Name: Grammar-Based Feature Generation for Time-Series Prediction (en Inglés)
Price: 92.43 USD
Availability: InStock
Author: De Silva, Anthony Mihirana ; Leong, Philip H. W.
ISBN: 9789812874108

portada Grammar-Based Feature Generation for Time-Series Prediction (en Inglés)

Formato

Libro Físico

Autor

Anthony Mihirana De Silva

Philip H. W. Leong

Editorial

Springer

Idioma

Inglés

N° páginas

Encuadernación

Tapa Blanda

Dimensiones

23.4 x 15.6 x 0.6 cm

Peso

0.17 kg.

ISBN13

9789812874108

Categorías

Matemáticas aplicadas
Ingeniería: general
Reconocimiento de formas
Visión por ordenador

Grammar-Based Feature Generation for Time-Series Prediction (en Inglés)

Anthony Mihirana De Silva (Autor) · Philip H. W. Leong (Autor) · Springer · Tapa Blanda

Libro Nuevo

$ 92.43

$ 142.21

Ahorras: $ 49.77

35% descuento

Envío normal

Origen: Estados Unidos (Costos de importación incluídos en el precio)

Se enviará desde nuestra bodega entre el Lunes 15 de Julio y el Miércoles 24 de Julio.

Lo recibirás en cualquier lugar de Ecuador entre 1 y 3 días hábiles luego del envío.

Reseña del libro "Grammar-Based Feature Generation for Time-Series Prediction (en Inglés)"

This book proposes a novel approach for time-series prediction using machine learning techniques with automatic feature generation. Application of machine learning techniques to predict time-series continues to attract considerable attention due to the difficulty of the prediction problems compounded by the non-linear and non-stationary nature of the real world time-series. The performance of machine learning techniques, among other things, depends on suitable engineering of features. This book proposes a systematic way for generating suitable features using context-free grammar. A number of feature selection criteria are investigated and a hybrid feature generation and selection algorithm using grammatical evolution is proposed. The book contains graphical illustrations to explain the feature generation process. The proposed approaches are demonstrated by predicting the closing price of major stock market indices, peak electricity load and net hourly foreign exchange client trade volume. The proposed method can be applied to a wide range of machine learning architectures and applications to represent complex feature dependencies explicitly when machine learning cannot achieve this by itself. Industrial applications can use the proposed technique to improve their predictions.