Article A Hybrid Method for Short-Term Wind Speed Forecasting

Size: px
Start display at page:

Download "Article A Hybrid Method for Short-Term Wind Speed Forecasting"

Transcription

1 Arcle A Hybrd Mehod for Shor-Term Wnd Speed Forecasng Jnlang Zhang 1,2, *, YMng We 2,3, Zhong-fu Tan 1, Wang Ke 2,3 and We Tan 4 1 School of Economcs and Managemen, Norh Chna Elecrc Power Unversy, Bejng , Chna; anzhongfubejngbj@163.com 2 Cener for Energy and Envronmenal Polcy Research, Bejng Insue of Technology, Bejng , Chna; we@b.edu.cn (Y.W.); wangkebejng@163.com (W.K.) 3 School of Managemen and Economcs, Bejng Insue of Technology, Bejng , Chna 4 School of Managemen and Economcs, Illnos Insue of Technology, Chcago, IL 60616, USA; anwe@homal.com * Correspondence: zhangjnlang1213@163.com; Tel.: ; Fax: Academc Edors: Lexun Yang, Peng Zhou and Nng Zhang Receved: 23 January 2017; Acceped: 7 Aprl 2017; Publshed: 12 Aprl 2017 Absrac: The accuracy of shor-erm wnd speed predcon s very mporan for wnd power generaon. In hs paper, a hybrd mehod combnng ensemble emprcal mode decomposon (EEMD), adapve neural nework based fuzzy nference sysem (ANFIS) and seasonal auo-regresson negraed movng average (SARIMA) s presened for shor-erm wnd speed forecasng. The orgnal wnd speed seres s decomposed no boh perodc and nonlnear seres. Then, he ANFIS model s used o cach he nonlnear seres and he SARIMA model s appled for he perodc seres. Numercal esng resuls based on wo wnd ses n Souh Dakoa show he effcency of hs hybrd mehod. Keywords: shor-erm wnd speed forecasng; ensemble emprcal mode decomposon (EEMD); adapve neural nework based fuzzy nference sysem (ANFIS); seasonal auo-regresson negraed movng average (SARIMA) 1. Inroducon Wnd energy has been consdered o be one of he mos mporan knds of clean energy. As a renewable energy resource, he use of wnd energy can save fossl energy and reduce greenhouse gases emsson. In recen years, he nsalled capacy of wnd power has been ncreasng rapdly. However, he use of wnd power generaon s very challengng for curren power sysem operaons. One reason for hs s ha wnd power s an nermen energy, whch has srong randomness and nsably. Anoher reason s ha wnd power s a non-dspachable energy source, whch canno be conrolled by operaors n he same way as oher generaon resources [1]. These problems can be effecvely resolved f wnd speed can be predced accuraely [2]. Therefore, mprovng he accuracy of shor-erm wnd speed forecasng s crucal for he operaon of wnd power plans. Dfferen mehods have been proposed o predc wnd speed, ncludng physcal mehods [3 5], spaal correlaon mehods [6 9], convenonal sascal mehods [10 14], and arfcal nellgence mehods [15 21]. Physcal mehods ake no accoun physcal nformaon such as emperaure, pressure and opography o predc he wnd speed, and hese mehods have become essenal for shor-erm and very shor-erm wnd speed predcon [22]. However, he necessary physcal nformaon s no avalable o all marke parcpans. Spaal correlaon mehods predc wnd speed based on he wnd speed seres of he suded se and s neghborng ses; however, he measuremen of he spaal correlaed ses wnd speed s dffcul. Compared wh spaal correlaon mehods, convenonal sascal mehods ulze only hsorcal daa o Susanably 2017, 9, 596; do: /su

2 Susanably 2017, 9, of 10 buld predcon models; however, hs mehod presens dffcules n forecasng he complcaed nonlnear componens n a gven wnd speed seres. Arfcal nellgence mehods, such as arfcal neural neworks (ANN), have been wdely used for wnd speed predcon. I has been proved ha he precson of arfcal nellgence mehods s hgher han oher mehods for shor-erm wnd speed forecasng [23]. Alhough ANN has nonlnear modelng capably, also has he drawback of beng wha s consdered as a black box, and he rules of ANN are no easly undersandable [24]. These rules can be undersood by fuzzy logc, bu has dffcules dealng wh oo many varables [25]. Therefore, adapve neural nework based fuzzy nference sysem (ANFIS) was proposed [26]. ANFIS ncorporaes he self-learnng capably of a neural nework and he lngusc expresson funcon of fuzzy logc nference, whch, combned, hus exhbs a superory over each of hem employed separaely. A wnd speed seres has noably random flucuaon and perodc varaon properes [27]. The ANFIS model s good a nonlnear forecasng, whle he seasonal auo-regresson negraed movng average (SARIMA) model s good a perodc forecasng [28]. Modelng he nonlnear componen of a wnd speed seres usng ANFIS model wll change he perodc componen. Thus, ensemble emprcal mode decomposon (EEMD) mehod s appled o decompose he orgnal wnd speed seres no some perodc seres and some nonlnear seres. EEMD s easly undersood, and he man dea of hs mehod s o separae he nonlnear componens and perodc componens by usng he Hlber-Huang ransform. Hence, n hs paper, a hybrd mehod combnng EEMD, ANFIS and SARIMA s proposed for he shor-erm wnd speed forecasng. Numercal es resuls show he effcency of he proposed mehod. The res of hs paper s organzed as follows. Secon 2 provdes a descrpon of he EEMD, ANFIS and SARIMA models. The proposed mehod s presened n Secon 3. Numercal resuls are presened n Secon 4. Secon 5 concludes hs paper. 2. Mehodology 2.1. EEMD Emprcal mode decomposon (EMD) s effecve n exracng he characersc nformaon from an orgnal wnd speed seres, whch can be decomposed no a se of nrnsc mode funcons (IMFs). The IMFs ndcae he oscllaory mode of he orgnal wnd speed seres. EMD s a self-adapve me seres processng mehod, whch can be perfecly used for complcaed processng [29]. The man drawback of EMD s s mode mxng problem. To resolve he mode mxng problem, EEMD mehod was proposed n [30]. The procedure of EEMD s descrbed as follows: (1) Inalze he number of ensemble M and he amplude of he added whe nose, se 1. (2) Add a whe nose seres o he orgnal wnd speed seres x (). x () x() n () (1) where n () denoes he -h added whe nose seres, and x () denoes he seres wh he added whe nose. (3) Decompose he seres x () no J IMFs c j () ( j 1, 2,, J ) by EMD mehod. Where c j () s he j -h IMF afer he -h ral, and J s he number of IMFs. (4) If M hen go o Sep (2) wh 1. Repea Sep (2) and (3) wh dfferen whe nose seres. (5) Calculae he ensemble mean cj () of he M rals for each IMF of he decomposon as he fnal resuls: 1 M 1 c j ( ) cj ( ), 1,2,..., M, j 1,2,..., J. (2) M where cj (), ( j 1,2,, J) s he j-h IMF componens usng he EEMD mehod.

3 Susanably 2017, 9, of ANFIS ANFIS s a mullayer feed forward nework, whch negraes he mers of neural neworks and fuzzy nference sysems [31]. In hs paper, ANFIS wh ype-3 reasonng mechansms s appled. The ypcal ANFIS wh ype-3 reasonng mechansms consss of fve layers, whch are shown n Fgure 1, he dealed descrpons of whch are gven n Reference [31]. The funcons of each layer are gven as follows. Layer 1: The oupus of hs layer are defned as: or: where x or y denoes he wnd speed seres, { 2 O1, ( x), 1, 2 (3) A O1, ( y), 3, 4 (4) B 2 O, B 1, B }, and (x) or (y) s he membershp funcon. The followng membershp funcon s ulzed: where ( x) s he Gaussan funcon; c and A 1 s he membershp degree of fuzzy se { A 1, A2} or ua ( x) exp[ 0.5{( x c)/ }], 1, 2 (5) are he mean and sandard devaon of he membershp funcon, respecvely. Layer 2: Ths layer s he operaon layer. Layer 3: All he npu varables are normalzed n he layer, and he oupu of hs layer s calculaed as: W O3, W W 1 W 2, 1, 2 (6) where O 3, s he oupu of Layer 3, and W s he ncenve srengh of rule. Layer 4: The followng node funcon s appled n hs layer: z W f W ( p xq y r), 1, 2 (7) where { p, q, r } s he parameer se of he nodes. Layer 5: The sngle node n hs layer summarzes all ncomng seres: z W1z1 W2z2 (8) x y x A 1 A 2 W 1 M W 1 z 1 z y B 1 W 2 M W 2 z 2 B 2 x y Fgure 1. The archecure of adapve neural nework based fuzzy nference sysem (ANFIS) nework wh ype-3 reasonng mechansms SARIMA SARIMA s he mos popular mehod for perodc me seres predcon, whch s descrbed as follows:

4 Susanably 2017, 9, of 10 s d s D F ( B) U ( B )(1 B) (1 B ) Z Q( B) V ( B ) e (9) s where F ( B), U( B ) denoes non-perodc and perodc auoregressve polynomal, respecvely. s Q ( B), V( B ) denoes non-perodc and perodc movng average polynomal, respecvely. Z denoes he wnd speed seres, and e represens he whe nose seres. d s he level of negraon, D s he level of perodc negraon, s s he order of perodcy, and B s he back-shf operaor. More deals abou SARIMA can been found n Reference [32]. In order o use he SARIMA model, he frs sep s o esmae he values of d and D. For hourly daa, a perodc dfference wh s = 24 and 168 are used o remove mos of he perodcy. The values of p and q are esmaed usng Auocorrelaon Funcon (ACF) and Paral Auocorrelaon Funcon (PACF). 3. The Proposed Mehod Due o he random feaures of wnd resource from me o me and from locaon o locaon, wnd speed forecasng s very challengng. Therefore, a deep nsgh no he orgnal wnd speed seres s mporan for provdng more accurae resuls. Fgure 2 shows he flowchar of he proposed mehod. As menoned above, a wnd speed seres has he complcaed feaure of nonlneary and perodcy. The hybrd mehod, whch has boh nonlnear and perodc modelng capables, wll be a good choce for wnd speed forecasng. By usng EEMD, he orgnal wnd speed seres s decomposed no some perodc seres and some nonlnear seres. Then, he ANFIS model s used o forecas he nonlnear seres and he SARIMA model s appled for he perodc seres. Wh he proposed mehod, boh he perodc and nonlnear componens of he wnd speed seres can be capured. The procedure s gven as follows. (1) The wnd speed seres s frsly decomposed no some IMFs and one resdual seres. n 1 s X () C() Rn() (10) where X () s he wnd speed seres, and C () and Rn () are he IMFs and he resdual seres, respecvely. (2) If he seres of C () and Rn () have he feaures of perodcy, hen hese seres are defned as Sj () ; oherwse, hey are defned as N (). Then, he orgnal wnd speed seres can be defned as: m n j n 1 jm1 (11) X () N () S () R () where N () and Sj () presen he nonlnear and perodc componen of he wnd speed seres, respecvely. (3) As for he seres of N () and Rn (), he ANFIS model s appled o forecas he seres of N () and Rn (). The forecasng resuls are defned as N ^ () and R ^ n (). The SARIMA model s used o forecas he seres of S j, and he forecasng resul s defned as ^ ^ (4) The wnd speed forecasng resul s he sum of N (), S j () ^ m ^ n ^ ^ j n 1 jm1 X () N () S () R () ^ S j (). and R ^ n () : (12) where ^ X () s he predced wnd speed.

5 Susanably 2017, 9, of 10 Fgure 2. Procedure of he proposed mehod. 4. Numercal Resuls 4.1. Daa Source The 10-mn wnd speed daa of wo ses n Souh Dakoa, USA was used o evaluae he effecveness of he proposed mehod. The daa of wo ses were recorded connuously and were averaged over every 10 mn o oban he wnd arbues. Wnd speeds were measured a 80 m above he ground. The wnd speed daa for four monhs, correspondng o February, May, Augus, and November, were seleced for he wner, sprng, summer, and fall seasons, respecvely. The wnd speed daa of he las day of each monh were used as he esng samples, whle he en days before he las day of each monh were used as he ranng samples. The mean, sandard devaon, mnmum velocy and maxmum velocy of wnd speed for he year 2006 are gven n Table Case Sudes Table 1. Sascal measures of he wnd speeds for he wo suded ses. Ses Mean (m/s) SD (m/s) Mn.Vel (m/s) Max.Vel (m/s) Se Se To verfy he accuracy of he proposed mehod, he forecasng resuls were compared wh oher mehods such as ANFIS and SARIMA. In hs sudy, he error crera, such as mean absolue error (MAE), roo mean square error (RMSE) and mean absolue percenage error (MAPE), are used o measure he predcon error. The mahemacal defnons of MAE, RMSE and MAPE are gven as follows: 1 T ^ T 1 MAE y y (13) 1 RMSE y y T ^ 2 ( ) (14) T 1

6 Susanably 2017, 9, of 10 1 ^ 1 T y y MAPE T (15) y where y and y ^ represen he acual and he forecas value, respecvely, and T s he me perod. For he sake of brevy, he procedure of he EEMD mehod o decompose he wnd speeds on 28 February 2006 for se 1 s used as an example, and oher esng days have hen been decomposed wh he same procedure Wnd Speed Seres Decomposon. The orgnal wnd speed seres s decomposed no nne IMFs and one resdual seres usng he EEMD mehod. The amplude of he added nose and ensemble number are 0.01 and 100, respecvely. The resuls can be seen n Fgure 3. Fgure 3. Decomposon resuls of he wnd speed seres usng EEMD.

7 Susanably 2017, 9, of Sub-Seres Forecasng As shown n Fgure 3, he perodc behavor s observed n IMF4, IMF5, IMF6, IMF7, IMF8 and IMF9, whch flucuae n dfferen perods. Thus, hey can be predced by he SARIMA model. Frs, he dfference and perodc dfference are used o make hese sub-seres more sable. Then, he ACF and he PACF are appled o denfy he parameers of p and q. Fnally, he SARIMA model s used o forecas he seres of IMF4, IMF5, IMF6, IMF7, IMF8 and IMF9. ANFIS s appled for he nonlnear sub-seres of IMF1, IMF2, IMF3 and he Resdual. Wh 5-pon Lker ype scales, hese seres are dvded no fve fuzzy subses, whch mples ha here are 25 rules. In hs sep, he generalzed bell-shaped membershp funcons are used o calculae he consequen parameers. Then, he nal value of sep lengh for he ranng s se o The selecon of he npu varables s crucal for achevng accurae forecasng resuls and he ACF and PACF are used for he npu varables selecon Comparsons of ANFIS, SARIMA and he Proposed Mehod In hs secon, he forecasng resuls obaned from he proposed mehod are compared wh hose from ANFIS and SARIMA. Because of he dfferen feaures of wnd speed n dfferen regons, he proposed mehod s appled o wo ses n Souh Dakoa. Furhermore, a dfferen forecas horzon wll also affec he predcon accuracy. Thus, forecas horzons of 3, 6, 12 and are used o demonsrae s effecveness. The MAE, RMSE and MAPE values of ANFIS, SARIMA and he proposed mehod for he wo ses are gven n Tables Predcon Resuls for From Tables 2 and 3, can be seen ha he MAE, RMSE and MAPE values of he proposed mehod are lower han oher mehods. The descrpon of he effecveness of he proposed mehod s presened as follows based on he predcon resuls of se 1. The MAPE value of he proposed mehod for he wner day s below 0.7%, whle he MAPE values for ANFIS and SARIMA are 1.87% and 1.83%, respecvely. The MAE value for he proposed mehod s 0.05, whch s smaller han ha obaned by ANFIS and SARIMA, whch are 0.15 and 0.14 respecvely. The RMSE value for he proposed mehod s 0.06, whch s also sgnfcanly smaller han ha obaned by ANFIS and SARIMA. For he sprng day, he proposed hybrd mehod s no as good as for he oher es days. However, accuracy s accepable wh he MAPE value below 2.4%. MAPE values for ANFIS and SARIMA are 3.98% and 5.06%, respecvely. The sprng day s no accuraely predced due o he sgnfcan varaon of wnd speed durng hs season. The proposed hybrd mehod s less accurae on he summer day han on he wner and fall days. However, he accuracy s accepable wh MAPE below 0.9%, whle he MAPE values for ANFIS and SARIMA are 1.44% and 2.92% on he summer day, respecvely. The proposed hybrd mehod s prey good for he fall day, wh MAPE below 0.7%, whereas he MAPE values for ANFIS and SARIMA are 1.17% and 1.30%, respecvely. Overall, he MAPE values obaned from all es days for ANFIS range from 1.17% o 3.98%, hose for SARIMA range from 1.30% o 5.06%, and hose for he proposed mehod range from 0.68% o 2.57%. The resuls demonsrae ha by combnng dfferen models, he forecasng accuracy ncreases noably. Table 2. Comparson of he predcon resuls of he hree mehods for se 1. Forecas Horzon Error ANFIS SARIMA Proposed Mehod 28 February May 2006 MAE RMSE MAPE (%) MAE RMSE MAPE (%)

8 Susanably 2017, 9, of Augus November 2006 MAE RMSE MAPE (%) MAE RMSE MAPE (%) Table 3. Comparson of he predcon resuls of he hree mehods for se 2. Forecas Horzon Error ANFIS SARIMA Proposed Mehod 28 February May Augus November Predcon Resuls for 3, 6 and 12 h MAE RMSE MAPE (%) MAE RMSE MAPE (%) MAE RMSE MAPE (%) MAE RMSE MAPE (%) To prove he superory of he proposed mehod, dfferen forecas horzons of 3, 6 and 12 h, whch are randomly seleced, have also been used for esng he proposed approach. 168 h prevous o he begnnng of each forecas horzon s used as he ranng samples. As can been seen from Tables 4 and 5, he MAPE values of he proposed mehod for all forecas horzons are obvously lower han he resuls obaned from oher mehods. The average MAPE value of se 1 for he proposed mehod s 1.38%, whch s less han ha obaned usng ANFIS (2.63%) and SARIMA (3.91%) echnques. Ths fndng shows he superor capably of hs proposed mehod, whch can capure he characerscs of seasonaly and nonlneary. Therefore, he proposed mehod could provde a consderable mprovemen n wnd speed forecasng. Table 4. Dfferen forecas horzons of he hree mehods for se 1. Proposed Forecas Horzon Error ANFIS SARIMA Mehod MAE h RMSE /02/2006 MAPE (%) MAE h RMSE /05/2006 MAPE (%) h 31/08/2006 Average MAE RMSE MAPE (%) MAE RMSE MAPE (%)

9 Susanably 2017, 9, of 10 Table 5. Dfferen forecas horzons of he hree mehods for se 2. Forecas Horzon Error ANFIS SARIMA Proposed Mehod 3 h 28/02/ h 31/05/ h 31/08/2006 Average MAE RMSE MAPE (%) MAE RMSE MAPE (%) MAE RMSE MAPE (%) MAE RMSE MAPE (%) Conclusons In hs paper, a new mehod combnng EEMD, ANFIS and SARIMA s proposed for shor-erm wnd speed forecasng. EEMD s used o decompose he orgnal wnd speed seres no perodc seres and nonlnear seres. The ANFIS model can more easly capure he nonlnear seres, whle he SARIMA model can capure he perodc seres. Suable npu varables are seleced for each sub-seres by usng he ACF and PACF. The proposed mehod has been examned by usng he daa of wo wnd ses n Souh Dakoa. Emprcal resuls show ha he proposed mehod can provde more accurae and effecve predcon resuls. Acknowledgmens: The auhors would lke o hank he suppor of Chna Naonal Scence Foundaon (No ). Auhor Conrbuons: Jnlang zhang had he orgnal dea and wre he paper. Oher auhors conrbued equally o he language of hs paper. Conflcs of Ineres: The auhors declare no conflc of neres. References 1. Erdem, E.; Sh, J. ARMA based approaches for forecasng he uple of wnd speed and drecon. Appl. Energy 2011, 88, Lu, H.P.; Sh, J.; Erdem, E. Predcon of wnd speed me seres usng modfed Taylor Krgng mehod. Energy 2010, 35, Wason, S.J.; Landberg, L.; Hallday, J.A. Applcaon of wnd speed forecasng o he negraon of wnd energy no a large scale power sysem. IEE Proc. Gener. Transm. Dsrb. 1994, 141, Landberg, L. Shor-erm predcon of he power producon from wnd farms. J. Wnd Eng. Ind. Aerodyn. 1999, 80, Negnevsky, M.; Johnson, P.; Sanoso, S. Shor erm wnd power forecasng usng hybrd nellgen sysems. In Proceedngs of he IEEE Power Engneerng General Meeng, Chcago, IL, USA, June 2007; pp Alexads, M.C.; Dokopoulos, P.S.; Sahsamanoglou, H.S.; Manousards, I.M. Shor erm forecasng of wnd speed and relaed elecrcal power. Sol. Energy 1998, 63, Damouss, I.G.; Alexads, M.C.; Theochars, J.B.; Dokopoulos, P.S. A fuzzy model for wnd speed predcon and power generaon n wnd parks usng spaal correlaon. IEEE Trans. Energy Convers. 2004, 19, Barbouns, T.G.; Theochars, J.B. A locally recurren fuzzy neural nework wh applcaon o he wnd speed predcon usng spaal correlaon. Neurocompung 2007, 70, Beccal, M.; Grrncone, G.; Marvugla, A.; Serpora, C. Esmaon of wnd velocy over a complex erran usng he generalzed mappng regressor. Appl. Energy 2010, 87, Brown, B.G.; Kaz, R.W.; Murphy, A.H. Tme seres models o smulae and forecas wnd speed and power. J. Clm. Appl. Meeorol. 1984, 23,

10 Susanably 2017, 9, of Lalarukh, K.; Yasmn, Z.J. Tme seres models o smulae and forecas hourly averaged wnd speed n Quea, Paksan. Sol. Energy 1997, 61, Pogg, P.; Musell, M.; Noon, G.; Crsofar, C.; Louche, A. Forecasng and smulang wnd speed n Corsca by usng an auoregressve model. Energy Convers. Manag. 2003, 44, Torres, J.L.; García, A.; De Blas, M.; De Francsco, A. Forecas of hourly average wnd speed wh ARMA models n Navarre. Sol. Energy 2005, 79, Kavasser, R.G.; Seeharaman, K. Day-ahead wnd speed forecasng usng f-arima models. Renew. Energy 2009, 34, Mohandes, M.; Halawan, T.; Rehman, S.; Hussan, A.A. Suppor vecor machnes for wnd speed predcon. Renew. Energy 2004, 29, Blgl, M.; Sahn, B.; Yasar, A. Applcaon of arfcal neural neworks for he wnd speed predcon of arge saon usng reference saons daa. Renew. Energy 2007, 32, Mabel, M.C.; Fernandez, E. Analyss of wnd power generaon and predcon usng ANN: A case sudy. Renew. Energy 2008, 33, Cadenas, E.; Rvera, W. Shor erm wnd speed forecasng n La Vena, Oaxaca, Méxco, usng arfcal neural neworks. Renew. Energy 2009, 34, Abdel-Aal, R.; Elhaddy, M.; Shaahd, S. Modelng and forecasng he mean hourly wnd speed me seres usng GMDH-based abducve neworks. Renew. Energy 2009, 34, Gong, L.; Sh, J. On comparng hree arfcal neural neworks for wnd speed forecasng. Appl. Energy 2010, 87, Thaw, L.; Sow, G.; Fall, S.S.; Kasse, M.; Sylla, E.; Thoye, S. A neural nework based approach for wnd resource and wnd generaors producon assessmen. Appl. Energy 2010, 87, Jung, J.; Broadwaer, R.P. Curren saus and fuure advances for wnd speed and power forecasng. Renew. Susan. Energy Rev. 2014, 31, Ma, L.; Luan, S.Y.; Jang, C.W.; Lu, H.L.; Zhang, Y. A revew on he forecasng of wnd speed and generaed power. Renew. Susan. Energy Rev. 2009, 13, Chen, T.L.; Cheng, C.H.; Teoh, H.J. Hgh-order fuzzy me-seres based on mul-perod adapaon model for forecasng sock markes. Physca A 2008, 387, Rodrguez, C.P.; Anders, G.J. Energy prce forecasng n he Onaro compeve power sysem marke. IEEE Trans. Power Sys. 2004, 19, Zhang, Y.; Zhou, Q.; Sun, C.X.; Le, S.L.; Lu, Y.M.; Song, Y. RBF neural nework and ANFIS-based shor-erm load forecasng approach n real-me prce envronmen. IEEE Trans. Power Sys. 2008, 23, Guo, Z.H.; Zhao, J.; Zhang, W.Y.; Wang, J.Z. A correced hybrd approach for wnd speed predcon n Hex Corrdor of Chna. Energy 2011, 36, Palm, F.C.; Zellner, A. To combne or no o combne? Issues of combnng forecass. In. J. Forecas. 1992, 11, Le, Y.G.; He, Z.J.; Z, Y.Y. Applcaon of he EEMD mehod o roor faul dagnoss of roang machnery. Mech. Sys. Sg. Process. 2009, 23, Wu, Z.; Huang, N. Ensemble emprcal mode decomposon: a nose asssed daa analyss mehod. Adv. Adap. Daa Anal. 2009, 1, Jang, J.S.R. ANFIS: Adapve-Nework-Based Fuzzy Inference Sysem. IEEE Trans. Sys. Man Cybern. 1993, 23, Box, G.E.P.; Jenkns, G.M. Tme Seres Analyss: Forecasng and Conrol; Holden Day: San Francsco, CA, USA, by he auhors. Lcensee MDPI, Basel, Swzerland. Ths arcle s an open access arcle dsrbued under he erms and condons of he Creave Commons Arbuon (CC BY) lcense (hp://creavecommons.org/lcenses/by/4.0/).

Robustness Experiments with Two Variance Components

Robustness Experiments with Two Variance Components Naonal Insue of Sandards and Technology (NIST) Informaon Technology Laboraory (ITL) Sascal Engneerng Dvson (SED) Robusness Expermens wh Two Varance Componens by Ana Ivelsse Avlés avles@ns.gov Conference

More information

Variants of Pegasos. December 11, 2009

Variants of Pegasos. December 11, 2009 Inroducon Varans of Pegasos SooWoong Ryu bshboy@sanford.edu December, 009 Youngsoo Cho yc344@sanford.edu Developng a new SVM algorhm s ongong research opc. Among many exng SVM algorhms, we wll focus on

More information

The Analysis of the Thickness-predictive Model Based on the SVM Xiu-ming Zhao1,a,Yan Wang2,band Zhimin Bi3,c

The Analysis of the Thickness-predictive Model Based on the SVM Xiu-ming Zhao1,a,Yan Wang2,band Zhimin Bi3,c h Naonal Conference on Elecrcal, Elecroncs and Compuer Engneerng (NCEECE The Analyss of he Thcknesspredcve Model Based on he SVM Xumng Zhao,a,Yan Wang,band Zhmn B,c School of Conrol Scence and Engneerng,

More information

Cubic Bezier Homotopy Function for Solving Exponential Equations

Cubic Bezier Homotopy Function for Solving Exponential Equations Penerb Journal of Advanced Research n Compung and Applcaons ISSN (onlne: 46-97 Vol. 4, No.. Pages -8, 6 omoopy Funcon for Solvng Eponenal Equaons S. S. Raml *,,. Mohamad Nor,a, N. S. Saharzan,b and M.

More information

Advanced time-series analysis (University of Lund, Economic History Department)

Advanced time-series analysis (University of Lund, Economic History Department) Advanced me-seres analss (Unvers of Lund, Economc Hsor Dearmen) 3 Jan-3 Februar and 6-3 March Lecure 4 Economerc echnues for saonar seres : Unvarae sochasc models wh Box- Jenns mehodolog, smle forecasng

More information

On One Analytic Method of. Constructing Program Controls

On One Analytic Method of. Constructing Program Controls Appled Mahemacal Scences, Vol. 9, 05, no. 8, 409-407 HIKARI Ld, www.m-hkar.com hp://dx.do.org/0.988/ams.05.54349 On One Analyc Mehod of Consrucng Program Conrols A. N. Kvko, S. V. Chsyakov and Yu. E. Balyna

More information

HEAT CONDUCTION PROBLEM IN A TWO-LAYERED HOLLOW CYLINDER BY USING THE GREEN S FUNCTION METHOD

HEAT CONDUCTION PROBLEM IN A TWO-LAYERED HOLLOW CYLINDER BY USING THE GREEN S FUNCTION METHOD Journal of Appled Mahemacs and Compuaonal Mechancs 3, (), 45-5 HEAT CONDUCTION PROBLEM IN A TWO-LAYERED HOLLOW CYLINDER BY USING THE GREEN S FUNCTION METHOD Sansław Kukla, Urszula Sedlecka Insue of Mahemacs,

More information

V.Abramov - FURTHER ANALYSIS OF CONFIDENCE INTERVALS FOR LARGE CLIENT/SERVER COMPUTER NETWORKS

V.Abramov - FURTHER ANALYSIS OF CONFIDENCE INTERVALS FOR LARGE CLIENT/SERVER COMPUTER NETWORKS R&RATA # Vol.) 8, March FURTHER AALYSIS OF COFIDECE ITERVALS FOR LARGE CLIET/SERVER COMPUTER ETWORKS Vyacheslav Abramov School of Mahemacal Scences, Monash Unversy, Buldng 8, Level 4, Clayon Campus, Wellngon

More information

Analysis And Evaluation of Econometric Time Series Models: Dynamic Transfer Function Approach

Analysis And Evaluation of Econometric Time Series Models: Dynamic Transfer Function Approach 1 Appeared n Proceedng of he 62 h Annual Sesson of he SLAAS (2006) pp 96. Analyss And Evaluaon of Economerc Tme Seres Models: Dynamc Transfer Funcon Approach T.M.J.A.COORAY Deparmen of Mahemacs Unversy

More information

Forecasting Using First-Order Difference of Time Series and Bagging of Competitive Associative Nets

Forecasting Using First-Order Difference of Time Series and Bagging of Competitive Associative Nets Forecasng Usng Frs-Order Dfference of Tme Seres and Baggng of Compeve Assocave Nes Shuch Kurog, Ryohe Koyama, Shnya Tanaka, and Toshhsa Sanuk Absrac Ths arcle descrbes our mehod used for he 2007 Forecasng

More information

Dynamic Team Decision Theory. EECS 558 Project Shrutivandana Sharma and David Shuman December 10, 2005

Dynamic Team Decision Theory. EECS 558 Project Shrutivandana Sharma and David Shuman December 10, 2005 Dynamc Team Decson Theory EECS 558 Proec Shruvandana Sharma and Davd Shuman December 0, 005 Oulne Inroducon o Team Decson Theory Decomposon of he Dynamc Team Decson Problem Equvalence of Sac and Dynamc

More information

Robust and Accurate Cancer Classification with Gene Expression Profiling

Robust and Accurate Cancer Classification with Gene Expression Profiling Robus and Accurae Cancer Classfcaon wh Gene Expresson Proflng (Compuaonal ysems Bology, 2005) Auhor: Hafeng L, Keshu Zhang, ao Jang Oulne Background LDA (lnear dscrmnan analyss) and small sample sze problem

More information

Bernoulli process with 282 ky periodicity is detected in the R-N reversals of the earth s magnetic field

Bernoulli process with 282 ky periodicity is detected in the R-N reversals of the earth s magnetic field Submed o: Suden Essay Awards n Magnecs Bernoull process wh 8 ky perodcy s deeced n he R-N reversals of he earh s magnec feld Jozsef Gara Deparmen of Earh Scences Florda Inernaonal Unversy Unversy Park,

More information

Comparison of Differences between Power Means 1

Comparison of Differences between Power Means 1 In. Journal of Mah. Analyss, Vol. 7, 203, no., 5-55 Comparson of Dfferences beween Power Means Chang-An Tan, Guanghua Sh and Fe Zuo College of Mahemacs and Informaon Scence Henan Normal Unversy, 453007,

More information

RELATIONSHIP BETWEEN VOLATILITY AND TRADING VOLUME: THE CASE OF HSI STOCK RETURNS DATA

RELATIONSHIP BETWEEN VOLATILITY AND TRADING VOLUME: THE CASE OF HSI STOCK RETURNS DATA RELATIONSHIP BETWEEN VOLATILITY AND TRADING VOLUME: THE CASE OF HSI STOCK RETURNS DATA Mchaela Chocholaá Unversy of Economcs Braslava, Slovaka Inroducon (1) one of he characersc feaures of sock reurns

More information

GENERATING CERTAIN QUINTIC IRREDUCIBLE POLYNOMIALS OVER FINITE FIELDS. Youngwoo Ahn and Kitae Kim

GENERATING CERTAIN QUINTIC IRREDUCIBLE POLYNOMIALS OVER FINITE FIELDS. Youngwoo Ahn and Kitae Kim Korean J. Mah. 19 (2011), No. 3, pp. 263 272 GENERATING CERTAIN QUINTIC IRREDUCIBLE POLYNOMIALS OVER FINITE FIELDS Youngwoo Ahn and Kae Km Absrac. In he paper [1], an explc correspondence beween ceran

More information

THEORETICAL AUTOCORRELATIONS. ) if often denoted by γ. Note that

THEORETICAL AUTOCORRELATIONS. ) if often denoted by γ. Note that THEORETICAL AUTOCORRELATIONS Cov( y, y ) E( y E( y))( y E( y)) ρ = = Var( y) E( y E( y)) =,, L ρ = and Cov( y, y ) s ofen denoed by whle Var( y ) f ofen denoed by γ. Noe ha γ = γ and ρ = ρ and because

More information

New M-Estimator Objective Function. in Simultaneous Equations Model. (A Comparative Study)

New M-Estimator Objective Function. in Simultaneous Equations Model. (A Comparative Study) Inernaonal Mahemacal Forum, Vol. 8, 3, no., 7 - HIKARI Ld, www.m-hkar.com hp://dx.do.org/.988/mf.3.3488 New M-Esmaor Objecve Funcon n Smulaneous Equaons Model (A Comparave Sudy) Ahmed H. Youssef Professor

More information

Approximate Analytic Solution of (2+1) - Dimensional Zakharov-Kuznetsov(Zk) Equations Using Homotopy

Approximate Analytic Solution of (2+1) - Dimensional Zakharov-Kuznetsov(Zk) Equations Using Homotopy Arcle Inernaonal Journal of Modern Mahemacal Scences, 4, (): - Inernaonal Journal of Modern Mahemacal Scences Journal homepage: www.modernscenfcpress.com/journals/jmms.aspx ISSN: 66-86X Florda, USA Approxmae

More information

Time Scale Evaluation of Economic Forecasts

Time Scale Evaluation of Economic Forecasts CENTRAL BANK OF CYPRUS EUROSYSTEM WORKING PAPER SERIES Tme Scale Evaluaon of Economc Forecass Anons Mchs February 2014 Worng Paper 2014-01 Cenral Ban of Cyprus Worng Papers presen wor n progress by cenral

More information

Research Article Day-Ahead Wind Speed Forecasting Using Relevance Vector Machine

Research Article Day-Ahead Wind Speed Forecasting Using Relevance Vector Machine Appled Mahemacs, Arcle ID 437592, 6 pages hp://dx.do.org/10.1155/2014/437592 Research Arcle Day-Ahead Wnd Speed Forecasng Usng Relevance Vecor Machne Guoqang Sun, 1 Yue Chen, 1 Zhnong We, 1 Xaolu L, 2

More information

CHAPTER 10: LINEAR DISCRIMINATION

CHAPTER 10: LINEAR DISCRIMINATION CHAPER : LINEAR DISCRIMINAION Dscrmnan-based Classfcaon 3 In classfcaon h K classes (C,C,, C k ) We defned dscrmnan funcon g j (), j=,,,k hen gven an es eample, e chose (predced) s class label as C f g

More information

FI 3103 Quantum Physics

FI 3103 Quantum Physics /9/4 FI 33 Quanum Physcs Aleander A. Iskandar Physcs of Magnesm and Phooncs Research Grou Insu Teknolog Bandung Basc Conces n Quanum Physcs Probably and Eecaon Value Hesenberg Uncerany Prncle Wave Funcon

More information

Lecture 6: Learning for Control (Generalised Linear Regression)

Lecture 6: Learning for Control (Generalised Linear Regression) Lecure 6: Learnng for Conrol (Generalsed Lnear Regresson) Conens: Lnear Mehods for Regresson Leas Squares, Gauss Markov heorem Recursve Leas Squares Lecure 6: RLSC - Prof. Sehu Vjayakumar Lnear Regresson

More information

A NEW TECHNIQUE FOR SOLVING THE 1-D BURGERS EQUATION

A NEW TECHNIQUE FOR SOLVING THE 1-D BURGERS EQUATION S19 A NEW TECHNIQUE FOR SOLVING THE 1-D BURGERS EQUATION by Xaojun YANG a,b, Yugu YANG a*, Carlo CATTANI c, and Mngzheng ZHU b a Sae Key Laboraory for Geomechancs and Deep Underground Engneerng, Chna Unversy

More information

Department of Economics University of Toronto

Department of Economics University of Toronto Deparmen of Economcs Unversy of Torono ECO408F M.A. Economercs Lecure Noes on Heeroskedascy Heeroskedascy o Ths lecure nvolves lookng a modfcaons we need o make o deal wh he regresson model when some of

More information

Introduction to Boosting

Introduction to Boosting Inroducon o Boosng Cynha Rudn PACM, Prnceon Unversy Advsors Ingrd Daubeches and Rober Schapre Say you have a daabase of news arcles, +, +, -, -, +, +, -, -, +, +, -, -, +, +, -, + where arcles are labeled

More information

Lecture VI Regression

Lecture VI Regression Lecure VI Regresson (Lnear Mehods for Regresson) Conens: Lnear Mehods for Regresson Leas Squares, Gauss Markov heorem Recursve Leas Squares Lecure VI: MLSC - Dr. Sehu Vjayakumar Lnear Regresson Model M

More information

Forecasting Time Series with Multiple Seasonal Cycles using Neural Networks with Local Learning

Forecasting Time Series with Multiple Seasonal Cycles using Neural Networks with Local Learning Forecasng Tme Seres wh Mulple Seasonal Cycles usng Neural Neworks wh Local Learnng Grzegorz Dudek Deparmen of Elecrcal Engneerng, Czesochowa Unversy of Technology, Al. Arm Krajowej 7, 42-200 Czesochowa,

More information

Time-interval analysis of β decay. V. Horvat and J. C. Hardy

Time-interval analysis of β decay. V. Horvat and J. C. Hardy Tme-nerval analyss of β decay V. Horva and J. C. Hardy Work on he even analyss of β decay [1] connued and resuled n he developmen of a novel mehod of bea-decay me-nerval analyss ha produces hghly accurae

More information

[ ] 2. [ ]3 + (Δx i + Δx i 1 ) / 2. Δx i-1 Δx i Δx i+1. TPG4160 Reservoir Simulation 2018 Lecture note 3. page 1 of 5

[ ] 2. [ ]3 + (Δx i + Δx i 1 ) / 2. Δx i-1 Δx i Δx i+1. TPG4160 Reservoir Simulation 2018 Lecture note 3. page 1 of 5 TPG460 Reservor Smulaon 08 page of 5 DISCRETIZATIO OF THE FOW EQUATIOS As we already have seen, fne dfference appromaons of he paral dervaves appearng n he flow equaons may be obaned from Taylor seres

More information

Short-Term Load Forecasting Using PSO-Based Phase Space Neural Networks

Short-Term Load Forecasting Using PSO-Based Phase Space Neural Networks Proceedngs of he 5h WSEAS In. Conf. on SIMULATION, MODELING AND OPTIMIZATION, Corfu, Greece, Augus 7-9, 005 (pp78-83) Shor-Term Load Forecasng Usng PSO-Based Phase Space Neural Neworks Jang Chuanwen, Fang

More information

Solution in semi infinite diffusion couples (error function analysis)

Solution in semi infinite diffusion couples (error function analysis) Soluon n sem nfne dffuson couples (error funcon analyss) Le us consder now he sem nfne dffuson couple of wo blocks wh concenraon of and I means ha, n a A- bnary sysem, s bondng beween wo blocks made of

More information

Linear Response Theory: The connection between QFT and experiments

Linear Response Theory: The connection between QFT and experiments Phys540.nb 39 3 Lnear Response Theory: The connecon beween QFT and expermens 3.1. Basc conceps and deas Q: ow do we measure he conducvy of a meal? A: we frs nroduce a weak elecrc feld E, and hen measure

More information

THE PREDICTION OF COMPETITIVE ENVIRONMENT IN BUSINESS

THE PREDICTION OF COMPETITIVE ENVIRONMENT IN BUSINESS THE PREICTION OF COMPETITIVE ENVIRONMENT IN BUSINESS INTROUCTION The wo dmensonal paral dfferenal equaons of second order can be used for he smulaon of compeve envronmen n busness The arcle presens he

More information

Relative controllability of nonlinear systems with delays in control

Relative controllability of nonlinear systems with delays in control Relave conrollably o nonlnear sysems wh delays n conrol Jerzy Klamka Insue o Conrol Engneerng, Slesan Techncal Unversy, 44- Glwce, Poland. phone/ax : 48 32 37227, {jklamka}@a.polsl.glwce.pl Keywor: Conrollably.

More information

Chapter 6: AC Circuits

Chapter 6: AC Circuits Chaper 6: AC Crcus Chaper 6: Oulne Phasors and he AC Seady Sae AC Crcus A sable, lnear crcu operang n he seady sae wh snusodal excaon (.e., snusodal seady sae. Complee response forced response naural response.

More information

Application of ARIMA Model for River Discharges Analysis

Application of ARIMA Model for River Discharges Analysis Alcaon of ARIMA Model for Rver Dscharges Analyss Bhola NS Ghmre Journal of Neal Physcal Socey Volume 4, Issue 1, February 17 ISSN: 39-473X Edors: Dr. Go Chandra Kahle Dr. Devendra Adhkar Mr. Deeendra Parajul

More information

On computing differential transform of nonlinear non-autonomous functions and its applications

On computing differential transform of nonlinear non-autonomous functions and its applications On compung dfferenal ransform of nonlnear non-auonomous funcons and s applcaons Essam. R. El-Zahar, and Abdelhalm Ebad Deparmen of Mahemacs, Faculy of Scences and Humanes, Prnce Saam Bn Abdulazz Unversy,

More information

TSS = SST + SSE An orthogonal partition of the total SS

TSS = SST + SSE An orthogonal partition of the total SS ANOVA: Topc 4. Orhogonal conrass [ST&D p. 183] H 0 : µ 1 = µ =... = µ H 1 : The mean of a leas one reamen group s dfferen To es hs hypohess, a basc ANOVA allocaes he varaon among reamen means (SST) equally

More information

Outline. Probabilistic Model Learning. Probabilistic Model Learning. Probabilistic Model for Time-series Data: Hidden Markov Model

Outline. Probabilistic Model Learning. Probabilistic Model Learning. Probabilistic Model for Time-series Data: Hidden Markov Model Probablsc Model for Tme-seres Daa: Hdden Markov Model Hrosh Mamsuka Bonformacs Cener Kyoo Unversy Oulne Three Problems for probablsc models n machne learnng. Compung lkelhood 2. Learnng 3. Parsng (predcon

More information

Econ107 Applied Econometrics Topic 5: Specification: Choosing Independent Variables (Studenmund, Chapter 6)

Econ107 Applied Econometrics Topic 5: Specification: Choosing Independent Variables (Studenmund, Chapter 6) Econ7 Appled Economercs Topc 5: Specfcaon: Choosng Independen Varables (Sudenmund, Chaper 6 Specfcaon errors ha we wll deal wh: wrong ndependen varable; wrong funconal form. Ths lecure deals wh wrong ndependen

More information

Chapter Lagrangian Interpolation

Chapter Lagrangian Interpolation Chaper 5.4 agrangan Inerpolaon Afer readng hs chaper you should be able o:. dere agrangan mehod of nerpolaon. sole problems usng agrangan mehod of nerpolaon and. use agrangan nerpolans o fnd deraes and

More information

5th International Conference on Advanced Design and Manufacturing Engineering (ICADME 2015)

5th International Conference on Advanced Design and Manufacturing Engineering (ICADME 2015) 5h Inernaonal onference on Advanced Desgn and Manufacurng Engneerng (IADME 5 The Falure Rae Expermenal Sudy of Specal N Machne Tool hunshan He, a, *, La Pan,b and Bng Hu 3,c,,3 ollege of Mechancal and

More information

Ordinary Differential Equations in Neuroscience with Matlab examples. Aim 1- Gain understanding of how to set up and solve ODE s

Ordinary Differential Equations in Neuroscience with Matlab examples. Aim 1- Gain understanding of how to set up and solve ODE s Ordnary Dfferenal Equaons n Neuroscence wh Malab eamples. Am - Gan undersandng of how o se up and solve ODE s Am Undersand how o se up an solve a smple eample of he Hebb rule n D Our goal a end of class

More information

Comb Filters. Comb Filters

Comb Filters. Comb Filters The smple flers dscussed so far are characered eher by a sngle passband and/or a sngle sopband There are applcaons where flers wh mulple passbands and sopbands are requred Thecomb fler s an example of

More information

Anisotropic Behaviors and Its Application on Sheet Metal Stamping Processes

Anisotropic Behaviors and Its Application on Sheet Metal Stamping Processes Ansoropc Behavors and Is Applcaon on Shee Meal Sampng Processes Welong Hu ETA-Engneerng Technology Assocaes, Inc. 33 E. Maple oad, Sue 00 Troy, MI 48083 USA 48-79-300 whu@ea.com Jeanne He ETA-Engneerng

More information

ELASTIC MODULUS ESTIMATION OF CHOPPED CARBON FIBER TAPE REINFORCED THERMOPLASTICS USING THE MONTE CARLO SIMULATION

ELASTIC MODULUS ESTIMATION OF CHOPPED CARBON FIBER TAPE REINFORCED THERMOPLASTICS USING THE MONTE CARLO SIMULATION THE 19 TH INTERNATIONAL ONFERENE ON OMPOSITE MATERIALS ELASTI MODULUS ESTIMATION OF HOPPED ARBON FIBER TAPE REINFORED THERMOPLASTIS USING THE MONTE ARLO SIMULATION Y. Sao 1*, J. Takahash 1, T. Masuo 1,

More information

UNIVERSITAT AUTÒNOMA DE BARCELONA MARCH 2017 EXAMINATION

UNIVERSITAT AUTÒNOMA DE BARCELONA MARCH 2017 EXAMINATION INTERNATIONAL TRADE T. J. KEHOE UNIVERSITAT AUTÒNOMA DE BARCELONA MARCH 27 EXAMINATION Please answer wo of he hree quesons. You can consul class noes, workng papers, and arcles whle you are workng on he

More information

Sampling Procedure of the Sum of two Binary Markov Process Realizations

Sampling Procedure of the Sum of two Binary Markov Process Realizations Samplng Procedure of he Sum of wo Bnary Markov Process Realzaons YURY GORITSKIY Dep. of Mahemacal Modelng of Moscow Power Insue (Techncal Unversy), Moscow, RUSSIA, E-mal: gorsky@yandex.ru VLADIMIR KAZAKOV

More information

WiH Wei He

WiH Wei He Sysem Idenfcaon of onlnear Sae-Space Space Baery odels WH We He wehe@calce.umd.edu Advsor: Dr. Chaochao Chen Deparmen of echancal Engneerng Unversy of aryland, College Par 1 Unversy of aryland Bacground

More information

( ) () we define the interaction representation by the unitary transformation () = ()

( ) () we define the interaction representation by the unitary transformation () = () Hgher Order Perurbaon Theory Mchael Fowler 3/7/6 The neracon Represenaon Recall ha n he frs par of hs course sequence, we dscussed he chrödnger and Hesenberg represenaons of quanum mechancs here n he chrödnger

More information

M. Y. Adamu Mathematical Sciences Programme, AbubakarTafawaBalewa University, Bauchi, Nigeria

M. Y. Adamu Mathematical Sciences Programme, AbubakarTafawaBalewa University, Bauchi, Nigeria IOSR Journal of Mahemacs (IOSR-JM e-issn: 78-578, p-issn: 9-765X. Volume 0, Issue 4 Ver. IV (Jul-Aug. 04, PP 40-44 Mulple SolonSoluons for a (+-dmensonalhroa-sasuma shallow waer wave equaon UsngPanlevé-Bӓclund

More information

Online Appendix for. Strategic safety stocks in supply chains with evolving forecasts

Online Appendix for. Strategic safety stocks in supply chains with evolving forecasts Onlne Appendx for Sraegc safey socs n supply chans wh evolvng forecass Tor Schoenmeyr Sephen C. Graves Opsolar, Inc. 332 Hunwood Avenue Hayward, CA 94544 A. P. Sloan School of Managemen Massachuses Insue

More information

Math 128b Project. Jude Yuen

Math 128b Project. Jude Yuen Mah 8b Proec Jude Yuen . Inroducon Le { Z } be a sequence of observed ndependen vecor varables. If he elemens of Z have a on normal dsrbuon hen { Z } has a mean vecor Z and a varancecovarance marx z. Geomercally

More information

FORECASTING NATURAL GAS CONSUMPTION USING PSO OPTIMIZED LEAST SQUARES SUPPORT VECTOR MACHINES

FORECASTING NATURAL GAS CONSUMPTION USING PSO OPTIMIZED LEAST SQUARES SUPPORT VECTOR MACHINES FORECASING NAURAL GAS CONSUMPION USING PSO OPIMIZED LEAS SQUARES SUPPOR VECOR MACHINES Hossen Iranmanesh 1, Majd Abdollahzade 2 and 3 Arash Mranan 1 Deparmen of Indusral Engneerng, Unversy of ehran & Insue

More information

Bayesian Inference of the GARCH model with Rational Errors

Bayesian Inference of the GARCH model with Rational Errors 0 Inernaonal Conference on Economcs, Busness and Markeng Managemen IPEDR vol.9 (0) (0) IACSIT Press, Sngapore Bayesan Inference of he GARCH model wh Raonal Errors Tesuya Takash + and Tng Tng Chen Hroshma

More information

Lecture 11 SVM cont

Lecture 11 SVM cont Lecure SVM con. 0 008 Wha we have done so far We have esalshed ha we wan o fnd a lnear decson oundary whose margn s he larges We know how o measure he margn of a lnear decson oundary Tha s: he mnmum geomerc

More information

The Dynamic Programming Models for Inventory Control System with Time-varying Demand

The Dynamic Programming Models for Inventory Control System with Time-varying Demand The Dynamc Programmng Models for Invenory Conrol Sysem wh Tme-varyng Demand Truong Hong Trnh (Correspondng auhor) The Unversy of Danang, Unversy of Economcs, Venam Tel: 84-236-352-5459 E-mal: rnh.h@due.edu.vn

More information

Survival Analysis and Reliability. A Note on the Mean Residual Life Function of a Parallel System

Survival Analysis and Reliability. A Note on the Mean Residual Life Function of a Parallel System Communcaons n Sascs Theory and Mehods, 34: 475 484, 2005 Copyrgh Taylor & Francs, Inc. ISSN: 0361-0926 prn/1532-415x onlne DOI: 10.1081/STA-200047430 Survval Analyss and Relably A Noe on he Mean Resdual

More information

Attribute Reduction Algorithm Based on Discernibility Matrix with Algebraic Method GAO Jing1,a, Ma Hui1, Han Zhidong2,b

Attribute Reduction Algorithm Based on Discernibility Matrix with Algebraic Method GAO Jing1,a, Ma Hui1, Han Zhidong2,b Inernaonal Indusral Informacs and Compuer Engneerng Conference (IIICEC 05) Arbue educon Algorhm Based on Dscernbly Marx wh Algebrac Mehod GAO Jng,a, Ma Hu, Han Zhdong,b Informaon School, Capal Unversy

More information

Clustering (Bishop ch 9)

Clustering (Bishop ch 9) Cluserng (Bshop ch 9) Reference: Daa Mnng by Margare Dunham (a slde source) 1 Cluserng Cluserng s unsupervsed learnng, here are no class labels Wan o fnd groups of smlar nsances Ofen use a dsance measure

More information

ABSTRACT KEYWORDS. Bonus-malus systems, frequency component, severity component. 1. INTRODUCTION

ABSTRACT KEYWORDS. Bonus-malus systems, frequency component, severity component. 1. INTRODUCTION EERAIED BU-MAU YTEM ITH A FREQUECY AD A EVERITY CMET A IDIVIDUA BAI I AUTMBIE IURACE* BY RAHIM MAHMUDVAD AD HEI HAAI ABTRACT Frangos and Vronos (2001) proposed an opmal bonus-malus sysems wh a frequency

More information

An introduction to Support Vector Machine

An introduction to Support Vector Machine An nroducon o Suppor Vecor Machne 報告者 : 黃立德 References: Smon Haykn, "Neural Neworks: a comprehensve foundaon, second edon, 999, Chaper 2,6 Nello Chrsann, John Shawe-Tayer, An Inroducon o Suppor Vecor Machnes,

More information

2. SPATIALLY LAGGED DEPENDENT VARIABLES

2. SPATIALLY LAGGED DEPENDENT VARIABLES 2. SPATIALLY LAGGED DEPENDENT VARIABLES In hs chaper, we descrbe a sascal model ha ncorporaes spaal dependence explcly by addng a spaally lagged dependen varable y on he rgh-hand sde of he regresson equaon.

More information

Neural Networks-Based Time Series Prediction Using Long and Short Term Dependence in the Learning Process

Neural Networks-Based Time Series Prediction Using Long and Short Term Dependence in the Learning Process Neural Neworks-Based Tme Seres Predcon Usng Long and Shor Term Dependence n he Learnng Process J. Puchea, D. Paño and B. Kuchen, Absrac In hs work a feedforward neural neworksbased nonlnear auoregresson

More information

Including the ordinary differential of distance with time as velocity makes a system of ordinary differential equations.

Including the ordinary differential of distance with time as velocity makes a system of ordinary differential equations. Soluons o Ordnary Derenal Equaons An ordnary derenal equaon has only one ndependen varable. A sysem o ordnary derenal equaons consss o several derenal equaons each wh he same ndependen varable. An eample

More information

Available online at ScienceDirect. Procedia CIRP 56 (2016 )

Available online at   ScienceDirect. Procedia CIRP 56 (2016 ) Avalable onlne a www.scencedrec.com ScenceDrec Proceda CIRP 56 (6 ) 8 87 9h Inernaonal Conference on Dgal Enerprse Technology- DET6 Inellgen Manufacurng n he Knowledge Economy Era Revson of bearng faul

More information

A Novel Object Detection Method Using Gaussian Mixture Codebook Model of RGB-D Information

A Novel Object Detection Method Using Gaussian Mixture Codebook Model of RGB-D Information A Novel Objec Deecon Mehod Usng Gaussan Mxure Codebook Model of RGB-D Informaon Lujang LIU 1, Gaopeng ZHAO *,1, Yumng BO 1 1 School of Auomaon, Nanjng Unversy of Scence and Technology, Nanjng, Jangsu 10094,

More information

Bayes rule for a classification problem INF Discriminant functions for the normal density. Euclidean distance. Mahalanobis distance

Bayes rule for a classification problem INF Discriminant functions for the normal density. Euclidean distance. Mahalanobis distance INF 43 3.. Repeon Anne Solberg (anne@f.uo.no Bayes rule for a classfcaon problem Suppose we have J, =,...J classes. s he class label for a pxel, and x s he observed feaure vecor. We can use Bayes rule

More information

Online Supplement for Dynamic Multi-Technology. Production-Inventory Problem with Emissions Trading

Online Supplement for Dynamic Multi-Technology. Production-Inventory Problem with Emissions Trading Onlne Supplemen for Dynamc Mul-Technology Producon-Invenory Problem wh Emssons Tradng by We Zhang Zhongsheng Hua Yu Xa and Baofeng Huo Proof of Lemma For any ( qr ) Θ s easy o verfy ha he lnear programmng

More information

January Examinations 2012

January Examinations 2012 Page of 5 EC79 January Examnaons No. of Pages: 5 No. of Quesons: 8 Subjec ECONOMICS (POSTGRADUATE) Tle of Paper EC79 QUANTITATIVE METHODS FOR BUSINESS AND FINANCE Tme Allowed Two Hours ( hours) Insrucons

More information

Machine Learning Linear Regression

Machine Learning Linear Regression Machne Learnng Lnear Regresson Lesson 3 Lnear Regresson Bascs of Regresson Leas Squares esmaon Polynomal Regresson Bass funcons Regresson model Regularzed Regresson Sascal Regresson Mamum Lkelhood (ML)

More information

Partial Availability and RGBI Methods to Improve System Performance in Different Interval of Time: The Drill Facility System Case Study

Partial Availability and RGBI Methods to Improve System Performance in Different Interval of Time: The Drill Facility System Case Study Open Journal of Modellng and Smulaon, 204, 2, 44-53 Publshed Onlne Ocober 204 n ScRes. hp://www.scrp.org/journal/ojms hp://dx.do.org/0.4236/ojms.204.2406 Paral Avalably and RGBI Mehods o Improve Sysem

More information

NPTEL Project. Econometric Modelling. Module23: Granger Causality Test. Lecture35: Granger Causality Test. Vinod Gupta School of Management

NPTEL Project. Econometric Modelling. Module23: Granger Causality Test. Lecture35: Granger Causality Test. Vinod Gupta School of Management P age NPTEL Proec Economerc Modellng Vnod Gua School of Managemen Module23: Granger Causaly Tes Lecure35: Granger Causaly Tes Rudra P. Pradhan Vnod Gua School of Managemen Indan Insue of Technology Kharagur,

More information

Highway Passenger Traffic Volume Prediction of Cubic Exponential Smoothing Model Based on Grey System Theory

Highway Passenger Traffic Volume Prediction of Cubic Exponential Smoothing Model Based on Grey System Theory Inernaonal Conference on on Sof Compung n Informaon Communcaon echnology (SCIC 04) Hghway Passenger raffc Volume Predcon of Cubc Exponenal Smoohng Model Based on Grey Sysem heory Wenwen Lu, Yong Qn, Honghu

More information

Modelling Wind Speed in Semarang City, Indonesia using Adaptive Neuro Fuzzy Inference Systems (ANFIS) Based on Stepwise Procedure

Modelling Wind Speed in Semarang City, Indonesia using Adaptive Neuro Fuzzy Inference Systems (ANFIS) Based on Stepwise Procedure Inernaonal Journal of Innovaons n Engneerng and Technology (IJIET) hp://dx.do.org/0.7/je.04.5 Modellng Wnd Speed n Semarang Cy, Indonesa usng Adapve Neuro Fuzzy Inference Sysems (ANFIS) Based on Sepwse

More information

Fall 2009 Social Sciences 7418 University of Wisconsin-Madison. Problem Set 2 Answers (4) (6) di = D (10)

Fall 2009 Social Sciences 7418 University of Wisconsin-Madison. Problem Set 2 Answers (4) (6) di = D (10) Publc Affars 974 Menze D. Chnn Fall 2009 Socal Scences 7418 Unversy of Wsconsn-Madson Problem Se 2 Answers Due n lecure on Thursday, November 12. " Box n" your answers o he algebrac quesons. 1. Consder

More information

Lecture 9: Dynamic Properties

Lecture 9: Dynamic Properties Shor Course on Molecular Dynamcs Smulaon Lecure 9: Dynamc Properes Professor A. Marn Purdue Unversy Hgh Level Course Oulne 1. MD Bascs. Poenal Energy Funcons 3. Inegraon Algorhms 4. Temperaure Conrol 5.

More information

A Novel Iron Loss Reduction Technique for Distribution Transformers. Based on a Combined Genetic Algorithm - Neural Network Approach

A Novel Iron Loss Reduction Technique for Distribution Transformers. Based on a Combined Genetic Algorithm - Neural Network Approach A Novel Iron Loss Reducon Technque for Dsrbuon Transformers Based on a Combned Genec Algorhm - Neural Nework Approach Palvos S. Georglaks Nkolaos D. Doulams Anasasos D. Doulams Nkos D. Hazargyrou and Sefanos

More information

CH.3. COMPATIBILITY EQUATIONS. Continuum Mechanics Course (MMC) - ETSECCPB - UPC

CH.3. COMPATIBILITY EQUATIONS. Continuum Mechanics Course (MMC) - ETSECCPB - UPC CH.3. COMPATIBILITY EQUATIONS Connuum Mechancs Course (MMC) - ETSECCPB - UPC Overvew Compably Condons Compably Equaons of a Poenal Vecor Feld Compably Condons for Infnesmal Srans Inegraon of he Infnesmal

More information

Tools for Analysis of Accelerated Life and Degradation Test Data

Tools for Analysis of Accelerated Life and Degradation Test Data Acceleraed Sress Tesng and Relably Tools for Analyss of Acceleraed Lfe and Degradaon Tes Daa Presened by: Reuel Smh Unversy of Maryland College Park smhrc@umd.edu Sepember-5-6 Sepember 28-30 206, Pensacola

More information

( t) Outline of program: BGC1: Survival and event history analysis Oslo, March-May Recapitulation. The additive regression model

( t) Outline of program: BGC1: Survival and event history analysis Oslo, March-May Recapitulation. The additive regression model BGC1: Survval and even hsory analyss Oslo, March-May 212 Monday May 7h and Tuesday May 8h The addve regresson model Ørnulf Borgan Deparmen of Mahemacs Unversy of Oslo Oulne of program: Recapulaon Counng

More information

Existence and Uniqueness Results for Random Impulsive Integro-Differential Equation

Existence and Uniqueness Results for Random Impulsive Integro-Differential Equation Global Journal of Pure and Appled Mahemacs. ISSN 973-768 Volume 4, Number 6 (8), pp. 89-87 Research Inda Publcaons hp://www.rpublcaon.com Exsence and Unqueness Resuls for Random Impulsve Inegro-Dfferenal

More information

Li An-Ping. Beijing , P.R.China

Li An-Ping. Beijing , P.R.China A New Type of Cpher: DICING_csb L An-Png Bejng 100085, P.R.Chna apl0001@sna.com Absrac: In hs paper, we wll propose a new ype of cpher named DICING_csb, whch s derved from our prevous sream cpher DICING.

More information

Dual Approximate Dynamic Programming for Large Scale Hydro Valleys

Dual Approximate Dynamic Programming for Large Scale Hydro Valleys Dual Approxmae Dynamc Programmng for Large Scale Hydro Valleys Perre Carpener and Jean-Phlppe Chanceler 1 ENSTA ParsTech and ENPC ParsTech CMM Workshop, January 2016 1 Jon work wh J.-C. Alas, suppored

More information

CS434a/541a: Pattern Recognition Prof. Olga Veksler. Lecture 4

CS434a/541a: Pattern Recognition Prof. Olga Veksler. Lecture 4 CS434a/54a: Paern Recognon Prof. Olga Veksler Lecure 4 Oulne Normal Random Varable Properes Dscrmnan funcons Why Normal Random Varables? Analycally racable Works well when observaon comes form a corruped

More information

Single-loop System Reliability-Based Design & Topology Optimization (SRBDO/SRBTO): A Matrix-based System Reliability (MSR) Method

Single-loop System Reliability-Based Design & Topology Optimization (SRBDO/SRBTO): A Matrix-based System Reliability (MSR) Method 10 h US Naonal Congress on Compuaonal Mechancs Columbus, Oho 16-19, 2009 Sngle-loop Sysem Relably-Based Desgn & Topology Opmzaon (SRBDO/SRBTO): A Marx-based Sysem Relably (MSR) Mehod Tam Nguyen, Junho

More information

Improvement in Estimating Population Mean using Two Auxiliary Variables in Two-Phase Sampling

Improvement in Estimating Population Mean using Two Auxiliary Variables in Two-Phase Sampling Rajesh ngh Deparmen of ascs, Banaras Hndu Unvers(U.P.), Inda Pankaj Chauhan, Nrmala awan chool of ascs, DAVV, Indore (M.P.), Inda Florenn marandache Deparmen of Mahemacs, Unvers of New Meco, Gallup, UA

More information

Genetic Algorithm in Parameter Estimation of Nonlinear Dynamic Systems

Genetic Algorithm in Parameter Estimation of Nonlinear Dynamic Systems Genec Algorhm n Parameer Esmaon of Nonlnear Dynamc Sysems E. Paeraks manos@egnaa.ee.auh.gr V. Perds perds@vergna.eng.auh.gr Ah. ehagas kehagas@egnaa.ee.auh.gr hp://skron.conrol.ee.auh.gr/kehagas/ndex.hm

More information

10. A.C CIRCUITS. Theoretically current grows to maximum value after infinite time. But practically it grows to maximum after 5τ. Decay of current :

10. A.C CIRCUITS. Theoretically current grows to maximum value after infinite time. But practically it grows to maximum after 5τ. Decay of current : . A. IUITS Synopss : GOWTH OF UNT IN IUIT : d. When swch S s closed a =; = d. A me, curren = e 3. The consan / has dmensons of me and s called he nducve me consan ( τ ) of he crcu. 4. = τ; =.63, n one

More information

12d Model. Civil and Surveying Software. Drainage Analysis Module Detention/Retention Basins. Owen Thornton BE (Mech), 12d Model Programmer

12d Model. Civil and Surveying Software. Drainage Analysis Module Detention/Retention Basins. Owen Thornton BE (Mech), 12d Model Programmer d Model Cvl and Surveyng Soware Dranage Analyss Module Deenon/Reenon Basns Owen Thornon BE (Mech), d Model Programmer owen.hornon@d.com 4 January 007 Revsed: 04 Aprl 007 9 February 008 (8Cp) Ths documen

More information

Multi-Objective Control and Clustering Synchronization in Chaotic Connected Complex Networks*

Multi-Objective Control and Clustering Synchronization in Chaotic Connected Complex Networks* Mul-Objecve Conrol and Cluserng Synchronzaon n Chaoc Conneced Complex eworks* JI-QIG FAG, Xn-Bao Lu :Deparmen of uclear Technology Applcaon Insue of Aomc Energy 043, Chna Fjq96@6.com : Deparmen of Auomaon,

More information

Data Collection Definitions of Variables - Conceptualize vs Operationalize Sample Selection Criteria Source of Data Consistency of Data

Data Collection Definitions of Variables - Conceptualize vs Operationalize Sample Selection Criteria Source of Data Consistency of Data Apply Sascs and Economercs n Fnancal Research Obj. of Sudy & Hypoheses Tesng From framework objecves of sudy are needed o clarfy, hen, n research mehodology he hypoheses esng are saed, ncludng esng mehods.

More information

ON THE WEAK LIMITS OF SMOOTH MAPS FOR THE DIRICHLET ENERGY BETWEEN MANIFOLDS

ON THE WEAK LIMITS OF SMOOTH MAPS FOR THE DIRICHLET ENERGY BETWEEN MANIFOLDS ON THE WEA LIMITS OF SMOOTH MAPS FOR THE DIRICHLET ENERGY BETWEEN MANIFOLDS FENGBO HANG Absrac. We denfy all he weak sequenal lms of smooh maps n W (M N). In parcular, hs mples a necessary su cen opologcal

More information

Testing a new idea to solve the P = NP problem with mathematical induction

Testing a new idea to solve the P = NP problem with mathematical induction Tesng a new dea o solve he P = NP problem wh mahemacal nducon Bacground P and NP are wo classes (ses) of languages n Compuer Scence An open problem s wheher P = NP Ths paper ess a new dea o compare he

More information

J i-1 i. J i i+1. Numerical integration of the diffusion equation (I) Finite difference method. Spatial Discretization. Internal nodes.

J i-1 i. J i i+1. Numerical integration of the diffusion equation (I) Finite difference method. Spatial Discretization. Internal nodes. umercal negraon of he dffuson equaon (I) Fne dfference mehod. Spaal screaon. Inernal nodes. R L V For hermal conducon le s dscree he spaal doman no small fne spans, =,,: Balance of parcles for an nernal

More information

Financial Volatility Forecasting by Least Square Support Vector Machine Based on GARCH, EGARCH and GJR Models: Evidence from ASEAN Stock Markets

Financial Volatility Forecasting by Least Square Support Vector Machine Based on GARCH, EGARCH and GJR Models: Evidence from ASEAN Stock Markets Inernaonal Journal of Economcs and Fnance February, Fnancal Volaly Forecasng by Leas Square Suppor Vecor Machne Based on GARCH, EGARCH and GJR Models: Evdence from ASEAN Sock Markes Phchhang Ou (correspondng

More information

Machine Vision based Micro-crack Inspection in Thin-film Solar Cell Panel

Machine Vision based Micro-crack Inspection in Thin-film Solar Cell Panel Sensors & Transducers Vol. 179 ssue 9 Sepember 2014 pp. 157-161 Sensors & Transducers 2014 by FSA Publshng S. L. hp://www.sensorsporal.com Machne Vson based Mcro-crack nspecon n Thn-flm Solar Cell Panel

More information

Computing Relevance, Similarity: The Vector Space Model

Computing Relevance, Similarity: The Vector Space Model Compung Relevance, Smlary: The Vecor Space Model Based on Larson and Hears s sldes a UC-Bereley hp://.sms.bereley.edu/courses/s0/f00/ aabase Managemen Sysems, R. Ramarshnan ocumen Vecors v ocumens are

More information