Papers by Ahmed Abu El atta
Predicting Biological Activity of 2, 4, 6-trisubstituted 1, 3, 5-triazines Using Random Forest
This paper presents an approach to predict the activity of analogues of 2,4,6-trisubstituted 1,3,... more This paper presents an approach to predict the activity of analogues of 2,4,6-trisubstituted 1,3,5-triazines as cannabinoid receptor (CB2) agonists using random forest technique. We compute twenty molecular descriptors for a data set of 58 analogues for the component, and depending on values of these descriptors we train random forest to find a relation between biological activity and molecular structure of analogues. The results obtained by random forest were compared with the decision tree and support vector machine classifiers and the random forest has 100% overall predicting accuracy and for decision tree and support vector machine were 93% and 67% respectively.
Student Project Allocation with Preference Lists over (Student, Project) Pairs
Student project allocations models (SPA) in which lecturers have preferences over students (proje... more Student project allocations models (SPA) in which lecturers have preferences over students (projects) have been studied in. We present new method to construct a general student project allocation model (SPA-(s, p)) in which the lecturers have preference lists over pairs (student, project), and the students have preference lists over projects. SPA-(s, p) is turned out to be very useful in combination between the student project allocation models with preference lists over students (or projects). Our model proposes several ways to construct the lecturer's preference lists which give us higher efficiency and accurate results. Furthermore, we present algorithmic issues for SPA-(s, p), the algorithm yields a stable matching of students to projects, which respects the preference lists and capacity constraints.
Uploads
Papers by Ahmed Abu El atta