Faults Classification of a Scooter Engine Platform Using Wavelet Transform and Artificial Neural Network

Size: px
Start display at page:

Download "Faults Classification of a Scooter Engine Platform Using Wavelet Transform and Artificial Neural Network"

Transcription

1 Proceedgs of the Iteratoal MultCoferece of Egeers ad Computer Scetsts 9 Vol I IMECS 9, March 8 -, 9, Hog Kog Faults Classfcato of a Scooter Ege Platform Usg Wavelet Trasform ad Artfcal Neural Network J.-D. Wu, E.-C. Chag, S.-Y. Lao, J.-M. Kuo ad C.-K. Huag Abstract Ths paper descrbes the developmet of a mechacal fault dagoss system for a scooter ege platform usg cotuous wavelet trasform ad artfcal eural etwork techques. Most of the covetoal techques for fault dagoss a mechacal system are based prmarly o aalyzg the dfferece of sgal ampltude the tme doma or frequecy spectrum. I the preset study, a cotuous wavelet trasform (CWT) algorthm combed wth a feature selecto method s proposed for aalyzg fault sgals a scooter fault dagoss system. The artfcal eural etwork techque usg back-propagato ad geeralzed regresso are both used the proposed system. The effectveess of the proposed system usg two algorthms CWT techque for scooter fault dagoss are vestgated ad compared. The expermetal results dcated that the proposed system acheved a fault recogto rate over 95% the expermetal platform of scooter fault dagoss system. Idex Terms Fault dagoss system, Cotuous wavelet trasform, Artfcal eural etwork. I. INTRODUCTION Wth the rapd growth of sgal processg techology, the vbrato ad soud emsso sgals ca be used to motor the codto of a mechacal system. A effectve codto motorg ca prevet serous damage. There exst a umber of fault dagoss techques the feld, ad most of the covetoal techques are used to observe the ampltude dfferece tme or frequecy doma for damage dagoss. Meawhle, order-trackg aalyss s also used to avod the smearg problem frequecy-varyg sgals []. Ufortuately, most of the covetoal approaches are dffcult to deal wth the case where the machery operates uder o-statoary rotatoal speed, s based o the assumpto of statoary sgals, ad s heretly usuted for o-statoary. Tme-frequecy aalyss ca be used to mprove the drawback of the Fourer trasform. The prmary Mauscrpt receved October 9, 8. Ths work was supported the Natoal Scece Coucl of Tawa, the Republc of Cha, uder project umber NSC-97--E-8-8. J.-D. Wu s wth the Isttute of Vehcle Egeerg, Natoal Chaghua Uversty of Educato, Chaghua 5, Tawa (correspodg author phoe: ; e-mal: jdwu@cc.cue.edu.tw). E.-C. Chag, S.-Y. Lao, J.-M. Kuo, C.-K. Huag were wth the Isttute of Vehcle Egeerg, Natoal Chaghua Uversty of Educato, Chaghua 5, Tawa. advatage of tme-frequecy aalyss s the represetato of sgals both the tme ad frequecy domas. The short tme Fourer trasform (STFT) has bee appled to aalyze the sgals of the fault both the tme ad frequecy domas []. However, STFT has a lmtato of tme resoluto because of usg fxed tme wdows. O the other had, the cotuous wavelet trasform wth a adjustable wdow sze has bee prove to have hgher effcecy accurate formato of aalyss sgals. The cotuous wavelet trasform (CWT) wth more precse tme resoluto ca mprove the performace of STFT. Research terest mechacal fault dagoss usg wavelet aalyss has developed the last few decades. The wavelet aalyss techque has become oe of the mportat approaches the feld of mechacal fault dagoss. I 993, Wag ad McFadde used wavelet aalyss the gear vbrato sgals ad detected dfferet types of faults, ad the results exhbt wavelet trasform s effectve codto motorg of gear health [3],[4]. I 995, Newlad derved a harmoc wavelet techque ad appled t to traset aalyss of vbrato sgal [5],[6]. I, L preseted a de-osg method based o Morlet wavelet appled fault dagoss [7]. I 4, Meltzer ad De aalyzed the effectveess of the CWT acoustcal dagostcs of gearboxes by plottg wavelet ampltude versus the rotatoal agle polar coordates [8]. I 5, Ya ad Gao preseted a approach to mache codto motorg ad health dagoss, based o the dscrete harmoc wavelet packet trasform (DHWPT) [9]. I, L et al. preseted a approach for motor rollg bearg fault dagoss usg eural etworks ad bearg vbrato aalyss []. I 4, Che ad Mob developed a method of tellget fault dagoss usg eural etwork classfer for detfyg the faults of rotatg machery []. I 5, Yag et al. developed a advaced sgal classfer for small recprocatg refrgerator compressors artfcal eural etworks ad support vector mache []. I the preset study, the CWT techque ad tme-frequecy aalyss are used to extract the feature of the dyamc characterstcs ad fault sgal from a scooter. The dagostc trouble code of a scooter ca be obtaed by usg spectrum tred feature method. A fault recogto techque based o eural etworks of back-propagato ad geeralzed regresso for a scooter health dagoss s preseted. Neural etworks classfers have a prove ablty the area of olear patter recogto by learg ad adaptg to the put from the scooter fault. Both of the eural etworks are ISBN: IMECS 9

2 Proceedgs of the Iteratoal MultCoferece of Egeers ad Computer Scetsts 9 Vol I IMECS 9, March 8 -, 9, Hog Kog used to verfy the effectveess of the preseted fault dagoss algorthm. There are three phases the preset fault dagoss system: the data acqusto phase, the feature extracto phase ad the fault classfcato phase, as show Fg.. I the feature extracto, the dagostc techque employs the wavelet trasform to decompose the tme-waveform sgals to two respectve parts the tme space ad frequecy doma ad to obta the feature of aalyss sgals. I the fault classfcato phase, the desg of the eural etwork dagoss algorthm s preseted to detfy the faults of the scooter. The prcples of wavelet trasform ad eural etwork the proposed system are descrbed the followg sectos. II. FEATURE EXTRACTION USING WAVELET TRANSFORM The wavelet trasform uses a seres of oscllatg fuctos wth dfferet frequeces as wdow fucto to sca or traslate the aalyss sgal. The wavelet techque has partcular advatages for characterzg sgals at dfferet localzato levels tme as well as frequecy domas. The wavelet algorthm used ths study s based o the results orgally developed by Goupllaud et al. [3],[7]. The prcples of cotuous wavelet trasform ad spectrum tred feature are descrbed the followg sectos. Let ψ () t be the basc wavelet fucto or mother wavelet, the correspodg famly of daughter wavelets cosst of t-b = a -/ ψ () ab, t a ψ where a s the scale factor ad b the tme locato, ad the -/ factor a s used esure that the eergy of the scaled ad traslated versos are the same as the mother wavelet. The wavelet trasform of sgal x() t s defed as the er product the Hlbert space of the L orm as follows: -/ * ab, ψ ab, W( a, b) = ψ (), t x() t = a x() t dt () Here the astersk stads for complex cojugate. Tme parameter b ad scale parameter a vary cotuously. The mother wavelet ψ () t s assumed to le L ( C) ad satsfes the admssblty codto: C = ˆ ψ ψ( ω) / ω d ω < - where L ( C) s the space of square tegrable complex fucto ad ψˆ ( ω) dcates the Fourer trasform of ψ () t. Wavelet coeffcets measure the smlarty of the sgal ad each daughter wavelet. I ths study, the Morlet wavelet [4] s used as the basc wavelet for feature extracto. Whe a wavelet fucto s chose, t s ecessary to decde the scales the wavelet trasform. For CWT aalyss, a arbtrary set of scales ca be used to buld up complete formato. I ths study, the scales are wrtte as follows: j δ j a = a, j =,,, J (4) j () (3) where a = δ t s the smallest resolvable scale ad δ j =.5, J=6. The choce of δ j deped o the wdth spectral space of wavelet fucto ad J determes the largest scale, δ t s the samplg terval. Whe the samplg frequecy s set as khz, the scales ca be obtaed the rage of. to 5..The cotuous wavelet power spectrum s defed as W( a j ). The tme-averaged wavelet spectrum s proposed to exhbt the dstrbuto of eergy of wavelet power spectrum the drecto of scale, s defed as j j N = N - W( a ) = W ( a ) (5) N,,,, where s the umber of samplg pots, j = J. I the applcato of fault dagoss, the sgal s sampled radomly ad the revoluto of the ege s ot stable, the eergy dstrbuto of tme average wavelet spectrum (TAWS) s dfferet from each other eve the same fault codto. I order to avod such a codto, a spectrum tred feature method s developed. By studyg the spectrum dstrbuto of varato for each fault spectrum, oe ca defe a rased tred of spectrum as ad a dropped tred of spectrum as betwee two eghbor scales. The feature vector ca be defed as follows: ( j+) W ( aj) ( j+) W( aj), W a > x(j)=, W a The feature vector s dagostc trouble code as the put for the fault classfcato usg eural etworks. Data acqusto Feature extracto (wavelet trasform) Fault detecto (eural etworks) Acoustc emsso sgals Feature vectors j =,,,, J - Data recorder Tme doma aalyss Frequecy aalyss Tme-frequecy aalyss Fault decso Fault classfcato Fgure Procedure of scooter fault dagoss. III. FAULTS CLASSIFICATION USING NEURAL NETWORKS I the desg of scooter fault dagoss schemes, a recogto method of scooter fault codto usg eural etworks s vestgated to evaluate the effectveess of the select feature set for a scooter dagoss. To determe f the proposed fault dagoss algorthm s able to correctly recogze dfferet scooter fault codtos s essetal. I ths paper, a multp percepto classfer traed wth error back-propagato algorthm ad geeralzed regresso eural etwork are used the fault dagoss system. The (6) ISBN: IMECS 9

3 Proceedgs of the Iteratoal MultCoferece of Egeers ad Computer Scetsts 9 Vol I IMECS 9, March 8 -, 9, Hog Kog expermetal comparso ad aalyss of the two algorthms are also descrbed scooter fault dagoss. The eural etwork usg a multp percepto classfer wth error back propagato (BP) algorthm based o supervsed learg rule s appled for trag ad testg the classfer the preset study [6]. A three- feed forward etwork wth sgmod actvato fucto s cosdered the frst fault classfcato. I the structure, each has a certa umber of odes ad all odes oe are coected wth all the other odes the succeedg, as show Fg.. Assocated wth each coecto, a umercal value s assged, whch s termed as weght. Iputs are submtted durg the BP algorthm trag sequetally. Durg the trag procedure, the weght ad bases of the etwork are teratvely adjusted to mmze the etwork performace whch s the mea square error betwee the etworks outputs ad desred outputs. The gradet descet search s performed to reduce the error through the adjustmet of weghts. The error s back propagated to chage the output ad hdde weghts. Ths trag process s repeated utl a sutable error s acheved. The trag process eeds a set of trag examples to update the weghts of the etwork. Provdg suffcet trag data s essetal order to esure accuracy of the classfer. Oce the etwork s suffcetly traed, the kowledge of the eural etwork wll perform the fault detecto. Feature Extracto Dagostc Trouble Code Network Trag Network Testg x x Iput sgals 3 w w j Error sgals l y y l value of y, gve oly a trag set. Assume that the f ( x, y ) represets the kow jot cotuous probablty desty fucto of a vector radom varables, x, ad a scalar radom varable. Let X be a partcular measured value of the radom varable x. The codtoal mea of y gve X s gve by E y X = - - yf ( X, y)dy f ( X, y)dy Whe the desty f ( x, y) s ot kow, t must usually be estmated from a sample of observatos of x ad y. The probablty estmator f ( X, Y) s based upo sample values X ad Y of the radom varables x ad y, where s the umber of sample observatos ad p s the dmeso of the vector varable x: f ˆ( X, Y )=( ) (P+)/ (P+) π σ T = ( X-X ) ( X-X ) ( Y-Y ) exp - exp - σ σ A physcal terpretato of the probablty estmate f ˆ( X, Y) s that t assgs sample probablty of wdth σ for each sample X ad Y, ad the probablty estmate s the sum of those sample probabltes. Defg the scalar fucto T ( ) ( ) D=X-X X-X (9) ad performg the dcated tegratos yelds the followg: D Y exp - σ D σ = ˆ( )= exp - = Y X (7) (8) () x Fault Decso Fgure Structure of back-propagato algorthm for fault dagoss. The geeralzed regresso eural etwork (GRNN) was proposed by Specht [6]. It s a oe-passg learg algorthm whch ca be used for estmato of cotuous varables. The GRNN does ot requre a teratve trag procedure to coverge to the desred soluto as BP eural etwork. It approxmates ay arbtrary fucto betwee put ad output vectors, drawg the fucto estmate drectly from the trag data. If the varables to be estmated relate output to put varables, the GRNN ca be used to model the system, as stadard regresso techques. By defto, the regresso of a depedet varable y o a depedet x estmates the most probable value for y, gve x ad a trag set. The GRNN s a method for estmatg the jot probablty desty fucto (PDF) of x ad y, order to produce the estmated Whe the smoothg parameter σ s made large, the estmated desty s forced to be smooth ad the lmt becomes a multvarate Gaussa wth covarace σ I. O the other had, a smaller value of allows the estmated desty to assume o-gaussa shapes, but wth the hazard that wld pots may have too great a effect o the estmate [4]. Fg. 3 shows the block dagram of the GRNN archtecture whch s dfferet from the archtecture of BP algorthm. The GRNN cossts of four s: put, patter, summato ad output. The put uts are merely dstrbuto uts the frst. The secod has the patter uts that are dedcated to oe cluster ceter. The outputs of the patter are passed o to the summato uts the thrd. The summato uts perform a dot product betwee a weght ad a vector from the patter. The fal covers the output uts. ISBN: IMECS 9

4 Proceedgs of the Iteratoal MultCoferece of Egeers ad Computer Scetsts 9 Vol I IMECS 9, March 8 -, 9, Hog Kog..5 x x Ŷ(X) x Ampltude p Iput Patter Summato Output Fgure 3 Block dagram of GRNN algorthm. IV. EXPERIMENTAL INVESTIGATION OF FAULTS CLASSIFICATION I order to evaluate the proposed algorthms faults classfcato, a expermet s carred out to verfy the performace by measurg soud emsso sgals varous ege operato codtos. The soud emsso sgal of a scooter ege platform s measured by a mcrophoe, a data acqusto system ad subsequetly aalyzed usg CWT algorthm. After extractg the features of wavelet power spectra, the feature vectors are selected for the fault classfcato usg eural etworks. The expermetal setup of the scooter fault dagoss system s show Fg. 4. The measurg apparatus used the expermet cossts of a mcrophoe (PCB 3D), a data acqusto system (NI-64E), a optcal ecoder (PW-PH) for shaft speed measuremet ad dyamc sgal aalyzer (SR785). The soud sgal s recorded from the scooter uder wthout fault codto ad four dfferet fault codtos fve fxed ege revolutos ad a ru-up ege operato codto. The expermet s coducted by usg four sythetc faults, cludg leakg of the take mafold, pulley damaged, belt damaged ad clutch damaged. The samplg rate of the data acqusto system s khz. Acoustc emsso sgals tme doma that were measured uder dle codtos (8 rpm) are show Fg. 5. Mc. Data Data acqusto system Fber optcal optcal sesor sesor Dyamc sgal aalyzer Acoustc Acoustc emsso emsso sgal sgal Tachometer sgal sgal Fault dagoss system system Fgure 4 Expermetal arragemet of scooter fault dagoss system. (e) Ampltude p p Tme (sec) Fgure 5 Soud emsso sgals measured from a scooter. wthout fault; leakage take mafold; pulley damaged; belt damaged; (e) clutch damaged. I order to evaluate the effectveess of the CWT for scooter fault dagoss, soud emsso sgals from each fault codto are aalyzed. The expermetal results of scooter wthout fault 8rpm ege speeds usg CWT represetato are show Fg. 6, whch preset the eergy dstrbuto of the soud emsso sgals tme-frequecy doma. The expermetal results of the other four faults 8rpm ege speeds are dcated Fg. 7. However, a ege practcal codtos may be operated by rug up or coastg dow. I the expermet of rug up vestgato, the ege operated at revolutos from 8 to 49 rpm. The expermet results of ru-up rotatoal speed codto usg CWT algorthm are dcated Fg. 8. O the bass of the tme-frequecy features thus obtaed, the trasets of the ru-up process ca be clearly observed. The expermetal results demostrated the CWT algorthm s effectve fault aalyss ad dagoss by usg soud emsso sgals. Frequecy (Hz) Tme (sec) Fgure 6 Tme-frequecy represetato of wavelet power spectrum wthout fault 8 rpm ege speeds. ISBN: IMECS 9

5 Proceedgs of the Iteratoal MultCoferece of Egeers ad Computer Scetsts 9 Vol I IMECS 9, March 8 -, 9, Hog Kog To further classfy the fault, the feature extracto of TAWS based o spectrum tred feature method s preseted. Fgure 9 represets the TAWS of fve codtos of ege dle operato. After processg of spectrum tred feature method, the feature vectors, show Fg., are dagostc trouble codes whch wll be provded for the eural etwork. The objectve of faults classfcato s to demostrate the effectveess of the proposed feature selected method. For ths purpose, the feature vectors each fault codto are appled to as the put of the eural etworks. There are data sets for each fault codto. I the fault classfcato expermet, 4 data sets of the data each fault codto are used for trag the etwork ad the remag 6 data sets of the data are used to test the etwork. The performace of the fault dagoss system to correctly classfy the faults to correspodg classes s evaluated. The fault recogto rate s defed as Number of correctly classfed samples Recogto rate = % () Total testg umber of samples TAWS (e) Frequecy (Hz) Frequecy (Hz) Tme (sec) Fgure 7 Tme-frequecy represetato of wavelet power spectrum wth varous fault 8 rpm ege speeds. leakage take mafold; pulley damaged; belt damaged; clutch damaged. Tme (sec) Fgure 8 Tme-frequecy represetato of wavelet power spectrum wthout fault ru-up codto Scale Fgure 9 TAWS of ege dle codto. Wthout fault; leakage of the take mafold; pulley damaged; belt damaged; (e) clutch damaged. Table shows the classfcato accuracy acheved s about 95 % by usg BP algorthm. I comparso, Table shows the result of GRNN classfer has acheved a overall classfcato rate of 99 % ege operato lower tha 5 rpm. Whe the ege operato speed s hgher tha 5 rpm, the fault recogto rate s decreased. The comparso dcated that the fault techque usg GRNN s more effectve tha usg BP algorthm the faults classfcato. Table. Performace of the recogto usg BP algorthm Revoluto codtos (rpm) Defect types dle Wthout fault 99.4% 99.4% 99.4% 99.4% 85% Leakage of the 99.4% 99.4% 99.4% 99.4% 99.5% take mafold Pulley damaged 96.3% 96.9% 98.8% 93.% 95.6% Belt damaged 97.5% 99.4% 99.4% 88.8% 98.8% Clutch damaged 99.4% 93.8% 98.8% 98.8% 85.6% Table. Performace of the recogto usg GRNN Revoluto codtos (rpm) Defect types dle Wthout fault % % % % % Leakage of the take mafold 99.4% 99.4% 99.4% 99.4% 99.4% Pulley damaged 99.4% 99.4% 99.4% 99.4% 98.8% Belt damaged 99.4% 99.4% 99.4% 9.5% 98.8% Clutch damaged 99.4% 99.4% 99.4% 99.4% 99.4% ISBN: IMECS 9

6 Proceedgs of the Iteratoal MultCoferece of Egeers ad Computer Scetsts 9 Vol I IMECS 9, March 8 -, 9, Hog Kog (e) j Fg.. Feature vectors of ege dle codto. Wthout fault; leakage of the take mafold; pulley damaged; belt damaged; (e) clutch damaged. V. CONCLUSIONS I ths paper, a scooter fault dagoss system based o cotuous wavelet trasform techque ad faults classfcato usg artfcal eural etwork for the purpose of the fault detecto has bee developed. Wavelet aalyss, whch allows the soud emsso sgals of frequecy cotet wth tme to be vsualzed, ca extract key features usg tme-frequecy represetato of soud emsso sgals from a scooter. A feature selecto method called spectrum tred feature method was proposed. The selected feature vectors are dagostc trouble codes correspodg to ther fault codto. The features are subsequetly used for the tellget classfer to evaluate the performace of proposed fault dagoss system. The proposed dagoss system usg GRNN method was able to reach a fault recogto rate of about 99%. The expermetal results show that the proposed fault dagoss system wth eural etwork ca be effectvely used scooter dagoss of varous faults through measuremet of scooter soud emsso sgal. [3] Wag, W. J., & McFadde, P. D. (996). Applcato of the wavelet trasform to gearbox vbrato sgals for fault detecto. Joural of Soud ad Vbrato, 9, [4] Wag, W. J., & McFadde, P. D. (995). Applcato of orthogoal wavelets to early gear damage detecto. Mechacal Systems ad Sgal Processg, 9, [5] Newlad, D. E. (995). Progress the applcato of wavelet theory to vbrato aalyss. Proceedgs of ASME 5th Beal Coferece o Mechacal Vbrato ad Nose, Bosto, 3, [6] Newlad, D. E. (999). Rdge ad phase detfcato the frequecy of traset sgals by harmoc wavelets. Amerca of Mechacal Egeers, Joural of Vbrato ad Acoustcs,, [7] L, J. (). Feature extracto of mache soud usg wavelet ad ts applcato fault dagoss. NDT & E Iteratoal, 34(), 5 3. [8] Meltzera, G., & De, N. P. (4). Fault dagoss gears operatg uder o-statoary rotatoal speed usg polar wavelet ampltude maps. Mechacal Systems ad Sgal Processg, 8, [9] Ya, R., & Gao, R. X. (5). A effcet approach to mache dagoss based o harmoc wavelet packet trasform. Robotcs ad Computer-Itegrated Maufacturg,, 9 3. [] L, B., Chow, M. Y., Tpsuwa, Y., & Hug, J. C. (). Neural-etwork-based motor rollg bearg fault dagoss. IEEE Trasactos o Idustral Electrocs, 47(5), [] Che, C., & Mob, C. (4). A method for tellget fault dagoss of rotatg machery. Dgtal Sgal Processg, 4, 3 7. [] Yag, B. S., Hwag, W. W., Km, D. J., & Ta, A. C. (5). Codto classfcato of small recprocatg compressor for refrgerators usg artfcal eural etworks ad support vector maches. Mechacal Systems ad Sgal Processg, 9, [3] Goupllaud, P., Grossma, A., & Morlet, J. (984). Cycle-octave ad related trasforms sesmc sgal aalyss. Geoexplorato, 3, 85. [4] L, J., & Qu, L. (). Feature extracto based o morlet wavelet ad ts applcato for mechacal fault dagoss. Joural of Soud ad Vbrato, 34(), [5] Zheg, H., L, Z., & Che, X. (). Gear fault dagoss based o cotuous wavelet trasform. Mechacal Systems ad Sgal Processg, 6, [6] Hayk, S. (999). Neural etworks a comprehesve foudato. Macmlla College Publshg Compay, New York. ACKNOWLEDGMENTS Ths study was supported by the Natoal Scece Coucl of Tawa, the Republc of Cha, uder project umber NSC-97--E-8-8. REFERENCES [] Ba, M. R., Jeg J., & Che, C. (). Adaptve order trackg techque usg recursve least-square algorthm. Amerca of Mechacal Egeers, Joural of Vbrato ad Acoustcs, 4(4), 5 5. [] Kle, R., Igma, D., & Brau S. (). No-statoary sgals: phase-eergy ad smulatos. Mechacal Systems ad Sgal Processg, 5(6), ISBN: IMECS 9

Introduction to local (nonparametric) density estimation. methods

Introduction to local (nonparametric) density estimation. methods Itroducto to local (oparametrc) desty estmato methods A slecture by Yu Lu for ECE 66 Sprg 014 1. Itroducto Ths slecture troduces two local desty estmato methods whch are Parze desty estmato ad k-earest

More information

Estimation of Stress- Strength Reliability model using finite mixture of exponential distributions

Estimation of Stress- Strength Reliability model using finite mixture of exponential distributions Iteratoal Joural of Computatoal Egeerg Research Vol, 0 Issue, Estmato of Stress- Stregth Relablty model usg fte mxture of expoetal dstrbutos K.Sadhya, T.S.Umamaheswar Departmet of Mathematcs, Lal Bhadur

More information

Functions of Random Variables

Functions of Random Variables Fuctos of Radom Varables Chapter Fve Fuctos of Radom Varables 5. Itroducto A geeral egeerg aalyss model s show Fg. 5.. The model output (respose) cotas the performaces of a system or product, such as weght,

More information

Fault Diagnosis Using Feature Vectors and Fuzzy Fault Pattern Rulebase

Fault Diagnosis Using Feature Vectors and Fuzzy Fault Pattern Rulebase Fault Dagoss Usg Feature Vectors ad Fuzzy Fault Patter Rulebase Prepared by: FL Lews Updated: Wedesday, ovember 03, 004 Feature Vectors The requred puts for the dagostc models are termed the feature vectors

More information

CHAPTER VI Statistical Analysis of Experimental Data

CHAPTER VI Statistical Analysis of Experimental Data Chapter VI Statstcal Aalyss of Expermetal Data CHAPTER VI Statstcal Aalyss of Expermetal Data Measuremets do ot lead to a uque value. Ths s a result of the multtude of errors (maly radom errors) that ca

More information

A New Family of Transformations for Lifetime Data

A New Family of Transformations for Lifetime Data Proceedgs of the World Cogress o Egeerg 4 Vol I, WCE 4, July - 4, 4, Lodo, U.K. A New Famly of Trasformatos for Lfetme Data Lakhaa Watthaacheewakul Abstract A famly of trasformatos s the oe of several

More information

A Method for Damping Estimation Based On Least Square Fit

A Method for Damping Estimation Based On Least Square Fit Amerca Joural of Egeerg Research (AJER) 5 Amerca Joural of Egeerg Research (AJER) e-issn: 3-847 p-issn : 3-936 Volume-4, Issue-7, pp-5-9 www.ajer.org Research Paper Ope Access A Method for Dampg Estmato

More information

Unsupervised Learning and Other Neural Networks

Unsupervised Learning and Other Neural Networks CSE 53 Soft Computg NOT PART OF THE FINAL Usupervsed Learg ad Other Neural Networs Itroducto Mture Destes ad Idetfablty ML Estmates Applcato to Normal Mtures Other Neural Networs Itroducto Prevously, all

More information

An Acoustic Method for Condition Classification in Live Sewer Networks

An Acoustic Method for Condition Classification in Live Sewer Networks 18th World Coferece o Nodestructve Testg, 16-2 Aprl 212, Durba, South Afrca A Acoustc Method for Codto Classfcato Lve Sewer Networks Zao FENG, Krll V. HOROSHENKOV, M. Tareq BIN ALI, Smo J. TAIT School

More information

Analysis of Variance with Weibull Data

Analysis of Variance with Weibull Data Aalyss of Varace wth Webull Data Lahaa Watthaacheewaul Abstract I statstcal data aalyss by aalyss of varace, the usual basc assumptos are that the model s addtve ad the errors are radomly, depedetly, ad

More information

ABOUT ONE APPROACH TO APPROXIMATION OF CONTINUOUS FUNCTION BY THREE-LAYERED NEURAL NETWORK

ABOUT ONE APPROACH TO APPROXIMATION OF CONTINUOUS FUNCTION BY THREE-LAYERED NEURAL NETWORK ABOUT ONE APPROACH TO APPROXIMATION OF CONTINUOUS FUNCTION BY THREE-LAYERED NEURAL NETWORK Ram Rzayev Cyberetc Isttute of the Natoal Scece Academy of Azerbaa Republc ramrza@yahoo.com Aygu Alasgarova Khazar

More information

Chapter 4 (Part 1): Non-Parametric Classification (Sections ) Pattern Classification 4.3) Announcements

Chapter 4 (Part 1): Non-Parametric Classification (Sections ) Pattern Classification 4.3) Announcements Aoucemets No-Parametrc Desty Estmato Techques HW assged Most of ths lecture was o the blacboard. These sldes cover the same materal as preseted DHS Bometrcs CSE 90-a Lecture 7 CSE90a Fall 06 CSE90a Fall

More information

Analysis of Lagrange Interpolation Formula

Analysis of Lagrange Interpolation Formula P IJISET - Iteratoal Joural of Iovatve Scece, Egeerg & Techology, Vol. Issue, December 4. www.jset.com ISS 348 7968 Aalyss of Lagrage Iterpolato Formula Vjay Dahya PDepartmet of MathematcsMaharaja Surajmal

More information

A Robust Total Least Mean Square Algorithm For Nonlinear Adaptive Filter

A Robust Total Least Mean Square Algorithm For Nonlinear Adaptive Filter A Robust otal east Mea Square Algorthm For Nolear Adaptve Flter Ruxua We School of Electroc ad Iformato Egeerg X'a Jaotog Uversty X'a 70049, P.R. Cha rxwe@chare.com Chogzhao Ha, azhe u School of Electroc

More information

Lecture 2 - What are component and system reliability and how it can be improved?

Lecture 2 - What are component and system reliability and how it can be improved? Lecture 2 - What are compoet ad system relablty ad how t ca be mproved? Relablty s a measure of the qualty of the product over the log ru. The cocept of relablty s a exteded tme perod over whch the expected

More information

UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS

UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS Postpoed exam: ECON430 Statstcs Date of exam: Jauary 0, 0 Tme for exam: 09:00 a.m. :00 oo The problem set covers 5 pages Resources allowed: All wrtte ad prted

More information

Bayesian Classification. CS690L Data Mining: Classification(2) Bayesian Theorem: Basics. Bayesian Theorem. Training dataset. Naïve Bayes Classifier

Bayesian Classification. CS690L Data Mining: Classification(2) Bayesian Theorem: Basics. Bayesian Theorem. Training dataset. Naïve Bayes Classifier Baa Classfcato CS6L Data Mg: Classfcato() Referece: J. Ha ad M. Kamber, Data Mg: Cocepts ad Techques robablstc learg: Calculate explct probabltes for hypothess, amog the most practcal approaches to certa

More information

Application of Calibration Approach for Regression Coefficient Estimation under Two-stage Sampling Design

Application of Calibration Approach for Regression Coefficient Estimation under Two-stage Sampling Design Authors: Pradp Basak, Kaustav Adtya, Hukum Chadra ad U.C. Sud Applcato of Calbrato Approach for Regresso Coeffcet Estmato uder Two-stage Samplg Desg Pradp Basak, Kaustav Adtya, Hukum Chadra ad U.C. Sud

More information

Bayes Estimator for Exponential Distribution with Extension of Jeffery Prior Information

Bayes Estimator for Exponential Distribution with Extension of Jeffery Prior Information Malaysa Joural of Mathematcal Sceces (): 97- (9) Bayes Estmator for Expoetal Dstrbuto wth Exteso of Jeffery Pror Iformato Hadeel Salm Al-Kutub ad Noor Akma Ibrahm Isttute for Mathematcal Research, Uverst

More information

Kernel-based Methods and Support Vector Machines

Kernel-based Methods and Support Vector Machines Kerel-based Methods ad Support Vector Maches Larr Holder CptS 570 Mache Learg School of Electrcal Egeerg ad Computer Scece Washgto State Uverst Refereces Muller et al. A Itroducto to Kerel-Based Learg

More information

13. Artificial Neural Networks for Function Approximation

13. Artificial Neural Networks for Function Approximation Lecture 7 3. Artfcal eural etworks for Fucto Approxmato Motvato. A typcal cotrol desg process starts wth modelg, whch s bascally the process of costructg a mathematcal descrpto (such as a set of ODE-s)

More information

Rolling Element Bearing Fault Feature Extraction Using EMD-Based Independent Component Analysis

Rolling Element Bearing Fault Feature Extraction Using EMD-Based Independent Component Analysis Rollg Elemet Bearg Fault Feature Extracto Usg EMD-Based Idepedet Compoet Aalyss Qag Mao Dog Wag School of Mechacal Electroc ad Idustral Egeerg Uversty of Electroc Scece ad Techology of Cha Chegdu Schua

More information

Bayes (Naïve or not) Classifiers: Generative Approach

Bayes (Naïve or not) Classifiers: Generative Approach Logstc regresso Bayes (Naïve or ot) Classfers: Geeratve Approach What do we mea by Geeratve approach: Lear p(y), p(x y) ad the apply bayes rule to compute p(y x) for makg predctos Ths s essetally makg

More information

best estimate (mean) for X uncertainty or error in the measurement (systematic, random or statistical) best

best estimate (mean) for X uncertainty or error in the measurement (systematic, random or statistical) best Error Aalyss Preamble Wheever a measuremet s made, the result followg from that measuremet s always subject to ucertaty The ucertaty ca be reduced by makg several measuremets of the same quatty or by mprovg

More information

Generative classification models

Generative classification models CS 75 Mache Learg Lecture Geeratve classfcato models Mlos Hauskrecht mlos@cs.ptt.edu 539 Seott Square Data: D { d, d,.., d} d, Classfcato represets a dscrete class value Goal: lear f : X Y Bar classfcato

More information

13. Parametric and Non-Parametric Uncertainties, Radial Basis Functions and Neural Network Approximations

13. Parametric and Non-Parametric Uncertainties, Radial Basis Functions and Neural Network Approximations Lecture 7 3. Parametrc ad No-Parametrc Ucertates, Radal Bass Fuctos ad Neural Network Approxmatos he parameter estmato algorthms descrbed prevous sectos were based o the assumpto that the system ucertates

More information

Dynamic Analysis of Axially Beam on Visco - Elastic Foundation with Elastic Supports under Moving Load

Dynamic Analysis of Axially Beam on Visco - Elastic Foundation with Elastic Supports under Moving Load Dyamc Aalyss of Axally Beam o Vsco - Elastc Foudato wth Elastc Supports uder Movg oad Saeed Mohammadzadeh, Seyed Al Mosayeb * Abstract: For dyamc aalyses of ralway track structures, the algorthm of soluto

More information

Chapter 8. Inferences about More Than Two Population Central Values

Chapter 8. Inferences about More Than Two Population Central Values Chapter 8. Ifereces about More Tha Two Populato Cetral Values Case tudy: Effect of Tmg of the Treatmet of Port-We tas wth Lasers ) To vestgate whether treatmet at a youg age would yeld better results tha

More information

A LFM Interference Suppression Scheme Based on FRFT and Subspace Projection

A LFM Interference Suppression Scheme Based on FRFT and Subspace Projection teratoal Joural of Emergg Egeerg esearch ad Techology Volume 3, ssue 6, Jue 15, PP 157-16 SS 349-4395 (Prt) & SS 349-449 (Ole) A LF terferece Suppresso Scheme Based o FFT ad Subspace Projecto Xg ZOU 1

More information

Summary of the lecture in Biostatistics

Summary of the lecture in Biostatistics Summary of the lecture Bostatstcs Probablty Desty Fucto For a cotuos radom varable, a probablty desty fucto s a fucto such that: 0 dx a b) b a dx A probablty desty fucto provdes a smple descrpto of the

More information

Solving Constrained Flow-Shop Scheduling. Problems with Three Machines

Solving Constrained Flow-Shop Scheduling. Problems with Three Machines It J Cotemp Math Sceces, Vol 5, 2010, o 19, 921-929 Solvg Costraed Flow-Shop Schedulg Problems wth Three Maches P Pada ad P Rajedra Departmet of Mathematcs, School of Advaced Sceces, VIT Uversty, Vellore-632

More information

Chapter 11 Systematic Sampling

Chapter 11 Systematic Sampling Chapter stematc amplg The sstematc samplg techue s operatoall more coveet tha the smple radom samplg. It also esures at the same tme that each ut has eual probablt of cluso the sample. I ths method of

More information

Study on a Fire Detection System Based on Support Vector Machine

Study on a Fire Detection System Based on Support Vector Machine Sesors & Trasducers, Vol. 8, Issue, November 04, pp. 57-6 Sesors & Trasducers 04 by IFSA Publshg, S. L. http://www.sesorsportal.com Study o a Fre Detecto System Based o Support Vector Mache Ye Xaotg, Wu

More information

Analyzing Fuzzy System Reliability Using Vague Set Theory

Analyzing Fuzzy System Reliability Using Vague Set Theory Iteratoal Joural of Appled Scece ad Egeerg 2003., : 82-88 Aalyzg Fuzzy System Relablty sg Vague Set Theory Shy-Mg Che Departmet of Computer Scece ad Iformato Egeerg, Natoal Tawa versty of Scece ad Techology,

More information

{ }{ ( )} (, ) = ( ) ( ) ( ) Chapter 14 Exercises in Sampling Theory. Exercise 1 (Simple random sampling): Solution:

{ }{ ( )} (, ) = ( ) ( ) ( ) Chapter 14 Exercises in Sampling Theory. Exercise 1 (Simple random sampling): Solution: Chapter 4 Exercses Samplg Theory Exercse (Smple radom samplg: Let there be two correlated radom varables X ad A sample of sze s draw from a populato by smple radom samplg wthout replacemet The observed

More information

Lecture 3. Sampling, sampling distributions, and parameter estimation

Lecture 3. Sampling, sampling distributions, and parameter estimation Lecture 3 Samplg, samplg dstrbutos, ad parameter estmato Samplg Defto Populato s defed as the collecto of all the possble observatos of terest. The collecto of observatos we take from the populato s called

More information

Chapter 5 Properties of a Random Sample

Chapter 5 Properties of a Random Sample Lecture 6 o BST 63: Statstcal Theory I Ku Zhag, /0/008 Revew for the prevous lecture Cocepts: t-dstrbuto, F-dstrbuto Theorems: Dstrbutos of sample mea ad sample varace, relatoshp betwee sample mea ad sample

More information

Research on SVM Prediction Model Based on Chaos Theory

Research on SVM Prediction Model Based on Chaos Theory Advaced Scece ad Techology Letters Vol.3 (SoftTech 06, pp.59-63 http://dx.do.org/0.457/astl.06.3.3 Research o SVM Predcto Model Based o Chaos Theory Sog Lagog, Wu Hux, Zhag Zezhog 3, College of Iformato

More information

Module 7: Probability and Statistics

Module 7: Probability and Statistics Lecture 4: Goodess of ft tests. Itroducto Module 7: Probablty ad Statstcs I the prevous two lectures, the cocepts, steps ad applcatos of Hypotheses testg were dscussed. Hypotheses testg may be used to

More information

KLT Tracker. Alignment. 1. Detect Harris corners in the first frame. 2. For each Harris corner compute motion between consecutive frames

KLT Tracker. Alignment. 1. Detect Harris corners in the first frame. 2. For each Harris corner compute motion between consecutive frames KLT Tracker Tracker. Detect Harrs corers the frst frame 2. For each Harrs corer compute moto betwee cosecutve frames (Algmet). 3. Lk moto vectors successve frames to get a track 4. Itroduce ew Harrs pots

More information

The Rolling Bearing Fault Feature Extraction Method Under Variable Conditions Based on Hilbert-Huang Transform and Singular Value Decomposition

The Rolling Bearing Fault Feature Extraction Method Under Variable Conditions Based on Hilbert-Huang Transform and Singular Value Decomposition The Rollg Bearg Fault Feature Extracto Method Uder Varable Codtos Based o Hlbert-Huag Trasform ad Sgular Value Decomposto Hogme Lu, Xua Wag ad Che Lu THE ROLLING BEARING FAULT FEATURE EXTRACTION METHOD

More information

6. Nonparametric techniques

6. Nonparametric techniques 6. Noparametrc techques Motvato Problem: how to decde o a sutable model (e.g. whch type of Gaussa) Idea: just use the orgal data (lazy learg) 2 Idea 1: each data pot represets a pece of probablty P(x)

More information

Multivariate Transformation of Variables and Maximum Likelihood Estimation

Multivariate Transformation of Variables and Maximum Likelihood Estimation Marquette Uversty Multvarate Trasformato of Varables ad Maxmum Lkelhood Estmato Dael B. Rowe, Ph.D. Assocate Professor Departmet of Mathematcs, Statstcs, ad Computer Scece Copyrght 03 by Marquette Uversty

More information

A Combination of Adaptive and Line Intercept Sampling Applicable in Agricultural and Environmental Studies

A Combination of Adaptive and Line Intercept Sampling Applicable in Agricultural and Environmental Studies ISSN 1684-8403 Joural of Statstcs Volume 15, 008, pp. 44-53 Abstract A Combato of Adaptve ad Le Itercept Samplg Applcable Agrcultural ad Evrometal Studes Azmer Kha 1 A adaptve procedure s descrbed for

More information

ENGI 4421 Joint Probability Distributions Page Joint Probability Distributions [Navidi sections 2.5 and 2.6; Devore sections

ENGI 4421 Joint Probability Distributions Page Joint Probability Distributions [Navidi sections 2.5 and 2.6; Devore sections ENGI 441 Jot Probablty Dstrbutos Page 7-01 Jot Probablty Dstrbutos [Navd sectos.5 ad.6; Devore sectos 5.1-5.] The jot probablty mass fucto of two dscrete radom quattes, s, P ad p x y x y The margal probablty

More information

Simulation Output Analysis

Simulation Output Analysis Smulato Output Aalyss Summary Examples Parameter Estmato Sample Mea ad Varace Pot ad Iterval Estmato ermatg ad o-ermatg Smulato Mea Square Errors Example: Sgle Server Queueg System x(t) S 4 S 4 S 3 S 5

More information

ECONOMETRIC THEORY. MODULE VIII Lecture - 26 Heteroskedasticity

ECONOMETRIC THEORY. MODULE VIII Lecture - 26 Heteroskedasticity ECONOMETRIC THEORY MODULE VIII Lecture - 6 Heteroskedastcty Dr. Shalabh Departmet of Mathematcs ad Statstcs Ida Isttute of Techology Kapur . Breusch Paga test Ths test ca be appled whe the replcated data

More information

Analysis of System Performance IN2072 Chapter 5 Analysis of Non Markov Systems

Analysis of System Performance IN2072 Chapter 5 Analysis of Non Markov Systems Char for Network Archtectures ad Servces Prof. Carle Departmet of Computer Scece U Müche Aalyss of System Performace IN2072 Chapter 5 Aalyss of No Markov Systems Dr. Alexader Kle Prof. Dr.-Ig. Georg Carle

More information

Supervised learning: Linear regression Logistic regression

Supervised learning: Linear regression Logistic regression CS 57 Itroducto to AI Lecture 4 Supervsed learg: Lear regresso Logstc regresso Mlos Hauskrecht mlos@cs.ptt.edu 539 Seott Square CS 57 Itro to AI Data: D { D D.. D D Supervsed learg d a set of eamples s

More information

An Introduction to. Support Vector Machine

An Introduction to. Support Vector Machine A Itroducto to Support Vector Mache Support Vector Mache (SVM) A classfer derved from statstcal learg theory by Vapk, et al. 99 SVM became famous whe, usg mages as put, t gave accuracy comparable to eural-etwork

More information

Econometric Methods. Review of Estimation

Econometric Methods. Review of Estimation Ecoometrc Methods Revew of Estmato Estmatg the populato mea Radom samplg Pot ad terval estmators Lear estmators Ubased estmators Lear Ubased Estmators (LUEs) Effcecy (mmum varace) ad Best Lear Ubased Estmators

More information

Simple Linear Regression

Simple Linear Regression Statstcal Methods I (EST 75) Page 139 Smple Lear Regresso Smple regresso applcatos are used to ft a model descrbg a lear relatoshp betwee two varables. The aspects of least squares regresso ad correlato

More information

Chapter 2 - Free Vibration of Multi-Degree-of-Freedom Systems - II

Chapter 2 - Free Vibration of Multi-Degree-of-Freedom Systems - II CEE49b Chapter - Free Vbrato of Mult-Degree-of-Freedom Systems - II We ca obta a approxmate soluto to the fudametal atural frequecy through a approxmate formula developed usg eergy prcples by Lord Raylegh

More information

Chapter 14 Logistic Regression Models

Chapter 14 Logistic Regression Models Chapter 4 Logstc Regresso Models I the lear regresso model X β + ε, there are two types of varables explaatory varables X, X,, X k ad study varable y These varables ca be measured o a cotuous scale as

More information

Rademacher Complexity. Examples

Rademacher Complexity. Examples Algorthmc Foudatos of Learg Lecture 3 Rademacher Complexty. Examples Lecturer: Patrck Rebesch Verso: October 16th 018 3.1 Itroducto I the last lecture we troduced the oto of Rademacher complexty ad showed

More information

A Study of the Reproducibility of Measurements with HUR Leg Extension/Curl Research Line

A Study of the Reproducibility of Measurements with HUR Leg Extension/Curl Research Line HUR Techcal Report 000--9 verso.05 / Frak Borg (borgbros@ett.f) A Study of the Reproducblty of Measuremets wth HUR Leg Eteso/Curl Research Le A mportat property of measuremets s that the results should

More information

BAYESIAN INFERENCES FOR TWO PARAMETER WEIBULL DISTRIBUTION

BAYESIAN INFERENCES FOR TWO PARAMETER WEIBULL DISTRIBUTION Iteratoal Joural of Mathematcs ad Statstcs Studes Vol.4, No.3, pp.5-39, Jue 06 Publshed by Europea Cetre for Research Trag ad Developmet UK (www.eajourals.org BAYESIAN INFERENCES FOR TWO PARAMETER WEIBULL

More information

Signal,autocorrelation -0.6

Signal,autocorrelation -0.6 Sgal,autocorrelato Phase ose p/.9.3.7. -.5 5 5 5 Tme Sgal,autocorrelato Phase ose p/.5..7.3 -. -.5 5 5 5 Tme Sgal,autocorrelato. Phase ose p/.9.3.7. -.5 5 5 5 Tme Sgal,autocorrelato. Phase ose p/.8..6.

More information

STRONG CONSISTENCY FOR SIMPLE LINEAR EV MODEL WITH v/ -MIXING

STRONG CONSISTENCY FOR SIMPLE LINEAR EV MODEL WITH v/ -MIXING Joural of tatstcs: Advaces Theory ad Alcatos Volume 5, Number, 6, Pages 3- Avalable at htt://scetfcadvaces.co. DOI: htt://d.do.org/.864/jsata_7678 TRONG CONITENCY FOR IMPLE LINEAR EV MODEL WITH v/ -MIXING

More information

Principal Components. Analysis. Basic Intuition. A Method of Self Organized Learning

Principal Components. Analysis. Basic Intuition. A Method of Self Organized Learning Prcpal Compoets Aalss A Method of Self Orgazed Learg Prcpal Compoets Aalss Stadard techque for data reducto statstcal patter matchg ad sgal processg Usupervsed learg: lear from examples wthout a teacher

More information

Assignment 5/MATH 247/Winter Due: Friday, February 19 in class (!) (answers will be posted right after class)

Assignment 5/MATH 247/Winter Due: Friday, February 19 in class (!) (answers will be posted right after class) Assgmet 5/MATH 7/Wter 00 Due: Frday, February 9 class (!) (aswers wll be posted rght after class) As usual, there are peces of text, before the questos [], [], themselves. Recall: For the quadratc form

More information

Outline. Point Pattern Analysis Part I. Revisit IRP/CSR

Outline. Point Pattern Analysis Part I. Revisit IRP/CSR Pot Patter Aalyss Part I Outle Revst IRP/CSR, frst- ad secod order effects What s pot patter aalyss (PPA)? Desty-based pot patter measures Dstace-based pot patter measures Revst IRP/CSR Equal probablty:

More information

Chapter 3 Sampling For Proportions and Percentages

Chapter 3 Sampling For Proportions and Percentages Chapter 3 Samplg For Proportos ad Percetages I may stuatos, the characterstc uder study o whch the observatos are collected are qualtatve ature For example, the resposes of customers may marketg surveys

More information

Feature Selection: Part 2. 1 Greedy Algorithms (continued from the last lecture)

Feature Selection: Part 2. 1 Greedy Algorithms (continued from the last lecture) CSE 546: Mache Learg Lecture 6 Feature Selecto: Part 2 Istructor: Sham Kakade Greedy Algorthms (cotued from the last lecture) There are varety of greedy algorthms ad umerous amg covetos for these algorthms.

More information

UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS

UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS Exam: ECON430 Statstcs Date of exam: Frday, December 8, 07 Grades are gve: Jauary 4, 08 Tme for exam: 0900 am 00 oo The problem set covers 5 pages Resources allowed:

More information

Lecture 1 Review of Fundamental Statistical Concepts

Lecture 1 Review of Fundamental Statistical Concepts Lecture Revew of Fudametal Statstcal Cocepts Measures of Cetral Tedecy ad Dsperso A word about otato for ths class: Idvduals a populato are desgated, where the dex rages from to N, ad N s the total umber

More information

Lecture 8: Linear Regression

Lecture 8: Linear Regression Lecture 8: Lear egresso May 4, GENOME 56, Sprg Goals Develop basc cocepts of lear regresso from a probablstc framework Estmatg parameters ad hypothess testg wth lear models Lear regresso Su I Lee, CSE

More information

Comparing Different Estimators of three Parameters for Transmuted Weibull Distribution

Comparing Different Estimators of three Parameters for Transmuted Weibull Distribution Global Joural of Pure ad Appled Mathematcs. ISSN 0973-768 Volume 3, Number 9 (207), pp. 55-528 Research Ida Publcatos http://www.rpublcato.com Comparg Dfferet Estmators of three Parameters for Trasmuted

More information

Point Estimation: definition of estimators

Point Estimation: definition of estimators Pot Estmato: defto of estmators Pot estmator: ay fucto W (X,..., X ) of a data sample. The exercse of pot estmato s to use partcular fuctos of the data order to estmate certa ukow populato parameters.

More information

Nonlinear Blind Source Separation Using Hybrid Neural Networks*

Nonlinear Blind Source Separation Using Hybrid Neural Networks* Nolear Bld Source Separato Usg Hybrd Neural Networks* Chu-Hou Zheg,2, Zh-Ka Huag,2, chael R. Lyu 3, ad Tat-g Lok 4 Itellget Computg Lab, Isttute of Itellget aches, Chese Academy of Sceces, P.O.Box 3, Hefe,

More information

Convergence of the Desroziers scheme and its relation to the lag innovation diagnostic

Convergence of the Desroziers scheme and its relation to the lag innovation diagnostic Covergece of the Desrozers scheme ad ts relato to the lag ovato dagostc chard Méard Evromet Caada, Ar Qualty esearch Dvso World Weather Ope Scece Coferece Motreal, August 9, 04 o t t O x x x y x y Oservato

More information

Cubic Nonpolynomial Spline Approach to the Solution of a Second Order Two-Point Boundary Value Problem

Cubic Nonpolynomial Spline Approach to the Solution of a Second Order Two-Point Boundary Value Problem Joural of Amerca Scece ;6( Cubc Nopolyomal Sple Approach to the Soluto of a Secod Order Two-Pot Boudary Value Problem W.K. Zahra, F.A. Abd El-Salam, A.A. El-Sabbagh ad Z.A. ZAk * Departmet of Egeerg athematcs

More information

Applications of Multiple Biological Signals

Applications of Multiple Biological Signals Applcatos of Multple Bologcal Sgals I the Hosptal of Natoal Tawa Uversty, curatve gastrectomy could be performed o patets of gastrc cacers who are udergoe the curatve resecto to acqure sgal resposes from

More information

Simple Linear Regression

Simple Linear Regression Correlato ad Smple Lear Regresso Berl Che Departmet of Computer Scece & Iformato Egeerg Natoal Tawa Normal Uversty Referece:. W. Navd. Statstcs for Egeerg ad Scetsts. Chapter 7 (7.-7.3) & Teachg Materal

More information

2.28 The Wall Street Journal is probably referring to the average number of cubes used per glass measured for some population that they have chosen.

2.28 The Wall Street Journal is probably referring to the average number of cubes used per glass measured for some population that they have chosen. .5 x 54.5 a. x 7. 786 7 b. The raked observatos are: 7.4, 7.5, 7.7, 7.8, 7.9, 8.0, 8.. Sce the sample sze 7 s odd, the meda s the (+)/ 4 th raked observato, or meda 7.8 c. The cosumer would more lkely

More information

Bootstrap Method for Testing of Equality of Several Coefficients of Variation

Bootstrap Method for Testing of Equality of Several Coefficients of Variation Cloud Publcatos Iteratoal Joural of Advaced Mathematcs ad Statstcs Volume, pp. -6, Artcle ID Sc- Research Artcle Ope Access Bootstrap Method for Testg of Equalty of Several Coeffcets of Varato Dr. Navee

More information

Bayesian Inferences for Two Parameter Weibull Distribution Kipkoech W. Cheruiyot 1, Abel Ouko 2, Emily Kirimi 3

Bayesian Inferences for Two Parameter Weibull Distribution Kipkoech W. Cheruiyot 1, Abel Ouko 2, Emily Kirimi 3 IOSR Joural of Mathematcs IOSR-JM e-issn: 78-578, p-issn: 9-765X. Volume, Issue Ver. II Ja - Feb. 05, PP 4- www.osrjourals.org Bayesa Ifereces for Two Parameter Webull Dstrbuto Kpkoech W. Cheruyot, Abel

More information

Block-Based Compact Thermal Modeling of Semiconductor Integrated Circuits

Block-Based Compact Thermal Modeling of Semiconductor Integrated Circuits Block-Based Compact hermal Modelg of Semcoductor Itegrated Crcuts Master s hess Defese Caddate: Jg Ba Commttee Members: Dr. Mg-Cheg Cheg Dr. Daqg Hou Dr. Robert Schllg July 27, 2009 Outle Itroducto Backgroud

More information

STATISTICAL PROPERTIES OF LEAST SQUARES ESTIMATORS. x, where. = y - ˆ " 1

STATISTICAL PROPERTIES OF LEAST SQUARES ESTIMATORS. x, where. = y - ˆ  1 STATISTICAL PROPERTIES OF LEAST SQUARES ESTIMATORS Recall Assumpto E(Y x) η 0 + η x (lear codtoal mea fucto) Data (x, y ), (x 2, y 2 ),, (x, y ) Least squares estmator ˆ E (Y x) ˆ " 0 + ˆ " x, where ˆ

More information

Dimensionality reduction Feature selection

Dimensionality reduction Feature selection CS 750 Mache Learg Lecture 3 Dmesoalty reducto Feature selecto Mlos Hauskrecht mlos@cs.ptt.edu 539 Seott Square CS 750 Mache Learg Dmesoalty reducto. Motvato. Classfcato problem eample: We have a put data

More information

THE FAULT ANALYSIS MADE BY PSW DATA RECORDER FOR NEUROLOGICAL DISEASE CLASSIFICATION SHORT NOTE 1. INTRODUCTION 2. THE DIAGNOSIS DESCRIPTORS

THE FAULT ANALYSIS MADE BY PSW DATA RECORDER FOR NEUROLOGICAL DISEASE CLASSIFICATION SHORT NOTE 1. INTRODUCTION 2. THE DIAGNOSIS DESCRIPTORS JOURNAL OF MEDICAL INFORMATICS & TECHNOLOGIES Vol.4/00, ISSN 64-6037 Karol KOPICERA *, Ja PIECHA *,** pedobarography, cocluso makg systems, medcal dagostcs THE FAULT ANALYSIS MADE BY PSW DATA RECORDER

More information

A new type of optimization method based on conjugate directions

A new type of optimization method based on conjugate directions A ew type of optmzato method based o cojugate drectos Pa X Scece School aj Uversty of echology ad Educato (UE aj Cha e-mal: pax94@sacom Abstract A ew type of optmzato method based o cojugate drectos s

More information

Lecture 1. (Part II) The number of ways of partitioning n distinct objects into k distinct groups containing n 1,

Lecture 1. (Part II) The number of ways of partitioning n distinct objects into k distinct groups containing n 1, Lecture (Part II) Materals Covered Ths Lecture: Chapter 2 (2.6 --- 2.0) The umber of ways of parttog dstct obects to dstct groups cotag, 2,, obects, respectvely, where each obect appears exactly oe group

More information

ECON 482 / WH Hong The Simple Regression Model 1. Definition of the Simple Regression Model

ECON 482 / WH Hong The Simple Regression Model 1. Definition of the Simple Regression Model ECON 48 / WH Hog The Smple Regresso Model. Defto of the Smple Regresso Model Smple Regresso Model Expla varable y terms of varable x y = β + β x+ u y : depedet varable, explaed varable, respose varable,

More information

L5 Polynomial / Spline Curves

L5 Polynomial / Spline Curves L5 Polyomal / Sple Curves Cotets Coc sectos Polyomal Curves Hermte Curves Bezer Curves B-Sples No-Uform Ratoal B-Sples (NURBS) Mapulato ad Represetato of Curves Types of Curve Equatos Implct: Descrbe a

More information

Lecture 7. Confidence Intervals and Hypothesis Tests in the Simple CLR Model

Lecture 7. Confidence Intervals and Hypothesis Tests in the Simple CLR Model Lecture 7. Cofdece Itervals ad Hypothess Tests the Smple CLR Model I lecture 6 we troduced the Classcal Lear Regresso (CLR) model that s the radom expermet of whch the data Y,,, K, are the outcomes. The

More information

Dimensionality Reduction and Learning

Dimensionality Reduction and Learning CMSC 35900 (Sprg 009) Large Scale Learg Lecture: 3 Dmesoalty Reducto ad Learg Istructors: Sham Kakade ad Greg Shakharovch L Supervsed Methods ad Dmesoalty Reducto The theme of these two lectures s that

More information

STK4011 and STK9011 Autumn 2016

STK4011 and STK9011 Autumn 2016 STK4 ad STK9 Autum 6 Pot estmato Covers (most of the followg materal from chapter 7: Secto 7.: pages 3-3 Secto 7..: pages 3-33 Secto 7..: pages 35-3 Secto 7..3: pages 34-35 Secto 7.3.: pages 33-33 Secto

More information

To use adaptive cluster sampling we must first make some definitions of the sampling universe:

To use adaptive cluster sampling we must first make some definitions of the sampling universe: 8.3 ADAPTIVE SAMPLING Most of the methods dscussed samplg theory are lmted to samplg desgs hch the selecto of the samples ca be doe before the survey, so that oe of the decsos about samplg deped ay ay

More information

Bayes Interval Estimation for binomial proportion and difference of two binomial proportions with Simulation Study

Bayes Interval Estimation for binomial proportion and difference of two binomial proportions with Simulation Study IJIEST Iteratoal Joural of Iovatve Scece, Egeerg & Techology, Vol. Issue 5, July 04. Bayes Iterval Estmato for bomal proporto ad dfferece of two bomal proportos wth Smulato Study Masoud Gaj, Solmaz hlmad

More information

Effect of Noise on Gradient Systems

Effect of Noise on Gradient Systems Effect of Nose o Gradet Systems Kev Ho, Hsa-Chg Chag, We-B Lee recet years, the aalyss o the effect of addtve multplcatve weght ose o the learg algorthms for multlayered perceptros has ee doe [1]-[15]

More information

Confidence Intervals for Double Exponential Distribution: A Simulation Approach

Confidence Intervals for Double Exponential Distribution: A Simulation Approach World Academy of Scece, Egeerg ad Techology Iteratoal Joural of Physcal ad Mathematcal Sceces Vol:6, No:, 0 Cofdece Itervals for Double Expoetal Dstrbuto: A Smulato Approach M. Alrasheed * Iteratoal Scece

More information

Unimodality Tests for Global Optimization of Single Variable Functions Using Statistical Methods

Unimodality Tests for Global Optimization of Single Variable Functions Using Statistical Methods Malaysa Umodalty Joural Tests of Mathematcal for Global Optmzato Sceces (): of 05 Sgle - 5 Varable (007) Fuctos Usg Statstcal Methods Umodalty Tests for Global Optmzato of Sgle Varable Fuctos Usg Statstcal

More information

Evaluation of uncertainty in measurements

Evaluation of uncertainty in measurements Evaluato of ucertaty measuremets Laboratory of Physcs I Faculty of Physcs Warsaw Uversty of Techology Warszawa, 05 Itroducto The am of the measuremet s to determe the measured value. Thus, the measuremet

More information

Uniform asymptotical stability of almost periodic solution of a discrete multispecies Lotka-Volterra competition system

Uniform asymptotical stability of almost periodic solution of a discrete multispecies Lotka-Volterra competition system Iteratoal Joural of Egeerg ad Advaced Research Techology (IJEART) ISSN: 2454-9290, Volume-2, Issue-1, Jauary 2016 Uform asymptotcal stablty of almost perodc soluto of a dscrete multspeces Lotka-Volterra

More information

Numerical Simulations of the Complex Modied Korteweg-de Vries Equation. Thiab R. Taha. The University of Georgia. Abstract

Numerical Simulations of the Complex Modied Korteweg-de Vries Equation. Thiab R. Taha. The University of Georgia. Abstract Numercal Smulatos of the Complex Moded Korteweg-de Vres Equato Thab R. Taha Computer Scece Departmet The Uversty of Georga Athes, GA 002 USA Tel 0-542-2911 e-mal thab@cs.uga.edu Abstract I ths paper mplemetatos

More information

Comparison of Dual to Ratio-Cum-Product Estimators of Population Mean

Comparison of Dual to Ratio-Cum-Product Estimators of Population Mean Research Joural of Mathematcal ad Statstcal Sceces ISS 30 6047 Vol. 1(), 5-1, ovember (013) Res. J. Mathematcal ad Statstcal Sc. Comparso of Dual to Rato-Cum-Product Estmators of Populato Mea Abstract

More information

Lecture Notes Types of economic variables

Lecture Notes Types of economic variables Lecture Notes 3 1. Types of ecoomc varables () Cotuous varable takes o a cotuum the sample space, such as all pots o a le or all real umbers Example: GDP, Polluto cocetrato, etc. () Dscrete varables fte

More information

THE ROYAL STATISTICAL SOCIETY GRADUATE DIPLOMA

THE ROYAL STATISTICAL SOCIETY GRADUATE DIPLOMA THE ROYAL STATISTICAL SOCIETY EXAMINATIONS SOLUTIONS GRADUATE DIPLOMA PAPER II STATISTICAL THEORY & METHODS The Socety provdes these solutos to assst caddates preparg for the examatos future years ad for

More information

MULTIDIMENSIONAL HETEROGENEOUS VARIABLE PREDICTION BASED ON EXPERTS STATEMENTS. Gennadiy Lbov, Maxim Gerasimov

MULTIDIMENSIONAL HETEROGENEOUS VARIABLE PREDICTION BASED ON EXPERTS STATEMENTS. Gennadiy Lbov, Maxim Gerasimov Iteratoal Boo Seres "Iformato Scece ad Computg" 97 MULTIIMNSIONAL HTROGNOUS VARIABL PRICTION BAS ON PRTS STATMNTS Geady Lbov Maxm Gerasmov Abstract: I the wors [ ] we proposed a approach of formg a cosesus

More information