A Background Layer Model for Object Tracking through Occlusion

Size: px
Start display at page:

Download "A Background Layer Model for Object Tracking through Occlusion"

Transcription

1 A Background Layer Model for Obec Trackng hrough Occluson Yue Zhou and Ha Tao Deparmen of Compuer Engneerng Unversy of Calforna, Sana Cruz, CA Absrac Moon layer esmaon has recenly emerged as a promsng obec rackng mehod. In hs paper, we exend prevous research on layer-based racker by nroducng he concep of background occludng layers and explcly nferrng deph orderng of foreground layers. The background occludng layers le n fron of, behnd, and n beween foreground layers. Each pxel n he background regons belongs o one of hese layers and occludes all he foreground layers behnd. Togeher wh he foreground orderng, he complee nformaon necessary for relably rackng obecs hrough occluson s ncluded n our represenaon. An MA esmaon framework s developed o smulaneously updae he moon layer parameers, he orderng parameers, and he background occludng layers. Expermenal resuls show ha under varous condons wh occluson, ncludng suaons wh movng obecs undergong complex moons or havng complex neracons, our rackng algorhm s able o handle many dffcul rackng asks relably. Inroducon In recen years, dynamc moon layer esmaon has emerged as a promsng approach for obec rackng [4],[9],[5],[8]. A moon layer s a regon n an mage ha undergoes a coheren moon. The wo chef problems n moon layer based rackng algorhms are how o represen moon layers and how o esmae he parameers assocaed wh hese layers. Wh he dynamc moon layer represenaon, rackng problem can be formulaed as he maxmum a poseror (MA) esmaon of a Hdden Markov Model (HMM) [8]. In a ypcal moon layer esmaon process, boh foreground obecs and background are modeled and hey compee wh each oher o maxmze he on poseror probably. Ths s one of he man reasons behnd he success of layer rackers. In erms of layer represenaon, n prevous work, only moon, segmenaon, and appearance are consdered. Ths obec represenaon works well for rackng mulple obecs when no occluson presens. However, s nsuffcen n accommodang occluson caused by foreground or background obec and n effecvely modelng he spaal relaonshp among movng obecs and he background. revous work on moon layer analyss and moon layer based rackng employed global or local moon represenaons [0],[],[]. The obec shape and appearance are ofen modeled as Gaussan dsrbuons [9], Markov Random Felds (MRF) [0] or oher mxure models []. To handle obec occluson n moon analyss and rackng, an explc generave occluson boundary model was proposed n [3]. To handle self-occluson on he foreground obecs and adapvely change he shapes of he foreground obecs o allow he rackng of non-rgd moon, [4] proposed a combned paramerc shape and moon model wh deph orderng o represen he vsbly of each layers. The Transformed Hdden Markov Model (THMM) algorhm [6] ncludes boh moon and appearance represenaon as he parameers n a generave model and formulaes he rackng problem as he learnng of hese parameers. In hs paper, we propose a novel scene represenaon wh orderng nformaon ha conans complee nformaon for nferrng he foreground obec and he background occluson. In hs represenaon, each movng obec s modeled as a foreground layer. Some background obecs such as rees may occlude foreground moon layers. To model he deph dfference n background, we nroduce background layers ha le beween foreground layers. Ths s dfferen from he prevous mehods where he background regon s modeled as a sngle layer. In addon, he deph orderng of foreground layers s reaed as a sae varable o explcly model he deph relaons among foreground obecs. Unlke he global shape model n [9], we also allow gradual bu arbrary changes n obecs shapes, whch are capured n he foreground mask. Based on hs new layer represenaon, we propose an esmaon algorhm ha esmaes he moon layer parameers, he foreground orderng, and he background layers n an MA framework. The overall formulaon can be wren as max arg ( Λ Λ, I,..., I 0 ) () Λ where Λ s he sae of he racker a me, and I s he mage observaon.

2 The res of he paper s organzed as follows. The deals of he proposed layer represenaon are presened n Secon. Secon 3 descrbes he MA esmaon of he layer sae. Secon 4 descrbes he mplemenaon and demonsraes he expermenal resuls. Some dscussons and conclusons can be found n Secon 5. Dynamc layer modelng. Deph orderng of he foreground and background layers In our proposed approach, a dynamc scene s represened by foreground and background layers. As shown n Fgure, foreground moon layers are ordered accordng o her relave deph from fron o back. The fron-mos layer s layer. Some background regons, whch are defned as he mage areas ha do no move, may le n beween foreground layers. These background regons are n fron of some foreground obecs and are called occludng background layers. In our model, as shown n Fgure, here s one background layer beween every wo neghborng foreground layers. There s also one background layer ha s behnd all foreground layers and one layer ha s n fron all foreground layers (layer ). If here are L foreground layers, he here are L + background layers. Foreground layers Layer Layer Layer Background layers Layer Layer 3 Fron Fgure. The ordered layer model. Fgure. An example of he background layers. Each foreground layer s descrbed by s moon, shape, and appearance. Each background layer s descrbed by s shape and appearance. If he background also moves, all background layers share a sngle moon. A any me, Back he se of all layer parameers s called he sae of he racker and s denoed by Λ. In laer secons, we wll descrbe n deal he models for hese sae varables. Fgure shows a real example of a vdeo frame and he op-mos occludng background layer. In hs example, only he shape of he fron-mos background layer s shown. Usng he above layer model, from he obec pon of vew, each obec belongs o one of he foreground layers. We explcly model and esmae he layer assgnmen for he obecs n he scene. The deph orderng of L foreground obecs a me s denoed as O =,,..., ]. The neger varable [, L] and [ L k l ff k l. If we assume ha obecs do no nerleave wh each oher, here are L! possble layer assgnmens for L foreground obecs. We furher assume ha he deph orderng s a random varable wh a unform dsrbuon. Ths means all he permuaons have he same probably and hus have he same pror probably ( O, ) = L!, where O, s an arbrary layer orderng confguraon. I should be noced ha he foreground layer orderng, ogeher wh he shape, appearance, and moon nformaon of all foreground and background layers, provde he complee nformaon for occluson reasonng.. Moon models We descrbe he background moon usng a D affne model. and esmaed hs model usng he so-called drec mehod []. All background layers share he same moon. Each foreground layer undergoes a D rgd moon, whch s descrbed usng poson µ, orenaon ω, scalng facor s, and her emporal dervaves. A consan velocy model s used o descrbe he dynamcs of he foreground layers. If we denoe he moon parameers of a layer as θ = [ µ, ω, s, & µ, & ω, s& ], hen he moon dynamcs s wren as ( θ θ ) = N( θ : Φθ, Q) () where θ s he moon parameer a me, Φ s he sandard ranson marx for a consan velocy model, and he noaon N ( x : µ, R) denoes a mulvarae Gaussan dsrbuon wh mean µ and covarance marx R..3 Shape models of he foreground and background layers Each foreground or background layer s assocaed wh a shape map. A each pxel locaon, he value of he shape map s he probably ha he obec n he layer presenng a ha pxel locaon ( may no be vsble hough). For he foreground layer and poson x a me, we denoe

3 he value of he shape map as τ ( x ). For he background layer, we use he noaon π ( x ) o represen s shape map. One dfference beween he foreground shape map and he background shape map s ha for he background, he probablsc values of all shape maps a each pxel mus sum up o. Ths reveals our underlyng assumpon ha here s only one background surface for each pxel. Ths s a reasonable assumpon because even here are more surfaces hey wll no be observable anyway..3. Layer vsbly Once he shape maps are defned for all layers, for each pxel x, we can compue he probably ha he h foreground layer s vsble. Ths s he probably of he on even ha background layers o are absen foreground layer o are absen and h foreground layer presens a x. The frs probably s l = π l ( x ) because here s only one background surface. The second probably s s= [ τ s ( x )], and he hrd probably s τ ( x ) (for smplcy, we gnore he subscrp ). As a resul he probably of he h foreground layer beng vsble a x s ( x ) = τ ( x ) ( π ( x )) [ τ ( x )] () l= l s= Smlarly, he probably of observng he background layer a x s k= s h B, ( x ) = π ( x ) ( τ k ( x )) (3) and he probably of observng one of he background layers s ( x ) B L+ π ( x ) ( τ k ( x )) (4) = k= =.3. Shape dynamcs If we assume he shape of he foreground does no change dramacally, hen we can use a consan value Gaussan model o descrbe he dynamcs of he shape changes over me. More specfcally, ( τ N( τ ( x ) τ ( x ); τ,, ) = γ + ( R( & ω )( x & µ ) / s& ), σ τ where γ represens he uncerany n he shape of he layer. The ransformaon R ( & ω )( x & µ ) / s& s used o algn he shape maps. ) (5).4 Appearance model The appearance of foreground layer s defned n he local coordnae sysem and s denoed as A,. We assume ha he mage observaon model s a Gaussan dsrbuon wh he appearance as he mean, or ( I ( x ) A, ( x )) = N( I ( x ) : A, ( x ), σ I ) (6) where σ I s he varance of he mage observaon. Lke he moon and shape models, we also assume ha he emporal changes of he layer appearance follow a consan value Gaussan dsrbuon. Ths s formulaed as ( A, ( x ) A, ( x )) = N( A, ( x ) : A, ( x ) : σ A) (7) where σ A s he appearance uncerany ha accouns for he appearance varaons..5 The MA esmaon The rackng procedure can be consdered as he maxmzaon of he poseror probably arg max ( Λ Λ, I,..., I 0 ) (8) Λ Usng Bayes rule and he HMM model, ( Λ Λ, I,..., I 0 ) = ( I Λ ) ( Λ Λ ) (9) where ( Λ Λ ) s he sae pror funcon, and ( I Λ ) s he lkelhood funcon. Based on our models n he prevous secons, he pror funcon s compued as where ( Λ Λ ) = (0) order fg _ shape bg _ shape moon appearance order = fg ( o o ) _ shape ( τ ( x ) τ, ( x )) = L N = = L + N bg _ shape = ( π ( x ) π, ( x )) = = L moon = ( θ θ = = L N appearance = =, ) ( A, ( x ) A, ( x )) Here we assume he mage has L foreground layers, L + background layers, and N pxels on he obec n layer. 3

4 To compue he lkelhood funcon, we need o frs oban he probablsc dsrbuon of he fron-mos layer a each pxel based on foreground layer orderng, foreground and background shapes, and he appearance models. More specfcally, we compue he lkelhood funcon as ( I N Λ ) = ( ( x ) + ( x )) () = where bgo ( x ) and ( x ) represen he lkelhood of one of he background or foreground layers s vsble a pxel x. They can be compued as and bgo x ) = ( I( x ) B( x )) ( x ) () bgo ( B [ ( I ( x ) A ( x )) ( x )] ( x ) (3) = L = x ) and x ) are defned n Eq(-4). B ( ( 3 Esmaon of he obec sae Solvng Eq(8) s a dffcul opmzaon problem because he sae space s very large. An approxmae soluon can be found by frs decomposng he orgnal problem no several sub-problems (see Fgure 3). Then opmzaon s performed o solve hese sub-problems sequenally. We found ha n pracce hs approach yelds feasble soluons. Hypohesze & deermne obec orderng Layer moon esmaon Foreground shape esmaon Background shape esmaon Appearance esmaon Fgure 3. Esmaon of he sae parameers. 3. Foreground layer orderng hypohess + Foreground layer orderng O s modeled as a unformly dsrbued random varable. Because of hs propery, he esmaon of O s raher smple: he algorhm goes hrough all he possble value of O, and fnds he one ha maxmzes he poseror probably. Snce all he oher parameer esmaon seps hghly depend on he deph orderng, s compued a he begnnng of each eraon. 3. Moon esmaon Maxmzng he poseror probably n Eq(8) w.r.. foreground layer moon s equvalen o opmzng he funcon n ( = bgo ( x ) + ( x )) moon (4) A search algorhm can be used o fnd he soluon around he predced poson. Roaon, ranslaon, and he scalng facor are dscrezed wh suffcen precson for hs purpose. For sequence wh movng background, a drec mehod [] s used o esmae he moon parameers. 3.3 Foreground shape esmaon From Eq(-3) and Eq(-4), can be observed ha he lkelhood s a lnear funcon of each foreground shape varable τ ( x ) and he pror erm s a Gaussan funcon of τ ( x ). If we opmze τ ( x ) ndependenly for each layer, he esmaon becomes he maxmzaon of a funcon n he form of ( x x0 ) / σ ( ax + b) e (5) where a and b are consans ha can be compued usng Eq(-3) and Eq(-4). The opmal soluon s 0,, or he roo of he quadrac equaon ax + ( b ax0 ) x ( bx0 + aσ ) = 0 (6) Ths equaon s derved by akng he dervaves of he funcon n Eq(5) and se o be Background shape esmaon Esmaon of he background shape s smlar o he esmaon of he foreground shape. However, here s one addonal consran needs o be enforced: he values of all shape maps should sum up o. Wh hs consran he global opmzaon becomes complcaed. However, we can use he resuls n he prevous frame or prevous eraon as he sarng pon o perform a greedy algorhm o fnd he local opmal soluon. We esmae each background level ndvdually wh he shape maps of oher layers fxed. Afer all shape values for all layers are esmaed, hey are normalzed so ha her sum becomes. There s anoher dfference beween he background shape esmaon and he foreground shape esmaon. For foreground, he obec shape does no change sgnfcanly over me because of he D rgd model. Therefore we use he shape n he prevous frame as our pror n he esmaon. However, n he background shape esmaon, he shape of each background layer hghly depends on obec moon. The occludng background shape n he same area can change quckly from me o me because of obec movemens. For example, a car may frs pass behnd a ree, urn around and hen pass n fron of he ree agan; n he frs case he ree s par of he occludng 4

5 background layer o he foreground layer of car, whle n he second case he ree belongs o he background layer ha does no occlude he same foreground. So n our algorhm f all he obecs leave an area for a ceran perod of me, we acually lack vsual nformaon o nfer background layer shapes. As a resul no maer wha he prevous background shape values are, hey becomes obsolee and he shape of all background layers are rese o a defaul value. 3.5 Appearance esmaon To esmae he appearance, we need o fnd A, ha maxmzes he funcon n ( ( x ) + ( x )) (7) = bgo appearance Snce boh he appearance observaon model Eq(6) and he appearance dynamcs Eq(7) are Gaussan funcons, he funcon n Eq(7) becomes a Gaussan mxure. The closed-form soluon o hs opmzaon problem s dffcul o fnd. However, appearance s a dscree funcon and we know he soluon should be beween he curren observaon and he prevous esmae. For each pxel, we can search for he appearance value n hs range o fnd he soluon. 4 Implemenaon and expermenal resuls 4. Inalzaon and deleon of obecs In addon o he rackng algorhm dscussed n he prevous secons, here are several oher ssues regardng he nalzaon and deleon of he foreground and background layers need o be addressed. In our mplemenaon, change mage s compued o deermne wheher a movng obec presens n he scene. A new obec s nalzed f a change blob s deeced far away from any exsng obecs. In hs case, we assume he cener of he obec s locaed a he cener of he change blob. The value of shape map a each pxel s proporonal o he nensy of he change mage. The appearance s se o be he orgnal mage nensy values. An addonal background layer s nsered. The new layer has he same shape map as s neghborng background layer. A normalzaon sep s hen appled o make sure hese background shape maps sum up o a each pxel. An obec s deleed f moves ou of he mage boundares or s occluded for a very long perod of me. Then he foreground layer of hs obec s removed from he daa srucure and wo background layers nex o merge no one layer wh he shape mask value equal o he sum of he orgnal wo shape maps. 4. Synhec vdeos We have esed he proposed algorhm usng synhec and real vdeo clps. (Vdeo clps of he resuls are avalable n he supplemenary fle). In Fgure 4 and Fgure 5 show he rackng resuls of wo synhec vdeos wh movng obecs. The vdeos nclude dffcul condons ncludng shadows, reflecons, and ransparen obecs (e.g. he waerfall), and ou-of-plane obec roaon. Our rackng algorhm locked on he movng obecs successfully hrough occluson n boh sequences. The esmaed sae varables n hree key frames of he second vdeo are shown n Fgure 6. I can be observed he background shape maps n row 3 accuraely descrbe he shape of he occludng ree. 4.3 Vehcle rackng hrough occluson We mplemened a rackng sysem based on he proposed algorhm for handlng obec occlusons. In Fgure 7, he rackng resul on a vdeo clp wh a car occluded by background s demonsraed. In hs example, background obecs such as rees, lgh poles, and he rsng ground occlude he car. The proposed rackng algorhm esmaes he layer parameers correcly hrough he sequence. The racker found one foreground layer and wo background layers. The esmaed sae varables n hree key frames are demonsraed n Fgure 8. The background shape maps are for he fron-mos layer. Fgure 6. Layer sae varables n hree frames of he vdeo n Fgure 5 (Row are he orgnal mages, Row are he foreground shapes, Row 3 are he background shapes, and Row 4 are he foreground appearances). 4.4 Human rackng Alhough our model of layer shape s D rgd, our racker s able o rack movng people by adusng he sysem parameers and focusng orso area, whch s relavely rgd compared o he oher pars of human body. Fgure 9 shows he rackng resul of wo persons passng accross each oher. The algorhm racked boh persons successfully hrough he occluson. 5

6 Fgure 0 demonsraes he rackng resuls on a vdeo clp n whch a walkng person s occluded by background obecs. Because he occludng background area s large, here s a long perod of full occluson. Snce he algorhm esmaes he background occludng layers, knows whch par of he foreground s occluded. As a resul he racker s aware of he occluson and wll no updae he obec appearance. The racker s able o regan correc values of layer sae soon afer he obec moves ou of he occludng background, as observed n he las frame. Fgure 8. Layer sae varables n hree frames of he vdeo n Fgure 7 (Row are he orgnal mages, Row are he foreground shapes, Row 3 are he background shapes, Row 4 are he foreground appearances). 5 Conclusons A novel moon layer based represenaon and he assocaed esmaon algorhm have been proposed n hs paper. Ths new approach exends he radonal layer model by nroducng he background layers and layer orderng. The expermenal resuls demonsrae he power of hs represenaon n handlng he dffcul occluson problem n rackng. One advanage of he proposed represenaon s ha models all possble neracon beween foreground and background obecs. No only he occluson caused by he foreground layer s modeled, bu also modeled s he occluson caused by he background layers. Some fuure research opcs for mprovng he proposed algorhm nclude he developmen of more flexble shape and moon models ha can handle arculaed and nonrgd moons and he nvesgaon of effcen opmzaon algorhms for fndng he opmal orderng of he foreground layers. References [] J. R. Bergen,. Anandan, K. J. Hanna, and R. Hngoran, Hearchcal model-based moon esmaon, n roc. of nd European Conference on Compuer Vson, pp. 37-5, 99. [] M.J. Black, D.J. Flee., and Y. Yacoob A framework for modelng appearance change n mage sequences. IEEE Inernaonal Conference on Compuer Vson, Mumba, Inda, January 998, pp [3] Black, M. J. and Flee D. J., robablsc deecon and rackng of moon boundares, In. J. of Compuer Vson, 38(3):3-45, July 000. [4] Allan D. Jepson, Davd J. Flee Mchael J. Black A Layered Moon represenaon wh occluson and compac spaal suppor. ECCV () 00: [5] Allan D. Jepson, Davd J. Flee and Thomas F. El-Maragh, Robus onlne appearance models for vsual rackng IEEE Conference on Compuer Vson and and aern Recognon, Kaua, 00, Vol. I, pp [6] N. Joc, N. erovc, B. Frey, and T. S. Huang, Transformed hdden Markov models: esmang mxure models of mages and nferrng spaal ransformaons n vdeo sequences, n roc. of he IEEE Conference on Compuer Vson and aern Recognon, pp.(ii) 6-33, 000. [7] N. Joc and B.J. Frey Learnng flexble spres n vdeo layers. In Compuer Vson and aern Recognon, pp. (I) 99-06, 00. [8] L.R. Rabner. A uoral on hdden Markov models and seleced applcaons n speech recognon. roceedngs of he IEEE, 77(): 57-85, 989. [9] H. Tao, H. Sawhney and R. Kumar, Obec rackng wh Bayesan esmaon of dynamc layer represenaons, IEEE Transacons On aern Analyss And Machne Inellgence. Jan. 00. [0] N. Vasconcelos and A. Lppman, Emprcal Bayesan EMbased moon segmenaon, n roc. of IEEE Conference on Compuer Vson and aern Recognon, pp , 997. [] J. Y. A. Wang and Edward H. Adelson, Layered represenaon for moon analyss, n roc. of IEEE conference on Compuer Vson and aern Recognon, pp , 993. [] Y. Wess and E. H. Adelson, A unfed mxure framework for moon segmenaon: ncorporang spaal coherence and esmang he number of models, n roc. of IEEE conference on Compuer Vson and aern Recognon, pp. 3-36,

7 Fgure 4. A synhec vdeo sequence wh a fgure movng horzonally. Fgure 5. A movng fgure moves behnd a ree. Fgure 7. A movng car s occluded by rees and he rsng ground. Fgure 9. Two people work across each oher. Fgure 0. A person walks behnd rees and bushes. 7

How To Calculate Backup From A Backup From An Oal To A Daa

How To Calculate Backup From A Backup From An Oal To A Daa 6 IJCSNS Inernaonal Journal of Compuer Scence and Nework Secury, VOL.4 No.7, July 04 Mahemacal Model of Daa Backup and Recovery Karel Burda The Faculy of Elecrcal Engneerng and Communcaon Brno Unversy

More information

An Anti-spam Filter Combination Framework for Text-and-Image Emails through Incremental Learning

An Anti-spam Filter Combination Framework for Text-and-Image Emails through Incremental Learning An An-spam Fler Combnaon Framework for Tex-and-Image Emals hrough Incremenal Learnng 1 Byungk Byun, 1 Chn-Hu Lee, 2 Seve Webb, 2 Danesh Iran, and 2 Calon Pu 1 School of Elecrcal & Compuer Engr. Georga

More information

PARTICLE FILTER BASED VEHICLE TRACKING APPROACH WITH IMPROVED RESAMPLING STAGE

PARTICLE FILTER BASED VEHICLE TRACKING APPROACH WITH IMPROVED RESAMPLING STAGE ISS: 0976-910(OLIE) ICTACT JOURAL O IMAGE AD VIDEO PROCESSIG, FEBRUARY 014, VOLUME: 04, ISSUE: 03 PARTICLE FILTER BASED VEHICLE TRACKIG APPROACH WITH IMPROVED RESAMPLIG STAGE We Leong Khong 1, We Yeang

More information

12/7/2011. Procedures to be Covered. Time Series Analysis Using Statgraphics Centurion. Time Series Analysis. Example #1 U.S.

12/7/2011. Procedures to be Covered. Time Series Analysis Using Statgraphics Centurion. Time Series Analysis. Example #1 U.S. Tme Seres Analyss Usng Sagraphcs Cenuron Nel W. Polhemus, CTO, SaPon Technologes, Inc. Procedures o be Covered Descrpve Mehods (me sequence plos, auocorrelaon funcons, perodograms) Smoohng Seasonal Decomposon

More information

Kalman filtering as a performance monitoring technique for a propensity scorecard

Kalman filtering as a performance monitoring technique for a propensity scorecard Kalman flerng as a performance monorng echnque for a propensy scorecard Kaarzyna Bjak * Unversy of Souhampon, Souhampon, UK, and Buro Informacj Kredyowej S.A., Warsaw, Poland Absrac Propensy scorecards

More information

Linear Extension Cube Attack on Stream Ciphers Abstract: Keywords: 1. Introduction

Linear Extension Cube Attack on Stream Ciphers Abstract: Keywords: 1. Introduction Lnear Exenson Cube Aack on Sream Cphers Lren Dng Yongjuan Wang Zhufeng L (Language Engneerng Deparmen, Luo yang Unversy for Foregn Language, Luo yang cy, He nan Provnce, 47003, P. R. Chna) Absrac: Basng

More information

Capacity Planning. Operations Planning

Capacity Planning. Operations Planning Operaons Plannng Capacy Plannng Sales and Operaons Plannng Forecasng Capacy plannng Invenory opmzaon How much capacy assgned o each producon un? Realsc capacy esmaes Sraegc level Moderaely long me horzon

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

Sensor Nework proposeations

Sensor Nework proposeations 008 Inernaoal Symposum on Telecommuncaons A cooperave sngle arge rackng algorhm usng bnary sensor neworks Danal Aghajaran, Reza Berang Compuer Engneerng Deparmen, Iran Unversy of Scence and Technology,

More information

A 3D Model Retrieval System Using The Derivative Elevation And 3D-ART

A 3D Model Retrieval System Using The Derivative Elevation And 3D-ART 3 Model Rereal Sysem Usng he erae leaon nd 3-R Jau-Lng Shh* ng-yen Huang Yu-hen Wang eparmen of ompuer Scence and Informaon ngneerng hung Hua Unersy Hsnchu awan RO -mal: sjl@chueduw bsrac In recen years

More information

Spline. Computer Graphics. B-splines. B-Splines (for basis splines) Generating a curve. Basis Functions. Lecture 14 Curves and Surfaces II

Spline. Computer Graphics. B-splines. B-Splines (for basis splines) Generating a curve. Basis Functions. Lecture 14 Curves and Surfaces II Lecure 4 Curves and Surfaces II Splne A long flexble srps of meal used by drafspersons o lay ou he surfaces of arplanes, cars and shps Ducks weghs aached o he splnes were used o pull he splne n dfferen

More information

Both human traders and algorithmic

Both human traders and algorithmic Shuhao Chen s a Ph.D. canddae n sascs a Rugers Unversy n Pscaaway, NJ. bhmchen@sa.rugers.edu Rong Chen s a professor of Rugers Unversy n Pscaaway, NJ and Peng Unversy, n Bejng, Chna. rongchen@sa.rugers.edu

More information

Methodology of the CBOE S&P 500 PutWrite Index (PUT SM ) (with supplemental information regarding the CBOE S&P 500 PutWrite T-W Index (PWT SM ))

Methodology of the CBOE S&P 500 PutWrite Index (PUT SM ) (with supplemental information regarding the CBOE S&P 500 PutWrite T-W Index (PWT SM )) ehodology of he CBOE S&P 500 PuWre Index (PUT S ) (wh supplemenal nformaon regardng he CBOE S&P 500 PuWre T-W Index (PWT S )) The CBOE S&P 500 PuWre Index (cker symbol PUT ) racks he value of a passve

More information

Pedro M. Castro Iiro Harjunkoski Ignacio E. Grossmann. Lisbon, Portugal Ladenburg, Germany Pittsburgh, USA

Pedro M. Castro Iiro Harjunkoski Ignacio E. Grossmann. Lisbon, Portugal Ladenburg, Germany Pittsburgh, USA Pedro M. Casro Iro Harjunkosk Ignaco E. Grossmann Lsbon Porugal Ladenburg Germany Psburgh USA 1 Process operaons are ofen subjec o energy consrans Heang and coolng ules elecrcal power Avalably Prce Challengng

More information

Pocket3D Designing a 3D Scanner by means of a PDA 3D DIGITIZATION

Pocket3D Designing a 3D Scanner by means of a PDA 3D DIGITIZATION Pocke3D Desgnng a 3D Scanner by means of a PDA 3D DIGITIZATION Subjec: 3D Dgzaon Insrucor: Dr. Davd Fof Suden: AULINAS Josep GARCIA Frederc GIANCARDO Luca Posgraduae n: VIBOT MSc Table of conens 1. Inroducon...

More information

MORE ON TVM, "SIX FUNCTIONS OF A DOLLAR", FINANCIAL MECHANICS. Copyright 2004, S. Malpezzi

MORE ON TVM, SIX FUNCTIONS OF A DOLLAR, FINANCIAL MECHANICS. Copyright 2004, S. Malpezzi MORE ON VM, "SIX FUNCIONS OF A DOLLAR", FINANCIAL MECHANICS Copyrgh 2004, S. Malpezz I wan everyone o be very clear on boh he "rees" (our basc fnancal funcons) and he "fores" (he dea of he cash flow model).

More information

DEPARTMENT OF ECONOMETRICS AND BUSINESS STATISTICS. Exponential Smoothing for Inventory Control: Means and Variances of Lead-Time Demand

DEPARTMENT OF ECONOMETRICS AND BUSINESS STATISTICS. Exponential Smoothing for Inventory Control: Means and Variances of Lead-Time Demand ISSN 440-77X ISBN 0 736 094 X AUSTRALIA DEPARTMENT OF ECONOMETRICS AND BUSINESS STATISTICS Exponenal Smoohng for Invenory Conrol: Means and Varances of Lead-Tme Demand Ralph D. Snyder, Anne B. Koehler,

More information

Genetic Algorithm with Range Selection Mechanism for Dynamic Multiservice Load Balancing in Cloud-Based Multimedia System

Genetic Algorithm with Range Selection Mechanism for Dynamic Multiservice Load Balancing in Cloud-Based Multimedia System ISSN : 2347-8446 (Onlne) Inernaonal Journal of Advanced Research n Genec Algorhm wh Range Selecon Mechansm for Dynamc Mulservce Load Balancng n Cloud-Based Mulmeda Sysem I Mchael Sadgun Rao Kona, II K.Purushoama

More information

Linear methods for regression and classification with functional data

Linear methods for regression and classification with functional data Lnear mehods for regresson and classfcaon wh funconal daa Glber Sapora Chare de Sasue Appluée & CEDRIC Conservaore Naonal des Ars e Méers 9 rue San Marn, case 44 754 Pars cedex 3, France sapora@cnam.fr

More information

INTERNATIONAL JOURNAL OF STRATEGIC MANAGEMENT

INTERNATIONAL JOURNAL OF STRATEGIC MANAGEMENT IJSM, Volume, Number, 0 ISSN: 555-4 INTERNATIONAL JOURNAL OF STRATEGIC MANAGEMENT SPONSORED BY: Angelo Sae Unversy San Angelo, Texas, USA www.angelo.edu Managng Edors: Professor Alan S. Khade, Ph.D. Calforna

More information

Modeling state-related fmri activity using change-point theory

Modeling state-related fmri activity using change-point theory Modelng sae-relaed fmri acvy usng change-pon heory Marn A. Lndqus 1*, Chrsan Waugh and Tor D. Wager 3 1. Deparmen of Sascs, Columba Unversy, New York, NY, 1007. Deparmen of Psychology, Unversy of Mchgan,

More information

Boosting for Learning Multiple Classes with Imbalanced Class Distribution

Boosting for Learning Multiple Classes with Imbalanced Class Distribution Boosng for Learnng Mulple Classes wh Imbalanced Class Dsrbuon Yanmn Sun Deparmen of Elecrcal and Compuer Engneerng Unversy of Waerloo Waerloo, Onaro, Canada y8sun@engmal.uwaerloo.ca Mohamed S. Kamel Deparmen

More information

A Heuristic Solution Method to a Stochastic Vehicle Routing Problem

A Heuristic Solution Method to a Stochastic Vehicle Routing Problem A Heursc Soluon Mehod o a Sochasc Vehcle Roung Problem Lars M. Hvaum Unversy of Bergen, Bergen, Norway. larsmh@.ub.no Arne Løkkeangen Molde Unversy College, 6411 Molde, Norway. Arne.Lokkeangen@hmolde.no

More information

RESOLUTION OF THE LINEAR FRACTIONAL GOAL PROGRAMMING PROBLEM

RESOLUTION OF THE LINEAR FRACTIONAL GOAL PROGRAMMING PROBLEM Revsa Elecrónca de Comuncacones y Trabajos de ASEPUMA. Rec@ Volumen Págnas 7 a 40. RESOLUTION OF THE LINEAR FRACTIONAL GOAL PROGRAMMING PROBLEM RAFAEL CABALLERO rafael.caballero@uma.es Unversdad de Málaga

More information

PerfCenter: A Methodology and Tool for Performance Analysis of Application Hosting Centers

PerfCenter: A Methodology and Tool for Performance Analysis of Application Hosting Centers PerfCener: A Mehodology and Tool for Performance Analyss of Applcaon Hosng Ceners Rukma P. Verlekar, Varsha Ape, Prakhar Goyal, Bhavsh Aggarwal Dep. of Compuer Scence and Engneerng Indan Insue of Technology

More information

Attribution Strategies and Return on Keyword Investment in Paid Search Advertising

Attribution Strategies and Return on Keyword Investment in Paid Search Advertising Arbuon Sraeges and Reurn on Keyword Invesmen n Pad Search Adversng by Hongshuang (Alce) L, P. K. Kannan, Sva Vswanahan and Abhshek Pan * December 15, 2015 * Honshuang (Alce) L s Asssan Professor of Markeng,

More information

Estimating intrinsic currency values

Estimating intrinsic currency values Cung edge Foregn exchange Esmang nrnsc currency values Forex marke praconers consanly alk abou he srenghenng or weakenng of ndvdual currences. In hs arcle, Jan Chen and Paul Dous presen a new mehodology

More information

Cooperative Distributed Scheduling for Storage Devices in Microgrids using Dynamic KKT Multipliers and Consensus Networks

Cooperative Distributed Scheduling for Storage Devices in Microgrids using Dynamic KKT Multipliers and Consensus Networks Cooperave Dsrbued Schedulng for Sorage Devces n Mcrogrds usng Dynamc KK Mulplers and Consensus Newors Navd Rahbar-Asr Yuan Zhang Mo-Yuen Chow Deparmen of Elecrcal and Compuer Engneerng Norh Carolna Sae

More information

How Much Life Insurance is Enough?

How Much Life Insurance is Enough? How Much Lfe Insurance s Enough? Uly-Based pproach By LJ Rossouw BSTRCT The paper ams o nvesgae how much lfe nsurance proecon cover a uly maxmsng ndvdual should buy. Ths queson s relevan n he nsurance

More information

APPLICATION OF CHAOS THEORY TO ANALYSIS OF COMPUTER NETWORK TRAFFIC Liudvikas Kaklauskas, Leonidas Sakalauskas

APPLICATION OF CHAOS THEORY TO ANALYSIS OF COMPUTER NETWORK TRAFFIC Liudvikas Kaklauskas, Leonidas Sakalauskas The XIII Inernaonal Conference Appled Sochasc Models and Daa Analyss (ASMDA-2009) June 30-July 3 2009 Vlnus LITHUANIA ISBN 978-9955-28-463-5 L. Sakalauskas C. Skadas and E. K. Zavadskas (Eds.): ASMDA-2009

More information

MODEL-BASED APPROACH TO CHARACTERIZATION OF DIFFUSION PROCESSES VIA DISTRIBUTED CONTROL OF ACTUATED SENSOR NETWORKS

MODEL-BASED APPROACH TO CHARACTERIZATION OF DIFFUSION PROCESSES VIA DISTRIBUTED CONTROL OF ACTUATED SENSOR NETWORKS MODEL-BASED APPROACH TO CHARACTERIZATION OF DIFFUSION PROCESSES IA DISTRIBUTED CONTROL OF ACTUATED SENSOR NETWORKS Kevn L. Moore and YangQuan Chen Cener for Self-Organzng and Inellgen Sysems Uah Sae Unversy

More information

Anomaly Detection in Network Traffic Using Selected Methods of Time Series Analysis

Anomaly Detection in Network Traffic Using Selected Methods of Time Series Analysis I. J. Compuer Nework and Informaon Secury, 2015, 9, 10-18 Publshed Onlne Augus 2015 n MECS (hp://www.mecs-press.org/) DOI: 10.5815/jcns.2015.09.02 Anomaly Deecon n Nework Traffc Usng Seleced Mehods of

More information

Distributed Load Balancing in a Multiple Server System by Shift-Invariant Protocol Sequences

Distributed Load Balancing in a Multiple Server System by Shift-Invariant Protocol Sequences 03 IEEE Wreess Communcaons and Neorkng Conference (WCNC): NETWORS Dsrbued Load Baancng n a Mupe Server Sysem by Shf-Invaran rooco Sequences Yupeng Zhang and Wng Shng Wong Deparmen of Informaon Engneerng

More information

Scaling Up POMDPs for Dialog Management: The Summary POMDP Method. Jason D. Williams and Steve Young

Scaling Up POMDPs for Dialog Management: The Summary POMDP Method. Jason D. Williams and Steve Young Scalng Up POMDPs for Dalog Managemen: The Summary POMDP Mehod Jason D. Wllams and Seve Young Cambrdge Unversy Engneerng Deparmen Trumpngon Sree, Cambrdge CB2 1PZ, UK jdw30@cam.ac.uk sjy@eng.cam.ac.uk BSTRCT

More information

A Hybrid AANN-KPCA Approach to Sensor Data Validation

A Hybrid AANN-KPCA Approach to Sensor Data Validation Proceedngs of he 7h WSEAS Inernaonal Conference on Appled Informacs and Communcaons, Ahens, Greece, Augus 4-6, 7 85 A Hybrd AANN-KPCA Approach o Sensor Daa Valdaon REZA SHARIFI, REZA LANGARI Deparmen of

More information

A Common Neural Network Model for Unsupervised Exploratory Data Analysis and Independent Component Analysis

A Common Neural Network Model for Unsupervised Exploratory Data Analysis and Independent Component Analysis A Common Neural Nework Model for Unsupervsed Exploraory Daa Analyss and Independen Componen Analyss Keywords: Unsupervsed Learnng, Independen Componen Analyss, Daa Cluserng, Daa Vsualsaon, Blnd Source

More information

An Introductory Study on Time Series Modeling and Forecasting

An Introductory Study on Time Series Modeling and Forecasting An Inroducory Sudy on Tme Seres Modelng and Forecasng Ranadp Adhkar R. K. Agrawal ACKNOWLEDGEMENT The mely and successful compleon of he book could hardly be possble whou he helps and suppors from a lo

More information

Time Series. A thesis. Submitted to the. Edith Cowan University. Perth, Western Australia. David Sheung Chi Fung. In Fulfillment of the Requirements

Time Series. A thesis. Submitted to the. Edith Cowan University. Perth, Western Australia. David Sheung Chi Fung. In Fulfillment of the Requirements Mehods for he Esmaon of Mssng Values n Tme Seres A hess Submed o he Faculy of Communcaons, ealh and Scence Edh Cowan Unversy Perh, Wesern Ausrala By Davd Sheung Ch Fung In Fulfllmen of he Requremens For

More information

Temporal and Spatial Distributed Event Correlation for Network Security

Temporal and Spatial Distributed Event Correlation for Network Security Temoral and Saal Dsrbued Even Correlaon for Nework Secury Guofe Jang, Member, IEEE and George Cybenko, Fellow, IEEE Absrac - Comuer neworks roduce large amoun of evenbased daa ha can be colleced for nework

More information

Cost- and Energy-Aware Load Distribution Across Data Centers

Cost- and Energy-Aware Load Distribution Across Data Centers - and Energy-Aware Load Dsrbuon Across Daa Ceners Ken Le, Rcardo Banchn, Margare Maronos, and Thu D. Nguyen Rugers Unversy Prnceon Unversy Inroducon Today, many large organzaons operae mulple daa ceners.

More information

An Architecture to Support Distributed Data Mining Services in E-Commerce Environments

An Architecture to Support Distributed Data Mining Services in E-Commerce Environments An Archecure o Suppor Dsrbued Daa Mnng Servces n E-Commerce Envronmens S. Krshnaswamy 1, A. Zaslavsky 1, S.W. Loke 2 School of Compuer Scence & Sofware Engneerng, Monash Unversy 1 900 Dandenong Road, Caulfeld

More information

THE USE IN BANKS OF VALUE AT RISK METHOD IN MARKET RISK MANAGEMENT. Ioan TRENCA *

THE USE IN BANKS OF VALUE AT RISK METHOD IN MARKET RISK MANAGEMENT. Ioan TRENCA * ANALELE ŞTIINłIFICE ALE UNIVERSITĂłII ALEXANDRU IOAN CUZA DIN IAŞI Tomul LVI ŞnŃe Economce 009 THE USE IN BANKS OF VALUE AT RISK METHOD IN MARKET RISK MANAGEMENT Ioan TRENCA * Absrac In sophscaed marke

More information

A GENERALIZED FRAMEWORK FOR CREDIT RISK PORTFOLIO MODELS

A GENERALIZED FRAMEWORK FOR CREDIT RISK PORTFOLIO MODELS A GENERALIZED FRAMEWORK FOR CREDIT RISK PORTFOLIO MODELS H. UGUR KOYLUOGLU ANDREW HICKMAN Olver, Wyman & Company CSFP Capal, Inc. * 666 Ffh Avenue Eleven Madson Avenue New Yor, New Yor 10103 New Yor, New

More information

Template-Based Reconstruction of Surface Mesh Animation from Point Cloud Animation

Template-Based Reconstruction of Surface Mesh Animation from Point Cloud Animation Temlae-Based Reconsrucon of Surface Mesh Anmaon from Pon Cloud Anmaon Sang Il Park and Seong-Jae Lm In hs aer, we resen a mehod for reconsrucng a surface mesh anmaon sequence from on cloud anmaon daa.

More information

A Hybrid Method for Forecasting Stock Market Trend Using Soft-Thresholding De-noise Model and SVM

A Hybrid Method for Forecasting Stock Market Trend Using Soft-Thresholding De-noise Model and SVM A Hybrd Mehod for Forecasng Sock Marke Trend Usng Sof-Thresholdng De-nose Model and SVM Xueshen Su, Qnghua Hu, Daren Yu, Zongxa Xe, and Zhongyng Q Harbn Insue of Technology, Harbn 150001, Chna Suxueshen@Gmal.com

More information

HEURISTIC ALGORITHM FOR SINGLE RESOURCE CONSTRAINED PROJECT SCHEDULING PROBLEM BASED ON THE DYNAMIC PROGRAMMING

HEURISTIC ALGORITHM FOR SINGLE RESOURCE CONSTRAINED PROJECT SCHEDULING PROBLEM BASED ON THE DYNAMIC PROGRAMMING Yugoslav Journal o Operaons Research Volume 19 (2009) Number 2, 281-298 DOI:10.2298/YUJOR0902281S HEURISTIC ALGORITHM FOR SINGLE RESOURCE CONSTRAINED PROJECT SCHEDULING PROBLEM BASED ON THE DYNAMIC PROGRAMMING

More information

The Definition and Measurement of Productivity* Mark Rogers

The Definition and Measurement of Productivity* Mark Rogers The Defnon and Measuremen of Producvy* Mark Rogers Melbourne Insue of Appled Economc and Socal Research The Unversy of Melbourne Melbourne Insue Workng Paper No. 9/98 ISSN 1328-4991 ISBN 0 7325 0912 6

More information

The Virtual Machine Resource Allocation based on Service Features in Cloud Computing Environment

The Virtual Machine Resource Allocation based on Service Features in Cloud Computing Environment Send Orders for Reprns o reprns@benhamscence.ae The Open Cybernecs & Sysemcs Journal, 2015, 9, 639-647 639 Open Access The Vrual Machne Resource Allocaon based on Servce Feaures n Cloud Compung Envronmen

More information

CLoud computing has recently emerged as a new

CLoud computing has recently emerged as a new 1 A Framework of Prce Bddng Confguraons for Resource Usage n Cloud Compung Kenl L, Member, IEEE, Chubo Lu, Keqn L, Fellow, IEEE, and Alber Y. Zomaya, Fellow, IEEE Absrac In hs paper, we focus on prce bddng

More information

TECNICHE DI DIAGNOSI AUTOMATICA DEI GUASTI. Silvio Simani silvio.simani@unife.it. References

TECNICHE DI DIAGNOSI AUTOMATICA DEI GUASTI. Silvio Simani silvio.simani@unife.it. References TECNICHE DI DIAGNOSI AUTOMATICA DEI GUASTI Re Neural per l Idenfcazone d Ssem non Lnear e Paern Recognon slvo.sman@unfe. References Texbook suggesed: Neural Neworks for Idenfcaon, Predcon, and Conrol,

More information

Testing techniques and forecasting ability of FX Options Implied Risk Neutral Densities. Oren Tapiero

Testing techniques and forecasting ability of FX Options Implied Risk Neutral Densities. Oren Tapiero Tesng echnques and forecasng ably of FX Opons Impled Rsk Neural Denses Oren Tapero 1 Table of Conens Absrac 3 Inroducon 4 I. The Daa 7 1. Opon Selecon Crerons 7. Use of mpled spo raes nsead of quoed spo

More information

The Multi-shift Vehicle Routing Problem with Overtime

The Multi-shift Vehicle Routing Problem with Overtime The Mul-shf Vehcle Roung Problem wh Overme Yngao Ren, Maged Dessouy, and Fernando Ordóñez Danel J. Epsen Deparmen of Indusral and Sysems Engneerng Unversy of Souhern Calforna 3715 McClnoc Ave, Los Angeles,

More information

A Model for Time Series Analysis

A Model for Time Series Analysis Aled Mahemaal Senes, Vol. 6, 0, no. 5, 5735-5748 A Model for Tme Seres Analyss me A. H. Poo Sunway Unversy Busness Shool Sunway Unversy Bandar Sunway, Malaysa ahhn@sunway.edu.my Absra Consder a me seres

More information

Network Effects on Standard Software Markets: A Simulation Model to examine Pricing Strategies

Network Effects on Standard Software Markets: A Simulation Model to examine Pricing Strategies Nework Effecs on Sandard Sofware Markes Page Nework Effecs on Sandard Sofware Markes: A Smulaon Model o examne Prcng Sraeges Peer Buxmann Absrac Ths paper examnes sraeges of sandard sofware vendors, n

More information

Y2K* Stephanie Schmitt-Grohé. Rutgers Uni ersity, 75 Hamilton Street, New Brunswick, New Jersey 08901 E-mail: grohe@econ.rutgers.edu.

Y2K* Stephanie Schmitt-Grohé. Rutgers Uni ersity, 75 Hamilton Street, New Brunswick, New Jersey 08901 E-mail: grohe@econ.rutgers.edu. Revew of Economc Dynamcs 2, 850856 Ž 1999. Arcle ID redy.1999.0065, avalable onlne a hp:www.dealbrary.com on Y2K* Sephane Schm-Grohé Rugers Unersy, 75 Hamlon Sree, New Brunswc, New Jersey 08901 E-mal:

More information

Human Crowd Behavior Analysis Based On Graph Modeling and Matching In Synoptic Video

Human Crowd Behavior Analysis Based On Graph Modeling and Matching In Synoptic Video ISSN (Onlne) : 2319-8753 ISSN (Prn) : 2347-6710 Inernaonal Journal of Innovave Research n Scence, Engneerng and Technology Volume 3, Specal Issue 3, March 2014 2014 Inernaonal Conference on Innovaons n

More information

Market-Clearing Electricity Prices and Energy Uplift

Market-Clearing Electricity Prices and Energy Uplift Marke-Clearng Elecrcy Prces and Energy Uplf Paul R. Grbk, Wllam W. Hogan, and Susan L. Pope December 31, 2007 Elecrcy marke models requre energy prces for balancng, spo and shor-erm forward ransacons.

More information

Analyzing Energy Use with Decomposition Methods

Analyzing Energy Use with Decomposition Methods nalyzng nergy Use wh Decomposon Mehods eve HNN nergy Technology Polcy Dvson eve.henen@ea.org nergy Tranng Week Pars 1 h prl 213 OCD/ 213 Dscusson nergy consumpon and energy effcency? How can energy consumpon

More information

Working Paper Tracking the new economy: Using growth theory to detect changes in trend productivity

Working Paper Tracking the new economy: Using growth theory to detect changes in trend productivity econsor www.econsor.eu Der Open-Access-Publkaonsserver der ZBW Lebnz-Informaonszenrum Wrschaf The Open Access Publcaon erver of he ZBW Lebnz Informaon Cenre for Economcs Kahn James A.; Rch Rober Workng

More information

The Prediction Algorithm Based on Fuzzy Logic Using Time Series Data Mining Method

The Prediction Algorithm Based on Fuzzy Logic Using Time Series Data Mining Method The Predcon Algorhm Based on Fuzzy Logc Usng Tme Seres Daa Mnng Mehod I Aydn, M Karakose, and E Akn Asrac Predcon of an even a a me seres s que mporan for engneerng and economy prolems Tme seres daa mnng

More information

CONTROLLER PERFORMANCE MONITORING AND DIAGNOSIS. INDUSTRIAL PERSPECTIVE

CONTROLLER PERFORMANCE MONITORING AND DIAGNOSIS. INDUSTRIAL PERSPECTIVE Copyrgh IFAC 5h Trennal World Congress, Barcelona, Span CONTROLLER PERFORMANCE MONITORING AND DIAGNOSIS. INDUSTRIAL PERSPECTIVE Derrck J. Kozub Shell Global Soluons USA Inc. Weshollow Technology Cener,

More information

Proceedings of the 2008 Winter Simulation Conference S. J. Mason, R. R. Hill, L. Mönch, O. Rose, T. Jefferson, J. W. Fowler eds.

Proceedings of the 2008 Winter Simulation Conference S. J. Mason, R. R. Hill, L. Mönch, O. Rose, T. Jefferson, J. W. Fowler eds. Proceedngs of he 008 Wner Smulaon Conference S. J. Mason, R. R. Hll, L. Mönch, O. Rose, T. Jefferson, J. W. Fowler eds. DEMAND FORECAST OF SEMICONDUCTOR PRODUCTS BASED ON TECHNOLOGY DIFFUSION Chen-Fu Chen,

More information

Optimization of Nurse Scheduling Problem with a Two-Stage Mathematical Programming Model

Optimization of Nurse Scheduling Problem with a Two-Stage Mathematical Programming Model Asa Pacfc Managemen Revew 15(4) (2010) 503-516 Opmzaon of Nurse Schedulng Problem wh a Two-Sage Mahemacal Programmng Model Chang-Chun Tsa a,*, Cheng-Jung Lee b a Deparmen of Busness Admnsraon, Trans World

More information

Applying the Theta Model to Short-Term Forecasts in Monthly Time Series

Applying the Theta Model to Short-Term Forecasts in Monthly Time Series Applyng he Thea Model o Shor-Term Forecass n Monhly Tme Seres Glson Adamczuk Olvera *, Marcelo Gonçalves Trenn +, Anselmo Chaves Neo ** * Deparmen of Mechancal Engneerng, Federal Technologcal Unversy of

More information

Modelling Operational Risk in Financial Institutions using Hybrid Dynamic Bayesian Networks. Authors:

Modelling Operational Risk in Financial Institutions using Hybrid Dynamic Bayesian Networks. Authors: Modellng Operaonal Rsk n Fnancal Insuons usng Hybrd Dynamc Bayesan Neworks Auhors: Professor Marn Nel Deparmen of Compuer Scence, Queen Mary Unversy of London, Mle nd Road, London, 1 4NS, Uned Kngdom Phone:

More information

Evaluation of the Stochastic Modelling on Options

Evaluation of the Stochastic Modelling on Options Zhjuan Mao, Zhan Lang, Jnguo Lan, Hongkun Zhang / Inernaonal Journal of Engneerng Research and Applcaons (IJERA) ISSN: 48-96 www.jera.com Vol., Issue 3, May-Jun 0, pp.463-473 Evaluaon of he Sochasc Modellng

More information

DESIGN OF OPTIMAL BONUS-MALUS SYSTEMS WITH A FREQUENCY AND A SEVERITY COMPONENT ON AN INDIVIDUAL BASIS IN AUTOMOBILE INSURANCE ABSTRACT KEYWORDS

DESIGN OF OPTIMAL BONUS-MALUS SYSTEMS WITH A FREQUENCY AND A SEVERITY COMPONENT ON AN INDIVIDUAL BASIS IN AUTOMOBILE INSURANCE ABSTRACT KEYWORDS DESIGN OF OPTIMAL BONUS-MALUS SYSTEMS WITH A FREQUENCY AND A SEVERITY COMPONENT ON AN INDIVIDUAL BASIS IN AUTOMOBILE INSURANCE BY NICHOLAS E. FRANGOS* AND SPYRIDON D. VRONTOS* ABSTRACT The maory of opmal

More information

Efficiency of General Insurance in Malaysia Using Stochastic Frontier Analysis (SFA)

Efficiency of General Insurance in Malaysia Using Stochastic Frontier Analysis (SFA) Inernaonal Journal of Modern Engneerng Research (IJMER) www.jmer.com Vol., Issue.5, Sep-Oc. 01 pp-3886-3890 ISSN: 49-6645 Effcency of General Insurance n Malaysa Usng Sochasc Froner Analyss (SFA) Mohamad

More information

Finance and Economics Discussion Series Divisions of Research & Statistics and Monetary Affairs Federal Reserve Board, Washington, D.C.

Finance and Economics Discussion Series Divisions of Research & Statistics and Monetary Affairs Federal Reserve Board, Washington, D.C. Fnance and Economcs Dscusson Seres Dvsons of Research & Sascs and Moneary Affars Federal Reserve Board, Washngon, D.C. Prcng Counerpary Rs a he Trade Level and CVA Allocaons Mchael Pyhn and Dan Rosen 200-0

More information

A binary powering Schur algorithm for computing primary matrix roots

A binary powering Schur algorithm for computing primary matrix roots Numercal Algorhms manuscr No. (wll be nsered by he edor) A bnary owerng Schur algorhm for comung rmary marx roos Federco Greco Bruno Iannazzo Receved: dae / Acceed: dae Absrac An algorhm for comung rmary

More information

An Ensemble Data Mining and FLANN Combining Short-term Load Forecasting System for Abnormal Days

An Ensemble Data Mining and FLANN Combining Short-term Load Forecasting System for Abnormal Days JOURNAL OF SOFTWARE, VOL. 6, NO. 6, JUNE 0 96 An Ensemble Daa Mnng and FLANN Combnng Shor-erm Load Forecasng Sysem for Abnormal Days Mng L College of Auomaon, Guangdong Unversy of Technology, Guangzhou,

More information

Revision: June 12, 2010 215 E Main Suite D Pullman, WA 99163 (509) 334 6306 Voice and Fax

Revision: June 12, 2010 215 E Main Suite D Pullman, WA 99163 (509) 334 6306 Voice and Fax .3: Inucors Reson: June, 5 E Man Sue D Pullman, WA 9963 59 334 636 Voce an Fax Oerew We connue our suy of energy sorage elemens wh a scusson of nucors. Inucors, lke ressors an capacors, are passe wo-ermnal

More information

SPC-based Inventory Control Policy to Improve Supply Chain Dynamics

SPC-based Inventory Control Policy to Improve Supply Chain Dynamics Francesco Cosanno e al. / Inernaonal Journal of Engneerng and Technology (IJET) SPC-based Invenory Conrol Polcy o Improve Supply Chan ynamcs Francesco Cosanno #, Gulo Gravo #, Ahmed Shaban #3,*, Massmo

More information

t φρ ls l ), l = o, w, g,

t φρ ls l ), l = o, w, g, Reservor Smulaon Lecure noe 6 Page 1 of 12 OIL-WATER SIMULATION - IMPES SOLUTION We have prevously lsed he mulphase flow equaons for one-dmensonal, horzonal flow n a layer of consan cross seconal area

More information

A New Approach to Linear Filtering and Prediction Problems 1

A New Approach to Linear Filtering and Prediction Problems 1 R. E. KALMAN Research Insue for Advanced Sudy, Balmore, Md. A New Approach o Lnear Flerng and Predcon Problems The classcal flerng and predcon problem s re-examned usng he Bode- Shannon represenaon of

More information

Lecture 40 Induction. Review Inductors Self-induction RL circuits Energy stored in a Magnetic Field

Lecture 40 Induction. Review Inductors Self-induction RL circuits Energy stored in a Magnetic Field ecure 4 nducon evew nducors Self-nducon crcus nergy sored n a Magnec Feld 1 evew nducon end nergy Transfers mf Bv Mechancal energy ransform n elecrc and hen n hermal energy P Fv B v evew eformulaon of

More information

Nonlinearity or Structural Break? - Data Mining in Evolving Financial Data Sets from a Bayesian Model Combination Perspective

Nonlinearity or Structural Break? - Data Mining in Evolving Financial Data Sets from a Bayesian Model Combination Perspective Proceedngs of he 38h Hawa Inernaonal Conference on Sysem Scences - 005 Nonlneary or Srucural Break? - Daa Mnng n Evolvng Fnancal Daa Ses from a Bayesan Model Combnaon Perspecve Hao Davd Zhou Managemen

More information

MULTI-WORKDAY ERGONOMIC WORKFORCE SCHEDULING WITH DAYS OFF

MULTI-WORKDAY ERGONOMIC WORKFORCE SCHEDULING WITH DAYS OFF Proceedngs of he 4h Inernaonal Conference on Engneerng, Projec, and Producon Managemen (EPPM 203) MULTI-WORKDAY ERGONOMIC WORKFORCE SCHEDULING WITH DAYS OFF Tar Raanamanee and Suebsak Nanhavanj School

More information

Prot sharing: a stochastic control approach.

Prot sharing: a stochastic control approach. Pro sharng: a sochasc conrol approach. Donaen Hanau Aprl 2, 2009 ESC Rennes. 35065 Rennes, France. Absrac A majory of lfe nsurance conracs encompass a guaraneed neres rae and a parcpaon o earnngs of he

More information

The Feedback from Stock Prices to Credit Spreads

The Feedback from Stock Prices to Credit Spreads Appled Fnance Projec Ka Fa Law (Keh) The Feedback from Sock Prces o Cred Spreads Maser n Fnancal Engneerng Program BA 3N Appled Fnance Projec Ka Fa Law (Keh) Appled Fnance Projec Ka Fa Law (Keh). Inroducon

More information

A robust optimisation approach to project scheduling and resource allocation. Elodie Adida* and Pradnya Joshi

A robust optimisation approach to project scheduling and resource allocation. Elodie Adida* and Pradnya Joshi In. J. Servces Operaons and Informacs, Vol. 4, No. 2, 2009 169 A robus opmsaon approach o projec schedulng and resource allocaon Elode Adda* and Pradnya Josh Deparmen of Mechancal and Indusral Engneerng,

More information

Partial Fingerprint Matching

Partial Fingerprint Matching Paral Fngerprn Machng Tsa-Yang Jea, Vraj S. Chavan, John K. Schneder and Venu Govndaraju Sae Unversy of New York a Buffalo Amhers, New York 14228, USA jea@cedar.buffalo.edu ABSTRACT Fngerprn denfcaon s

More information

How To Understand The Theory Of The Power Of The Market

How To Understand The Theory Of The Power Of The Market Sysem Dynamcs models for generaon expanson plannng n a compeve framework: olgopoly and marke power represenaon J.J. Sánchez, J. Barquín, E. Ceneno, A. López-Peña Insuo de Invesgacón Tecnológca Unversdad

More information

Nonparametric deconvolution of hormone time-series: A state-space approach *

Nonparametric deconvolution of hormone time-series: A state-space approach * onparamerc deconvoluon of hormone me-seres: A sae-space approach * Guseppe De colao, Gancarlo Ferrar recae, Marco Franzos Dparmeno d Informaca e Ssemsca Unversà degl Sud d Pava Va Ferraa 7 Pava (Ialy el:

More information

Index Mathematics Methodology

Index Mathematics Methodology Index Mahemacs Mehodology S&P Dow Jones Indces: Index Mehodology Ocober 2015 Table of Conens Inroducon 4 Dfferen Varees of Indces 4 The Index Dvsor 5 Capalzaon Weghed Indces 6 Defnon 6 Adjusmens o Share

More information

Event Based Project Scheduling Using Optimized Ant Colony Algorithm Vidya Sagar Ponnam #1, Dr.N.Geethanjali #2

Event Based Project Scheduling Using Optimized Ant Colony Algorithm Vidya Sagar Ponnam #1, Dr.N.Geethanjali #2 Inernaonal Journal of Compuer Trends and Technology (IJCTT) Volume 18 Number 6 Dec 2014 Even Based Projec Schedulng Usng Opmzed An Colony Algorhm Vdya Sagar Ponnam #1, Dr.N.Geehanjal #2 1 Research Scholar,

More information

Temi di Discussione. Modelling Italian potential output and the output gap. (Working Papers) September 2010

Temi di Discussione. Modelling Italian potential output and the output gap. (Working Papers) September 2010 Tem d Dscussone (Workng Papers) Modellng Ialan poenal oupu and he oupu gap by Anono Bassane, Mchele Cavano and Albero Locarno Sepember 2010 Number 771 Tem d dscussone (Workng papers) Modellng Ialan poenal

More information

Social security, education, retirement and growth*

Social security, education, retirement and growth* Hacenda P úblca Espa ñola / Revsa de Econom ía P úblca, 198-(3/2011): 9-36 2011, Insuo de Esudos Fscales Socal secury, educaon, reremen and growh* CRUZ A. ECHEVARR ÍA AMAIA IZA** Unversdad del Pa ís Vasco

More information

FOREIGN AID AND ECONOMIC GROWTH: NEW EVIDENCE FROM PANEL COINTEGRATION

FOREIGN AID AND ECONOMIC GROWTH: NEW EVIDENCE FROM PANEL COINTEGRATION JOURAL OF ECOOMIC DEVELOPME 7 Volume 30, umber, June 005 FOREIG AID AD ECOOMIC GROWH: EW EVIDECE FROM PAEL COIEGRAIO ABDULASSER HAEMI-J AD MAUCHEHR IRADOUS * Unversy of Skövde and Unversy of Örebro he

More information

Currency Exchange Rate Forecasting from News Headlines

Currency Exchange Rate Forecasting from News Headlines Currency Exchange Rae Forecasng from News Headlnes Desh Peramunelleke Raymond K. Wong School of Compuer Scence & Engneerng Unversy of New Souh Wales Sydney, NSW 2052, Ausrala deshp@cse.unsw.edu.au wong@cse.unsw.edu.au

More information

A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting*

A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting* journal of compuer and sysem scences 55, 119139 (1997) arcle no. SS971504 A Decson-heorec Generalzaon of On-Lne Learnng and an Applcaon o Boosng* Yoav Freund and Rober E. Schapre - A6 Labs, 180 Park Avenue,

More information

THE IMPACT OF QUICK RESPONSE IN INVENTORY-BASED COMPETITION

THE IMPACT OF QUICK RESPONSE IN INVENTORY-BASED COMPETITION Workng Paper WP no 722 November, 2007 THE IMPACT OF QUICK RESPONSE IN INVENTORY-BASED COMPETITION Felpe Caro Vícor Marínez de Albénz 2 Professor, UCLA Anderson School of Managemen 2 Professor, Operaons

More information

GUIDANCE STATEMENT ON CALCULATION METHODOLOGY

GUIDANCE STATEMENT ON CALCULATION METHODOLOGY GUIDANCE STATEMENT ON CALCULATION METHODOLOGY Adopon Dae: 9/28/0 Effecve Dae: //20 Reroacve Applcaon: No Requred www.gpssandards.org 204 CFA Insue Gudance Saemen on Calculaon Mehodology GIPS GUIDANCE STATEMENT

More information

Best estimate calculations of saving contracts by closed formulas Application to the ORSA

Best estimate calculations of saving contracts by closed formulas Application to the ORSA Bes esmae calculaons of savng conracs by closed formulas Applcaon o he ORSA - Franços BONNIN (Ala) - Frédérc LANCHE (Unversé Lyon 1, Laboraore SAF) - Marc JUILLARD (Wner & Assocés) 01.5 (verson modfée

More information

Case Study on Web Service Composition Based on Multi-Agent System

Case Study on Web Service Composition Based on Multi-Agent System 900 JOURNAL OF SOFTWARE, VOL. 8, NO. 4, APRIL 2013 Case Sudy on Web Servce Composon Based on Mul-Agen Sysem Shanlang Pan Deparmen of Compuer Scence and Technology, Nngbo Unversy, Chna PanShanLang@gmal.com

More information

Return Persistence, Risk Dynamics and Momentum Exposures of Equity and Bond Mutual Funds

Return Persistence, Risk Dynamics and Momentum Exposures of Equity and Bond Mutual Funds Reurn Perssence, Rsk Dynamcs and Momenum Exposures of Equy and Bond Muual Funds Joop Hu, Marn Marens, and Therry Pos Ths Verson: 22-2-2008 Absrac To analyze perssence n muual fund performance, s common

More information

THE IMPACT OF UNSECURED DEBT ON FINANCIAL DISTRESS AMONG BRITISH HOUSEHOLDS. Ana del Río and Garry Young. Documentos de Trabajo N.

THE IMPACT OF UNSECURED DEBT ON FINANCIAL DISTRESS AMONG BRITISH HOUSEHOLDS. Ana del Río and Garry Young. Documentos de Trabajo N. THE IMPACT OF UNSECURED DEBT ON FINANCIAL DISTRESS AMONG BRITISH HOUSEHOLDS 2005 Ana del Río and Garry Young Documenos de Trabajo N.º 0512 THE IMPACT OF UNSECURED DEBT ON FINANCIAL DISTRESS AMONG BRITISH

More information

SHIPPING ECONOMIC ANALYSIS FOR ULTRA LARGE CONTAINERSHIP

SHIPPING ECONOMIC ANALYSIS FOR ULTRA LARGE CONTAINERSHIP Journal of he Easern Asa Socey for Transporaon Sudes, Vol. 6, pp. 936-951, 2005 SHIPPING ECONOMIC ANALYSIS FOR ULTRA LARGE CONTAINERSHIP Chaug-Ing HSU Professor Deparen of Transporaon Technology and Manageen

More information

The Joint Cross Section of Stocks and Options *

The Joint Cross Section of Stocks and Options * The Jon Cross Secon of Socks and Opons * Andrew Ang Columba Unversy and NBER Turan G. Bal Baruch College, CUNY Nusre Cakc Fordham Unversy Ths Verson: 1 March 2010 Keywords: mpled volaly, rsk premums, reurn

More information

Omar Shatnawi. Eks p l o a t a c j a i Ni e z a w o d n o s c Ma in t e n a n c e a n d Reliability Vo l.16, No. 4, 2014 585. 1.

Omar Shatnawi. Eks p l o a t a c j a i Ni e z a w o d n o s c Ma in t e n a n c e a n d Reliability Vo l.16, No. 4, 2014 585. 1. Arcle caon nfo: Shanaw O. Measurng commercal sofware operaonal relably: an nerdscplnary modellng approach. Esploaacja Nezawodnosc Manenance and Relably 014; 16 (4): 585 594. Omar Shanaw Measurng commercal

More information