Search

Prediction of research project execution using data augmentation and deep learning

Portada
MARC record
Tag12Value
LDR  00000cab a2200000 4500
001  MAP20230010006
003  MAP
005  20231214131745.0
008  230522e2023 esp|||p |0|||b|eng d
040  ‎$a‎MAP‎$b‎spa‎$d‎MAP
084  ‎$a‎922.134
1001 ‎$0‎MAPA20230004074‎$a‎Flores, Anibal
24510‎$a‎Prediction of research project execution using data augmentation and deep learning ‎$c‎Anibal Flores, Hugo Tito-Chura, Lissethe Zea-Rospigliosi
520  ‎$a‎Since most of the dataset prediction features are of the nominal type (true or false), this paper proposes a simple novel data augmentation technique for this type of features. Taking as inspiration the input data type of a neural network, the proposal data augmentation technique considers nominal features as numeric, and obtain random values close to them to generate synthetic records. The results show that most of deep learning models with data augmentation significantly outperform models with just class balancing in terms of accuracy, precision, f1-score and specificity, being the main improvements of 17.39%, 80.00%, 25.00% and 20.00% respectively
650 4‎$0‎MAPA20080611200‎$a‎Inteligencia artificial
650 4‎$0‎MAPA20080563790‎$a‎Predicciones
650 4‎$0‎MAPA20080576158‎$a‎Gestión de datos
650 4‎$0‎MAPA20080578848‎$a‎Análisis de datos
7001 ‎$0‎MAPA20230004081‎$a‎Tito Chura, Hugo
7001 ‎$0‎MAPA20230004104‎$a‎Zea Rospigliosi, Lissethe
7730 ‎$w‎MAP20200034445‎$g‎13/03/2023 Volumen 26 Número 71 - marzo 2023 , pp. 46-58‎$x‎1988-3064‎$t‎Revista Iberoamericana de Inteligencia Artificial‎$d‎ : IBERAMIA, Sociedad Iberoamericana de Inteligencia Artificial , 2018-
85600‎$y‎MÁS INFORMACIÓN‎$u‎ mailto:centrodocumentacion@fundacionmapfre.org?subject=Consulta%20de%20una%20publicaci%C3%B3n%20&body=Necesito%20m%C3%A1s%20informaci%C3%B3n%20sobre%20este%20documento%3A%20%0A%0A%5Banote%20aqu%C3%AD%20el%20titulo%20completo%20del%20documento%20del%20que%20desea%20informaci%C3%B3n%20y%20nos%20pondremos%20en%20contacto%20con%20usted%5D%20%0A%0AGracias%20%0A