Speech enhancement is a challenging problem

Size: px
Start display at page:

Download "Speech enhancement is a challenging problem"

Transcription

1 Journal of Advances n Computer Engneerng and Technology, () 5 A New Shuffled Sub-swarm Partcle Swarm Optmzaton Algorthm for Speech Enhancement Masoud Geravanchzadeh, Sna Ghalam Osgoue Receved (-9-) Accepted (--) Abstract - In ths paper, we propose a novel algorthm to enhance the nosy speech n the framework of dual-channel speech enhancement. The new method s a hybrd optmzaton algorthm, whch employs the combnaton of the conventonal θ-pso and the shuffled subswarms partcle optmzaton (SSPSO) technque. It s known that the θ-pso algorthm has better optmzaton performance than standard PSO algorthm, when dealng wth some smple benchmark functons. To mprove further the performance of the conventonal PSO, the SSPSO algorthm has been suggested to ncrease the dversty of partcles n the swarm. The proposed speech enhancement method, called θ-sspso, s a hybrd technque, whch ncorporates both θ-pso and SSPSO, wth the goal of explotng the advantages of both algorthms. It s shown that the new θ-sspso algorthm s qute effectve n achevng global convergence for adaptve flters, whch results n a better suppresson of nose from nput speech sgnal. Expermental results ndcate that the new algorthm outperforms the standard PSO, θ-pso, and SSPSO n a sense of convergence rate and SNR-mprovement. Index Terms - Adaptve flterng, Partcle Swarm Optmzaton, Shuffled Sub-Swarm, Speech Enhancement, θ-pso. - Masoud Geravanchzadeh s wth Electrcal & Computer Engneerng faculty, Unversty of Tabrz, IRAN (geravanchzadeh@tabrzu.ac.r). - Sna Ghalam Osgoue s wth Electrcal & Computer Engneerng faculty, Unversty of Tabrz, IRAN (sna.ghalam@yahoo.com). I. INTRODUCTION Speech enhancement s a challengng problem n speech processng research, whch ams at recoverng clean speech from nosy speech. So far many types of gradent-based algorthms have been proposed n speech enhancement, whch employ dfferent schemes to adjust the flter weghts based on dfferent crtera. Some of the common algorthms are the Least-Mean- Squares (LMS) [], the normalzed verson of LMS [NLMS], and Recursve-Least-Squares (RLS) []. However, when the error surface s multmodal, gradent descent algorthms that work well for FIR adaptve flters, are not sutable for IIR flters. A further drawback of gradent descent technques s that they are lkely to get trapped n a local mnmum soluton. A few modfcatons to gradent decent algorthms exst that can mprove the performance, such as addng nose to the gradent calculaton to make t more lkely to escape from a local mnma, or usng the equaton error adaptaton to transform the error surface to unmodal [3]. An alternatve to gradent descent-based technques s a structured stochastc search of error space. These types of global search methods are ndependent from system structure, because a gradent s not calculated and the adaptve flter structure, asde from error computaton, does not drectly nfluence parameter updates. Due to ths property, these types of technques are potentally capable of globally optmzng any class of adaptve flter structures or objectve functons [4]. Stochastc optmzaton algorthms, such as PSO, have been studed for use n adaptve flterng problems, where the Mean-Square-Error (MSE) surface s ll-condtoned [5]. Although the standard PSO fnds good

2 44 Journal of Advances n Computer Engneerng and Technology, () 5 solutons much faster than other stochastc algorthms [6], s stll suffers from premature convergence, when complcated problems are optmzed, and needs further mprovements to avod entrappng n local optma. Some suggest modfcatons and varatons of the standard PSO algorthm to mprove the overall effcency [7-8]. In ths paper, we propose a novel algorthm, called θ-shuffled sub-swarms partcle optmzaton (θ-sspso) technque to solve the above mentoned problems and compare the results wth the standard PSO, θ-pso, and SSPSO algorthms for speech enhancement. The paper s organzed as follows. Secton II descrbes the structure of a dual-channel speech enhancement system, together wth the technques of standard PSO, θ-pso, and SSPSO. Secton III ntroduces the proposed θ-sspso algorthm. The results of applyng the proposed method to speech enhancement are presented n Secton IV. Concludng remarks are gven n Secton V. Speech Source s (n) + Nosy Speech Recovered Sgnal + + b(n) + d (n)=s(n)+b(n) + _ e (n) r (n) Nose Source P (z) W (z) y (n) Fgure. Dual-channel speech enhancement II. BACKGROUND. Dual-channel Speech Enhancement Fgure shows the block dagram for a general two-channel enhancement system [9]. The clean speech sgnal s(n) s assumed to be present n only one channel, whch s then corrupted by the background nose b(n) to generate the nosy speech sgnal d(n). The second channel has the reference nose sgnal r(n). The adaptve flter, W(z), tres to model the transfer functon P(z). As a result, the flter output y(n) becomes an estmate of only the nose present n d(n). Fnally, the output of the structure e(n) wll be an estmate of the clean sgnal s(n). Suppose that the unknown system P(z), whch we want to estmate, s descrbed by L M () = = yn ( ) = axn ( ) byn ( ). where a, b are the unknown parameters, whch should be determned n an teratve way. The parameters of the unknown system P(z) are estmated by mnmzng the Mean-Square Error (MSE) between the nosy speech d(n) and the output of the adaptve flter y(n). The enhanced sgnal s obtaned by subtractng the estmated nose y(n) from the nosy speech d(n).. Standard PSO Algorthm Partcle swarm optmzaton (PSO) was ntroduced by Kennedy and Eberhart n 995 []. Ths optmzaton technque, whch s nspred by the socal behavor of anmals (e.g., fsh schoolng and brd flockng) has already come to be wdely used n many areas []. The conventonal PSO algorthm [] begns by ntalzng a random swarm of M partcles, each havng R unknown parameters to be optmzed. At each epoch, the ftness of each partcle s evaluated accordng to the ftness functon. The algorthm stores and progressvely replaces the best prevous poston of each partcle (pbest, =,,...,M ). as well as a sngle best partcle (gbest). Start Intalze partcles wth random postons and velocty vectors For each partcle s poston, evaluate the ftness If ftness of p s better than ftness of pbest, then pbest = p Set best of pbests as gbest Update partcle s velocty and poston by Eq. and Eq.3 Yes Is the stop condton satsfed? No Stop, and gve gbest as the optmal soluton Fgure. Flowchart of the standard PSO algorthm The parameters are updated at each epoch (k) accordng to x ( k + ) = x ( k) + vel ( k + ) () d d d ( ) ( gbestd d (), ) vel ( k + ) = wv ( k) + c r p x ( k) + d d pbestd d cr p x k (3)

3 Journal of Advances n Computer Engneerng and Technology, () 5 45 where vel s the velocty vector of the partcle, r, r are random numbers unformly dstrbuted n the nterval (,), c and c are the cogntve and socal coeffcents toward gbest and pbest, respectvely, and w s the nerta weght. Inerta weght s updated as follow: T t w w w w T ( ) ( ), = n end + end (4) where T s the maxmum number of teratons. w n and w end are ntal and fnal values of the nerta weght, respectvely. Through the run of PSO, the nerta weght decreases from a relatvely large value to a small value. Usng ths technque, n early stages of the algorthm, the partcles search the space globally. As the process goes on, ther velocty decreases gradually, where at some pont the partcles begn to search the soluton space locally [3]. Fgure represents flowchart of the standard PSO algorthm. 3. Standard θ-pso Algorthm Here, we ntroduce the θ-pso algorthm to mprove the performance of the standard PSO algorthm, whch appears to be a promsng approach of functon optmzaton. In θ-pso, the velocty and poston of each partcle are replaced by phase and phase ncrement usng a mappng functon [8]. The standard θ-pso can be descrbed n vector notaton as follow ( ) ( θgbest θ ) θ ( t+ ) = w θ () t + cr() t θ () t θ () t + pbest cr() t () t () t θ ( t+ ) = θ ( t) + θ ( t+ ) (6) ( ) xθ t = f t (7) () () ( t ) F( t) = ftness x ( ), (8) (5) of phase angle, θ () t s the phase angle of best p soluton (pbest ), θ () t s the phase angle of global g best (gbest), and F (t) s the ftness value. In ths paper, we defne the mappng functon as max mn max mn ( ) x x j sn( j ) x + f θ = θ + x, (9) where π π π π θj,, θj,. 4. SSPSO Algorthm In SSPSO (Shuffled Sub-swarms Partcle Swarm Optmzer) [7], the swarm s parttoned equally nto sub-swarms to ncrease the dversty of partcles. The dvson of sub-swarms s not done randomly, but s based on the ftness of partcles. Wthn each sub-swarm, the ndvdual partcles hold deas (.e., nformaton) of searchng for the destnaton that can be nfluenced by deas of other partcles. The partcles of each sub-swarm evolve through a process of standard PSO algorthm. After a predefned number of generatons, all sub-swarms are shuffled to produce a new swarm, durng whch the deas are passed among sub-swarms. If the stop condton of the optmzaton process s not satsfed, the new swarm wll be agan parttoned nto several new sub-swarms, and the computatons are resumed. Ths process wll be contnued untl the stop condton s satsfed. The dvson procedure for partcle swarm n the SSPSO algorthm s shown as n Fgure 3. wth θ j ( θmn, θmax ), θj θ θ mn max (, ) (, ), xj xmn xmax for -th ( =,, s) partcle the j-th (j =,,n) component, t s an ndex of tme (teraton), f s a monotonc mappng functon, c and c are cogntve and socal coeffcents, respectvely, w s the nerta weght, and r (t) and r (t) are random numbers unformly dstrbuted n the nterval (,). x (t) s the partcle poston vector, decded by the mappng functon f -, θ () t s the phase angle, θ () t s the ncrement Swarm Sub-swarm Sub-swarm Sub-swarm Swarm Fgure3. The dvson and shuffle of sub-swarm mode

4 46 Journal of Advances n Computer Engneerng and Technology, () 5 III. PROPOSED METHOD FOR SPEECH ENHANCEMENT In ths part, we propose a hybrd method, called θ-sspso as a new optmzaton method to mprove further the performance of prevously dscussed algorthms, and apply t to dual-channel speech enhancement. ALGORITHM : SUMMARY OF Θ-SSPSO ALGORITHM - Intalzaton: π π π π angle,, phase ncreament,,,, p - best gbest w =.9, w =.4, c =.5, c =., x =, x = nt end - Loop n =,,, mn max x x x + x max mn max mn poston( n, j) = sn( θnj ) +,.- Compute cost functon value for each partcle..- Rank partcles by ther correspondng ftness values. The mnmum cost takes the frst rank..3- Dvde partcles to sub-swarms based on ther ranks. 3- Update partcles n each sub-swarm. Loop =,,3, 3.- If th -partcle s cost functon < (fttness value of pbest) Cost of pbest = th -partcle s fttness value; pbest = angle(); endf 3.- If th partcle s fttness value < gbest fttness value endf gbest fttness value = th partcle s fttness value gbest vector = angle(); 3.3- Update angle and phase ncrement by Eq.5, Eq.6 End loop 4- Shuffle sub-swarms and generate one swarm. End loop. θ-sspso Algorthm In ths paper, we propose a new optmzaton algorthm by combnng the θ-pso and SSPSO algorthms. As dscussed above, θ-pso has better convergence behavor than standard PSO. So, t seems reasonable to combne the θ-pso algorthm wth the shuffled sub-swarms procedure to obtan a robust optmzaton algorthm. The resultng hybrd θ-sspso algorthm enhances the dversty of partcles, whch leads to decrease the possblty of entrappng n local mnma. The θ-sspso method can be descrbed as follows: Step. Intalze randomly the postons and veloctes of all partcles. Set m = number of sub-swarms and n = number of partcles n each sub-swarm. Step. Compute the ftness of each partcle. Step3. Rank partcles by ther ftnesses. Step4. Partton partcles nto sub-swarms accordng to ther ftness. For example, for the number of sub-swarm m=3, rank goes to the frst sub-swarm, rank goes to the second subswarm, rank 3 goes to the thrd sub-swarm, rank 4 goes to the frst sub-swarm, and so on. Step5. Update the phase angle and phase angle ncrement of partcles based on Eq. (5) and Eq. (6) n each sub-swarm. Step6. Shuffle sub-swarms to produce a new swarm after a predefned number of teratons and rank partcles accordng to ther ftness. Step7. Go to Step 4, f the stop condton s not satsfed. Otherwse, stop and obtan the results from the global best poston (gbest) and the global best ftness. Algorthm shows pseudo code of our proposed method..θ-sspso Algorthm for Speech Enhancement The structure of a dual-channel speech enhancement s shown n Fgure. The nput sgnals are processed n frames. In the stochastc optmzaton-based speech enhancement, we need to defne the cost functon to evaluate the ftness of each partcle. The average error between the nosy speech sgnal, d(n), and the estmated nose sgnal n each frame s used as the cost functon. Ftter partcles have less cost functon values. The cost functon of the -th partcle s gven as: N J [ ( ) ( )] = dk y k, + () N k = where N s the number of samples n each frame, and y(k) s the output of W(z) desgned by the algorthm. When J s mnmum, then the parameters of W(z) represent the best estmaton of the unknown system P(z). In PSO-based optmzaton speech enhancement, the poston of each partcle n the swarm s a canddate for the coeffcents of the adaptve flter. After a predefned number of teratons, the optmal adaptve flter W(z) s

5 Journal of Advances n Computer Engneerng and Technology, () 5 47 calculated accordng to the poston vector of the best (global) partcle n the swarm (gbest). Then, y(n) s determned by modfyng the nose reference r(n) by the adaptve flter W(z). Fnally, the enhanced frame s obtaned by subtractng y(n) from d(n). IV. SIMULATION RESULTS For our smulatons, we use speech sgnal from the NOIZEUS database [4]. As the nose references, we take noses from the NOISEX-9 database [5]. The nosy speech s obtaned by addng the clean speech sgnal to the nose reference modfed by the transfer functon P(z). As example, we have used the followng flter P(z) as acoustc path n our smulatons: Pz ( ) =.z +.36z () Correspondng to the selected (acoustc path) flter P(z), the adaptve flter W(z) consdered for the partcle n the smulatons s gven as [5]: p W ( z ) =, () + + pz pz 3 where p j s the j-th dmenson of the -th partcle n swarm. As objectve evaluaton of our proposed method, we use the segmental SNR (SNR seg ) and PESQ [6] tests. For the computaton of SNR seg, speech sgnals are frst segmented nto frames. Then, SNR n each frame s computed as sgnal-to-nose power rato. Fnally, the computed SNR values are averaged over all frames. The overall process of obtanng SNR seg can be gven as: SNR seg = T N s [ n Nm T + ] N n= log. m= N N ' ( s[ n + Nm] s [ n + Nm] ) n= ' where s[ n + Nm] and s [ n Nm] (3) + are the n th sample of the m th frame of the clean and the enhanced speech sgnals, respectvely, N s the number of samples n each frame, and T s the number of frames. The perceptual evaluaton of speech qualty (PESQ) measure s an alternatve objectve measure whch s able to predct subjectve qualty of speech sgnals. Ths objectve measure s based on models of human audtory speech percepton whch s selected as the ITU-T recommendatons P.86 [7]. The range of the PESQ score s.5 to 4.5, although for most cases the output range wll be a MOS-lke score,.e., a score between. and 4.5. The PESQ score s computed as a lnear combnaton of the average dsturbance value d sym and the average asymmetrcal dsturbance value d asym as follows: PESQ = d d (4) sym.39. asym where d sym and d asym are computed as: d d sym asym ''' ( Dt) k k k = ( tk ) k ''' ( DAkt k) k = ( tk ) k. (5) (6) ''' ''' Here, D k and DA k are the averaged frame dsturbance values as descrbed n [7]. The summaton over k s performed over the speechactve ntervals, and t k are weghts appled to the frame dsturbances and depend on the length of the sgnal. Four stochastc optmzaton technques (.e., PSO, θ-pso, SSPSO, and θ-sspso) are used to assess our proposed method. The expermental condtons for these algorthms are shown n Table I. The SNR of the nput nosy sgnal for engne, babble, and whte nose types s set at -,, and 5 db, respectvely. The results of each algorthm are averaged over tral runs. Table III shows the SNR-mprovement for each algorthm. It can be seen from ths table that the θ-sspso algorthm outperforms other algorthms n a sense of SNRmprovement. Table IV shows PESQ-mprovement for each algorthm. The results of ths evaluaton show clearly that the θ-sspso algorthm outperforms other algorthms. The tme waveforms of the nosy, clean, and enhanced speech obtaned by the PSO, θ-pso, SSPSO, and θ-sspso algorthms, respectvely, are llustrated n Fgure 4. The MSE (cost functon) of the best partcle n the populaton durng the teratons (.e.,gbest) are shown n Fgure 5 for PSO, θ-pso, SSPSO and θ-sspso. It can be seen from the fgure that

6 48 Journal of Advances n Computer Engneerng and Technology, () 5 our proposed method outperforms smulated stochastc-based algorthms n a sense of convergence rate and steady state error. TABLEI. EXPERIMENTAL CONDITIONS FOR THE PSO, Θ-PSO, SSPSO, Θ -SSPSO ALGORITHMS Algorthms Parameters Range of Values PSO, θ-pso, SSPSO, and θ-sspso nerta weght lnearly decreasng from.9 to.4 c.5 c. populaton sze 3 teraton 5 frame overlap 5% frame length (n samples) 4 SSPSO, θ-sspso sub-swarm number 4 TABLEII. THE EXPERIMENTAL RESULTS OF PSO-BASED ALGORITHMS FOR DIFFERENT BENCHMARK FUNCTIONS Expermental Condtons Optmzaton results Benchmarks Formula Soluton space Sphere Functon Rastrgn Functon 4 = x f x ( x ( π x ) = = f( x) ( ) = cos + [-,] [-3,3] Iteraton Actual mnmum Standard PSO θ-pso SSPSO θ-sspso TABLEIII. SNR-IMPROVEMNET OF DIFFERENT ALGORITHMS FOR DIFFERENT NOISY INPUT CONDITIONS Algorthms SNR-Improvement (db) Engne nose Babble nose SNR of - db SNR of db Whte nose SNR of 5 db Standard PSO θ-pso SSPSO θ-sspso As subjectve measure, we use the MUlt Stmulus test wth Hdden Reference and Anchor (MUSHRA) whch s a ITU-R Recommendaton BS.534- [8] as mplemented n [9]. The subjects are provded wth test utterances plus one reference and one hdden anchor, and are asked to rate the dfferent sgnals on a scale of to, where s the best score. The lsteners are permtted to lsten to each sentence several tmes and always have access to the clean sgnal reference. The test sgnals are the same as those, whch are used for the objectve evaluaton. Three types of nose (.e., whte nose, destroyer engne nose, and babble nose) are used n our lstenng tests. A total of lsteners ( females, 8 males between the ages of 8 to 3) have partcpated n these tests. Table V shows the subjectve results of each algorthm for dfferent nose types. As an alternatve way of evaluatng the performance of our proposed hybrd optmzaton algorthm, we use two famous benchmarks, whch are composed of Sphere and Rastrgn functons. The optmzaton results of each algorthm n each benchmark are shown n Table II. TABLE IV. PESQ-IMPROVEMNET OF DIFFERENT ALGORITHMS FOR DIFFERENT NOISY INPUT CONDITIONS PESQ-Improvement Algorthms Engne nose SNR of - db Babble nose SNR of db Whte nose SNR of 5 db Standard PSO θ-pso SSPSO θ-sspso TABLE V. THE RESULTS OF MUSHRA COMPARATIVE LISTENING TEST FOR THE STANDARD PSO, θ-pso, SSPSO, AND θ-sspso ALGORITHMS FOR DIFFERENT NOISY INPUTS AND DIFFERENT SNR VALUES MSE (db) Nose type Engne nose SNR of - db Babble nose SNR of db Whte nose SNR of 5 db Nosy speech Standard PSO Speech Sgnals θ-pso SSPSO θ-sspso MSE Plot for Babble Nose pso teta-pso sspso teta-sspso Iteraton Fgure 4. Mean-Square-Error plot for PSO, PSO, θ-pso, SSPSO, and θ-sspso algorthms.

7 49 Journal of Advances n Computer Engneerng and Technology, () 5 V. CONCLUSION In Secton II, we presented θ-pso and SSPSO as two optmzatons technques. The major drawback of θ-pso s that t may easly stck n local mnma, when handlng some complex or mult-mode functons. On the other hand, SSPSO has the advantage that t ncreases the dversty of partcles n the search space. Ths n turn avods entrappng the optmzaton algorthm n local optma. The proposed hybrd θ-sspso algorthm combnes the standard θ-pso algorthm wth shufflng sub-swarm dea. In order to evaluate our proposed method, we test our new method n some famous benchmarks. As the results show, the θ-sspso algorthm has the least fnal ftness value. In order to assess our proposed method n the framework of speech enhancement, we examne the qualty of the enhanced speech both subjectvely and objectvely. As objectve assessment, we nvestgate the MSE plot, SNR-mprovements, and PESQmprovements. From the MSE plot, t can be obvously seen that θ-sspso converges faster than other algorthms. By consderng the results of SNR and PESQ, we conclude that the θ-sspso algorthm outperforms other methods objectvely. Ampltude Nosy Speech x 4 Clean Speech x 4 Enhanced Speech by PSO x 4 Enhanced Speech by TETA-PSO x 4 Enhanced Speech by SSPSO x 4 Enhanced Speech by TETA-SSPSO tme x 4 Fgure 5. From the top, tme waveforms of the nosy, the clean, and the recovered sgnals wth PSO, θ-pso, SSPSO, and θ-sspso algorthms, respectvely The qualty of the enhanced speech s evaluated subjectvely by lstenng tests. Lstenng tests show once agan that the speech enhanced by our proposed optmzaton method has the best qualty among the enhanced sgnals processed by all other methods. In general, t can be nferred from the conducted experments that the new optmzaton method (.e., θ-sspso) has the best performance n the framework of speech enhancement as compared wth other mplemented algorthms. By consderng the advantages of the new optmzaton method, t s worthwhle to utlze ths new method n other applcatons whch ncorporate optmzaton n the heart of ther work. As future works, the SSPSO algorthm can further be mproved by employng other modfed PSO-based algorthms nstead of the standard PSO technque. REFERENCES [] B. Wdrow, and S. Stearns, Adaptve Sgnal Processng, Englewood Clffs, NJ: Prentce Hall, 985. [] T.Ueda, H suzuk, Performance of Equlzers Employng a Re-tranng RLS Algorthm for Dgtal Moble Rado Communatons,4th IEEE Vehcular Thechnoly Conference, pp , 99. [3] Shynk, J.J., Adaptve IIR Flterng, IEEE ASSP Magazne, pp. 4-, Aprl 989 [4] Kruscnsk, D.J. and Jenkns, W.K., Adaptve Flterng Va Partcle Swarm Optmzaton, Proc. 37 Aslomar Conf on Sgnals, Systems. And Computers, November 3. [5] D. J. Krusensk and W. K. Jenkns, Desgn and Performance of Adaptve Systems Based on Structured Stochastc Optmzaton Strateges, Crcuts and Systems Magazne, Vol. 5, No., pp 8, February 5. [6] P. Mars, J, R. Chen, and R. Nambar, Learnng Algorthms: Theory and Applcaton n Sgnal Processng, Control, and Communcatons, CRCPress, Inc, 996. [7] Hu Wang, Feng Qan, An Improved Partcle Swarm Optmzer wth Shuffled Sub_swarm an ts Applcaton n Soft-sensor of Gasolne Endpont, Atlants Press, 7. [8] W.M. Zhong, S.J. L, F. Qan, θ-pso: A New Strategy of Partcle Swarm Optmzaton, Journal of Zhejang Unversty SCIENCE, submtted. [9] L.Badr asl,m geravanchzadeh, Dual-Channel Speech Enhancement based on Stochastc Optmzaton Strateges, -th Internatonal Conference on Informaton Scence, Sgnal Processng and ther applcatons (ISSPA ), Malaysa,. [] J. Kennedy, R.C. Eberhart, Partcle swarm optmzaton. Prof. of the IEEE Internatonal Conference on Neural Networks, IEEE Press, pp , 995. [] X. Hu, Y.Sh, R.C. Eberhart, Recent advances n Partcle Swarm, Prof. of the IEEE Internatonal Conference on Evolutonary Computaton. Portland, pp.9-97, 4. [] Felx T.S Chan and Manoj Kumar Tawar, Swarm

8 5 Journal of Advances n Computer Engneerng and Technology, () 5 Intellgence Focus on Ant and Partcle Swarm Optmzaton, Frst Edton, I-Tech Educaton and Publshng, December 7. [3] Y Sh, R Eberhart, Emprcal study of partcle swarm optmzaton, Internatonal Conference on Evolutonary Computaton, IEEE, Washngton, USA, pp , 999. [4] [5] Secton/Data/nosex.html [6] A. W. Rx, J. G. Beerends, M. P. Holler, and A. P. Hekstra, Perceptual evaluaton of speech qualty (PESQ) A new method for speech qualty assessment of telephone networks and codecs, n Proc. 6th IEEE Int. Conf. Acoust. Speech Sgnal Process., ICASSP-, vol., pp ,. [7] Phlpos C. Lozou, Speech Enhancement Theory and Practce, CRC Press, Edton, 7. [8] ITU-R, Recommendaton BS543-: Method for the Subjectve Assessment of Intermedate Qualty Level of Codng Systems,. [9] E. Vncent, MUSHRAM: A MATLAB Interface for MUSHRA Lstenng Tests, [Onlne] avalable.

Clustering Algorithm Combining CPSO with K-Means Chunqin Gu 1, a, Qian Tao 2, b

Clustering Algorithm Combining CPSO with K-Means Chunqin Gu 1, a, Qian Tao 2, b Internatonal Conference on Advances n Mechancal Engneerng and Industral Informatcs (AMEII 05) Clusterng Algorthm Combnng CPSO wth K-Means Chunqn Gu, a, Qan Tao, b Department of Informaton Scence, Zhongka

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

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

Estimation of Image Corruption Inverse Function and Image Restoration Using a PSObased

Estimation of Image Corruption Inverse Function and Image Restoration Using a PSObased Internatonal Journal of Vdeo& Image Processng and Network Securty IJVIPNS-IJENS Vol:10 No:06 1 Estmaton of Image Corrupton Inverse Functon and Image Restoraton Usng a PSObased Algorthm M. Pourmahmood,

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

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

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

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

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

Recommended Items Rating Prediction based on RBF Neural Network Optimized by PSO Algorithm

Recommended Items Rating Prediction based on RBF Neural Network Optimized by PSO Algorithm Recommended Items Ratng Predcton based on RBF Neural Network Optmzed by PSO Algorthm Chengfang Tan, Cayn Wang, Yuln L and Xx Q Abstract In order to mtgate the data sparsty and cold-start problems of recommendaton

More information

An Influence of the Noise on the Imaging Algorithm in the Electrical Impedance Tomography *

An Influence of the Noise on the Imaging Algorithm in the Electrical Impedance Tomography * Open Journal of Bophyscs, 3, 3, 7- http://dx.do.org/.436/ojbphy.3.347 Publshed Onlne October 3 (http://www.scrp.org/journal/ojbphy) An Influence of the Nose on the Imagng Algorthm n the Electrcal Impedance

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

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

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

Using Particle Swarm Optimization for Enhancing the Hierarchical Cell Relay Routing Protocol

Using Particle Swarm Optimization for Enhancing the Hierarchical Cell Relay Routing Protocol 2012 Thrd Internatonal Conference on Networkng and Computng Usng Partcle Swarm Optmzaton for Enhancng the Herarchcal Cell Relay Routng Protocol Hung-Y Ch Department of Electrcal Engneerng Natonal Sun Yat-Sen

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

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

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

Chinese Word Segmentation based on the Improved Particle Swarm Optimization Neural Networks

Chinese Word Segmentation based on the Improved Particle Swarm Optimization Neural Networks Chnese Word Segmentaton based on the Improved Partcle Swarm Optmzaton Neural Networks Ja He Computatonal Intellgence Laboratory School of Computer Scence and Engneerng, UESTC Chengdu, Chna Department of

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

Positive Semi-definite Programming Localization in Wireless Sensor Networks

Positive Semi-definite Programming Localization in Wireless Sensor Networks Postve Sem-defnte Programmng Localzaton n Wreless Sensor etworks Shengdong Xe 1,, Jn Wang, Aqun Hu 1, Yunl Gu, Jang Xu, 1 School of Informaton Scence and Engneerng, Southeast Unversty, 10096, anjng Computer

More information

Network Intrusion Detection Based on PSO-SVM

Network Intrusion Detection Based on PSO-SVM TELKOMNIKA Indonesan Journal of Electrcal Engneerng Vol.1, No., February 014, pp. 150 ~ 1508 DOI: http://dx.do.org/10.11591/telkomnka.v1.386 150 Network Intruson Detecton Based on PSO-SVM Changsheng Xang*

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

Classifying Acoustic Transient Signals Using Artificial Intelligence

Classifying Acoustic Transient Signals Using Artificial Intelligence Classfyng Acoustc Transent Sgnals Usng Artfcal Intellgence Steve Sutton, Unversty of North Carolna At Wlmngton (suttons@charter.net) Greg Huff, Unversty of North Carolna At Wlmngton (jgh7476@uncwl.edu)

More information

Comparison of Heuristics for Scheduling Independent Tasks on Heterogeneous Distributed Environments

Comparison of Heuristics for Scheduling Independent Tasks on Heterogeneous Distributed Environments Comparson of Heurstcs for Schedulng Independent Tasks on Heterogeneous Dstrbuted Envronments Hesam Izakan¹, Ath Abraham², Senor Member, IEEE, Václav Snášel³ ¹ Islamc Azad Unversty, Ramsar Branch, Ramsar,

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

The Codesign Challenge

The Codesign Challenge ECE 4530 Codesgn Challenge Fall 2007 Hardware/Software Codesgn The Codesgn Challenge Objectves In the codesgn challenge, your task s to accelerate a gven software reference mplementaton as fast as possble.

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

Classifier Swarms for Human Detection in Infrared Imagery

Classifier Swarms for Human Detection in Infrared Imagery Classfer Swarms for Human Detecton n Infrared Imagery Yur Owechko, Swarup Medasan, and Narayan Srnvasa HRL Laboratores, LLC 3011 Malbu Canyon Road, Malbu, CA 90265 {owechko, smedasan, nsrnvasa}@hrl.com

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

An Improved Particle Swarm Optimization for Feature Selection

An Improved Particle Swarm Optimization for Feature Selection Journal of Bonc Engneerng 8 (20)?????? An Improved Partcle Swarm Optmzaton for Feature Selecton Yuannng Lu,2, Gang Wang,2, Hulng Chen,2, Hao Dong,2, Xaodong Zhu,2, Sujng Wang,2 Abstract. College of Computer

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

High-Boost Mesh Filtering for 3-D Shape Enhancement

High-Boost Mesh Filtering for 3-D Shape Enhancement Hgh-Boost Mesh Flterng for 3-D Shape Enhancement Hrokazu Yagou Λ Alexander Belyaev y Damng We z Λ y z ; ; Shape Modelng Laboratory, Unversty of Azu, Azu-Wakamatsu 965-8580 Japan y Computer Graphcs Group,

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

Optimizing SVR using Local Best PSO for Software Effort Estimation

Optimizing SVR using Local Best PSO for Software Effort Estimation Journal of Informaton Technology and Computer Scence Volume 1, Number 1, 2016, pp. 28 37 Journal Homepage: www.jtecs.ub.ac.d Optmzng SVR usng Local Best PSO for Software Effort Estmaton Dnda Novtasar 1,

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

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

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

EECS 730 Introduction to Bioinformatics Sequence Alignment. Luke Huan Electrical Engineering and Computer Science

EECS 730 Introduction to Bioinformatics Sequence Alignment. Luke Huan Electrical Engineering and Computer Science EECS 730 Introducton to Bonformatcs Sequence Algnment Luke Huan Electrcal Engneerng and Computer Scence http://people.eecs.ku.edu/~huan/ HMM Π s a set of states Transton Probabltes a kl Pr( l 1 k Probablty

More information

ARTICLE IN PRESS. Applied Soft Computing xxx (2012) xxx xxx. Contents lists available at SciVerse ScienceDirect. Applied Soft Computing

ARTICLE IN PRESS. Applied Soft Computing xxx (2012) xxx xxx. Contents lists available at SciVerse ScienceDirect. Applied Soft Computing ASOC-11; o. of Pages 1 Appled Soft Computng xxx (1) xxx xxx Contents lsts avalable at ScVerse ScenceDrect Appled Soft Computng j ourna l ho mepage: www.elsever.com/locate/asoc A herarchcal partcle swarm

More information

A Clustering Algorithm Solution to the Collaborative Filtering

A Clustering Algorithm Solution to the Collaborative Filtering Internatonal Journal of Scence Vol.4 No.8 017 ISSN: 1813-4890 A Clusterng Algorthm Soluton to the Collaboratve Flterng Yongl Yang 1, a, Fe Xue, b, Yongquan Ca 1, c Zhenhu Nng 1, d,* Hafeng Lu 3, e 1 Faculty

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

Analysis of Particle Swarm Optimization and Genetic Algorithm based on Task Scheduling in Cloud Computing Environment

Analysis of Particle Swarm Optimization and Genetic Algorithm based on Task Scheduling in Cloud Computing Environment Analyss of Partcle Swarm Optmzaton and Genetc Algorthm based on Tas Schedulng n Cloud Computng Envronment Frederc Nzanywayngoma School of Computer and Communcaton Engneerng Unversty of Scence and Technology

More information

Fuzzy Filtering Algorithms for Image Processing: Performance Evaluation of Various Approaches

Fuzzy Filtering Algorithms for Image Processing: Performance Evaluation of Various Approaches Proceedngs of the Internatonal Conference on Cognton and Recognton Fuzzy Flterng Algorthms for Image Processng: Performance Evaluaton of Varous Approaches Rajoo Pandey and Umesh Ghanekar Department of

More information

A Robust Method for Estimating the Fundamental Matrix

A Robust Method for Estimating the Fundamental Matrix Proc. VIIth Dgtal Image Computng: Technques and Applcatons, Sun C., Talbot H., Ourseln S. and Adraansen T. (Eds.), 0- Dec. 003, Sydney A Robust Method for Estmatng the Fundamental Matrx C.L. Feng and Y.S.

More information

Research of Neural Network Classifier Based on FCM and PSO for Breast Cancer Classification

Research of Neural Network Classifier Based on FCM and PSO for Breast Cancer Classification Research of Neural Network Classfer Based on FCM and PSO for Breast Cancer Classfcaton Le Zhang 1, Ln Wang 1, Xujewen Wang 2, Keke Lu 2, and Ajth Abraham 3 1 Shandong Provncal Key Laboratory of Network

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

Optimizing Document Scoring for Query Retrieval

Optimizing Document Scoring for Query Retrieval Optmzng Document Scorng for Query Retreval Brent Ellwen baellwe@cs.stanford.edu Abstract The goal of ths project was to automate the process of tunng a document query engne. Specfcally, I used machne learnng

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

Structural optimization using artificial bee colony algorithm

Structural optimization using artificial bee colony algorithm 2 nd Internatonal Conference on Engneerng Optmzaton September 6-9, 2010, Lsbon, ortugal Structural optmzaton usng artfcal bee colony algorthm Al Hadd 1, Sna Kazemzadeh Azad 2, Saed Kazemzadeh Azad Department

More information

Repeater Insertion for Two-Terminal Nets in Three-Dimensional Integrated Circuits

Repeater Insertion for Two-Terminal Nets in Three-Dimensional Integrated Circuits Repeater Inserton for Two-Termnal Nets n Three-Dmensonal Integrated Crcuts Hu Xu, Vasls F. Pavlds, and Govann De Mchel LSI - EPFL, CH-5, Swtzerland, {hu.xu,vasleos.pavlds,govann.demchel}@epfl.ch Abstract.

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

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

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

A novel parameter estimation method for metal oxide surge arrester models

A novel parameter estimation method for metal oxide surge arrester models Sādhanā Vol. 36, Part 6, December 2011, pp. 941 961. c Indan Academy of Scences A novel parameter estmaton method for metal oxde surge arrester models MEHDI NAFAR 1,, GEVORK B GHAREHPETIAN 2 and TAHER

More information

3. CR parameters and Multi-Objective Fitness Function

3. CR parameters and Multi-Objective Fitness Function 3 CR parameters and Mult-objectve Ftness Functon 41 3. CR parameters and Mult-Objectve Ftness Functon 3.1. Introducton Cogntve rados dynamcally confgure the wreless communcaton system, whch takes beneft

More information

Invariant Shape Object Recognition Using B-Spline, Cardinal Spline, and Genetic Algorithm

Invariant Shape Object Recognition Using B-Spline, Cardinal Spline, and Genetic Algorithm Proceedngs of the 5th WSEAS Int. Conf. on Sgnal Processng, Robotcs and Automaton, Madrd, Span, February 5-7, 6 (pp4-45) Invarant Shape Obect Recognton Usng B-Splne, Cardnal Splne, and Genetc Algorthm PISIT

More information

Solving two-person zero-sum game by Matlab

Solving two-person zero-sum game by Matlab Appled Mechancs and Materals Onlne: 2011-02-02 ISSN: 1662-7482, Vols. 50-51, pp 262-265 do:10.4028/www.scentfc.net/amm.50-51.262 2011 Trans Tech Publcatons, Swtzerland Solvng two-person zero-sum game by

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

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

Assignment # 2. Farrukh Jabeen Algorithms 510 Assignment #2 Due Date: June 15, 2009.

Assignment # 2. Farrukh Jabeen Algorithms 510 Assignment #2 Due Date: June 15, 2009. Farrukh Jabeen Algorthms 51 Assgnment #2 Due Date: June 15, 29. Assgnment # 2 Chapter 3 Dscrete Fourer Transforms Implement the FFT for the DFT. Descrbed n sectons 3.1 and 3.2. Delverables: 1. Concse descrpton

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

A Unified Framework for Semantics and Feature Based Relevance Feedback in Image Retrieval Systems

A Unified Framework for Semantics and Feature Based Relevance Feedback in Image Retrieval Systems A Unfed Framework for Semantcs and Feature Based Relevance Feedback n Image Retreval Systems Ye Lu *, Chunhu Hu 2, Xngquan Zhu 3*, HongJang Zhang 2, Qang Yang * School of Computng Scence Smon Fraser Unversty

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

MULTIOBJECTIVE OPTIMIZATION USING PARALLEL VECTOR EVALUATED PARTICLE SWARM OPTIMIZATION

MULTIOBJECTIVE OPTIMIZATION USING PARALLEL VECTOR EVALUATED PARTICLE SWARM OPTIMIZATION MULTIOBJECTIVE OPTIMIZATION USING PARALLEL VECTOR EVALUATED PARTICLE OPTIMIZATION K.E. Parsopoulos, D.K. Tasouls, M.N. Vrahats Department of Mathematcs, Unversty of Patras Artfcal Intellgence Research

More information

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching A Fast Vsual Trackng Algorthm Based on Crcle Pxels Matchng Zhqang Hou hou_zhq@sohu.com Chongzhao Han czhan@mal.xjtu.edu.cn Ln Zheng Abstract: A fast vsual trackng algorthm based on crcle pxels matchng

More information

A hybrid sequential approach for data clustering using K-Means and particle swarm optimization algorithm

A hybrid sequential approach for data clustering using K-Means and particle swarm optimization algorithm MultCraft Internatonal Journal of Engneerng, Scence and Technology Vol., No. 6, 00, pp. 67-76 INTERNATIONAL JOURNAL OF ENGINEERING, SCIENCE AND TECHNOLOGY www.jest-ng.com 00 MultCraft Lmted. All rghts

More information

CS246: Mining Massive Datasets Jure Leskovec, Stanford University

CS246: Mining Massive Datasets Jure Leskovec, Stanford University CS46: Mnng Massve Datasets Jure Leskovec, Stanford Unversty http://cs46.stanford.edu /19/013 Jure Leskovec, Stanford CS46: Mnng Massve Datasets, http://cs46.stanford.edu Perceptron: y = sgn( x Ho to fnd

More information

Load Balancing for Hex-Cell Interconnection Network

Load Balancing for Hex-Cell Interconnection Network Int. J. Communcatons, Network and System Scences,,, - Publshed Onlne Aprl n ScRes. http://www.scrp.org/journal/jcns http://dx.do.org/./jcns.. Load Balancng for Hex-Cell Interconnecton Network Saher Manaseer,

More information

A New Hybrid Method Based on Improved Particle Swarm Optimization, Ant Colony Algorithm and HMM for Web Information Extraction

A New Hybrid Method Based on Improved Particle Swarm Optimization, Ant Colony Algorithm and HMM for Web Information Extraction A New Hybrd Method Based on Improved Partcle Swarm Optmzaton, Ant Colony Algorthm and HMM for Web Informaton Extracton Rong LI, Hong-bn WANG Department of Computer, Xnzhou Teachers Unversty, Xnzhou, Chna

More information

A Modified Median Filter for the Removal of Impulse Noise Based on the Support Vector Machines

A Modified Median Filter for the Removal of Impulse Noise Based on the Support Vector Machines A Modfed Medan Flter for the Removal of Impulse Nose Based on the Support Vector Machnes H. GOMEZ-MORENO, S. MALDONADO-BASCON, F. LOPEZ-FERRERAS, M. UTRILLA- MANSO AND P. GIL-JIMENEZ Departamento de Teoría

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

A Time-driven Data Placement Strategy for a Scientific Workflow Combining Edge Computing and Cloud Computing

A Time-driven Data Placement Strategy for a Scientific Workflow Combining Edge Computing and Cloud Computing > REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) < 1 A Tme-drven Data Placement Strategy for a Scentfc Workflow Combnng Edge Computng and Cloud Computng Bng Ln, Fangnng

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

CHAPTER 4 OPTIMIZATION TECHNIQUES

CHAPTER 4 OPTIMIZATION TECHNIQUES 48 CHAPTER 4 OPTIMIZATION TECHNIQUES 4.1 INTRODUCTION Unfortunately no sngle optmzaton algorthm exsts that can be appled effcently to all types of problems. The method chosen for any partcular case wll

More information

X- Chart Using ANOM Approach

X- Chart Using ANOM Approach ISSN 1684-8403 Journal of Statstcs Volume 17, 010, pp. 3-3 Abstract X- Chart Usng ANOM Approach Gullapall Chakravarth 1 and Chaluvad Venkateswara Rao Control lmts for ndvdual measurements (X) chart are

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

The Research of Ellipse Parameter Fitting Algorithm of Ultrasonic Imaging Logging in the Casing Hole

The Research of Ellipse Parameter Fitting Algorithm of Ultrasonic Imaging Logging in the Casing Hole Appled Mathematcs, 04, 5, 37-3 Publshed Onlne May 04 n ScRes. http://www.scrp.org/journal/am http://dx.do.org/0.436/am.04.584 The Research of Ellpse Parameter Fttng Algorthm of Ultrasonc Imagng Loggng

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

The Research of Support Vector Machine in Agricultural Data Classification

The Research of Support Vector Machine in Agricultural Data Classification The Research of Support Vector Machne n Agrcultural Data Classfcaton Le Sh, Qguo Duan, Xnmng Ma, Me Weng College of Informaton and Management Scence, HeNan Agrcultural Unversty, Zhengzhou 45000 Chna Zhengzhou

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

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

APPLICATION OF PREDICTION-BASED PARTICLE FILTERS FOR TELEOPERATIONS OVER THE INTERNET

APPLICATION OF PREDICTION-BASED PARTICLE FILTERS FOR TELEOPERATIONS OVER THE INTERNET APPLICATION OF PREDICTION-BASED PARTICLE FILTERS FOR TELEOPERATIONS OVER THE INTERNET Jae-young Lee, Shahram Payandeh, and Ljljana Trajovć School of Engneerng Scence Smon Fraser Unversty 8888 Unversty

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

Straight Line Detection Based on Particle Swarm Optimization

Straight Line Detection Based on Particle Swarm Optimization Sensors & ransducers 013 b IFSA http://www.sensorsportal.com Straght Lne Detecton Based on Partcle Swarm Optmzaton Shengzhou XU, Jun IE College of computer scence, South-Central Unverst for Natonaltes,

More information

UB at GeoCLEF Department of Geography Abstract

UB at GeoCLEF Department of Geography   Abstract UB at GeoCLEF 2006 Mguel E. Ruz (1), Stuart Shapro (2), June Abbas (1), Slva B. Southwck (1) and Davd Mark (3) State Unversty of New York at Buffalo (1) Department of Lbrary and Informaton Studes (2) Department

More information

A Two-Stage Algorithm for Data Clustering

A Two-Stage Algorithm for Data Clustering A Two-Stage Algorthm for Data Clusterng Abdolreza Hatamlou 1 and Salwan Abdullah 2 1 Islamc Azad Unversty, Khoy Branch, Iran 2 Data Mnng and Optmsaton Research Group, Center for Artfcal Intellgence Technology,

More information

FINDING IMPORTANT NODES IN SOCIAL NETWORKS BASED ON MODIFIED PAGERANK

FINDING IMPORTANT NODES IN SOCIAL NETWORKS BASED ON MODIFIED PAGERANK FINDING IMPORTANT NODES IN SOCIAL NETWORKS BASED ON MODIFIED PAGERANK L-qng Qu, Yong-quan Lang 2, Jng-Chen 3, 2 College of Informaton Scence and Technology, Shandong Unversty of Scence and Technology,

More information

A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION

A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION 1 THE PUBLISHING HOUSE PROCEEDINGS OF THE ROMANIAN ACADEMY, Seres A, OF THE ROMANIAN ACADEMY Volume 4, Number 2/2003, pp.000-000 A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION Tudor BARBU Insttute

More information

APPLICATION OF PREDICTION-BASED PARTICLE FILTERS FOR TELEOPERATIONS OVER THE INTERNET

APPLICATION OF PREDICTION-BASED PARTICLE FILTERS FOR TELEOPERATIONS OVER THE INTERNET APPLICATION OF PREDICTION-BASED PARTICLE FILTERS FOR TELEOPERATIONS OVER THE INTERNET Jae-young Lee, Shahram Payandeh, and Ljljana Trajovć School of Engneerng Scence Smon Fraser Unversty 8888 Unversty

More information

Edge Detection in Noisy Images Using the Support Vector Machines

Edge Detection in Noisy Images Using the Support Vector Machines Edge Detecton n Nosy Images Usng the Support Vector Machnes Hlaro Gómez-Moreno, Saturnno Maldonado-Bascón, Francsco López-Ferreras Sgnal Theory and Communcatons Department. Unversty of Alcalá Crta. Madrd-Barcelona

More information

Learning-Based Top-N Selection Query Evaluation over Relational Databases

Learning-Based Top-N Selection Query Evaluation over Relational Databases Learnng-Based Top-N Selecton Query Evaluaton over Relatonal Databases Lang Zhu *, Wey Meng ** * School of Mathematcs and Computer Scence, Hebe Unversty, Baodng, Hebe 071002, Chna, zhu@mal.hbu.edu.cn **

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

Proper Choice of Data Used for the Estimation of Datum Transformation Parameters

Proper Choice of Data Used for the Estimation of Datum Transformation Parameters Proper Choce of Data Used for the Estmaton of Datum Transformaton Parameters Hakan S. KUTOGLU, Turkey Key words: Coordnate systems; transformaton; estmaton, relablty. SUMMARY Advances n technologes and

More information

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data A Fast Content-Based Multmeda Retreval Technque Usng Compressed Data Borko Furht and Pornvt Saksobhavvat NSF Multmeda Laboratory Florda Atlantc Unversty, Boca Raton, Florda 3343 ABSTRACT In ths paper,

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

Programming in Fortran 90 : 2017/2018

Programming in Fortran 90 : 2017/2018 Programmng n Fortran 90 : 2017/2018 Programmng n Fortran 90 : 2017/2018 Exercse 1 : Evaluaton of functon dependng on nput Wrte a program who evaluate the functon f (x,y) for any two user specfed values

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

[33]. As we have seen there are different algorithms for compressing the speech. The

[33]. As we have seen there are different algorithms for compressing the speech. The 49 5. LD-CELP SPEECH CODER 5.1 INTRODUCTION Speech compresson s one of the mportant doman n dgtal communcaton [33]. As we have seen there are dfferent algorthms for compressng the speech. The mportant

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