國立虎尾科技大學 |

Grammar-based feature generation for time-series prediction

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Grammar-based feature generation for time-series prediction/ by Anthony Mihirana De Silva, Philip H. W. Leong.
Author:	De Silva, Anthony Mihirana.
other author:	Leong, Philip H. W.
Published:	Singapore :Springer Singapore : : 2015.,
Description:	xi, 99 p. :ill., digital ; : 24 cm.;
Contained By:	Springer eBooks
Subject:	Machine learning. -
Online resource:	http://dx.doi.org/10.1007/978-981-287-411-5
ISBN:	9789812874115 (electronic bk.)

Grammar-based feature generation for time-series prediction
De Silva, Anthony Mihirana.

Grammar-based feature generation for time-series prediction[electronic resource] /by Anthony Mihirana De Silva, Philip H. W. Leong. - Singapore :Springer Singapore :2015. - xi, 99 p. :ill., digital ;24 cm. - SpringerBriefs in applied sciences and technology, Computational intelligence,2191-530X. - SpringerBriefs in applied sciences and technology.Computational intelligence..

Introduction -- Feature Selection -- Grammatical Evolution -- Grammar Based Feature Generation -- Application of Grammar Framework to Time-series Prediction -- Case Studies -- Conclusion.

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.

ISBN: 9789812874115 (electronic bk.)

Standard No.: 10.1007/978-981-287-411-5doiSubjects--Topical Terms:

561253
Machine learning.

LC Class. No.: Q325.5

Dewey Class. No.: 006.3

Grammar-based feature generation for time-series prediction
LDR:02543nam a2200325 a 4500 001 836429
003 DE-He213
005 20150921152144.0
006 m d
007 cr nn 008maaau
008 160421s2015 si s 0 eng d
020 $a 9789812874115 (electronic bk.)
020 $a 9789812874108 (paper)
024 7 $a 10.1007/978-981-287-411-5 $2 doi
035 $a 978-981-287-411-5
040 $a GP $c GP
041 0 $a eng
050 4 $a Q325.5
072 7 $a UYQ $2 bicssc
072 7 $a COM004000 $2 bisacsh
082 0 4 $a 006.3 $2 23
090 $a Q325.5 $b .D457 2015
100 1 $a De Silva, Anthony Mihirana. $3 1066547
245 1 0 $a Grammar-based feature generation for time-series prediction $h [electronic resource] / $c by Anthony Mihirana De Silva, Philip H. W. Leong.
260 $a Singapore : $c 2015. $b Springer Singapore : $b Imprint: Springer,
300 $a xi, 99 p. : $b ill., digital ; $c 24 cm.
490 1 $a SpringerBriefs in applied sciences and technology, Computational intelligence, $x 2191-530X
505 0 $a Introduction -- Feature Selection -- Grammatical Evolution -- Grammar Based Feature Generation -- Application of Grammar Framework to Time-series Prediction -- Case Studies -- Conclusion.
520 $a 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.
650 0 $a Machine learning. $3 561253
650 0 $a Time-series analysis $x Data processing. $3 671213
650 1 4 $a Engineering. $3 561152
650 2 4 $a Computational Intelligence. $3 768837
650 2 4 $a Pattern Recognition. $3 669796
650 2 4 $a Quantitative Finance. $3 669372
700 1 $a Leong, Philip H. W. $3 1066548
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer eBooks
830 0 $a SpringerBriefs in applied sciences and technology. $p Computational intelligence. $3 1019443
856 4 0 $u http://dx.doi.org/10.1007/978-981-287-411-5
950 $a Engineering (Springer-11647)