Assembly of classifiers to determine the academic profile of students
| Autor: | Alexa Naveda, Karina Rojas, Jesús Silva, Claudia Medina, Carlos Vargas Mercado, Rosio Barrios |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Majority rule
decision trees Artificial neural network Computer science business.industry Decision tree 020206 networking & telecommunications 02 engineering and technology Base (topology) Machine learning computer.software_genre Assembly of classifiers 0202 electrical engineering electronic engineering information engineering General Earth and Planetary Sciences 020201 artificial intelligence & image processing Artificial intelligence Apprenticeship Decision table business computer artificial neural network General Environmental Science |
| Zdroj: | ANT/EDI40 Procedia Computer Science REDICUC-Repositorio CUC Corporación Universidad de la Costa instacron:Corporación Universidad de la Costa |
| ISSN: | 1877-0509 |
| DOI: | 10.1016/j.procs.2020.03.102 |
| Popis: | The assembly methods, or combination of models, arise with the purpose of improving the accuracy of predictions. An assembly contains a number of apprentices (base models) which, when of the same type are called homogeneous and if of different, heterogeneous. The characteristic is that these apprentices do not perform well. The assembly is generated using another algorithm that combines the apprentices, examples of which are the majority vote, the decision table and the neural networks [1]. This article proposes the use of an assembly of classifiers to determine the academic profile of the student, based on the student’s overall average and data related to educational factors. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|