000 03406nam a22005055i 4500
001 vtls000562941
003 RU-ToGU
005 20210922090805.0
007 cr nn 008mamaa
008 170213s2015 si | s |||| 0|eng d
020 _a9789812874115
_9978-981-287-411-5
024 7 _a10.1007/978-981-287-411-5
_2doi
035 _ato000562941
040 _aSpringer
_cSpringer
_dRU-ToGU
050 4 _aQ342
072 7 _aUYQ
_2bicssc
072 7 _aCOM004000
_2bisacsh
082 0 4 _a006.3
_223
100 1 _aDe Silva, Anthony Mihirana.
_eauthor.
_9470487
245 1 0 _aGrammar-Based Feature Generation for Time-Series Prediction
_helectronic resource
_cby Anthony Mihirana De Silva, Philip H. W. Leong.
260 _aSingapore :
_bSpringer Singapore :
_bImprint: Springer,
_c2015.
300 _aXI, 99 p. 28 illus.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
490 1 _aSpringerBriefs in Applied Sciences and Technology,
_x2191-530X
505 0 _aIntroduction -- Feature Selection -- Grammatical Evolution -- Grammar Based Feature Generation -- Application of Grammar Framework to Time-series Prediction -- Case Studies -- Conclusion.
520 _aThis 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 _aengineering.
_9224332
650 0 _aPattern Recognition.
_9304129
650 0 _aEconomics, Mathematical.
_9304111
650 0 _aComputational Intelligence.
_9307538
650 1 4 _aEngineering.
_9224332
650 2 4 _aComputational Intelligence.
_9307538
650 2 4 _aPattern Recognition.
_9304129
650 2 4 _aQuantitative Finance.
_9304891
700 1 _aLeong, Philip H. W.
_eauthor.
_9470488
710 2 _aSpringerLink (Online service)
_9143950
773 0 _tSpringer eBooks
830 0 _aSpringerBriefs in Applied Sciences and Technology,
_9410983
856 4 0 _uhttp://dx.doi.org/10.1007/978-981-287-411-5
912 _aZDB-2-ENG
999 _c417074