Name: Ensemble data mining method for predicting outbreak disease (en Inglés)
SKU: 57223924
Price: 78080.00 CLP
Availability: InStock
Author: Leopord, Hakizimana
ISBN: 9786138921462

portada Ensemble data mining method for predicting outbreak disease (en Inglés)

Ensemble data mining method for predicting outbreak disease (en Inglés)

Formato

Libro Físico

Autor

Hakizimana Leopord

Editorial

Scholars' Press

Idioma

Inglés

N° páginas

128

Encuadernación

Tapa Blanda

Dimensiones

22.9x15.2x0.8 cm

Peso

0.20 kg.

ISBN13

9786138921462

Categorías

Tecnología de la información: cuestiones generales

Ensemble data mining method for predicting outbreak disease (en Inglés)

Hakizimana Leopord (Autor) · Scholars' Press · Tapa Blanda

Libro Nuevo Importado

Envío: 20 a 24 días háb.

$ 141.960$ 78.080

-45%

Costos de importación incluídos en el precio ✅

Libro Nuevo

Quedan 10 unidades

$ 78.080

Llega entre el 29 Sep y el 05 Oct a Santiago, Región Metropolitana. Seleccionar ubicación

Agregar a lista de deseos

Reseña del libro "Ensemble data mining method for predicting outbreak disease (en Inglés)"

Data mining has played a significant role in outbreak disease prediction. However, issues persist due to gaps in existing research based on concerns about low predictive accuracy. Some algorithms of classification method are weak and the classification methods applied to malaria outbreak prediction are still very rare and more are needed to be established. To fill these gaps, the overall goal of this book is to propose an ensemble data mining classification method for malaria outbreak prediction that an organization can adopt to obtain better results. The research used qualitative and quantitative approaches to examine existing results and literature from various sources. Weka software as a machine learning tool has been used to ensemble DT (LF), LWL, SMO and complement Naive Bayes algorithms. The results of the study showed that the ensemble data mining classification method for the prediction of malaria outbreak is very accurate and powerful as compared to traditional algorithms.