OPTIMIZATION OF FUZZY RULE BASES USING CONTINUOUS ANT COLONY SYSTEM

Size: px
Start display at page:

Download "OPTIMIZATION OF FUZZY RULE BASES USING CONTINUOUS ANT COLONY SYSTEM"

Transcription

1 Proceedng of the Frst Internatonal Conference on Modelng, Smulaton and Appled Optmzaton, Sharah, U.A.E. February -3, 005 OPTIMIZATION OF FUZZY RULE BASES USING CONTINUOUS ANT COLONY SYSTEM Had Nobahar Sharf Unversty of Technology Department of Aerospace Engneerng P.O.Box , Tehran, Iran. Sed H. Pourtadoust Sharf Unversty of Technology Department of Aerospace Engneerng P.O.Box , Tehran, Iran ABSTRACT The well-nown Ant Colony Optmzaton method s appled to the problem of tunng the parameters of a Taag-Sugeno fuzzy rule base. The latest developed Contnuous Ant Colony System algorthm s used to fnd the global soluton of the contnuous optmzaton problem. The method s systematcally tested for the approxmaton of one analytcal test functon and the performance of the proposed scheme s compared wth the Standard Genetc Algorthm.. INTRODUCTION The concept of Fuzzy Logc (FL) was proposed by Professor Lotf Zadeh n 965, at frst as a way of processng data by allowng partal set membershp rather than crsp membershp. Soon after, t was proven to be an excellent choce for many control system applcatons snce t mmcs human control logc. Today, fuzzy rule bases are wdely used to express the nowledge of operators or experts n varous domans such as decson, control, modelng, dentfcaton and so on [,]. However there are some lmtatons to ther development, the most mportant of whch s: the nowledge does not always completely exst and the manual tunng of all the base parameters taes tme. The lac of portablty of the rule bases when the dmensons of the control system change, maes the later dffculty stll more serous. To coop wth these problems, the learnng methods have been ntroduced. The frst attempt was made by Procy and Mamdan n 979, wth a "self tunng controller" [3]. The gradent descent method was used by Taag and Sugeno n 985 as a learnng tool for fuzzy modelng and dentfcaton [4]. It was used by Nomura, et al. n 99 as a self tunng method for fuzzy control [5]. The gradent descent method s approprate for smple problems and real tme learnng, snce t s fast. But t may be trapped nto local mnma. Also the calculaton of the gradents depends on the shape of membershp functons employed, the operators used for fuzzy nferences as well as the selected cost functon. So, there s a need for more general and flexble methods capable to search wthn wde soluton spaces and ntellgent enough to avod local mnma. These methods must not be lned to a gven type of applcaton and they must be applcable to several types of fuzzy rule bases and cost functons. In 998, Sarry and Guely appled the well-nown Genetc Algorthm to the problem of tunng the parameters of a Taag- Sugeno fuzzy rule base [6]. In ths artcle, we have ntegrated ths parametrc learnng problem wth our latest developed Contnuous Ant Colony System (CACS) [7], whch s based on the well-nown Ant Colony Optmzaton (ACO) [8,9]. ACO has been nspred from the ants' pheromone tral followng behavor. It can fnd the global mnmum of the problem to optmze, and t can handle any cost functon.. THE TAKAGI-SUGENO FUZZY RULE BASE Taag-Sugeno (TS) rules dffer from Mamdan rules n that ther outputs are not defned by membershp functons but by nonfuzzy analytcal functons (usually constants). Ths feature should permt to express complcated nowledge wth small number of rules. Unfortunately, TS rules are less ntutve and t s more dffcult to translate human expertse nto such rules as compared wth Mamdan rules. Therefore TS rules have been mostly used tll now for modelng purposes and buldng adaptve controllers [6]. Ther wder applcaton s becomng more common, as effectve learnng technques are devsed. In ths paper, a Taag-Sugeno fuzzy rule base was used to approxmate an m nputs analytcal functon f(x). The rule base has m nputs, one output, and s composed of n rules. The output of the fuzzy rule base s denoted by y(x). Each rule R can be wrtten as R : f ( x s g ) and...( x then y = f ( x,..., x ) m s g ) and...( x m s g where x s the -th nput, g the membershp functon of the -th rule defned on x, the output of rule R s y, and analytcal functon of the output defned for the -th rule. m ) f s the ICMSA0/05-

2 Proceedng of the Frst Internatonal Conference on Modelng, Smulaton and Appled Optmzaton, Sharah, U.A.E. February -3, 005 In ths paper, rulesr wth constant outputs w are consdered, so that y = w. But the method s applcable to other types of output functons as well. Fgure. Trangular symmetrc membershp functon The membershp functons g are defned as follows (normed trangular symmetrc, shown n Fg. ): x g = 0 a / b f x a otherwse The and operator s the multplcaton, so that µ = =, m b () g ( x ) () where µ s the actvaton degree of the rule R. The output of the rule base s calculated usng the center of gravty operator: µ w =, n f µ y x = = n 0 ( ), µ =, n 0 otherwse Let us defne the quadratc error E: E = p samp ( y( x p ) f ( x p )) p= where x p s the p-th tranng sample and p samp s the number of samples. The purpose of learnng s to mnmze the quadratc error E. mnmzaton of E s performed by tunng the a, b and w parameters. Optmzng the membershp functon parameters s a complex problem for the followng reasons:. The cost functon s not dervable everywhere.. µ b a g ( x ) the cost functon s not contnuous everywhere (the case when membershp functons do not overlap).. numerous parameters have to be optmzed (for the case consdered n ths paper, there s 60 parameter to optmze) x (3) (4) 3. ANT COLONY OPTIMIZATION Ant algorthms were nspred by the observaton of the real ant colones. An mportant and nterestng behavor of ant colones s ther foragng behavor, and n partcular, how ants can fnd the shortest path wthout usng vsual cues. Whle walng from the food sources to the nest and vce versa, ants depost on the ground a chemcal substance called pheromone whch maes a pheromone tral. Ants use pheromone trals as a medum to communcate wth each other. They can smell pheromone and when they choose ther way, they tend to choose paths wth more pheromone. The pheromone tral allows the ants to fnd ther way bac to the food source or to the nest. Also, the other ants can use t to fnd the locaton of the food sources, whch are prevously found by ther nest mates. Ths pheromone tral followng behavor can converge to the shortest path, once employed by a colony of ants. It means that, when there are more paths from the nest to a food source, a colony of ants may be able to use the pheromone trals left by the ndvdual ants to dscover the shortest path from the nest to the food source and bac. Consder two dfferent paths from the nest to the food source wth dfferent lengths. Intally there s no pheromone on the two branches, so ants select them wth the same probablty. Snce the ants move at approxmately constant speed, at each nstant of tme the number of ants who have passed the shorter path s greater than the number of ants who have not. Therefore when the ants start ther return trp, more pheromone s present on the shorter path, ncreasng the probablty of choosng t. Returnng the ants through the shorter path refreshes t faster than the other one and compensates the pheromone evaporaton. Thus n ths way pheromone s accumulated on the shorter path and for the new ants who want to go to the food source, the probablty of choosng t, wll ncrease. Very soon all the ants wll be usng the shorter path. 3.. Ant Colony System Basc Features Ant Colony System (ACS) was one of the frst algorthms proposed based on ACO. It was a dscrete algorthm, and at frst t was appled to the well-nown Travelng Salesman Problem (TSP) [8], whch s a dscrete optmzaton problem. In ths part we wll shortly revew the basc dea of ACS. Then n the subsequent part, the contnuous verson of ACS wll be presented. Consder a set of ctes. TSP s defned as the problem of fndng a mnmal cost closed tour that vsts all ctes and each cty only once. In a graph representaton, the ctes are the nodes and the connecton lnes between them are the edges. Each edge s assocated wth a cost measure, whch determnes the dstance or cost of travel between two ctes. Ant colony system uses a graph representaton, whch s the same as that defned for TSP. In addton to the cost measure, each edge has also a desrablty measure, called pheromone ntensty, updated at run tme by the ants. ICMSA0/05-

3 Proceedng of the Frst Internatonal Conference on Modelng, Smulaton and Appled Optmzaton, Sharah, U.A.E. February -3, 005 Ant colony system wors as follows: Each ant generates a complete tour by choosng the ctes accordng to a probablstc state transton rule. Ants prefer to move to ctes, whch are connected by short edges wth a hgh amount of pheromone, whle n some nstances, ther selecton may be random. Every tme an ant n one cty has to choose another cty to move to, t samples a random number, q n [0,]. If q becomes less than a gven q 0, then the destnaton cty s chosen by explotaton. It means that the one connected by the edge wth the most rato of pheromone ntensty to dstance, s chosen. Otherwse a cty s chosen by exploraton. In ths case the one connected by the edge wth the most rato of pheromone ntensty to dstance, has the most chance to be chosen, but all other ctes have also ther chances to be chosen proportonal to ther rato of pheromone ntensty to dstance. Whle constructng a tour, ants also modfy the amount of pheromone on the vsted edges by applyng a local updatng rule. It concurrently smulates the evaporaton of the prevous pheromone and the accumulaton of the new pheromone deposted by the ants when they are buldng ther solutons. Once all the ants have completed ther tours, the amount of pheromone s modfed agan, by applyng a global updatng rule. Agan a part of pheromone evaporates and all edges that belong to the globally best tour, receve addtonal pheromone conversely proportonal to ther length. 3.. Contnuous Ant Colony System Algorthm A contnuous optmzaton problem s defned as the problem of fndng the absolute mnmum of a postve non-zero contnuous cost functon f(x), wthn a gven nterval [a,b], whch the mnmum occurs at a pont x s. In general f can be a mult-varable functon, defned on a subset of a, b ], =,..., n. [ n R delmted by n ntervals The latest developed Contnuous Ant Colony System (CACS) has all the maor characterstcs of ACS, but certanly n a contnuous frame. These are a pheromone dstrbuton over the search space whch models the desrablty of dfferent regons for the ants, a state transton rule wth both exploraton and explotaton strateges, and a pheromone updatng rule whch concurrently smulates pheromone accumulaton and pheromone evaporaton Contnuous Pheromone Model Although pheromone dstrbuton has been frst modeled over dscrete sets, le the edges of the travelng salesman problem, n the case of real ants, pheromone deposton occurs over a contnuous space. Consder a food source, whch s surrounded by several ants. The ants aggregaton around the food source causes the most pheromone ntensty to occur at the food source poston. Then ncreasng the dstance of a sample pont from the food source wll decrease ts pheromone ntensty. CACS models ths varaton of pheromone ntensty, n the form of a normal dstrbuton functon: ( x xmn ) σ τ( x ) = e (5) Where x mn s the best pont n the nterval [a,b] whch has been found from the begnnng of the tral and σ can be nterpreted as an ndex of the ants aggregaton around the current mnmum. Note that τ has been modeled as a Probablty Dstrbuton Functon (PDF) whch determnes the probablty of choosng each pont x wthn the nterval [a,b] State Transton Rule In CACS, pheromone ntensty s modeled usng a normal PDF, the center of whch s the last best global soluton and ts varance depends on the aggregaton of the promsng areas around the best one. So t contans explotaton behavor. In the other hand, a normal PDF permts all ponts of the search space to be chosen, ether close to or far from the current soluton. So t also contans exploraton behavor. It means that ants can use a random generator wth a normal PDF as the state transton rule to choose the next pont to move to Pheromone Update Ants choose ther destnatons through the probablstc strategy of equaton (5). At the frst teraton, there sn't any nowledge about the mnmum pont and the ants choose ther destnatons only by exploraton. It means that they must use a hgh value of σ (assocated wth an arbtrary x ) to approxmately model a unform dstrbuton postons. Durng each teraton, pheromone dstrbuton over the search space wll be updated usng the acqured nowledge of the evaluated ponts by the ants. Ths process gradually ncreases the explotaton behavor of the algorthm, whle ts exploraton behavor wll decrease. Pheromone updatng can be stated as follows: The value of obectve functon s evaluated for the new selected ponts by the ants. Then, the best pont found from the begnnng of the tral s assgned to x. Also the value of σ s updated based on the evaluated ponts durng the last teraton and the aggregaton of those ponts around x. To satsfy smultaneously the ftness and aggregaton crtera, a concept of weghted varance s defned as follows: ( x xmn ) = f f mn (6) σ =, for all n whch f f mn f f = mn where s the number of ants. Ths strategy means that the center of regon dscovered durng the subsequent teraton s the last best pont and the narrowness of ts wdth s dependent on the aggregaton of the other compettors around the best one. The closer the better solutons get (durng the last teraton) to the best one, the smaller σ s assgned to the next teraton. Durng each teraton, the heght of pheromone dstrbuton functon ncreases wth respect to the prevous teraton and ts narrowness decreases. So ths strategy concurrently smulates pheromone accumulaton over the promsng regons and mn mn mn ICMSA0/05-3

4 Proceedng of the Frst Internatonal Conference on Modelng, Smulaton and Appled Optmzaton, Sharah, U.A.E. February -3, 005 pheromone evaporaton from the others, whch are the two maor characterstcs of ACS pheromone updatng rule. procedure CACS() ntalze() whle(termnaton_crteron_not_satsfed) move_ants_to_new_locatons() pheromone_update() end whle procedure ntalze() ntally guess the best pont usng a unform random generator set the ntal values of weghted varances (large enough) procedure move_ants_to_new_locatons() for =, for =,n choose the new x() for the th ant usng a normal random generator end for end for procedure pheromone_update update the globally best pont for =,n update the value of sgma_ end for Fgure. The CACS scheme n pseudo-code, s the number of ants, n s the number of varables to optmze 3.3. Algorthmc Model of CACS The pseudo-code of CACS scheme s shown n Fg.. A hgh level descrpton of CACS desgned to mnmze a general multvarable contnuous cost functon f x,..., x ), can be summarzed as follows: ( n Step : choose randomly the ntally guessed mnmum pont x,..., x over the search space and calculate the value of the ( n) mn functon f at ths pont, namely f mn PDF over the nterval a, ]. [ b. For each x use a unform Step : Set the ntal value of weghted varance for each pheromone ntensty dstrbuton functon: σ = ( b a ), 3 ( =,..., n ). It wll be large enough to approxmately generate unformly dstrbuted ntal values of a, b ]. [ x wthn the nterval Step 3: Send ants to ponts ( x,..., ), =,...,. To generate these random locatons, a random generator wth normal PDF s x n utlzed for each x, where ts mean and varance are ( x ) mn and σ respectvely. Note that f a generated x s outsde the gven nterval [ a, b ], t s dscarded and a new x s regenerated agan. Step 4: Evaluate f, at each dscovered pont, namely Compare these values wth the current mnmum value determne the updated f mn and ts assocated (,..., xn ) mn f,..., f. f and mn x. Step 5: f a stoppng crteron s satsfed (for the case whch s examned n ths paper, the algorthm stops after evaluatons) then stop, else update the weghted varance parameter σ for each varable x usng equaton (7) and go bac to step 3. σ = f f = mn [( x ) f f = mn ( x ) mn 4. EXPERIMENTS The same problem as [6] s consdered to evaluate the learnng method and to compare the results wth those of GA. The problem s approxmatng the followng analytcal functon wth a fuzzy rule base. 9x + 3x + / 3 x [0,/ 3] f ( x) = x / 3 x [/ 3,/ ] (8) 0.03/( (4.5x 3.85) ) x [0,/ 3] It presents the followng propertes (Fg. 3):. A dscontnuty of the dervatve at x=/3. A dscontnuty at x=/. A pea wth a hgh curvature zone around x=0.85 As [6], a Taag-Sugeno fuzzy rule base s consdered wth 0 rules. Here the learnng process means to fnd the optmal values of the a, b and w ( =,..., 0). Therefore the number of unnowns s 60. The optmzaton problem s to mnmze the quadratc error E, whch s calculated wth a set of testng samples. The test samples are numerous enough and regularly dstrbuted n the nterval on whch the analytcal functon s defned. To mae the results comparable wth those of [6], 00 sample ponts were taen and a lmtaton of evaluatons of the quadratc error E, per run, was mposed. A typcal result s shown n Fg. 3, obtaned after evaluatons of E, usng 0 ants. The best value of E was E = It s clear from ths fgure that f (x) s well optmum approxmated, but that the obtaned membershp functons seem rather dffcult to nterpret n a lngustc way. The correspondng values of a, b and w are lsted n table. ] (7) ICMSA0/05-4

5 Proceedng of the Frst Internatonal Conference on Modelng, Smulaton and Appled Optmzaton, Sharah, U.A.E. February -3, columns report the average values, whle the numbers n the parenthess are the standard devatons. The notatons used n the subsequent tables, are defned as follows: f(x) Fuzzy System Output Analytcal Functon E best : Mnmum value of E obtaned over all evaluated ponts by the ants (It allows to evaluate the convergence qualty) Eval ( Ebest ) : Number of evaluatons at whch E best was obtaned Eval ( Eave /0) : Number of evaluatons at whch the average error s below tenth of ts ntal value at the frst teraton (It allows to evaluate the convergence speed at the begnnng) Fgure 3. Typcal approxmaton obtaned and the assocated membershp functons. Table. Typcal Soluton for a, b and a x e e e-00.4e e e e e e e-00.54e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e e-00.44e e e e e e e e e e e e e e e e e-00 b w w Table. Averaged results vs. the number of ants E Eval E ) Eval E /0) best (0.0678) (0.0053) (0.008) (0.07) (5938) 6740 (65) 7385 (9048) 5530 (43) 384 (03) 04 (4) 4738 (38) 4708 (8758) The presented results of Fg. 4, Fg. 5 and table, show that, the sze of the populaton of ants has a clear effect on the observed results. As mentoned n [7], CACS s not responsve enough for < 0. Small number of ants (e.g. = 5 ) yelds a fast convergence speed at the frst evaluatons, but at the same tme t may cause an unrpe convergence to a local mnmum (Fg. 4 and Eval E ) n table ). In the case of small number of ants the probablty of fallng nto a local mnmum ncreases because t s very probable that durng one teraton all ants choose the ponts near to the current mnmum. Ths n turn decreases the values of the weghted varances, whch magnfy the aggregaton of the later teraton ponts around the local mnmum. When the value of the weghted varances become several tmes smaller than the dstance to the nearest local mnmum, t s no longer possble to ump to a better local mnmum and the mnmzaton process stops. 0 0 No. of Ants = 5 No. of Ants = 0 No. of Ants = 0 No. of Ants = Parameter Study E mn 0 - CACS has only one parameter to set whch s the number of ants,. Accordng to [7], CACS needs at least 0 ants to propose relatvely good results. The varaton of E versus the number of evaluatons s shown n Fg. 4 and Fg. 5. The later one s concentrated over the frst 5000 evaluatons to observe more precsely the ntal behavor. Also table gves the results obtaned wth dfferent number of ants ( = 5,0, 0,50). All presented results are averaged over 0 dfferent runs. The mn Number of Evaluatons Fgure 4. Mnma found vs. number of evaluatons (the effect of the number of ants). ICMSA0/05-5

6 Proceedng of the Frst Internatonal Conference on Modelng, Smulaton and Appled Optmzaton, Sharah, U.A.E. February -3, CONCLUSIONS E mn Number of Evaluatons No. of Ants = 5 No. of Ants = 0 No. of Ants = 0 No. of Ants = 50 Fgure 5. Mnma found durng the frst 5000 evaluatons (the effect of the number of ants). The best results are observed for = 0 (see Fg. 4 and the obtaned E and Eval E /0) n table ). The convergence best rate decreases for greater number of ants (wth 0 ants, E 0.0, whle E < 0. 0 wth 0 ants). opt opt 4.. Comparson wth Standard Genetc Algorthm In order to compare the overall performance of CACS wth other algorthms, the results obtaned for = 0 are lsted n table 3, and have been compared wth the well-nown Genetc Algorthm of [6], whch utlzes the Standard Genetc Algorthm (SGA) wth 500 chromosomes, a mutaton rate of 0.005, a crossover rate 0.6, 8 bt for codng fuzzy parameters and 400 generatons. Table 3 shows that the best mnma found are at the same order, but a lttle better for SGA than CACS. At the same tme comparng Eval E ) and Eval E /0) between two methods, reveals a better convergence speed for CACS than SGA. A ey pont n CACS s ts smplcty. One can easly fnd that mplementaton and use of CACS s very smpler than SGA, whch s due to ts smpler structure and ts fewer control parameters. Table 3. Comparson of CACS and GA results A recently developed Contnuous Ant Colony System algorthm, based on Ant Colony Optmzaton, s appled to the problem of fndng optmum parameters of a fuzzy rule base. The proposed scheme s used to approxmate an analytcal test functon. The performance of CACS s compared wth the Standard Genetc Algorthm. The overall results are compatble. Although SGA can fnd the mnmum slghtly better, but t has poorer convergence rate compared wth CACS. One of the best advantages of the CACS scheme s ts smplcty, whch s manly due to ts smpler structure. Also t has fewer control parameters, whch maes the parameter settngs process easer than many other methods. 6. REFERENCES [] Wang, L. X., A Course n Fuzzy Systems and Control, Pearson Educaton POD, 997. [] Dranov, D. and Palm, R., Advances n Fuzzy Control, Hedelberg: Physca-Verlag, 998. [3] Procy, T. J. and Mamdan, E. H., "A lngustc selforganzng process controller," Automatca, IFAC, Vol. 5, 979, [4] Taag, T. and Sugeno, M., "Fuzzy dentfcaton of systems and ts applcaton to modelng and control," IEEE Trans. Systems, Man and Cybernetcs, Vol. 5, 985, 6-3. [5] Nomura, H., Hayash, I., Waam, N., "A Self Tunng Method of Fuzzy Control by Descent Method," Proceedngs of the Internatonal Fuzzy Systems Asscaton, IFSA9, Engneerng Vol., Bruxelles, 99, [6] Sarry, P. and Guely, F., "A Genetc Algorthm for Optmzng Taag-Sugeno Fuzzy Rule Bases," Fuzzy Sets and Systems, Vol. 99, 998, [7] Pourtadoust, S. H. and Nobahar, H., "An Extenson of Ant Colony System to contnuous optmzaton problems," Lecture Notes n Computer Scence, Vol. 37, 004, [8] Colorn, A., Dorgo, M. and Manezzo, V., "Dstrbuted optmzaton by ant colones," Proceedngs of the Frst European Conference on Artfcal Lfe, Elsever Scence Publsher, 99, [9] Dorgo M. and Gambardella, L. M., "Ant colony system: A cooperatve learnng approach to the travelng salesman problem," IEEE Transactons on Evolutonary Computaton, Vol., No., 997, Method CACS SGA E Eval E ) Eval E /0) best (0.0053) (0.003) 6740 (5938) (683) 04 (03) 000 (87) ICMSA0/05-6

Ant Colony Optimization Applied to Minimum Weight Dominating Set Problem

Ant Colony Optimization Applied to Minimum Weight Dominating Set Problem Ant Colony Optmzaton Appled to Mnmum Weght Domnatng Set Problem Raa JOVANOVIC Mlan TUBA Dana SIMIAN Texas AM Unversty Faculty of Computer Scence Department of Computer Scence at Qatar Megatrend Unversty

More information

Support Vector Machines

Support Vector Machines /9/207 MIST.6060 Busness Intellgence and Data Mnng What are Support Vector Machnes? Support Vector Machnes Support Vector Machnes (SVMs) are supervsed learnng technques that analyze data and recognze patterns.

More information

Meta-heuristics for Multidimensional Knapsack Problems

Meta-heuristics for Multidimensional Knapsack Problems 2012 4th Internatonal Conference on Computer Research and Development IPCSIT vol.39 (2012) (2012) IACSIT Press, Sngapore Meta-heurstcs for Multdmensonal Knapsack Problems Zhbao Man + Computer Scence Department,

More information

Learning the Kernel Parameters in Kernel Minimum Distance Classifier

Learning the Kernel Parameters in Kernel Minimum Distance Classifier Learnng the Kernel Parameters n Kernel Mnmum Dstance Classfer Daoqang Zhang 1,, Songcan Chen and Zh-Hua Zhou 1* 1 Natonal Laboratory for Novel Software Technology Nanjng Unversty, Nanjng 193, Chna Department

More information

NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS

NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS ARPN Journal of Engneerng and Appled Scences 006-017 Asan Research Publshng Network (ARPN). All rghts reserved. NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS Igor Grgoryev, Svetlana

More information

Parallelism for Nested Loops with Non-uniform and Flow Dependences

Parallelism for Nested Loops with Non-uniform and Flow Dependences Parallelsm for Nested Loops wth Non-unform and Flow Dependences Sam-Jn Jeong Dept. of Informaton & Communcaton Engneerng, Cheonan Unversty, 5, Anseo-dong, Cheonan, Chungnam, 330-80, Korea. seong@cheonan.ac.kr

More information

A New Approach For the Ranking of Fuzzy Sets With Different Heights

A New Approach For the Ranking of Fuzzy Sets With Different Heights New pproach For the ankng of Fuzzy Sets Wth Dfferent Heghts Pushpnder Sngh School of Mathematcs Computer pplcatons Thapar Unversty, Patala-7 00 Inda pushpndersnl@gmalcom STCT ankng of fuzzy sets plays

More information

Cluster Analysis of Electrical Behavior

Cluster Analysis of Electrical Behavior Journal of Computer and Communcatons, 205, 3, 88-93 Publshed Onlne May 205 n ScRes. http://www.scrp.org/ournal/cc http://dx.do.org/0.4236/cc.205.350 Cluster Analyss of Electrcal Behavor Ln Lu Ln Lu, School

More information

An Efficient Genetic Algorithm with Fuzzy c-means Clustering for Traveling Salesman Problem

An Efficient Genetic Algorithm with Fuzzy c-means Clustering for Traveling Salesman Problem An Effcent Genetc Algorthm wth Fuzzy c-means Clusterng for Travelng Salesman Problem Jong-Won Yoon and Sung-Bae Cho Dept. of Computer Scence Yonse Unversty Seoul, Korea jwyoon@sclab.yonse.ac.r, sbcho@cs.yonse.ac.r

More information

The Greedy Method. Outline and Reading. Change Money Problem. Greedy Algorithms. Applications of the Greedy Strategy. The Greedy Method Technique

The Greedy Method. Outline and Reading. Change Money Problem. Greedy Algorithms. Applications of the Greedy Strategy. The Greedy Method Technique //00 :0 AM Outlne and Readng The Greedy Method The Greedy Method Technque (secton.) Fractonal Knapsack Problem (secton..) Task Schedulng (secton..) Mnmum Spannng Trees (secton.) Change Money Problem Greedy

More information

Backpropagation: In Search of Performance Parameters

Backpropagation: In Search of Performance Parameters Bacpropagaton: In Search of Performance Parameters ANIL KUMAR ENUMULAPALLY, LINGGUO BU, and KHOSROW KAIKHAH, Ph.D. Computer Scence Department Texas State Unversty-San Marcos San Marcos, TX-78666 USA ae049@txstate.edu,

More information

S1 Note. Basis functions.

S1 Note. Basis functions. S1 Note. Bass functons. Contents Types of bass functons...1 The Fourer bass...2 B-splne bass...3 Power and type I error rates wth dfferent numbers of bass functons...4 Table S1. Smulaton results of type

More information

Subspace clustering. Clustering. Fundamental to all clustering techniques is the choice of distance measure between data points;

Subspace clustering. Clustering. Fundamental to all clustering techniques is the choice of distance measure between data points; Subspace clusterng Clusterng Fundamental to all clusterng technques s the choce of dstance measure between data ponts; D q ( ) ( ) 2 x x = x x, j k = 1 k jk Squared Eucldean dstance Assumpton: All features

More information

A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS

A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS Proceedngs of the Wnter Smulaton Conference M E Kuhl, N M Steger, F B Armstrong, and J A Jones, eds A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS Mark W Brantley Chun-Hung

More information

Training ANFIS Structure with Modified PSO Algorithm

Training ANFIS Structure with Modified PSO Algorithm Proceedngs of the 5th Medterranean Conference on Control & Automaton, July 7-9, 007, Athens - Greece T4-003 Tranng ANFIS Structure wth Modfed PSO Algorthm V.Seyd Ghomsheh *, M. Alyar Shoorehdel **, M.

More information

CHAPTER 2 PROPOSED IMPROVED PARTICLE SWARM OPTIMIZATION

CHAPTER 2 PROPOSED IMPROVED PARTICLE SWARM OPTIMIZATION 24 CHAPTER 2 PROPOSED IMPROVED PARTICLE SWARM OPTIMIZATION The present chapter proposes an IPSO approach for multprocessor task schedulng problem wth two classfcatons, namely, statc ndependent tasks and

More information

Type-2 Fuzzy Non-uniform Rational B-spline Model with Type-2 Fuzzy Data

Type-2 Fuzzy Non-uniform Rational B-spline Model with Type-2 Fuzzy Data Malaysan Journal of Mathematcal Scences 11(S) Aprl : 35 46 (2017) Specal Issue: The 2nd Internatonal Conference and Workshop on Mathematcal Analyss (ICWOMA 2016) MALAYSIAN JOURNAL OF MATHEMATICAL SCIENCES

More information

Performance Evaluation of an ANFIS Based Power System Stabilizer Applied in Multi-Machine Power Systems

Performance Evaluation of an ANFIS Based Power System Stabilizer Applied in Multi-Machine Power Systems Performance Evaluaton of an ANFIS Based Power System Stablzer Appled n Mult-Machne Power Systems A. A GHARAVEISI 1,2 A.DARABI 3 M. MONADI 4 A. KHAJEH-ZADEH 5 M. RASHIDI-NEJAD 1,2,5 1. Shahd Bahonar Unversty

More information

An Optimal Algorithm for Prufer Codes *

An Optimal Algorithm for Prufer Codes * J. Software Engneerng & Applcatons, 2009, 2: 111-115 do:10.4236/jsea.2009.22016 Publshed Onlne July 2009 (www.scrp.org/journal/jsea) An Optmal Algorthm for Prufer Codes * Xaodong Wang 1, 2, Le Wang 3,

More information

Feature Subset Selection Based on Ant Colony Optimization and. Support Vector Machine

Feature Subset Selection Based on Ant Colony Optimization and. Support Vector Machine Proceedngs of the 7th WSEAS Int. Conf. on Sgnal Processng, Computatonal Geometry & Artfcal Vson, Athens, Greece, August 24-26, 27 182 Feature Subset Selecton Based on Ant Colony Optmzaton and Support Vector

More information

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization Problem efntons and Evaluaton Crtera for Computatonal Expensve Optmzaton B. Lu 1, Q. Chen and Q. Zhang 3, J. J. Lang 4, P. N. Suganthan, B. Y. Qu 6 1 epartment of Computng, Glyndwr Unversty, UK Faclty

More information

Image Feature Selection Based on Ant Colony Optimization

Image Feature Selection Based on Ant Colony Optimization Image Feature Selecton Based on Ant Colony Optmzaton Lng Chen,2, Bolun Chen, Yxn Chen 3, Department of Computer Scence, Yangzhou Unversty,Yangzhou, Chna 2 State Key Lab of Novel Software Tech, Nanng Unversty,

More information

Biostatistics 615/815

Biostatistics 615/815 The E-M Algorthm Bostatstcs 615/815 Lecture 17 Last Lecture: The Smplex Method General method for optmzaton Makes few assumptons about functon Crawls towards mnmum Some recommendatons Multple startng ponts

More information

(1) The control processes are too complex to analyze by conventional quantitative techniques.

(1) The control processes are too complex to analyze by conventional quantitative techniques. Chapter 0 Fuzzy Control and Fuzzy Expert Systems The fuzzy logc controller (FLC) s ntroduced n ths chapter. After ntroducng the archtecture of the FLC, we study ts components step by step and suggest a

More information

EVALUATION OF THE PERFORMANCES OF ARTIFICIAL BEE COLONY AND INVASIVE WEED OPTIMIZATION ALGORITHMS ON THE MODIFIED BENCHMARK FUNCTIONS

EVALUATION OF THE PERFORMANCES OF ARTIFICIAL BEE COLONY AND INVASIVE WEED OPTIMIZATION ALGORITHMS ON THE MODIFIED BENCHMARK FUNCTIONS Academc Research Internatonal ISS-L: 3-9553, ISS: 3-9944 Vol., o. 3, May 0 EVALUATIO OF THE PERFORMACES OF ARTIFICIAL BEE COLOY AD IVASIVE WEED OPTIMIZATIO ALGORITHMS O THE MODIFIED BECHMARK FUCTIOS Dlay

More information

Maximum Variance Combined with Adaptive Genetic Algorithm for Infrared Image Segmentation

Maximum Variance Combined with Adaptive Genetic Algorithm for Infrared Image Segmentation Internatonal Conference on Logstcs Engneerng, Management and Computer Scence (LEMCS 5) Maxmum Varance Combned wth Adaptve Genetc Algorthm for Infrared Image Segmentaton Huxuan Fu College of Automaton Harbn

More information

ELECTROMAGNETIC WAVE PROPAGATION MODELING USING THE ANT COLONY OPTIMIZATION ALGORITHM

ELECTROMAGNETIC WAVE PROPAGATION MODELING USING THE ANT COLONY OPTIMIZATION ALGORITHM Radoengneerng Electromagnetc Wave Propagaton Modelng usng the Ant Colony Optmzaton Algorthm 1 Vol. 11, No. 3, September 2002 P. PECHAČ ELECTROMAGNETIC WAVE PROPAGATION MODELING USING THE ANT COLONY OPTIMIZATION

More information

Determining the Optimal Bandwidth Based on Multi-criterion Fusion

Determining the Optimal Bandwidth Based on Multi-criterion Fusion Proceedngs of 01 4th Internatonal Conference on Machne Learnng and Computng IPCSIT vol. 5 (01) (01) IACSIT Press, Sngapore Determnng the Optmal Bandwdth Based on Mult-crteron Fuson Ha-L Lang 1+, Xan-Mn

More information

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance Tsnghua Unversty at TAC 2009: Summarzng Mult-documents by Informaton Dstance Chong Long, Mnle Huang, Xaoyan Zhu State Key Laboratory of Intellgent Technology and Systems, Tsnghua Natonal Laboratory for

More information

Smoothing Spline ANOVA for variable screening

Smoothing Spline ANOVA for variable screening Smoothng Splne ANOVA for varable screenng a useful tool for metamodels tranng and mult-objectve optmzaton L. Rcco, E. Rgon, A. Turco Outlne RSM Introducton Possble couplng Test case MOO MOO wth Game Theory

More information

GA-Based Learning Algorithms to Identify Fuzzy Rules for Fuzzy Neural Networks

GA-Based Learning Algorithms to Identify Fuzzy Rules for Fuzzy Neural Networks Seventh Internatonal Conference on Intellgent Systems Desgn and Applcatons GA-Based Learnng Algorthms to Identfy Fuzzy Rules for Fuzzy Neural Networks K Almejall, K Dahal, Member IEEE, and A Hossan, Member

More information

R s s f. m y s. SPH3UW Unit 7.3 Spherical Concave Mirrors Page 1 of 12. Notes

R s s f. m y s. SPH3UW Unit 7.3 Spherical Concave Mirrors Page 1 of 12. Notes SPH3UW Unt 7.3 Sphercal Concave Mrrors Page 1 of 1 Notes Physcs Tool box Concave Mrror If the reflectng surface takes place on the nner surface of the sphercal shape so that the centre of the mrror bulges

More information

Optimal Design of Nonlinear Fuzzy Model by Means of Independent Fuzzy Scatter Partition

Optimal Design of Nonlinear Fuzzy Model by Means of Independent Fuzzy Scatter Partition Optmal Desgn of onlnear Fuzzy Model by Means of Independent Fuzzy Scatter Partton Keon-Jun Park, Hyung-Kl Kang and Yong-Kab Km *, Department of Informaton and Communcaton Engneerng, Wonkwang Unversty,

More information

Fast Computation of Shortest Path for Visiting Segments in the Plane

Fast Computation of Shortest Path for Visiting Segments in the Plane Send Orders for Reprnts to reprnts@benthamscence.ae 4 The Open Cybernetcs & Systemcs Journal, 04, 8, 4-9 Open Access Fast Computaton of Shortest Path for Vstng Segments n the Plane Ljuan Wang,, Bo Jang

More information

Machine Learning: Algorithms and Applications

Machine Learning: Algorithms and Applications 14/05/1 Machne Learnng: Algorthms and Applcatons Florano Zn Free Unversty of Bozen-Bolzano Faculty of Computer Scence Academc Year 011-01 Lecture 10: 14 May 01 Unsupervsed Learnng cont Sldes courtesy of

More information

Compiler Design. Spring Register Allocation. Sample Exercises and Solutions. Prof. Pedro C. Diniz

Compiler Design. Spring Register Allocation. Sample Exercises and Solutions. Prof. Pedro C. Diniz Compler Desgn Sprng 2014 Regster Allocaton Sample Exercses and Solutons Prof. Pedro C. Dnz USC / Informaton Scences Insttute 4676 Admralty Way, Sute 1001 Marna del Rey, Calforna 90292 pedro@s.edu Regster

More information

Course Introduction. Algorithm 8/31/2017. COSC 320 Advanced Data Structures and Algorithms. COSC 320 Advanced Data Structures and Algorithms

Course Introduction. Algorithm 8/31/2017. COSC 320 Advanced Data Structures and Algorithms. COSC 320 Advanced Data Structures and Algorithms Course Introducton Course Topcs Exams, abs, Proects A quc loo at a few algorthms 1 Advanced Data Structures and Algorthms Descrpton: We are gong to dscuss algorthm complexty analyss, algorthm desgn technques

More information

Outline. Type of Machine Learning. Examples of Application. Unsupervised Learning

Outline. Type of Machine Learning. Examples of Application. Unsupervised Learning Outlne Artfcal Intellgence and ts applcatons Lecture 8 Unsupervsed Learnng Professor Danel Yeung danyeung@eee.org Dr. Patrck Chan patrckchan@eee.org South Chna Unversty of Technology, Chna Introducton

More information

Extraction of Fuzzy Rules from Trained Neural Network Using Evolutionary Algorithm *

Extraction of Fuzzy Rules from Trained Neural Network Using Evolutionary Algorithm * Extracton of Fuzzy Rules from Traned Neural Network Usng Evolutonary Algorthm * Urszula Markowska-Kaczmar, Wojcech Trelak Wrocław Unversty of Technology, Poland kaczmar@c.pwr.wroc.pl, trelak@c.pwr.wroc.pl

More information

Sum of Linear and Fractional Multiobjective Programming Problem under Fuzzy Rules Constraints

Sum of Linear and Fractional Multiobjective Programming Problem under Fuzzy Rules Constraints Australan Journal of Basc and Appled Scences, 2(4): 1204-1208, 2008 ISSN 1991-8178 Sum of Lnear and Fractonal Multobjectve Programmng Problem under Fuzzy Rules Constrants 1 2 Sanjay Jan and Kalash Lachhwan

More information

NGPM -- A NSGA-II Program in Matlab

NGPM -- A NSGA-II Program in Matlab Verson 1.4 LIN Song Aerospace Structural Dynamcs Research Laboratory College of Astronautcs, Northwestern Polytechncal Unversty, Chna Emal: lsssswc@163.com 2011-07-26 Contents Contents... 1. Introducton...

More information

Unsupervised Learning

Unsupervised Learning Pattern Recognton Lecture 8 Outlne Introducton Unsupervsed Learnng Parametrc VS Non-Parametrc Approach Mxture of Denstes Maxmum-Lkelhood Estmates Clusterng Prof. Danel Yeung School of Computer Scence and

More information

y and the total sum of

y and the total sum of Lnear regresson Testng for non-lnearty In analytcal chemstry, lnear regresson s commonly used n the constructon of calbraton functons requred for analytcal technques such as gas chromatography, atomc absorpton

More information

Combining Cellular Automata and Particle Swarm Optimization for Edge Detection

Combining Cellular Automata and Particle Swarm Optimization for Edge Detection Combnng Cellular Automata and Partcle Swarm Optmzaton for Edge Detecton Safa Djemame Ferhat Abbes Unversty Sétf, Algera Mohamed Batouche Mentour Unversty Constantne, Algera ABSTRACT Cellular Automata can

More information

GSLM Operations Research II Fall 13/14

GSLM Operations Research II Fall 13/14 GSLM 58 Operatons Research II Fall /4 6. Separable Programmng Consder a general NLP mn f(x) s.t. g j (x) b j j =. m. Defnton 6.. The NLP s a separable program f ts objectve functon and all constrants are

More information

Complexity Analysis of Problem-Dimension Using PSO

Complexity Analysis of Problem-Dimension Using PSO Proceedngs of the 7th WSEAS Internatonal Conference on Evolutonary Computng, Cavtat, Croata, June -4, 6 (pp45-5) Complexty Analyss of Problem-Dmenson Usng PSO BUTHAINAH S. AL-KAZEMI AND SAMI J. HABIB,

More information

The Shortest Path of Touring Lines given in the Plane

The Shortest Path of Touring Lines given in the Plane Send Orders for Reprnts to reprnts@benthamscence.ae 262 The Open Cybernetcs & Systemcs Journal, 2015, 9, 262-267 The Shortest Path of Tourng Lnes gven n the Plane Open Access Ljuan Wang 1,2, Dandan He

More information

SLAM Summer School 2006 Practical 2: SLAM using Monocular Vision

SLAM Summer School 2006 Practical 2: SLAM using Monocular Vision SLAM Summer School 2006 Practcal 2: SLAM usng Monocular Vson Javer Cvera, Unversty of Zaragoza Andrew J. Davson, Imperal College London J.M.M Montel, Unversty of Zaragoza. josemar@unzar.es, jcvera@unzar.es,

More information

A Notable Swarm Approach to Evolve Neural Network for Classification in Data Mining

A Notable Swarm Approach to Evolve Neural Network for Classification in Data Mining A Notable Swarm Approach to Evolve Neural Network for Classfcaton n Data Mnng Satchdananda Dehur 1, Bjan Bhar Mshra 2 and Sung-Bae Cho 1 1 Soft Computng Laboratory, Department of Computer Scence, Yonse

More information

CS 534: Computer Vision Model Fitting

CS 534: Computer Vision Model Fitting CS 534: Computer Vson Model Fttng Sprng 004 Ahmed Elgammal Dept of Computer Scence CS 534 Model Fttng - 1 Outlnes Model fttng s mportant Least-squares fttng Maxmum lkelhood estmaton MAP estmaton Robust

More information

Parallel matrix-vector multiplication

Parallel matrix-vector multiplication Appendx A Parallel matrx-vector multplcaton The reduced transton matrx of the three-dmensonal cage model for gel electrophoress, descrbed n secton 3.2, becomes excessvely large for polymer lengths more

More information

Active Contours/Snakes

Active Contours/Snakes Actve Contours/Snakes Erkut Erdem Acknowledgement: The sldes are adapted from the sldes prepared by K. Grauman of Unversty of Texas at Austn Fttng: Edges vs. boundares Edges useful sgnal to ndcate occludng

More information

Ant Colony Algorithm for the Weighted Item Layout Optimization Problem

Ant Colony Algorithm for the Weighted Item Layout Optimization Problem Ant Colony Algorthm for the Weghted Item Layout Optmzaton Problem Y-Chun Xu 1, Fang-Mn Dong 1, Yong Lu 1, Ren-Bn Xao 2, Martyn Amos 3,* 1 Insttute of Intellgent Vson and Image Informaton, Chna Three Gorges

More information

CMPS 10 Introduction to Computer Science Lecture Notes

CMPS 10 Introduction to Computer Science Lecture Notes CPS 0 Introducton to Computer Scence Lecture Notes Chapter : Algorthm Desgn How should we present algorthms? Natural languages lke Englsh, Spansh, or French whch are rch n nterpretaton and meanng are not

More information

An Iterative Solution Approach to Process Plant Layout using Mixed Integer Optimisation

An Iterative Solution Approach to Process Plant Layout using Mixed Integer Optimisation 17 th European Symposum on Computer Aded Process Engneerng ESCAPE17 V. Plesu and P.S. Agach (Edtors) 2007 Elsever B.V. All rghts reserved. 1 An Iteratve Soluton Approach to Process Plant Layout usng Mxed

More information

An Entropy-Based Approach to Integrated Information Needs Assessment

An Entropy-Based Approach to Integrated Information Needs Assessment Dstrbuton Statement A: Approved for publc release; dstrbuton s unlmted. An Entropy-Based Approach to ntegrated nformaton Needs Assessment June 8, 2004 Wllam J. Farrell Lockheed Martn Advanced Technology

More information

A New Token Allocation Algorithm for TCP Traffic in Diffserv Network

A New Token Allocation Algorithm for TCP Traffic in Diffserv Network A New Token Allocaton Algorthm for TCP Traffc n Dffserv Network A New Token Allocaton Algorthm for TCP Traffc n Dffserv Network S. Sudha and N. Ammasagounden Natonal Insttute of Technology, Truchrappall,

More information

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration Improvement of Spatal Resoluton Usng BlockMatchng Based Moton Estmaton and Frame Integraton Danya Suga and Takayuk Hamamoto Graduate School of Engneerng, Tokyo Unversty of Scence, 6-3-1, Nuku, Katsuska-ku,

More information

MIXED INTEGER-DISCRETE-CONTINUOUS OPTIMIZATION BY DIFFERENTIAL EVOLUTION Part 1: the optimization method

MIXED INTEGER-DISCRETE-CONTINUOUS OPTIMIZATION BY DIFFERENTIAL EVOLUTION Part 1: the optimization method MIED INTEGER-DISCRETE-CONTINUOUS OPTIMIZATION BY DIFFERENTIAL EVOLUTION Part : the optmzaton method Joun Lampnen Unversty of Vaasa Department of Informaton Technology and Producton Economcs P. O. Box 700

More information

Simulation Based Analysis of FAST TCP using OMNET++

Simulation Based Analysis of FAST TCP using OMNET++ Smulaton Based Analyss of FAST TCP usng OMNET++ Umar ul Hassan 04030038@lums.edu.pk Md Term Report CS678 Topcs n Internet Research Sprng, 2006 Introducton Internet traffc s doublng roughly every 3 months

More information

Helsinki University Of Technology, Systems Analysis Laboratory Mat Independent research projects in applied mathematics (3 cr)

Helsinki University Of Technology, Systems Analysis Laboratory Mat Independent research projects in applied mathematics (3 cr) Helsnk Unversty Of Technology, Systems Analyss Laboratory Mat-2.08 Independent research projects n appled mathematcs (3 cr) "! #$&% Antt Laukkanen 506 R ajlaukka@cc.hut.f 2 Introducton...3 2 Multattrbute

More information

expermental results on NRP nstances. Secton V dscusses some related wor and Secton VI concludes ths paper. II. PRELIMINARIES Ths secton gves the defnt

expermental results on NRP nstances. Secton V dscusses some related wor and Secton VI concludes ths paper. II. PRELIMINARIES Ths secton gves the defnt A Hybrd ACO Algorthm for the Next Release Problem He Jang School of Software Dalan Unversty of Technology Dalan 116621, Chna janghe@dlut.edu.cn Jngyuan Zhang School of Software Dalan Unversty of Technology

More information

CS434a/541a: Pattern Recognition Prof. Olga Veksler. Lecture 15

CS434a/541a: Pattern Recognition Prof. Olga Veksler. Lecture 15 CS434a/541a: Pattern Recognton Prof. Olga Veksler Lecture 15 Today New Topc: Unsupervsed Learnng Supervsed vs. unsupervsed learnng Unsupervsed learnng Net Tme: parametrc unsupervsed learnng Today: nonparametrc

More information

USING MODIFIED FUZZY PARTICLE SWARM OPTIMIZATION ALGORITHM FOR PARAMETER ESTIMATION OF SURGE ARRESTERS MODELS

USING MODIFIED FUZZY PARTICLE SWARM OPTIMIZATION ALGORITHM FOR PARAMETER ESTIMATION OF SURGE ARRESTERS MODELS Internatonal Journal of Innovatve Computng, Informaton and Control ICIC Internatonal c 2012 ISSN 1349-4198 Volume 8, Number 1(B), January 2012 pp. 567 581 USING MODIFIED FUZZY PARTICLE SWARM OPTIMIZATION

More information

Multiobjective fuzzy optimization method

Multiobjective fuzzy optimization method Buletnul Ştnţfc al nverstăţ "Poltehnca" dn Tmşoara Sera ELECTRONICĂ ş TELECOMNICAŢII TRANSACTIONS on ELECTRONICS and COMMNICATIONS Tom 49(63, Fasccola, 24 Multobjectve fuzzy optmzaton method Gabrel Oltean

More information

Lecture 5: Multilayer Perceptrons

Lecture 5: Multilayer Perceptrons Lecture 5: Multlayer Perceptrons Roger Grosse 1 Introducton So far, we ve only talked about lnear models: lnear regresson and lnear bnary classfers. We noted that there are functons that can t be represented

More information

Classifier Selection Based on Data Complexity Measures *

Classifier Selection Based on Data Complexity Measures * Classfer Selecton Based on Data Complexty Measures * Edth Hernández-Reyes, J.A. Carrasco-Ochoa, and J.Fco. Martínez-Trndad Natonal Insttute for Astrophyscs, Optcs and Electroncs, Lus Enrque Erro No.1 Sta.

More information

A Binarization Algorithm specialized on Document Images and Photos

A Binarization Algorithm specialized on Document Images and Photos A Bnarzaton Algorthm specalzed on Document mages and Photos Ergna Kavalleratou Dept. of nformaton and Communcaton Systems Engneerng Unversty of the Aegean kavalleratou@aegean.gr Abstract n ths paper, a

More information

Mathematics 256 a course in differential equations for engineering students

Mathematics 256 a course in differential equations for engineering students Mathematcs 56 a course n dfferental equatons for engneerng students Chapter 5. More effcent methods of numercal soluton Euler s method s qute neffcent. Because the error s essentally proportonal to the

More information

FEATURE EXTRACTION. Dr. K.Vijayarekha. Associate Dean School of Electrical and Electronics Engineering SASTRA University, Thanjavur

FEATURE EXTRACTION. Dr. K.Vijayarekha. Associate Dean School of Electrical and Electronics Engineering SASTRA University, Thanjavur FEATURE EXTRACTION Dr. K.Vjayarekha Assocate Dean School of Electrcal and Electroncs Engneerng SASTRA Unversty, Thanjavur613 41 Jont Intatve of IITs and IISc Funded by MHRD Page 1 of 8 Table of Contents

More information

PARETO BAYESIAN OPTIMIZATION ALGORITHM FOR THE MULTIOBJECTIVE 0/1 KNAPSACK PROBLEM

PARETO BAYESIAN OPTIMIZATION ALGORITHM FOR THE MULTIOBJECTIVE 0/1 KNAPSACK PROBLEM PARETO BAYESIAN OPTIMIZATION ALGORITHM FOR THE MULTIOBJECTIVE 0/ KNAPSACK PROBLEM Josef Schwarz Jří Očenáše Brno Unversty of Technology Faculty of Engneerng and Computer Scence Department of Computer Scence

More information

K-means Optimization Clustering Algorithm Based on Hybrid PSO/GA Optimization and CS validity index

K-means Optimization Clustering Algorithm Based on Hybrid PSO/GA Optimization and CS validity index Orgnal Artcle Prnt ISSN: 3-6379 Onlne ISSN: 3-595X DOI: 0.7354/jss/07/33 K-means Optmzaton Clusterng Algorthm Based on Hybrd PSO/GA Optmzaton and CS valdty ndex K Jahanbn *, F Rahmanan, H Rezae 3, Y Farhang

More information

A mathematical programming approach to the analysis, design and scheduling of offshore oilfields

A mathematical programming approach to the analysis, design and scheduling of offshore oilfields 17 th European Symposum on Computer Aded Process Engneerng ESCAPE17 V. Plesu and P.S. Agach (Edtors) 2007 Elsever B.V. All rghts reserved. 1 A mathematcal programmng approach to the analyss, desgn and

More information

Quality Improvement Algorithm for Tetrahedral Mesh Based on Optimal Delaunay Triangulation

Quality Improvement Algorithm for Tetrahedral Mesh Based on Optimal Delaunay Triangulation Intellgent Informaton Management, 013, 5, 191-195 Publshed Onlne November 013 (http://www.scrp.org/journal/m) http://dx.do.org/10.36/m.013.5601 Qualty Improvement Algorthm for Tetrahedral Mesh Based on

More information

MULTI-OBJECTIVE OPTIMIZATION OF TIME-COST-QUALITY USING MULTI-COLONY ANT ALGORITHM

MULTI-OBJECTIVE OPTIMIZATION OF TIME-COST-QUALITY USING MULTI-COLONY ANT ALGORITHM ASIAN JOURNAL OF CIVIL ENGINEERING (BUILDING AND HOUSING) VOL. 8, NO. 2 (2007) PAGES 113-124 MULTI-OBJECTIVE OPTIMIZATION OF TIME-COST-QUALITY USING MULTI-COLONY ANT ALGORITHM A. Afshar, A. Kaveh and O.R.

More information

Some Advanced SPC Tools 1. Cumulative Sum Control (Cusum) Chart For the data shown in Table 9-1, the x chart can be generated.

Some Advanced SPC Tools 1. Cumulative Sum Control (Cusum) Chart For the data shown in Table 9-1, the x chart can be generated. Some Advanced SP Tools 1. umulatve Sum ontrol (usum) hart For the data shown n Table 9-1, the x chart can be generated. However, the shft taken place at sample #21 s not apparent. 92 For ths set samples,

More information

Multi-objective Design Optimization of MCM Placement

Multi-objective Design Optimization of MCM Placement Proceedngs of the 5th WSEAS Int. Conf. on Instrumentaton, Measurement, Crcuts and Systems, Hangzhou, Chna, Aprl 6-8, 26 (pp56-6) Mult-objectve Desgn Optmzaton of MCM Placement Chng-Ma Ko ab, Yu-Jung Huang

More information

Fitting: Deformable contours April 26 th, 2018

Fitting: Deformable contours April 26 th, 2018 4/6/08 Fttng: Deformable contours Aprl 6 th, 08 Yong Jae Lee UC Davs Recap so far: Groupng and Fttng Goal: move from array of pxel values (or flter outputs) to a collecton of regons, objects, and shapes.

More information

APPLICATION OF MULTIVARIATE LOSS FUNCTION FOR ASSESSMENT OF THE QUALITY OF TECHNOLOGICAL PROCESS MANAGEMENT

APPLICATION OF MULTIVARIATE LOSS FUNCTION FOR ASSESSMENT OF THE QUALITY OF TECHNOLOGICAL PROCESS MANAGEMENT 3. - 5. 5., Brno, Czech Republc, EU APPLICATION OF MULTIVARIATE LOSS FUNCTION FOR ASSESSMENT OF THE QUALITY OF TECHNOLOGICAL PROCESS MANAGEMENT Abstract Josef TOŠENOVSKÝ ) Lenka MONSPORTOVÁ ) Flp TOŠENOVSKÝ

More information

An Analysis of Different Variations of Ant Colony Optimization to the Minimum Weight Vertex Cover Problem

An Analysis of Different Variations of Ant Colony Optimization to the Minimum Weight Vertex Cover Problem Mlan Tuba, Raa Jovanovc An Analyss of Dfferent Varatons of Ant Colony Optmzaton to the Mnmum Weght Vertex Cover Problem MILAN TUBA Faculty of Computer Scence Megatrend Unversty Belgrade Bulevar umetnost

More information

Design of Structure Optimization with APDL

Design of Structure Optimization with APDL Desgn of Structure Optmzaton wth APDL Yanyun School of Cvl Engneerng and Archtecture, East Chna Jaotong Unversty Nanchang 330013 Chna Abstract In ths paper, the desgn process of structure optmzaton wth

More information

Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers

Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers IOSR Journal of Electroncs and Communcaton Engneerng (IOSR-JECE) e-issn: 78-834,p- ISSN: 78-8735.Volume 9, Issue, Ver. IV (Mar - Apr. 04), PP 0-07 Content Based Image Retreval Usng -D Dscrete Wavelet wth

More information

Wishing you all a Total Quality New Year!

Wishing you all a Total Quality New Year! Total Qualty Management and Sx Sgma Post Graduate Program 214-15 Sesson 4 Vnay Kumar Kalakband Assstant Professor Operatons & Systems Area 1 Wshng you all a Total Qualty New Year! Hope you acheve Sx sgma

More information

Genetic learning of accurate and compact fuzzy rule based systems based on the 2-tuples linguistic representation q

Genetic learning of accurate and compact fuzzy rule based systems based on the 2-tuples linguistic representation q Internatonal Journal of Approxmate Reasonng 44 (2007) 45 64 www.elsever.com/locate/jar Genetc learnng of accurate and compact fuzzy rule based systems based on the 2-tuples lngustc representaton q Rafael

More information

LECTURE : MANIFOLD LEARNING

LECTURE : MANIFOLD LEARNING LECTURE : MANIFOLD LEARNING Rta Osadchy Some sldes are due to L.Saul, V. C. Raykar, N. Verma Topcs PCA MDS IsoMap LLE EgenMaps Done! Dmensonalty Reducton Data representaton Inputs are real-valued vectors

More information

Applying Continuous Action Reinforcement Learning Automata(CARLA) to Global Training of Hidden Markov Models

Applying Continuous Action Reinforcement Learning Automata(CARLA) to Global Training of Hidden Markov Models Applyng Contnuous Acton Renforcement Learnng Automata(CARLA to Global Tranng of Hdden Markov Models Jahanshah Kabudan, Mohammad Reza Meybod, and Mohammad Mehd Homayounpour Department of Computer Engneerng

More information

Ant Colony Algorithm for Clustering through of Cliques

Ant Colony Algorithm for Clustering through of Cliques Ant Colony Algorthm for Clusterng through of Clques Julo Cesar Ponce Gallegos a, Felpe Padlla Díaz a, Carlos Alberto Ochoa Ortz Zezzatt b, Alejandro Padlla Díaz a, Eunce Esther Ponce de León a y Fatma

More information

Optimization of integrated circuits by means of simulated annealing. Jernej Olenšek, Janez Puhan, Árpád Bűrmen, Sašo Tomažič, Tadej Tuma

Optimization of integrated circuits by means of simulated annealing. Jernej Olenšek, Janez Puhan, Árpád Bűrmen, Sašo Tomažič, Tadej Tuma Optmzaton of ntegrated crcuts by means of smulated annealng Jernej Olenšek, Janez Puhan, Árpád Bűrmen, Sašo Tomažč, Tadej Tuma Unversty of Ljubljana, Faculty of Electrcal Engneerng, Tržaška 25, Ljubljana,

More information

Stochastic optimization algorithm with probability vector in mathematical function minimization and travelling salesman problem

Stochastic optimization algorithm with probability vector in mathematical function minimization and travelling salesman problem Stochastc optmzaton algorthm wth probablty vector n mathematcal functon mnmzaton and travellng salesman problem JAN POHL, VÁCLAV JIRSÍK, PETR HONZÍK Department of Control and Instrumentaton Brno Unversty

More information

Stochastic optimization algorithm with probability vector

Stochastic optimization algorithm with probability vector Proceedngs of the 4th WSEAS Internatonal Conference on COMPUTATIONAL INTELLIGENCE Stochastc optmzaton algorthm th probablty vector JAN POHL, VÁCLAV JIRSÍK, PETR HONZÍK Department of Control and Instrumentaton

More information

A new paradigm of fuzzy control point in space curve

A new paradigm of fuzzy control point in space curve MATEMATIKA, 2016, Volume 32, Number 2, 153 159 c Penerbt UTM Press All rghts reserved A new paradgm of fuzzy control pont n space curve 1 Abd Fatah Wahab, 2 Mohd Sallehuddn Husan and 3 Mohammad Izat Emr

More information

SHAPE OPTIMIZATION OF STRUCTURES BY MODIFIED HARMONY SEARCH

SHAPE OPTIMIZATION OF STRUCTURES BY MODIFIED HARMONY SEARCH INTERNATIONAL JOURNAL OF OPTIMIZATION IN CIVIL ENGINEERING Int. J. Optm. Cvl Eng., 2011; 3:485-494 SHAPE OPTIMIZATION OF STRUCTURES BY MODIFIED HARMONY SEARCH S. Gholzadeh *,, A. Barzegar and Ch. Gheyratmand

More information

An Application of the Dulmage-Mendelsohn Decomposition to Sparse Null Space Bases of Full Row Rank Matrices

An Application of the Dulmage-Mendelsohn Decomposition to Sparse Null Space Bases of Full Row Rank Matrices Internatonal Mathematcal Forum, Vol 7, 2012, no 52, 2549-2554 An Applcaton of the Dulmage-Mendelsohn Decomposton to Sparse Null Space Bases of Full Row Rank Matrces Mostafa Khorramzadeh Department of Mathematcal

More information

TECHNIQUE OF FORMATION HOMOGENEOUS SAMPLE SAME OBJECTS. Muradaliyev A.Z.

TECHNIQUE OF FORMATION HOMOGENEOUS SAMPLE SAME OBJECTS. Muradaliyev A.Z. TECHNIQUE OF FORMATION HOMOGENEOUS SAMPLE SAME OBJECTS Muradalyev AZ Azerbajan Scentfc-Research and Desgn-Prospectng Insttute of Energetc AZ1012, Ave HZardab-94 E-mal:aydn_murad@yahoocom Importance of

More information

Module Management Tool in Software Development Organizations

Module Management Tool in Software Development Organizations Journal of Computer Scence (5): 8-, 7 ISSN 59-66 7 Scence Publcatons Management Tool n Software Development Organzatons Ahmad A. Al-Rababah and Mohammad A. Al-Rababah Faculty of IT, Al-Ahlyyah Amman Unversty,

More information

An Image Fusion Approach Based on Segmentation Region

An Image Fusion Approach Based on Segmentation Region Rong Wang, L-Qun Gao, Shu Yang, Yu-Hua Cha, and Yan-Chun Lu An Image Fuson Approach Based On Segmentaton Regon An Image Fuson Approach Based on Segmentaton Regon Rong Wang, L-Qun Gao, Shu Yang 3, Yu-Hua

More information

Application of Improved Fish Swarm Algorithm in Cloud Computing Resource Scheduling

Application of Improved Fish Swarm Algorithm in Cloud Computing Resource Scheduling , pp.40-45 http://dx.do.org/10.14257/astl.2017.143.08 Applcaton of Improved Fsh Swarm Algorthm n Cloud Computng Resource Schedulng Yu Lu, Fangtao Lu School of Informaton Engneerng, Chongqng Vocatonal Insttute

More information

5 The Primal-Dual Method

5 The Primal-Dual Method 5 The Prmal-Dual Method Orgnally desgned as a method for solvng lnear programs, where t reduces weghted optmzaton problems to smpler combnatoral ones, the prmal-dual method (PDM) has receved much attenton

More information

Elsevier Editorial System(tm) for Expert Systems With Applications Manuscript Draft

Elsevier Editorial System(tm) for Expert Systems With Applications Manuscript Draft Elsever Edtoral System(tm) for Expert Systems Wth Applcatons Manuscrpt Draft Manuscrpt Number: ESWA-D-08-00701 tle: An Ordnal Optmzaton heory Based Algorthm for a Class of Smulaton Optmzaton Problems and

More information

A Learning Automata based Algorithm for Solving Traveling Salesman Problem improved by Frequency-based Pruning

A Learning Automata based Algorithm for Solving Traveling Salesman Problem improved by Frequency-based Pruning Internatonal Journal of Computer Applcatons (0975 8887) Volume 46 No.7, May 202 A Learnng Automata based Algorthm for Solvng Travelng Salesman Problem mproved by Frequencybased Prunng Mr Mohammad Alpour

More information