Web Page Clustering by Combining Dense Units

Size: px
Start display at page:

Download "Web Page Clustering by Combining Dense Units"

Transcription

1 Web Page Clusterg by Combg Dese Uts Morteza Haghr Chehregha, Hassa Abolhassa ad Mostafa Haghr Chehregha Departmet of CE, Sharf Uversty of Techology, Tehra, IRA {haghr, Departmet of ECE, Uversty of Tehra, Tehra, Ira, Abstract Oe of the most mportat approaches of extractg kowledge from the web s to cluster the web data. I ths paper a ovel method for clusterg the web pages s preseted whch at frst fds the dese uts usg K-Meas method ad the os these uts for costructg fal sutable clusters. The method also s exteded for herarchcal clusterg. The expermetal results show the hgh qualty of both flat ad herarchcal clusters. Idex Terms Web Mg, Web clusterg, herarchcal clusters, K-Meas. I. ITRODUCTIO Data clusterg s a mportat pre-processg task formato mg that ca provde useful results. Clusterg volves dvdg a set of data obects to o-specfed groups. The data obects wth each group should exhbt a large degree of smlarty whle the smlarty amog dfferet clusters should be mmzed. Clusterg takes a mportat role o the web; t ca be used for ehacg search results, ehacg web crawlg, ad orgazg ad presetg doma kowledge. Up to ow varous methods have bee troduced for clusterg the web, more of them use techques such as lk aalyss [], [,9], cotet mg [] ad combato of them [,]. I a overall categorzato, web data clusterg algorthms ca be dvded to two categores: Herarchal ad Parttog algorthms. Herarchcal algorthms cluster the web pages a mult level ad tree-lke structure, whle parttog methods cluster the web data a sgle ad flat level [,]. I geeral oly algorthms such as graph-based [,] ad tree-based [] methods ad methods that fd a set of cetrods (K-Meas) [], are appled for clusterg the web data []. Although herarchcal methods are ofte sad to have better results from qualty respectve, but usually they do ot provde the repetto ad the reassgmet of pages, whch may have bee poorly clustered the early steps []. Moreover, the tme complexty of the herarchcal methods s ofte quadratc [0]. Parttog methods dvde a collecto of documets to a set of groups, so as to maxmze a pre-defed ftess measure. It seems that the recet parttog clusterg methods are well suted for clusterg a large documet dataset due to ther relatvely low computatoal requremets [0]. The best kow parttog algorthm s K-Meas [] that a smple form selects K pots as cluster ceters ad assgs each data pot to the earest ceter. The updatg ad reassgg process ca be kept utl a covergece crtero s met. Ths algorthm ca be performed o a large data set almost lear tme complexty. K-Meas has some problems that make t approprate for may applcatos. I secto we wll expla some of ts drawbacks. I ths paper we propose a ew method whch at frst fds dese uts of the etre data set ad the combes them for creatg fal clusters. The combato process s doe ether flat or herarchcal modes ad so ca geerate flat or herarchcal clusters. Whle creatg dese uts, a ceter of gravty s determed for each of them. I the combato step, these ceters are used as represetatves of dese uts average dstace combato. The remag of the paper s orgazed as follows: I secto, some prmary deftos ad cocepts are troduced. Secto cotas a complete descrpto of the proposed method ad ts tme complexty aalyss. The expermetal results of the method are evaluated secto ad fally a cocluso s gve secto. II. PRIMARY DEIITIOS AD COCEPTS A. Documet Represetato ad Smlarty Measures I the most data mg algorthms, each data pot (such as a documet) s represeted as a V = { v,,, } vector v v v, where s the weght of dmeso vector space. About text documets, ths s kow as Vector Space Model [] that each weght v represets the weght of assocated term of the documet. The most commo term weghtg approach s the combato of Term requecy wth Iverse Documet requecy (T-ID) []. I ths approach the weght of term documet s defed as (). w = tf df = tf log ( / df) () That tf s the umber of occurreces of term the documet ; df s the total term frequecy data set ad s the umber of documets. The vector space model gves us a good opportuty for defg varous metrcs of smlarty betwee two documets. The most commo smlarty metrcs are Mkowsk dstaces [] ad cose measure []. Mkowsk dstaces

2 computes the dstace of documets m p ad m by () (for = t s coverted to Eucldea dstace). d / m D( mp, m) = m, p m, () = Cose measure s defed by (), where m t pm s the er product of two vectors. Both metrcs are wdely used text clusterg lteratures. However t seems that the cases whch the umber of dmesos of two vectors dffers cosderably, the cose s more useful. t mm p cos( mp, m) = m m () p B. Descrpto of K-Meas Algorthm K-Meas chooses K pots as cetrods ad assgs each web page to the earest oe. The the cetrods are updated. The assgg ad updatg process s kept utl a covergece crtero s met. Sce clusterg s a P-Complete problem, so ths algorthm (lke other algorthms) s a heurstc soluto that fds the earest local optmum of the search space. The local optmum ad therefore the qualty of the results are depedet to the tal selecto of the ceters. Dfferet steps of K- Meas are show gure.. Ital Step : Select K tal pots by radom;. Repeat for each data pot dp data set: fd the earest cetrod to dp; assg dp to the earest cetrod; for each cluster c cluster set: update the cetrod c;. utl (covergece s cofrmed) g.. The K-Meas algorthm. I the algorthm of gure, the crtero used for dstgushg the covergece ad so falzg the process s defed as (). Ths measure s kow as mmzg Sum of Squared Errors. K E( A, C) = ( a ) D ( c, x ) () = = I (), A s the assgmet matrx (shows whch web page has bee assged to whch cetrod) ad C = { c } s the set of K cetrods. Assgmet matrx cludes values of 0 ad ( crsp clusterg) ad s obtaed by assgg each data pot to the correspodg cetrod. I the algorthm of gure, updatg the cetrods s doe accordg to (). c = ( a ) x = a =, K () K-Meas has several drawbacks. The ma drawback s the sestvty of result clusters to the tal cetrods; so that t may covergece to the local optma [9] that s ot acceptable. I fact, K-meas s a optmzato soluto that fds the local optmum placed the vcty of the tal soluto. But the same tal cluster cetrods a dataset wll always geerate the same cluster results ad so repeatg the algorthm for achevg better results must be doe wth dfferet tal cetrods. III. PROPOSED ALGORITHM I ths secto, we troduce our algorthm ad aalyze ts tme complexty. The algorthm cludes two steps: costructg dese uts ad combg them for creatg fal clusters. The combato process ca be doe ether flat or herarchcal mode. I followg we descrbe each step wth eough detals. A. Costructg Dese Uts The algorthm at frst selects a costat value for cetrods deoted by C. It s a large value that s related to the umber of all data pots. If shows the umber of data pots, the C s selected as MPts. Where MPts shows the mmum requred data pots that must resde a small rego so that the rego ca be cosdered as dese. I the ext step, each data pot s assged to the cetrods ad after assgmet; the cetrods are updated accordg to (). The process s repeated utl the covergece crtero s met (smlar to typcal K-Meas). The covergece s met whe the posto of cetrods do ot chage more after. Therefore at the ed of ths step we wll have umerous sphercal dese uts whch each of them has a ceter pot represetg the dstrbuto of desty. The process has bee depcted gure.. Ital Step : Select MPts; Select C as MPts ;. Repeat for each data pot dp data set: assg dp to the earest ceter; for each ut u: update the ceter of u;. utl (covergece s cofrmed) g.. dg dese uts. B. lat combato of Dese Uts I the ext step we combe the dese uts for costructg fal clusters. Combg these dese uts a optmum way so that the fal clusters would be the best combato s a P-Complete problem. Ths s proofed Theorem. Theorem - dg the best combato of dese uts that yelds best clusters s a P-Complete problem. Proof- We kow that data clusterg s a P-Complete problem []. We ca costruct a hyper graph wth odes represetg the dese uts. Each ode has lks to two kds of odes: odes that correspod to the data

3 pots sde the dese ut, ad cotermous odes (w.r.t dstace betwee the ceters of dese uts). We kow that each hyper ode (dese ut) has a lmted umber of data pots. So the umber of hyper odes wll be tself from O(). Therefore combato of these uts ca be smulated as a clusterg problem ad so fdg the optmum soluto s a P-Complete problem. So, because of complexty cosderatos, we should take a heurstc method whch ca perform combato wth a reasoable tme complexty. or ths we propose two alteratves:. Defe a threshold ad every two dese uts whch have the smlarly more tha ths threshold, o together ad costruct a uque dese ut. So the resultat clusters wll be depedet o the order of traversg the dese uts. So the combato may lead to a local optmum whle for achevg better results several rus may be eeded.. Wth respect to the drawbacks of the frst approach, we ca follow a more heurstc method. We follow a process smlar to the average lkage herarchcal clusterg [0] but produce the clusters flat format. The method repeatedly combes smaller uts ad produces bgger oes. The crtero used for combg the smaller groups s average dstace betwee data sde two uts. The created clusters have hgh qualty, but fdg the average dstace betwee dfferet dese uts requres hgh tme complexty. Our process has a cosderable preferece for applyg ths method: I the step of costructg sphercal dese uts, the ceter of each ut s gaed whle assgg ad updatg process. Therefore agast of other lkage methods, here there s o eed for fdg average dstace betwee base clusters; comparg the dstace betwee uts ca be doe oly by comparg the dstace betwee ther ceters. Betwee these two methods, we select the secod oe. So after costructg the dese uts, we follow the process of gure. I the algorthm of gure, fdg ew ceter s doe accordg to ().. Italze Select K as the desred umber of clusters;. Repeat d the two earest uts; Jo them as a uque ut; d the ceter of ew ut;. utl (there are oly K uts) g.. The Combato Step. ew Ceter = C + C + + () That ad shows the umber of members of uts ad, respectvely. So, the ew ceter s weghted average of two ceters. The og process s kept utl the desred clusters are obtaed. C. Avalg Herarchcal Clusterg I ths secto we mprove the method for herarchcal clusterg. or ths each combato step, we must exame whether the combato yelds a compoud ut the same ut or a ew ut must be costructed hgher level. Usg a costat threshold as agglomerato level ca ot be useful. However small low level clusters should use smaller thresholds whle bg hgh level clusters should have greater thresholds. Sce the clusters are costructed from smaller oes to bgger oes ad we wat about the og thresholds to act ths maer, so we establsh a relatoshp betwee the thresholds ad the ot uts. We defe a measure ad try to optmze t durg the combato process. The measure s defed relato (). Max ( Clustered Ds ta ces of C ad C )? M () Ds tace betwee two ceters M s a costat value whch s determed by user. Therefore, accordg to the result of equato () we have two stuatos (we ame the left part of () as L):. If L M, the these two dese uts wll o wth each other ad wll costruct a uque ut the same level. The ceter of the ew ut s updated by the weghted averagg of relato (). Also, other parameters of the ew ut are calculated.. If L < M, the a ew ut wll be costructed a hgher level ad the two uts wll be ts chldre. The ew ut cotas combed uts wth ther updated parameters. Ths method gves us a heurstc way for costructg the herarchcal clusters. D. Aalyss of Tme Complexty of the Method K-Meas requres O() tme of complexty for fdg a lmted umber of cluster cetrods. But sce the umber of the cetrods s tself from O(), so the total tme complexty of the frst step wll be equal to O( ). Secod step (combato step) ca be mplemeted wth the tme complexty of O( ) whether flat or herarchcal mode. Ths process ca be doe as follows: at frst we cosder a array wth the sze of m- (m s the umber of dese uts). We store each cell of array the earest ceter to the ceter dexed by the array's d as well as the correspodg dstace. I each combato the shortest dstace s foud wth O(m). After fdg the shortest dstace, the array s updated for the ewly created ut whch ths ca be doe wth O(m) tme of complexty, too. Therefore the total tme complexty for ths part wll be from O(m ) that t s tself equal to O( ).

4 IV. EXPERIMETAL RESULTS or evaluato of proposed method we have used two data sets: Oe data set s collected from the set of REUTERS documets ad aother oe s collected from Poltcs area cotag web pages that are selected radomly about the some topcs of Poltcs doma. The propertes of the data sets are show Table. or stemmg we have used the Porter algorthm ad after calculatg the T/ID values of vectors, they were ormalzed. TABLE. Examed Data Sets. Data Set REUTERS Poltcs Sze 00 o.of Clusters 0 Selected MPts There are several methods for evaluato of clusterg results most two well kow methods amog them are etropy-based methods ([,0]) ad -measure []. Because of more geeralty of -measure for evaluato of web searches, we use ths measure for evaluato of our results. -measure combes two measures precso ad recall ad evaluates whether the clusterg ca remove the ose pages ad geerate clusters wth hgh qualty. If P ad R show Precso ad Recall respectvely, ths measure s defed by () where precso ad recall are obtaed by (9). I these formulas shows the sze of cluster, g shows the sze of class ad (,) shows the umber of pages of class cluster. ( P (, )* R (, )) gt (, ) =, = max{ (, )} () ( P (, ) + R (, ) P(, ) = (, )/, R(, ) = (, )/ g (9) TABLE - Comparso of methods for the frst data set. CETER ID K-Meas Proposed Method or more comparsos we have mplemeted the K- Meas ad have evaluated ts results (sce the results of the K-Meas are depedet o the tal cetrods, so we have ru the K-Meas fve tmes wth dfferet tal ceters ad have selected the best result). The evaluato results are show Tables ad. About the frst data set, the total -Measure s 0.0 for the proposed algorthm whle ts value s 0. for K-Meas method. The dfferece betwee these two values shows the qualty of the proposed algorthm. About the secod data set, the total -Measure value of the K-Meas ad the proposed method are 0.0 ad 0.9, respectvely. These values also show the effcecy of the proposed method. TABLE - Comparso of methods for the secod data set. CETERID 9 0 K-Meas Proposed Method I the ext step we exame the herarchcal clusterg. or ths we select M equal to 0. ad costruct the herarchy. The resultat herarchy s depcted gure. The umbers exstg each cluster depct ther umber of members ad we assg a uque ID for each cluster a left to rght BS order. g.. The obtaed herarchy. Evaluato methods such as -measure ad etropy are developed for evaluato of flat clusters (or lowest level of herarchcal clusters). So here we use a ehaced verso for herarchcal clusterg developed []. Accordg to [] the -measure values of dfferet clusters follow from a butto-up process: The precso of a paret cluster s calculated from the precso of ts chldre accordg to (0). I (0) P R shows the precso of the cluster members whch do ot belog to ay other clusters. Sce for computg the recall we must calculate the R R (s defed smlar wth P R ) by traversg all web pages, so a more smple way ca be doe by calculatg recall wthout cosderg pre-calculated values for sub-clusters []. k k k C. chldre PC = Pk + PR (0) k C. chldre However usg the adapted measure, the results are brought Table. We have appled the herarchcal method oly o the frst data set. I ths case the

5 obtaed total -Measure s 0.9 whch s acceptable for a herarchcal clusterg. TABLE - The results of herarchcal algorthm. CETER ID P V. COCLUSIO R I ths paper, a ew method for clusterg the web documets s troduced. I fact, the proposed method tres to overcome some drawbacks of the well kow K- Meas algorthm whch fds oly the earest local optmum. The method tres to mprove the local optmum toward global optmum. Ths method, at frst, fds dese uts by bombardg the data space wth too may cetrods. Therefore at the ed, we have dese uts wth a represetatve pot (ceter) for each of them. Havg these ceter pots, we ca apply average lkage clusterg algorthm o the dese uts ad costruct the fal clusters by og them. The method has bee exteded for herarchcal clusterg. or ths purpose a heurstc measure has bee defed ad optmzed each cluster. If a ew ot cluster does ot satsfy the measure, the cluster s created hgher level. The method has bee evaluated by well kow - Measure ad ts mproved verso for herarchcal clusters. Accordg to the evaluato results, both of the flat ad herarchcal clusters have sutable qualty. REERECES [] Cos K., Pedrycs W., Swarsk R., "Data Mg- Methods for Kowledge Dscovery", Kluwer Academc Publshers, 99. [] Evertt, B., "Cluster Aalyss", d Edto. Halsted Press, ew York, 90. [] Getoor, L., "Lk Mg: A ew Data Mg Challege", ACM SIGKDD Exploratos ewsletter, Vol., pp. 9, 00. [] Grra,., Crucau, M., Bouemaa,., "Usupervsed ad Sem-supervsed Clusterg: a Bref Survey", th ACM SIGMM teratoal workshop o Multmeda formato retreval, pp. 9-, 00. [] Haghr Chehregha, Morteza, Abolhassa, H., ad Haghr Chehregha, Mostafa, "Attag hgher qualty for Desty Based Algorthms", Web Reasog ad Rule Systems, LCS (Sprger), pp. 9-, 00. [] Hea, X., ad Zhaa, H., Dg, C.H.Q., Smo, H.D., "Web documet clusterg usg hyperlk structures", Computatoal Statstcs & Data Aalyss, Vol., pp.9-, 00. [] Hezger, M., "Hyperlk aalyss o the world wde web", Sxteeth ACM coferece o Hypertext ad hypermeda HYPERTEXT '0, pp., 00. [] Ja, A. K., Murty, M.., ad ly, P. J., "Data Clusterg: A Revew", ACM Computg Surveys (CSUR), Vol., Issue, pp., 999. [9] Kleberg, M., "Authortatve sources a hyperlked evromet", th Aual ACM-SIAM Symposum o Dscrete Algorthms, SODA, 99. [0] Koller, D., Saham, M., "Herarchcally classfyg documets usg very few words", th Iteratoal Coferece o Mache Learg, pp. 0, 99. [] Larse, B., ad Aoe, C., "ast ad effectve text mg usg lear-tme documet clusterg", SIGKDD 99, CA, pp., 999. [] Lu, B., Chag, K.C.-C., "Edtoral: Specal Issue o Web Cotet Mg", ACM SIGKDD Exploratos ewsletter, Vol., Issue, pp. -, 00. [] McQuee, J., "Some methods for classfcato ad aalyss of multvarate observatos", fth Berkeley Symposum o Mathematcal Statstcs ad Probablty, pp. -9, 9. [] evlle, J., Adler, M., Jese, D., "Clusterg Relatoal Data Usg Attrbute ad Lk Iformato", th Iteratoal Coferece o Artfcal Itellgece, 00. [] urme, M., Hokarata, A., Kärkkäe, T., "ExtMer: Combg Multple Rakg ad Clusterg Algorthms for Structured Documet Retreval", Sxteeth Workshop o Database ad Expert Systems Applcatos, pp. 0-00, 00. [] Qula, R.J., "C.: Programs for Mache Learg", Morga Kaufma, 99. [] Scheker, A., Last, A., Buke, H., Kadel, A., "A Comparso of Two ovel Algorthms for Clusterg Web Documets", d Iteratoal Workshop o Web Documet Aalyss, pp. -, 00. [] Salto, G., Buckley, C., "Term-weghtg approaches automatc text retreval". Iformato Processg ad Maagemet, (): pp. -, 9. [9] Selm, S.Z., Ismal, M.A. "K-meas type algorthms: A geeralzed covergece theorem ad characterzato of local optmalty", IEEE Tras. Patter Aal. Mach. Itell., pp., 9. [0] Stebach, M, Karyps, G., Kumar, V., "A Comparso of Documet Clusterg techques", KDD 000, Techcal report of Uversty of Mesota, 000. [] Wag, Y., ad Ktsuregawa, M., "Ehacg Cotet- Lk Coupled Web Page Clusterg ad It's Evaluato", DEWS' 00, 00. [] Wess, R., Vélez, B., ad Sheldo, M.A., "HyPursut: A Herarchcal etwork Search Ege that Explots Cotet-Lk Hypertext Clusterg", th ACM coferece o Hypertext, USA, pp. 0-9, 99. [] Yao, Z., ad Cho, B., "Bdrectoal Herarchcal Clusterg for Web Mg", IEEE/WIC Iteratoal Coferece o Web Itellgece WI, pp. 0-, 00. [] Zamr,O., Etzo, O., "Web documet clusterg: A feasblty demostrato", 9 th Iteratoal ACM SIGIR Coferece o Research ad Developmet of Iformato Retreval, pp.-, Australa, 99.

Clustering documents with vector space model using n-grams

Clustering documents with vector space model using n-grams Clusterg documets wth vector space model usg -grams Klas Skogmar, d97ksk@efd.lth.se Joha Olsso, d97jo@efd.lth.se Lud Isttute of Techology Supervsed by: Perre Nugues, Perre.Nugues@cs.lth.se Abstract Ths

More information

Machine Learning: Algorithms and Applications

Machine Learning: Algorithms and Applications /03/ Mache Learg: Algorthms ad Applcatos Florao Z Free Uversty of Boze-Bolzao Faculty of Computer Scece Academc Year 0-0 Lecture 3: th March 0 Naïve Bayes classfer ( Problem defto A trag set X, where each

More information

CS 2710 Foundations of AI Lecture 22. Machine learning. Machine Learning

CS 2710 Foundations of AI Lecture 22. Machine learning. Machine Learning CS 7 Foudatos of AI Lecture Mache learg Mlos Hauskrecht mlos@cs.ptt.edu 539 Seott Square Mache Learg The feld of mache learg studes the desg of computer programs (agets) capable of learg from past eperece

More information

Face Recognition using Supervised & Unsupervised Techniques

Face Recognition using Supervised & Unsupervised Techniques Natoal Uversty of Sgapore EE5907-Patter recogto-2 NAIONAL UNIVERSIY OF SINGAPORE EE5907 Patter Recogto Project Part-2 Face Recogto usg Supervsed & Usupervsed echques SUBMIED BY: SUDEN NAME: harapa Reddy

More information

Bezier curves. 1. Defining a Bezier curve. A closed Bezier curve can simply be generated by closing its characteristic polygon

Bezier curves. 1. Defining a Bezier curve. A closed Bezier curve can simply be generated by closing its characteristic polygon Curve represetato Copyrght@, YZU Optmal Desg Laboratory. All rghts reserved. Last updated: Yeh-Lag Hsu (--). Note: Ths s the course materal for ME55 Geometrc modelg ad computer graphcs, Yua Ze Uversty.

More information

APPLICATION OF CLUSTERING METHODS IN BANK S PROPENSITY MODEL

APPLICATION OF CLUSTERING METHODS IN BANK S PROPENSITY MODEL APPLICATION OF CLUSTERING METHODS IN BANK S PROPENSITY MODEL Sergej Srota Haa Řezaková Abstract Bak s propesty models are beg developed for busess support. They should help to choose clets wth a hgher

More information

Text Categorization Based on a Similarity Approach

Text Categorization Based on a Similarity Approach Text Categorzato Based o a Smlarty Approach Cha Yag Ju We School of Computer Scece & Egeerg, Uversty of Electroc Scece ad Techology of Cha, Chegdu 60054, P.R. Cha Abstract Text classfcato ca effcetly ehace

More information

1-D matrix method. U 4 transmitted. incident U 2. reflected U 1 U 5 U 3 L 2 L 3 L 4. EE 439 matrix method 1

1-D matrix method. U 4 transmitted. incident U 2. reflected U 1 U 5 U 3 L 2 L 3 L 4. EE 439 matrix method 1 -D matrx method We ca expad the smple plae-wave scatterg for -D examples that we ve see to a more versatle matrx approach that ca be used to hadle may terestg -D problems. The basc dea s that we ca break

More information

An Improved Fuzzy C-Means Clustering Algorithm Based on Potential Field

An Improved Fuzzy C-Means Clustering Algorithm Based on Potential Field 07 d Iteratoal Coferece o Advaces Maagemet Egeerg ad Iformato Techology (AMEIT 07) ISBN: 978--60595-457-8 A Improved Fuzzy C-Meas Clusterg Algorthm Based o Potetal Feld Yua-hag HAO, Zhu-chao YU *, X GAO

More information

A Web Mining Based Network Personalized Learning System Hua PANG1, a, Jian YU1, Long WANG2, b

A Web Mining Based Network Personalized Learning System Hua PANG1, a, Jian YU1, Long WANG2, b 3rd Iteratoal Coferece o Machery, Materals ad Iformato Techology Applcatos (ICMMITA 05) A Web Mg Based Network Persoalzed Learg System Hua PANG, a, Ja YU, Log WANG, b College of Educato Techology, Sheyag

More information

A hybrid method using FAHP and TOPSIS for project selection Xuan Lia, Jiang Jiangb and Su Deng c

A hybrid method using FAHP and TOPSIS for project selection Xuan Lia, Jiang Jiangb and Su Deng c 5th Iteratoal Coferece o Computer Sceces ad Automato Egeerg (ICCSAE 205) A hybrd method usg FAHP ad TOPSIS for project selecto Xua La, Jag Jagb ad Su Deg c College of Iformato System ad Maagemet, Natoal

More information

A Genetic K-means Clustering Algorithm Applied to Gene Expression Data

A Genetic K-means Clustering Algorithm Applied to Gene Expression Data A Geetc K-meas Clusterg Algorthm Appled to Gee Expresso Data Fag-Xag Wu, W. J. Zhag, ad Athoy J. Kusal Dvso of Bomedcal Egeerg, Uversty of Sasatchewa, Sasatoo, S S7N 5A9, CANADA faw34@mal.usas.ca, zhagc@egr.usas.ca

More information

Descriptive Statistics: Measures of Center

Descriptive Statistics: Measures of Center Secto 2.3 Descrptve Statstcs: Measures of Ceter Frequec dstrbutos are helpful provdg formato about categorcal data, but wth umercal data we ma wat more formato. Statstc: s a umercal measure calculated

More information

Differentiated Service of Streaming Media Playback Technology

Differentiated Service of Streaming Media Playback Technology Iteratoal Coferece o Advaced Iformato ad Commucato Techology for Educato (ICAICTE 2013) Dfferetated Servce of Streamg Meda Playback Techology CHENG Z-ao 1 MENG Bo 1 WANG Da-hua 1 ZHAO Yue 1 1 Iformatzato

More information

APR 1965 Aggregation Methodology

APR 1965 Aggregation Methodology Sa Joaqu Valley Ar Polluto Cotrol Dstrct APR 1965 Aggregato Methodology Approved By: Sged Date: March 3, 2016 Araud Marjollet, Drector of Permt Servces Backgroud Health rsk modelg ad the collecto of emssos

More information

Area and Power Efficient Modulo 2^n+1 Multiplier

Area and Power Efficient Modulo 2^n+1 Multiplier Iteratoal Joural of Moder Egeerg Research (IJMER) www.jmer.com Vol.3, Issue.3, May-Jue. 013 pp-137-1376 ISSN: 49-6645 Area ad Power Effcet Modulo ^+1 Multpler K. Ptambar Patra, 1 Saket Shrvastava, Sehlata

More information

Optimal Allocation of Complex Equipment System Maintainability

Optimal Allocation of Complex Equipment System Maintainability Optmal Allocato of Complex Equpmet System ataablty X Re Graduate School, Natoal Defese Uversty, Bejg, 100091, Cha edcal Protecto Laboratory, Naval edcal Research Isttute, Shagha, 200433, Cha Emal:rexs841013@163.com

More information

Enumerating XML Data for Dynamic Updating

Enumerating XML Data for Dynamic Updating Eumeratg XML Data for Dyamc Updatg Lau Ho Kt ad Vcet Ng Departmet of Computg, The Hog Kog Polytechc Uversty, Hug Hom, Kowloo, Hog Kog cstyg@comp.polyu.edu.h Abstract I ths paper, a ew mappg model, called

More information

Constructive Semi-Supervised Classification Algorithm and Its Implement in Data Mining

Constructive Semi-Supervised Classification Algorithm and Its Implement in Data Mining Costructve Sem-Supervsed Classfcato Algorthm ad Its Implemet Data Mg Arvd Sgh Chadel, Arua Twar, ad Naredra S. Chaudhar Departmet of Computer Egg. Shr GS Ist of Tech.& Sc. SGSITS, 3, Par Road, Idore (M.P.)

More information

Eight Solved and Eight Open Problems in Elementary Geometry

Eight Solved and Eight Open Problems in Elementary Geometry Eght Solved ad Eght Ope Problems Elemetary Geometry Floret Smaradache Math & Scece Departmet Uversty of New Mexco, Gallup, US I ths paper we revew eght prevous proposed ad solved problems of elemetary

More information

Point Estimation-III: General Methods for Obtaining Estimators

Point Estimation-III: General Methods for Obtaining Estimators Pot Estmato-III: Geeral Methods for Obtag Estmators RECAP 0.-0.6 Data: Radom Sample from a Populato of terest o Real valued measuremets: o Assumpto (Hopefully Reasoable) o Model: Specfed Probablty Dstrbuto

More information

A Comparison of Univariate Smoothing Models: Application to Heart Rate Data Marcus Beal, Member, IEEE

A Comparison of Univariate Smoothing Models: Application to Heart Rate Data Marcus Beal, Member, IEEE A Comparso of Uvarate Smoothg Models: Applcato to Heart Rate Data Marcus Beal, Member, IEEE E-mal: bealm@pdx.edu Abstract There are a umber of uvarate smoothg models that ca be appled to a varety of olear

More information

Chapter 3 Descriptive Statistics Numerical Summaries

Chapter 3 Descriptive Statistics Numerical Summaries Secto 3.1 Chapter 3 Descrptve Statstcs umercal Summares Measures of Cetral Tedecy 1. Mea (Also called the Arthmetc Mea) The mea of a data set s the sum of the observatos dvded by the umber of observatos.

More information

MINIMIZATION OF THE VALUE OF DAVIES-BOULDIN INDEX

MINIMIZATION OF THE VALUE OF DAVIES-BOULDIN INDEX MIIMIZATIO OF THE VALUE OF DAVIES-BOULDI IDEX ISMO ÄRÄIE ad PASI FRÄTI Departmet of Computer Scece, Uversty of Joesuu Box, FI-800 Joesuu, FILAD ABSTRACT We study the clusterg problem whe usg Daves-Bould

More information

Journal of Chemical and Pharmaceutical Research, 2015, 7(3): Research Article

Journal of Chemical and Pharmaceutical Research, 2015, 7(3): Research Article Avalable ole www.ocpr.com Joural of Chemcal ad Pharmaceutcal Research, 2015, 73):476-481 Research Artcle ISSN : 0975-7384 CODENUSA) : JCPRC5 Research o cocept smlarty calculato method based o sematc grd

More information

Parallel Ant Colony for Nonlinear Function Optimization with Graphics Hardware Acceleration

Parallel Ant Colony for Nonlinear Function Optimization with Graphics Hardware Acceleration Proceedgs of the 009 IEEE Iteratoal Coferece o Systems Ma ad Cyberetcs Sa Atoo TX USA - October 009 Parallel At Coloy for Nolear Fucto Optmzato wth Graphcs Hardware Accelerato Wehag Zhu Departmet of Idustral

More information

Using The ACO Algorithm in Image Segmentation for Optimal Thresholding 陳香伶財務金融系

Using The ACO Algorithm in Image Segmentation for Optimal Thresholding 陳香伶財務金融系 教專研 95P- Usg The ACO Algorthm Image Segmetato for Optmal Thresholdg Abstract Usg The ACO Algorthm Image Segmetato for Optmal Thresholdg 陳香伶財務金融系 Despte the fact that the problem of thresholdg has bee qute

More information

ITEM ToolKit Technical Support Notes

ITEM ToolKit Technical Support Notes ITEM ToolKt Notes Fault Tree Mathematcs Revew, Ic. 2875 Mchelle Drve Sute 300 Irve, CA 92606 Phoe: +1.240.297.4442 Fax: +1.240.297.4429 http://www.itemsoft.com Page 1 of 15 6/1/2016 Copyrght, Ic., All

More information

Fitting. We ve learned how to detect edges, corners, blobs. Now what? We would like to form a. compact representation of

Fitting. We ve learned how to detect edges, corners, blobs. Now what? We would like to form a. compact representation of Fttg Fttg We ve leared how to detect edges, corers, blobs. Now what? We would lke to form a hgher-level, h l more compact represetato of the features the mage b groupg multple features accordg to a smple

More information

Software Clustering Techniques and the Use of Combined Algorithm

Software Clustering Techniques and the Use of Combined Algorithm Software Clusterg Techques ad the Use of Combed Algorthm M. Saeed, O. Maqbool, H.A. Babr, S.Z. Hassa, S.M. Sarwar Computer Scece Departmet Lahore Uversty of Maagemet Sceces DHA Lahore, Paksta oaza@lums.edu.pk

More information

For all questions, answer choice E) NOTA" means none of the above answers is correct. A) 50,500 B) 500,000 C) 500,500 D) 1,001,000 E) NOTA

For all questions, answer choice E) NOTA means none of the above answers is correct. A) 50,500 B) 500,000 C) 500,500 D) 1,001,000 E) NOTA For all questos, aswer choce " meas oe of the above aswers s correct.. What s the sum of the frst 000 postve tegers? A) 50,500 B) 500,000 C) 500,500 D),00,000. What s the sum of the tegers betwee 00 ad

More information

Unsupervised Discretization Using Kernel Density Estimation

Unsupervised Discretization Using Kernel Density Estimation Usupervsed Dscretzato Usg Kerel Desty Estmato Maregle Bba, Floraa Esposto, Stefao Ferll, Ncola D Mauro, Teresa M.A Basle Departmet of Computer Scece, Uversty of Bar Va Oraboa 4, 7025 Bar, Italy {bba,esposto,ferll,dm,basle}@d.uba.t

More information

Using Linear-threshold Algorithms to Combine Multi-class Sub-experts

Using Linear-threshold Algorithms to Combine Multi-class Sub-experts Usg Lear-threshold Algorthms to Combe Mult-class Sub-experts Chrs Mesterharm MESTERHA@CS.RUTGERS.EDU Rutgers Computer Scece Departmet 110 Frelghuyse Road Pscataway, NJ 08854 USA Abstract We preset a ew

More information

ChEn 475 Statistical Analysis of Regression Lesson 1. The Need for Statistical Analysis of Regression

ChEn 475 Statistical Analysis of Regression Lesson 1. The Need for Statistical Analysis of Regression Statstcal-Regresso_hadout.xmcd Statstcal Aalss of Regresso ChE 475 Statstcal Aalss of Regresso Lesso. The Need for Statstcal Aalss of Regresso What do ou do wth dvdual expermetal data pots? How are the

More information

International Mathematical Forum, 1, 2006, no. 31, ON JONES POLYNOMIALS OF GRAPHS OF TORUS KNOTS K (2, q ) Tamer UGUR, Abdullah KOPUZLU

International Mathematical Forum, 1, 2006, no. 31, ON JONES POLYNOMIALS OF GRAPHS OF TORUS KNOTS K (2, q ) Tamer UGUR, Abdullah KOPUZLU Iteratoal Mathematcal Forum,, 6, o., 57-54 ON JONES POLYNOMIALS OF RAPHS OF TORUS KNOTS K (, q ) Tamer UUR, Abdullah KOPUZLU Atatürk Uverst Scece Facult Dept. of. Math. 54 Erzurum, Turkey tugur@atau.edu.tr

More information

Nine Solved and Nine Open Problems in Elementary Geometry

Nine Solved and Nine Open Problems in Elementary Geometry Ne Solved ad Ne Ope Problems Elemetary Geometry Floret Smaradache Math & Scece Departmet Uversty of New Mexco, Gallup, US I ths paper we revew e prevous proposed ad solved problems of elemetary D geometry

More information

COMSC 2613 Summer 2000

COMSC 2613 Summer 2000 Programmg II Fal Exam COMSC 63 Summer Istructos: Name:. Prt your ame the space provded Studet Id:. Prt your studet detfer the space Secto: provded. Date: 3. Prt the secto umber of the secto whch you are

More information

A genetic procedure used to train RFB neural networks

A genetic procedure used to train RFB neural networks A geetc procedure used to tra RFB eural etworks Costat-Iula VIZITIU Commucatos ad Electroc Systems Departmet Mltary Techcal Academy George Cosbuc Aveue 8-83 5 th Dstrct Bucharest ROMANIA vc@mta.ro http://www.mta.ro

More information

Eight Solved and Eight Open Problems in Elementary Geometry

Eight Solved and Eight Open Problems in Elementary Geometry Eght Solved ad Eght Ope Problems Elemetary Geometry Floret Smaradache Math & Scece Departmet Uversty of New Mexco, Gallup, US I ths paper we revew eght prevous proposed ad solved problems of elemetary

More information

Process Quality Evaluation based on Maximum Entropy Principle. Yuhong Wang, Chuanliang Zhang, Wei Dai a and Yu Zhao

Process Quality Evaluation based on Maximum Entropy Principle. Yuhong Wang, Chuanliang Zhang, Wei Dai a and Yu Zhao Appled Mechacs ad Materals Submtted: 204-08-26 ISSN: 662-7482, Vols. 668-669, pp 625-628 Accepted: 204-09-02 do:0.4028/www.scetfc.et/amm.668-669.625 Ole: 204-0-08 204 Tras Tech Publcatos, Swtzerlad Process

More information

An Ensemble Multi-Label Feature Selection Algorithm Based on Information Entropy

An Ensemble Multi-Label Feature Selection Algorithm Based on Information Entropy The Iteratoal Arab Joural of Iformato Techology, Vol., No. 4, July 204 379 A Esemble Mult-Label Feature Selecto Algorthm Based o Iformato Etropy Shg L, Zheha Zhag, ad Jaq Dua School of Computer Scece,

More information

Adaptive Clustering Algorithm for Mining Subspace Clusters in High-Dimensional Data Stream *

Adaptive Clustering Algorithm for Mining Subspace Clusters in High-Dimensional Data Stream * ISSN 673-948 CODEN JKYTA8 E-mal: fcst@vp.63.com Joural of Froters of Computer Scece ad Techology http://www.ceaj.org 673-948/200/04(09)-0859-06 Tel: +86-0-566056 DOI: 0.3778/j.ss.673-948.200.09.009 *,2,

More information

Interactive Change Detection Using High Resolution Remote Sensing Images Based on Active Learning with Gaussian Processes

Interactive Change Detection Using High Resolution Remote Sensing Images Based on Active Learning with Gaussian Processes Iteractve Chage Detecto Usg Hgh Resoluto Remote Sesg Images Based o Actve Learg wth Gaussa Processes Hu Ru a, Hua Yu a,, Pgpg Huag b, We Yag a a School of Electroc Iformato, Wuha Uversty, 43007 Wuha, Cha

More information

Automatic Document Clustering and Knowledge Discovery

Automatic Document Clustering and Knowledge Discovery Iteratoal Joural of Egeerg ad Techcal Research (IJETR) ISSN: 31-0869, Volume-, Issue-1, December 014 Automatc Documet Clusterg ad Koledge Dscovery Ms. Khuresh Ruhsar Afree Itzar Ahmed, Mrs. Vshaarma P

More information

Associated Pagerank: A Content Relevance Weighted Pagerank Algorithm

Associated Pagerank: A Content Relevance Weighted Pagerank Algorithm Assocated Pagerak: A Cotet Relevace Weghted Pagerak Algorthm Jh-Shh Hsu,Cha-Che Ye Assocated Pagerak: A Cotet Relevace Weghted Pagerak Algorthm 1 Jh-Shh Hsu, 2 Cha-Che Ye 1 Natoal Yul Uversty of Scece

More information

Fuzzy Partition based Similarity Measure for Spectral Clustering. Xi an , China Abstract

Fuzzy Partition based Similarity Measure for Spectral Clustering. Xi an , China Abstract Iteratoal Joural of Sgal Processg, Image Processg ad Patter Recogto Vol.9, No., (6), pp.47-48 http://dx.do.org/.457/sp.6.9..39 Fuzzy Partto based Smlarty Measure for Spectral Clusterg Yfag Yag ad Yupg

More information

Developer Recommendation with Awareness of Accuracy and Cost

Developer Recommendation with Awareness of Accuracy and Cost Developer Recommedato wth Awareess of Accuracy ad Cost * J Lu, Yquz Ta State Key Lab of Software Egeerg Computer School, Wuha Uversty Wuha, Cha *Correspodg author jlu@whu.edu.c tayquz@whu.edu.c Lag Hog

More information

Machine Learning. CS 2750 Machine Learning. Administration. Lecture 1. Milos Hauskrecht 5329 Sennott Square, x4-8845

Machine Learning. CS 2750 Machine Learning. Administration. Lecture 1. Milos Hauskrecht 5329 Sennott Square, x4-8845 CS 75 Mache Learg Lecture Mache Learg Mlos Hauskrecht mlos@cs.ptt.edu 539 Seott Square, 5 people.cs.ptt.edu/~mlos/courses/cs75/ Admstrato Istructor: Prof. Mlos Hauskrecht mlos@cs.ptt.edu 539 Seott Square,

More information

Vertex Odd Divisor Cordial Labeling of Graphs

Vertex Odd Divisor Cordial Labeling of Graphs IJISET - Iteratoal Joural of Iovatve Scece, Egeerg & Techology, Vol. Issue 0, October 0. www.jset.com Vertex Odd Dvsor Cordal Labelg of Graphs ISSN 48 68 A. Muthaya ad P. Pugaleth Assstat Professor, P.G.

More information

Blind Steganalysis for Digital Images using Support Vector Machine Method

Blind Steganalysis for Digital Images using Support Vector Machine Method 06 Iteratoal Symposum o Electrocs ad Smart Devces (ISESD) November 9-30, 06 Bld Stegaalyss for Dgtal Images usg Support Vector Mache Method Marcelus Hery Meor School of Electrcal Egeerg ad Iformatcs Badug

More information

Classification Web Pages By Using User Web Navigation Matrix By Mementic Algorithm

Classification Web Pages By Using User Web Navigation Matrix By Mementic Algorithm Classfcato Web Pages By Usg User Web Navgato Matrx By Memetc Algorthm 1 Parvaeh roustae 2 Mehd sadegh zadeh 1 Studet of Computer Egeerg Software EgeergDepartmet of ComputerEgeerg, Bushehr brach,

More information

AN IMPROVED TEXT CLASSIFICATION METHOD BASED ON GINI INDEX

AN IMPROVED TEXT CLASSIFICATION METHOD BASED ON GINI INDEX Joural of Theoretcal ad Appled Iformato Techology 30 th September 0. Vol. 43 No. 005-0 JATIT & LLS. All rghts reserved. ISSN: 99-8645 www.jatt.org E-ISSN: 87-395 AN IMPROVED TEXT CLASSIFICATION METHOD

More information

Application of Genetic Algorithm for Computing a Global 3D Scene Exploration

Application of Genetic Algorithm for Computing a Global 3D Scene Exploration Joural of Software Egeerg ad Applcatos, 2011, 4, 253-258 do:10.4236/jsea.2011.44028 Publshed Ole Aprl 2011 (http://www.scrp.org/joural/jsea) 253 Applcato of Geetc Algorthm for Computg a Global 3D Scee

More information

A Comparison of Heuristics for Scheduling Spatial Clusters to Reduce I/O Cost in Spatial Join Processing

A Comparison of Heuristics for Scheduling Spatial Clusters to Reduce I/O Cost in Spatial Join Processing Edth Cowa Uversty Research Ole ECU Publcatos Pre. 20 2006 A Comparso of Heurstcs for Schedulg Spatal Clusters to Reduce I/O Cost Spatal Jo Processg Jta Xao Edth Cowa Uversty 0.09/ICMLC.2006.258779 Ths

More information

Biconnected Components

Biconnected Components Presetato for use wth the textbook, Algorthm Desg ad Applcatos, by M. T. Goodrch ad R. Tamassa, Wley, 2015 Bcoected Compoets SEA PVD ORD FCO SNA MIA 2015 Goodrch ad Tamassa Bcoectvty 1 Applcato: Networkg

More information

CLUSTERING ASSISTED FUNDAMENTAL MATRIX ESTIMATION

CLUSTERING ASSISTED FUNDAMENTAL MATRIX ESTIMATION CLUSERING ASSISED FUNDAMENAL MARIX ESIMAION Hao Wu ad Y Wa School of Iformato Scece ad Egeerg, Lazhou Uversty, Cha wuhao1195@163com, wayjs@163com ABSRAC I computer vso, the estmato of the fudametal matrx

More information

Region Matching by Optimal Fuzzy Dissimilarity

Region Matching by Optimal Fuzzy Dissimilarity Rego Matchg by Optmal Fuzzy Dssmlarty Zhaggu Zeg, Ala Fu ad Hog Ya School of Electrcal ad formato Egeerg The Uversty of Sydey Phoe: +6--935-6659 Fax: +6--935-3847 Emal: zzeg@ee.usyd.edu.au Abstract: Ths

More information

Content-Based Image Retrieval Using Associative Memories

Content-Based Image Retrieval Using Associative Memories Proceedgs of the 6th WSEAS It. Coferece o ELECOMMUNICAIONS ad INFORMAICS, Dallas, exas, USA, March 22-24, 2007 99 Cotet-Based Image Retreval Usg Assocatve Memores ARUN KULKARNI Computer Scece Departmet

More information

LP: example of formulations

LP: example of formulations LP: eample of formulatos Three classcal decso problems OR: Trasportato problem Product-m problem Producto plag problem Operatos Research Massmo Paolucc DIBRIS Uversty of Geova Trasportato problem The decso

More information

The Similarity Measures and their Impact on OODB Fragmentation Using Hierarchical Clustering Algorithms

The Similarity Measures and their Impact on OODB Fragmentation Using Hierarchical Clustering Algorithms The Smlarty Measures ad ther Impact o OODB Fragmetato Usg Herarchcal Clusterg Algorthms ADRIAN SERGIU DARABANT, HOREA TODORAN, OCTAVIAN CRET, GEORGE CHIS Dept. of Computer Scece Babes Bolya Uversty, Techcal

More information

FEATURE SELECTION ON COMBINATIONS FOR EFFICIENT LEARNING FROM IMAGES. Rong Xiao, Lei Zhang, and Hong-Jiang Zhang

FEATURE SELECTION ON COMBINATIONS FOR EFFICIENT LEARNING FROM IMAGES. Rong Xiao, Lei Zhang, and Hong-Jiang Zhang FEATURE SELECTION ON COMBINATIONS FOR EFFICIENT LEARNING FROM IMAGES Rog Xao, Le Zhag, ad Hog-Jag Zhag Mcrosoft Research Asa, Bejg 100080, P.R. Cha {t-rxao, lezhag, hjzhag}@mcrosoft.com ABSTRACT Due to

More information

Fingerprint Classification Based on Spectral Features

Fingerprint Classification Based on Spectral Features Fgerprt Classfcato Based o Spectral Features Hosse Pourghassem Tarbat Modares Uversty h_poorghasem@modares.ac.r Hassa Ghassema Tarbat Modares Uversty ghassem@modares.ac.r Abstract: Fgerprt s oe of the

More information

An Optimized Algorithm for Big Data Classification using Neuro Fuzzy Approach

An Optimized Algorithm for Big Data Classification using Neuro Fuzzy Approach Ida Joural of Scece ad Techology, Vol 9(28), DOI: 0.7485/jst/206/v928/87995, July 206 ISSN (Prt) : 0974-6846 ISSN (Ole) : 0974-5645 A Optmzed Algorthm for Bg Data Classfcato usg Neuro Fuzzy Approach Naveet

More information

An Ensemble Approach to Classifier Construction based on Bootstrap Aggregation

An Ensemble Approach to Classifier Construction based on Bootstrap Aggregation A Esemble Approach to Classfer Costructo based o Bootstrap Aggregato Dewa Md. Fard Jahagragar Uversty Dhaka-342, Bagladesh Mohammad Zahdur Rahma Jahagragar Uversty Dhaka-342, Bagladesh Chowdhury Mofzur

More information

Collaborative Filtering Support for Adaptive Hypermedia

Collaborative Filtering Support for Adaptive Hypermedia Collaboratve Flterg Support for Adaptve Hypermeda Mart Balík, Iva Jelíek Departmet of Computer Scece ad Egeerg, Faculty of Electrcal Egeerg Czech Techcal Uversty Karlovo áměstí 3, 35 Prague, Czech Republc

More information

A PROCEDURE FOR SOLVING INTEGER BILEVEL LINEAR PROGRAMMING PROBLEMS

A PROCEDURE FOR SOLVING INTEGER BILEVEL LINEAR PROGRAMMING PROBLEMS ISSN: 39-8753 Iteratoal Joural of Iovatve Research Scece, Egeerg ad Techology A ISO 397: 7 Certfed Orgazato) Vol. 3, Issue, Jauary 4 A PROCEDURE FOR SOLVING INTEGER BILEVEL LINEAR PROGRAMMING PROBLEMS

More information

Term Weighting Schemes Experiment Based on SVD for Malay Text Retrieval

Term Weighting Schemes Experiment Based on SVD for Malay Text Retrieval IJCSS Iteratoal Joural o Computer Scece ad etwork Securty, VOL.8 o.0, October 2008 357 Term Weghtg Schemes Expermet Based o SVD or Malay Text Retreval ordaah Ab Samat, Masrah Azrah Azm Murad, Muhamad Tauk

More information

Some Interesting SAR Change Detection Studies

Some Interesting SAR Change Detection Studies Some Iterestg SAR Chage Detecto Studes Lesle M. ovak Scetfc Sstems Compa, Ic. 500 West Cummgs Park, Sute 3000 Wobur, MA 080 USA E-mal lovak@ssc.co ovakl@charter.et ABSTRACT Performace results of coheret

More information

Transistor/Gate Sizing Optimization

Transistor/Gate Sizing Optimization Trasstor/Gate Szg Optmzato Gve: Logc etwork wth or wthout cell lbrary Fd: Optmal sze for each trasstor/gate to mmze area or power, both uder delay costrat Statc szg: based o tmg aalyss ad cosder all paths

More information

A Novel Clustering Algorithm Based on Graph Matching

A Novel Clustering Algorithm Based on Graph Matching JOURNAL OF SOFTWARE, VOL. 8, NO. 4, APRIL 203 035 A Novel Clusterg Algorthm Based o raph Matchg uoyua L School of Computer Scece ad Techology, Cha Uversty of Mg ad Techology, Xuzhou, Cha State Key Laboratory

More information

Optimization of Light Switching Pattern on Large Scale using Genetic Algorithm

Optimization of Light Switching Pattern on Large Scale using Genetic Algorithm Optmzato of Lght Swtchg Patter o Large Scale usg Geetc Algorthm Pryaka Sambyal, Pawaesh Abrol 2, Parvee Lehaa 3,2 Departmet of Computer Scece & IT 3 Departmet of Electrocs Uversty of Jammu, Jammu, J&K,

More information

A New Hybrid Audio Classification Algorithm Based on SVM Weight Factor and Euclidean Distance

A New Hybrid Audio Classification Algorithm Based on SVM Weight Factor and Euclidean Distance Proceedgs of the 2007 WSEAS Iteratoal Coferece o Computer Egeerg ad Applcatos, Gold Coast, Australa, Jauary 7-9, 2007 52 A New Hybrd Audo Classfcato Algorthm Based o SVM Weght Factor ad Eucldea Dstace

More information

Fuzzy ID3 Decision Tree Approach for Network Reliability Estimation

Fuzzy ID3 Decision Tree Approach for Network Reliability Estimation IJCSI Iteratoal Joural of Computer Scece Issues, Vol. 9, Issue 1, o 1, Jauary 2012 ISS (Ole): 1694-0814 www.ijcsi.org 446 Fuzzy ID3 Decso Tree Approach for etwor Relablty Estmato A. Ashaumar Sgh 1, Momtaz

More information

SVM Classification Method Based Marginal Points of Representative Sample Sets

SVM Classification Method Based Marginal Points of Representative Sample Sets P P College P P College P Iteratoal Joural of Iformato Techology Vol. No. 9 005 SVM Classfcato Method Based Margal Pots of Represetatve Sample Sets Wecag ZhaoP P, Guagrog JP P, Ru NaP P, ad Che FegP of

More information

Mining Web Content Outliers using Structure Oriented Weighting Techniques and N-Grams

Mining Web Content Outliers using Structure Oriented Weighting Techniques and N-Grams 2005 ACM Symposum o Appled Computg Mg Web Cotet Outlers usg Structure Oreted Weghtg Techques ad N-Grams Mal Agyemag Ke Barer Rada S. Alha Departmet of Computer Scece Uversty of Calgary 2500 Uversty Drve

More information

Greater Knowledge Extraction Based on Fuzzy Logic And GKPFCM Clustering Algorithm

Greater Knowledge Extraction Based on Fuzzy Logic And GKPFCM Clustering Algorithm 6th WSEAS It. Coferece o Computatoal Itellgece, Ma-Mache Systems ad Cyberetcs, Teerfe, Spa, December 14-16, 2007 47 Greater Kowledge Extracto Based o uzzy Logc Ad GKPCM Clusterg Algorthm BEJAMÍ OJEDA-MAGAÑA

More information

ABSTRACT Keywords

ABSTRACT Keywords A Preprocessg Scheme for Hgh-Cardalty Categorcal Attrbutes Classfcato ad Predcto Problems Daele Mcc-Barreca ClearCommerce Corporato 1100 Metrc Blvd. Aust, TX 78732 ABSTRACT Categorcal data felds characterzed

More information

COMBINATORIAL METHOD OF POLYNOMIAL EXPANSION OF SYMMETRIC BOOLEAN FUNCTIONS

COMBINATORIAL METHOD OF POLYNOMIAL EXPANSION OF SYMMETRIC BOOLEAN FUNCTIONS COMBINATORIAL MTHOD O POLYNOMIAL XPANSION O SYMMTRIC BOOLAN UNCTIONS Dala A. Gorodecky The Uted Isttute of Iformatcs Prolems of Natoal Academy of Sceces of Belarus, Msk,, Belarus, dala.gorodecky@gmal.com.

More information

Evaluation of Node and Link Importance Based on Network Topology and Traffic Information DU Xun-Wei, LIU Jun, GUO Wei

Evaluation of Node and Link Importance Based on Network Topology and Traffic Information DU Xun-Wei, LIU Jun, GUO Wei Advaced Materals Research Submtted: 2014-08-29 ISSN: 1662-8985, Vols. 1049-1050, pp 1765-1770 Accepted: 2014-09-01 do:10.4028/www.scetfc.et/amr.1049-1050.1765 Ole: 2014-10-10 2014 Tras Tech Publcatos,

More information

From Math to Efficient Hardware. James C. Hoe Department of ECE Carnegie Mellon University

From Math to Efficient Hardware. James C. Hoe Department of ECE Carnegie Mellon University FFT Compler: From Math to Effcet Hardware James C. Hoe Departmet of ECE Carege Mello Uversty jot wor wth Peter A. Mlder, Fraz Frachett, ad Marus Pueschel the SPIRAL project wth support from NSF ACR-3493,

More information

Delay based Duplicate Transmission Avoid (DDA) Coordination Scheme for Opportunistic routing

Delay based Duplicate Transmission Avoid (DDA) Coordination Scheme for Opportunistic routing Delay based Duplcate Trasmsso Avod (DDA) Coordato Scheme for Opportustc routg Ng L, Studet Member IEEE, Jose-Fera Martez-Ortega, Vcete Heradez Daz Abstract-Sce the packet s trasmtted to a set of relayg

More information

Office Hours. COS 341 Discrete Math. Office Hours. Homework 8. Currently, my office hours are on Friday, from 2:30 to 3:30.

Office Hours. COS 341 Discrete Math. Office Hours. Homework 8. Currently, my office hours are on Friday, from 2:30 to 3:30. Oce Hours Curretly, my oce hours are o Frday, rom :30 to 3:30. COS 31 Dscrete Math 1 Oce Hours Curretly, my oce hours are o Frday, rom :30 to 3:30. Nobody seems to care. Chage oce hours? Tuesday, 8 PM

More information

Marcus Gallagher School of Information Technology and Electrical Engineering The University of Queensland QLD 4072, Australia

Marcus Gallagher School of Information Technology and Electrical Engineering The University of Queensland QLD 4072, Australia O the Importace of Dversty Mateace Estmato of Dstrbuto Algorthms Bo Yua School of Iformato Techology ad Electrcal Egeerg The Uversty of Queeslad QLD 4072, Australa +6-7-3365636 boyua@tee.uq.edu.au Marcus

More information

NEURO FUZZY MODELING OF CONTROL SYSTEMS

NEURO FUZZY MODELING OF CONTROL SYSTEMS NEURO FUZZY MODELING OF CONTROL SYSTEMS Efré Gorrosteta, Carlos Pedraza Cetro de Igeería y Desarrollo Idustral CIDESI, Av Pe de La Cuesta 70. Des. Sa Pablo. Querétaro, Qro, Méxco gorrosteta@teso.mx pedraza@cdes.mx

More information

DEEP (Displacement Estimation Error Back-Propagation) Method for Cascaded ViSPs (Visually Servoed Paired Structured Light Systems)

DEEP (Displacement Estimation Error Back-Propagation) Method for Cascaded ViSPs (Visually Servoed Paired Structured Light Systems) DEEP (Dsplacemet Estmato Error Back-Propagato) Method for Cascaded VSPs (Vsually Servoed Pared Structured Lght Systems) Haem Jeo 1), Jae-Uk Sh 2), Wachoel Myeog 3), Yougja Km 4), ad *Hyu Myug 5) 1), 3),

More information

Software reliability is defined as the probability of failure

Software reliability is defined as the probability of failure Evolutoary Regresso Predcto for Software Cumulatve Falure Modelg: a comparatve study M. Beaddy, M. Wakrm & S. Aljahdal 2 : Dept. of Math. & Ifo. Equpe MMS, Ib Zohr Uversty Morocco. beaddym@yahoo.fr 2:

More information

Comparison Studies on Classification for Remote Sensing Image Based on Data Mining Method

Comparison Studies on Classification for Remote Sensing Image Based on Data Mining Method Hag Xao ad Xub Zhag Comparso Studes o Classfcato for Remote Sesg Image Based o Data Mg Method Hag XIAO 1, Xub ZHANG 1 1: School of Electroc, Iformato ad Electrcal Egeerg Shagha Jaotog Uversty No. 1954,

More information

Keywords- clustering; naïve Bayesian classifier; boosting; hybrid classifier.

Keywords- clustering; naïve Bayesian classifier; boosting; hybrid classifier. World of Computer Scece ad Iformato Techology Joural (WCSIT) ISSN: 2221-0741 Vol. 1, No. 3, 105-109, 2011. A Hybrd Classfer usg Boostg, Clusterg, ad Naïve Bayesa Classfer A. J. M. Abu Afza, Dewa Md. Fard,

More information

Expert Systems with Applications

Expert Systems with Applications Expert Systems wth Applcatos 38 (0) 9400 9406 Cotets lsts avalable at SceceDrect Expert Systems wth Applcatos joural homepage: www.elsever.com/locate/eswa OPSIS wth fuzzy belef structure for group belef

More information

Grid Resource Discovery Algorithm Based on Distance

Grid Resource Discovery Algorithm Based on Distance 966 JOURNAL OF SOFTWARE, OL. 9, NO., NOEMBER 4 Grd Resource Dscovery Algorthm Based o Dstace Zhogpg Zhag,, Log He, Chao Zhag The School of Iformato Scece ad Egeerg, Yasha Uversty, Qhuagdao, Hebe, 664,

More information

Spatial Interpolation Using Neural Fuzzy Technique

Spatial Interpolation Using Neural Fuzzy Technique Wog, K.W., Gedeo, T., Fug, C.C. ad Wog, P.M. (00) Spatal terpolato usg eural fuzzy techque. I: Proceedgs of the 8th Iteratoal Coferece o Neural Iformato Processg (ICONIP), Shagha, Cha Spatal Iterpolato

More information

Weighting Cache Replace Algorithm for Storage System

Weighting Cache Replace Algorithm for Storage System Weghtg Cache Replace Algorthm for Storage System Yhu Luo 2 Chagsheg Xe 2 Chegfeg Zhag 2 School of mathematcs ad Computer Scece, Hube Uversty, Wuha 430062, P.R. Cha 2 Natoal Storage System Laboratory, School

More information

Performance Impact of Load Balancers on Server Farms

Performance Impact of Load Balancers on Server Farms erformace Impact of Load Balacers o Server Farms Ypg Dg BMC Software Server Farms have gaed popularty for provdg scalable ad relable computg / Web servces. A load balacer plays a key role ths archtecture,

More information

PERSPECTIVES OF THE USE OF GENETIC ALGORITHMS IN CRYPTANALYSIS

PERSPECTIVES OF THE USE OF GENETIC ALGORITHMS IN CRYPTANALYSIS PERSPECTIVES OF THE USE OF GENETIC ALGORITHMS IN CRYPTANALYSIS Lal Besela Sokhum State Uversty, Poltkovskaa str., Tbls, Georga Abstract Moder cryptosystems aalyss s a complex task, the soluto of whch s

More information

A NOVEL ADAPTIVE FUZZY INFERENCE SYSTEM FOR MOBILE ROBOT NAVIGATION

A NOVEL ADAPTIVE FUZZY INFERENCE SYSTEM FOR MOBILE ROBOT NAVIGATION A NOVEL ADAPTIVE FUZZY INFERENCE SYSTEM FOR MOBILE ROBOT NAVIGATION J. HOSSEN, S. SAYEED, 3 A. HUDAYA, 4 M. F. A. ABDULLAH, 5 I. YUSOF Faculty of Egeerg ad Techology (FET), Multmeda Uversty (MMU), Malaysa,,3,4,5

More information

Network Security Evaluation Based on Variable Weight Fuzzy Cloud Model

Network Security Evaluation Based on Variable Weight Fuzzy Cloud Model 207 2 d Iteratoal Coferece o Computer Scece ad Techology (CST 207) ISBN: 978--60595-46-5 Networ Securty Evaluato Based o Varable Weght Fuzzy Cloud Model Yag JIANG a*, Cheg-ha LI, Zh-peg LI ad Mg-ca SUN

More information

TDT-2004: ADAPTIVE TOPIC TRACKING AT MARYLAND

TDT-2004: ADAPTIVE TOPIC TRACKING AT MARYLAND TDT-2004: ADAPTIVE TOPIC TRACKING AT MARYLAND Tamer Elsayed, Douglas W. Oard, Davd Doerma Isttute for Advaced r Studes Uversty of Marylad, College Park, MD 20742 Cotact author: telsayed@cs.umd.edu Gary

More information

WEB PAGE CLASSIFIERS FOR TOPICAL CRAWLER

WEB PAGE CLASSIFIERS FOR TOPICAL CRAWLER 244 WEB PAGE CLASSIFIERS FOR TOPICAL CRAWLER Dw H. Wdyatoro, Masayu L. Khodra, Paramta * School of Iformatcs ad Electrcal Egeerg - Isttut Tekolog Badug Jl. Gaesha 0 Badug Telephoe 62 22 250835 emal : dw@f.tb.ac.d,

More information

A Type of Variation of Hamilton Path Problem with Applications

A Type of Variation of Hamilton Path Problem with Applications Edth Cowa Uersty Research Ole ECU Publcatos Pre. 20 2008 A Type of Varato of Hamlto Path Problem wth Applcatos Jta Xao Edth Cowa Uersty Ju Wag Wezhou Uersty, Zhejag, Cha 0.09/ICYCS.2008.470 Ths artcle

More information

Pattern Extraction, Classification and Comparison Between Attribute Selection Measures

Pattern Extraction, Classification and Comparison Between Attribute Selection Measures Subrata Pramak et al. / (IJCSIT) Iteratoal Joural of Computer Scece ad Iformato Techoes, Vol. 1 (5), 010, 371-375 Patter Extracto, Classfcato ad Comparso Betwee ttrbute Selecto Measures Subrata Pramak,

More information