: What is the Learing Techniques ? Answer : Introducation The capability of predicting the performance of students is a very important aspect in university level learning. Moreover, the technique is best while assessing distance learning. The content of this paper is organized in form of a literature review to analyze various techniques of predicting learner performance as follows. Using Data mining algorithms to classify student is a study work done by (Romero et.al 2008). The study discusses the application of various data mining techniques and Moodle data usage to classify students and commonly used in computer science class. It involves combination of various tools of data mining in order to come up with one specific one(Kabra and Bikar, 2011). The authors used real data, numerical data and recombanitional data from the University of Cordoba to create the tool which has approved to be useful to instructors, students as well as parents. This tool is important since it can measure how quantitative and qualitative data can affect various algorithms. Performance prediction of engineering students using decision making tree is a study conducted (Kabra and Bichkar 2011). According to this study data mining is based decision making system. Classification of learners based on this tool involves the application of a decision tree classifier and student past performance (Kabra and Bichkar 2011). In this case the decision tree algorithm was applied to engineering students previous performance. The result of this tool is the ability of a teacher to predict failure and provide appropriate guidance and inputs required for better performance. The study on classification via clustering for predicting final student based on the student participation in various forums. The study focusses on the creation of a classification tool based student participation in forums (Lopez et.al 2012). This kind of tool is always applied to the performance of SSC students for ICT courses. It involves the use of experiments on traditional classification algorithms and Moodle forum. This techniques helps instructors in universities to identify a failure and success based on clusters attributes. Final grade prediction using decision tree is commonly used in high school in computer science class. The technique is suitable for prediction of student grade in several subject. This tool involves data mining and contains various hidden features brought to light during historical data mining (Khan al 2015). The strategy also comprises the use of decision tree classifier based on the divide and rule strategy(Echegary and Barrios, 2015). This technique is applied to previous J48 with the help of decision tree in order to develop a model important for predicting students final grade and laying of failure preventive measures. Optimal selection of factors using genetic algorithms and neural networks for the prediction of students academic performance by (Echegaray and Barrios 2015). This slant has been used to develop an anomaly grounded network intrusion exposure system in the field of medicine. The study resulted into creation of performance prediction tool which is 84% accurate. The two authors used genetic algorithms together with neural network fitness to predict learners success by classifying leaners ability in relation to their optic and neural fitness. References Kabra, R.R. and Bichkar, R.S., 2011. Performance prediction of engineering students using decision trees. International Journal of Computer Applications, 36(11), pp.8-12. Lopez, M.I., Luna, J.M., Romero, C. and Ventura, S., 2012. Classification via clustering for predicting final marks based on student participation in forums. International Educational Data Mining Society. Khan, B., Khiyal, M.S.H. and Khattak, M.D., 2015. Final Grade Prediction of Secondary School Student using Decision Tree. International Journal of Computer Applications, 115(21). Romero, C., Ventura, S., Espejo, P.G. and Hervs, C., 2008, June. Data mining algorithms to classify students. In Educational Data Mining 2008. Echegaray-Calderon, O.A. and Barrios-Aranibar, D., 2015, October. Optimal selection of factors using Genetic Algorithms and Neural Networks for the prediction of students' academic performance. In Computational Intelligence (LA-CCI), 2015 Latin America Congress on (pp. 1-6). IEEE.