The main objective of this research work is to develop the performance of education in higher schools elearning systems. This is accomplished with the aide of data mining (DM) techniques. The proposed model is applied on different students. Data is collected using online school tests, reports and quizzes. This paper applies SVM with accuracy 89%, Decision tree with accuracy 89%, M5-Rules with RMS error equal to 1.4621 and Linear Regression with RMS error equal to 2.0017, 3.0089 and 3.6057. Once getting both first and second grades, the presented results show a high predictive accuracy. Not only past student's evaluations affected in their academic achievement, but also other factors like father's and mother's jobs and absences. Briefly, student performance can be improved depending on predictive results and enhancing school systems.

The supply of drinking water has become a major challenge, despite large but relatively polluted quantities of groundwater, especially in southeastern Algeria. The use of solar energy for water desalination has become the subject of many local and global researchers. To solve this problem, we carried out an experimental study on two solar stills with a single slope. One was provided by a new absorber designed with multilayer composite materials and the other still was taken as a reference or control. The dimensions of the solar still was 0.5 × 0.5 m and the thickness of the layer of water used was 0.01 m. The results obtained show that the quantity of fresh water produced from the modified solar still was 4,312 l/m2 per day, while that of the reference solar still was 4,488 l/m2 per day, showing a difference in productivity of 3 %.

No abstract

No abstract