LEADER 03945nam 22006735 450 001 9910299694603321 005 20200630183021.0 010 $a981-287-411-9 024 7 $a10.1007/978-981-287-411-5 035 $a(CKB)3710000000359231 035 $a(EBL)1974090 035 $a(SSID)ssj0001452093 035 $a(PQKBManifestationID)11806906 035 $a(PQKBTitleCode)TC0001452093 035 $a(PQKBWorkID)11478913 035 $a(PQKB)10854794 035 $a(DE-He213)978-981-287-411-5 035 $a(MiAaPQ)EBC1974090 035 $a(PPN)184495393 035 $a(EXLCZ)993710000000359231 100 $a20150214d2015 u| 0 101 0 $aeng 135 $aur|n|---||||| 181 $ctxt 182 $cc 183 $acr 200 10$aGrammar-Based Feature Generation for Time-Series Prediction /$fby Anthony Mihirana De Silva, Philip H. W. Leong 205 $a1st ed. 2015. 210 1$aSingapore :$cSpringer Singapore :$cImprint: Springer,$d2015. 215 $a1 online resource (105 p.) 225 1 $aSpringerBriefs in Computational Intelligence,$x2625-3704 300 $aDescription based upon print version of record. 311 $a981-287-410-0 320 $aIncludes bibliographical references. 327 $aIntroduction -- Feature Selection -- Grammatical Evolution -- Grammar Based Feature Generation -- Application of Grammar Framework to Time-series Prediction -- Case Studies -- Conclusion. 330 $aThis book proposes a novel approach for time-series prediction using machine learning techniques with automatic feature generation. Application of machine learning techniques to predict time-series continues to attract considerable attention due to the difficulty of the prediction problems compounded by the non-linear and non-stationary nature of the real world time-series. The performance of machine learning techniques, among other things, depends on suitable engineering of features. This book proposes a systematic way for generating suitable features using context-free grammar. A number of feature selection criteria are investigated and a hybrid feature generation and selection algorithm using grammatical evolution is proposed. The book contains graphical illustrations to explain the feature generation process. The proposed approaches are demonstrated by predicting the closing price of major stock market indices, peak electricity load and net hourly foreign exchange client trade volume. The proposed method can be applied to a wide range of machine learning architectures and applications to represent complex feature dependencies explicitly when machine learning cannot achieve this by itself. Industrial applications can use the proposed technique to improve their predictions. 410 0$aSpringerBriefs in Computational Intelligence,$x2625-3704 606 $aComputational intelligence 606 $aPattern perception 606 $aEconomics, Mathematical 606 $aComputational Intelligence$3https://scigraph.springernature.com/ontologies/product-market-codes/T11014 606 $aPattern Recognition$3https://scigraph.springernature.com/ontologies/product-market-codes/I2203X 606 $aQuantitative Finance$3https://scigraph.springernature.com/ontologies/product-market-codes/M13062 615 0$aComputational intelligence. 615 0$aPattern perception. 615 0$aEconomics, Mathematical. 615 14$aComputational Intelligence. 615 24$aPattern Recognition. 615 24$aQuantitative Finance. 676 $a006.3 676 $a006.4 676 $a519 676 $a620 700 $aDe Silva$b Anthony Mihirana$4aut$4http://id.loc.gov/vocabulary/relators/aut$01063322 702 $aLeong$b Philip H. W$4aut$4http://id.loc.gov/vocabulary/relators/aut 906 $aBOOK 912 $a9910299694603321 996 $aGrammar-Based Feature Generation for Time-Series Prediction$92531583 997 $aUNINA