000 03211nam a22005055i 4500
001 978-981-287-411-5
003 DE-He213
005 20200420221302.0
007 cr nn 008mamaa
008 150214s2015 si | s |||| 0|eng d
020 _a9789812874115
_9978-981-287-411-5
024 7 _a10.1007/978-981-287-411-5
_2doi
050 4 _aQ342
072 7 _aUYQ
_2bicssc
072 7 _aCOM004000
_2bisacsh
082 0 4 _a006.3
_223
100 1 _aDe Silva, Anthony Mihirana.
_eauthor.
245 1 0 _aGrammar-Based Feature Generation for Time-Series Prediction
_h[electronic resource] /
_cby Anthony Mihirana De Silva, Philip H. W. Leong.
264 1 _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
347 _atext file
_bPDF
_2rda
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.
650 0 _aPattern recognition.
650 0 _aEconomics, Mathematical.
650 0 _aComputational intelligence.
650 1 4 _aEngineering.
650 2 4 _aComputational Intelligence.
650 2 4 _aPattern Recognition.
650 2 4 _aQuantitative Finance.
700 1 _aLeong, Philip H. W.
_eauthor.
710 2 _aSpringerLink (Online service)
773 0 _tSpringer eBooks
776 0 8 _iPrinted edition:
_z9789812874108
830 0 _aSpringerBriefs in Applied Sciences and Technology,
_x2191-530X
856 4 0 _uhttp://dx.doi.org/10.1007/978-981-287-411-5
912 _aZDB-2-ENG
942 _cEBK
999 _c53246
_d53246