Progressive Filtering Using Multiresolution Histograms for Query by Humming System

Size: px
Start display at page:

Download "Progressive Filtering Using Multiresolution Histograms for Query by Humming System"

Transcription

1 Progressve Flterng Usng Multresoluton Hstograms for Query by Hummng System Trsladev C. Nagav 1 and Nagappa U. Bhajantr 2 1 Department of Computer Scence and Engneerng S.J.College of Engneerng Mysore, Karnataka, Inda tnagav@yahoo.com 2 Department of Computer Scence and Engneerng Government Engneerng College Chamarajanagar, Karnataka, Inda bhajan3nu@gmal.com Abstract. The rsng avalablty of dgtal musc stpulates effectve categorzaton and retreval methods. Real world scenaros are characterzed by mammoth musc collectons through pertnent and non-pertnent songs wth reference to the user nput. The prmary goal of the research work s to counter balance the perlous mpact of non-relevant songs through Progressve Flterng (PF) for Query by Hummng (QBH) system. PF s a technque of problem solvng through reduced space. Ths paper presents the concept of PF and ts effcent desgn based on Mult-Resoluton Hstograms (MRH) to accomplsh searchng n manfolds. Intally the entre musc database s searched to obtan hgh recall rate and narrowed search space. Later steps accomplsh slow search n the reduced perphery and acheve addtonal accuracy. Expermentaton on large musc database usng recursve programmng substantates the potental of the method. The outcome of proposed strategy glmpses that MRH effectvely locate the patterns. Dstances of MRH at lower level are the lower bounds of the dstances at hgher level, whch guarantees evason of false dsmssals durng PF. In due course, proposed method helps to strke a balance between effcency and effectveness. The system s scalable for large musc retreval systems and also data drven for performance optmzaton as an added advantage. Keywords: Progressve Flterng, Multresoluton Hstograms, Multresoluton Analyss and Query by Hummng. 1 Introducton Content based onlne musc enablng systems are beng developed and revamped n order to keep up wth expectatons of search and browse functonalty. These approaches as a group descrbe the Musc Informaton Retreval (MIR) systems and have been the area under exhaustve research. The ratonale of MIR research s to develop new theory and technques for processng and searchng musc databases by ts content. The QBH s a specal branch of MIR and also a popular content based musc retreval method where the user enters a search query by hummng.

2 Most of the research works on QBH[2][3][11][13][10] are based on the musc processng and focused on components lke melody extracton, representaton, smlarty measurement, sze of databases, query and search algorthms. The strong lterature supports the symbolc representaton for melody n the form of zero-cross detecton, energy, Modfed Dscrete Cosne Transform (MDCT) [5], ptch contour [10], rhythm [18] and quantzed ptch change descrptor [11]. Also there s a remarkable amount of research work [6] [7] [12] n the broader areas of smlarty measurement wth reference to musc patterns. Most of the approaches proposed n the lterature are not suted for real-world applcatons of musc retreval from a large musc database. Perhaps, s due to ether undue complexty n computaton whch leads to longer response tme or performance degradaton; subsequently leadng to erroneous retreval results. Strkng a balance between computaton and performance s the ultmate goal for such retreval systems. As a result there are a few speedng up [14] [19] [20] mechansms proposed for QBH. Qute extensve lterature[2][3][11][13][5][10][6][18][7][12] s avalable on QBH system, but there s no sgnfcant amount of lterature[21][9][16][1][8] towards desgnng flterng procedures. Authors [9] have projected a mathematcal analyss for a two-stage Query by Sngng\Hummng (QBSH) system, whch s the frst applcaton of PF to QBSH. In another work authors [17] proposed the concept of teratve deepenng Dynamc Tme Warpng (DTW), whch s a specal form of PF for speedng up DTW. Improvement n the form of mult phase PF for QBSH wthout much desgn analyss s presented n [19] [16]. Research work [17], proposes a smplfed verson of PF wth a constant computaton tme wth respect to survval rates for each comparson stage. However, most of the proposed methods stll portray the defct n metculous nvestgaton, effcency and effectveness. Therefore, n ths paper we have proposed to apply PF usng MRH approach for QBH system to accomplsh the mproved retreval accuracy. Real-world applcatons of musc retreval symbolze huge amount of non relevant songs wth reference to user queres causng nput mbalance problem. We expect that these two technques are most applcable to mtgate the effect of nput mbalance. The exhaustve expermentaton substantates the potental of proposed method to construct an effectve musc retreval system based on hummng nput. In ths paper, as explaned above, we have motvated to use PF as a flterng procedure. So, the next secton gves a bref vew of PF used for search space reducton. In secton 3 we have made dlgent dscusson on MRH framework for pattern matchng n musc retreval systems. Whle secton 4 elaborates the detals on smlarty measure stratagem for QBH. In secton 5, expermental results are presented and dscussed. The last secton enumerates the concluson. 2 Progressve Flterng (PF) The nspraton behnd PF s to apply a seres of comparsons, n whch each comparson wll select a smaller set that s lkely to contan the target of the nput query. The process s repeated untl fnal output contans lst of songs wth

3 approprate length, say 10 or 20. PF on QBH s performed by applyng multple stages of comparsons between a query and the songs n the database, usng an ncreasngly more complcated recognton mechansm to the decreasng canddate pool. So that the correct song wll reman n the fnal canddate pool wth a maxmum probablty. Intutvely, the ntal few stages are quck and mpure such that the most unlkely songs n the database are elmnated. On the other hand, the last few stages are more sophstcated and tme consumng such that the most lkely songs are dentfed [9]. After each stage of PF, the number of survvng canddates n the canddate pool of the database becomes smaller, and the recognton technque turns nto refned and effectual. The fnal output s the survvng canddate songs at the last stage. The multstage representaton of PF s shown n Fg. 1, where there are m stages, correspondng to dfferent comparson methods wth varyng complexty. Fg. 1. Multstage Representaton of Progressve Flterng For stage, the nput s the query and n -1 survvng songs from the prevous stage. The output of stage s a reduced set of canddate songs of sze n =n -1 s for the succeedng stage +1. In other words, each stage performs a flterng process that reduces the number of the canddate songs by a factor of the survval rate s. Each stage s characterzed by ts capablty to select the most lkely song canddates as the nput to the succeedng stage. For a gven stage, ths capablty can be represented by ts recognton rate, whch s defned as the probablty that the target song of a gven query s retaned n the output song lst of ths stage. Intutvely, the recognton rate s a functon of the survval rate.

4 3 Mult-Resoluton Hstograms (MRH) 3.1 Essence Over the past few years Mult-Resoluton Analyss (MRA) s recevng major attenton by researchers n the doman of computer graphcs, geometrc modelng, sgnal analyss and vsualzaton. It s a most mportant approach for profcently representng sgnals at many levels of detal wth numerous advantages lke compresson, dfferent layers of detals dsplay and progressve transmsson [4]. The term mult-resoluton s used n dverse perspectve such as mult-resoluton based wavelets, subdvsons, herarches and mult-grds. Hstograms provde a very effectve means of data reducton and depct many attrbutes of the data lke locaton, spread, and symmetry. It s also possble to decompose musc sgnal and buld hstograms on the underlyng cumulatve data dstrbutons. Hstograms gve better approxmaton for cumulatve data dstrbutons wth less space usage. However, hstograms provde a comprehensve analyss of the data dstrbuton by excludng sequence detals of values. MRH depcton s proposed for enhanced dscrmnaton of musc data based on ther poston fne ponts to assst effectual QBH system. The musc sgnal s recursvely decomposed and cumulatve hstograms are bult. Together all these cumulatve hstograms of a musc sgnal are remarked as MRH. The selecton of number of levels l s drectly proportonal to precson. Early phase cumulatve hstograms exhbt lesser amount of musc nformaton than later phases. These early phase MRH are used to provde quck approxmate answers to musc retreval queres n the begnnng. Later phase of searchng wth next level MRH gves us better estmates. In ths paper, a MRH based representaton s proposed to approxmate musc sgnal that s nvarant to shftng and scalng. The MRH representaton detects exstence of a pattern along wth shape matchng. In the early phases of searchng musc sgnals wth specfc specfed pattern are retreved, then search contnues for shape matchng yeldng result set of musc sgnals that are of nterest to the user. The herarchcal MRH framework s shown n Fg. 2. The symbol HR ndcates the hstogram representaton at level. Fg. 2. Mult-Resoluton Hstogram Representaton

5 3.2 Connotaton of Mathematcs Hstogram functon h counts the number of samples that fall nto each of the dsjont sets known as bns. Thus, f n s the total number of samples and t s the total number of bns, the hstogram functon h s defned as followng: t n h (1) 1 A cumulatve hstogram functon counts the cumulatve number of samples n all of the bns up to the specfed bn. In partcular, the cumulatve hstogram functon hc of a hstogram functon h j s specfed as: hc j1 h (2) Cumulatve frequency dstrbutons authorze users to approxmate frequences over numerous bns. There s no standard value for number of bns, and dfferent number of bns exhbt dfferent features of the samples. Based on the data dstrbuton and the objectve of the analyss, dfferent bn wdths are chosen. The numbers of bns t are calculated from a recommended bn wdth w as: max( S) mn( S) t w (3) where S=samples to be hstogrammed. Also the equal szed bn wdths are found by dvdng the range wth the number of bns t. Prmary objectve of our research s to develop search crtera usng smlarty based queres over one dmensonal musc sgnal. Such musc sgnal S s defned as a sequence of values: S=[s 1,s 2,...s N] (4) where N, the number of samples n S and s s a vector of values that was sampled at tmestamp t. Gven a musc sgnal database D={S,S,...S } (5) 1 2 M and a query Q, the am s to fnd all the musc sgnals n D that contan the specfed query Q as well as hstogram shape smlar to that of Q. MRH are constructed by dvdng the range [mn D,max D ] of musc database D nto t non-overlappng equal sze sub-regons, dentfed as hstogram bns. Hstogram H s s computed by countng the number of data values h ( t) that are located n each hstogram bn. s 1 2 t j H =[h,h,...h ] (6) A cumulatve MRH s a mappng that counts the cumulatve number of observatons n all of the bns up to the specfed bn. That s, the cumulatve hstogram HC s of a hstogram H s s defned as: HC s t h (7) 1 MRH at hgher levels have enhanced dscrmnaton power; however, the computaton of MRH Dstance (MRHD) at hgher scales s more expensve than those at lower

6 levels. So the number of levels trade-off should be establshed to balance complexty and precson. 3.3 Proposed Strategy MRH constructon system for database D s depcted n Fg. 2 and steps are shown n the followng algorthm 1. Algorthm 1: Procedure to Construct Mult-Resoluton Hstograms for Musc Database I n p u t : a musc database D, number of levels l and the number of hstogram bns t Out put: a hstogram data set H D 1. level l=0 2. repeat S of database D do 3. for each 4. dvde the S nto 2 l non overlappng equal segments S l,l and S r,l 5. locate max D and mn D values of the D 6. dvde the range [mn D,max D] nto t non-overlappng equal sze bns h l,l and h r,l 7. for each S l,l and Sr,l of D do 8. for each data pont l,l and sr,l S and S 9. for each bn hl,land hr,l do h s h then 10. f,,, s of l,l r,l respectvely do l lowerlmt l l l uppperlmt 11. h l,l h l,l 1; 12. end f h s h then 13. f,,, r lowerlmt r l r uppperlmt 14. h r,l h r,l 1; 15. end f 16. end for 17. end for 18. end for 19. nsert generated 20. end for 21. l=l+1 //ncrease level by 1 / / 22. untl (l=user specfed levels) 23. return the result data set H D H and H to the result data set H D S l,l S r,l

7 4 Smlarty Measure Stratagem for Query By Hummng 4.1 Mult-Resoluton Hstograms Dstance (MRHD) Measure In order to recognze the query pattern n the musc database, we have attempted to develop a smlarty functon whch separately consders sgnal frequency as well as postonal nformaton. Gven a song S of musc database D and hummng query Q, feature vectors H by means of the MRHD measure: where S f extracted from song MRH are matched wth query MRH t S Q S f Q f S Q (8) 1 2 MRHD( H, H ) mn( H, H ) s a Eucldean Dstance functon. 2 d( H, H ) t S Q s q 2 (9) 0 d( H, H ) ( h h ) H Q f 4.2 Database Prunng Usng Threshold MRHD for whole musc database s calculated usng equaton 8 and 9. The average of the MRHD consdered as the upper lmt and 0 as the lower lmt of threshold as shown n equaton 10 and 11: and T upperlmt 1 = ( ) M M MRHD (10) 1 T lowerlmt =0 (11) where M=no of songs n the database. Unlkely songs are quckly elmnated by comparng MRHD values of database songs wth threshold range. The song whose threshold s not n the range wll be elmnated from the pruned database. In other words, f the followng condton s not satsfed such song may be purged: T MRHD T (12) lowerlmt S upperlmt Ths procedure s carred out at dfferent hstogram resoluton level to form PF. The database prunng rate analyss s depcted n Fg Results and Dscussons The relatve performance of the proposed QBH method demonstrates several nterestng trends and ths secton s dedcated to evaluate the proposed approach. Substantaton of feasblty of the proposed crtera s done through expermentaton. In the sequel, three seres of experments were conducted wth correspondng target

8 and query corpus by varyng the number of hstogram bns from 100 to 1000 and hstogram resoluton level from 1 to 5. Fnally, comprehensve dscussons of performances are portrayed n terms of error rate, database prunng, Mean Recprocal Rank (MRR), Mean of Accuracy (MoA) and Top X Ht Rate. 5.1 Target Corpus We are proposng a novel QBH system exclusvely for Indan musc songs, so the corpus chosen for ths study conssts of 1000 Indan Kannada devotonal monophonc MP3 songs. Ths collecton s prepared from 39 subjects ncludng songs from 22 males and 17 female sngers. The correspondng tranng set ncludes a subset of 100, 200, 500 and 1000 songs for dfferent experments. MP3 songs contan convoluted melody nformaton and even nose. Thus preprocessng s appled on the MP3 songs database to extract nformaton needed by the system. In musc, human vocal part always plays an mportant role n representng melody rather than ts background musc therefore t s desred to segregate both [15]. 5.2 Query Corpus For system evaluaton, we employ a monophonc query corpus contanng total 200 sample queres from ten partcpants. Each partcpant was asked to hum begnnng of the target song two or three tmes each. The partcpants were selected from varety of muscal backgrounds lke wth and wthout consderable muscal tranng. Also they were nstructed to hum each query as naturally as possble usng the lyrcs of the target corpus. 5.3 Error Rate Analyss

9 Fg. 3. Error Rate Analyss Usng the query and target corpus descrbed above, the error rate s computed for the QBH system mplementatons presented n sectons 2 through 4. Fg. 3 dsplays the error rate for fve hstogram resoluton levels. The target database number of hstogram bns s represented along the horzontal axs and the error rate along the vertcal axs. As expected, drect comparson of error rates wth ncreasng hstogram bn numbers, yelds the better performance, ths mprovement dmnshes as the number of bns decrease. Through promnent observaton t was found that fne gran level musc sgnal approxmaton s possble wth hgher number of hstogram bns, whch yelds better performance. However, error rate ncreases wth the decrease n the number of hstogram bns. 5.4 Database Prunng Rate Analyss Fg. 4. Database Prunng Rate Analyss Fg. 4 dsplays the prunng rate analyss for QBH system across dfferent szed target databases wth fve hstogram resoluton levels. The target database's number of bns are represented along the horzontal axs and the prunng rate along the vertcal axs. In ths fgure, the prunng rate for hstogram resoluton level 1,2,3,4 and 5 are shown wth a lne, dashed lne, small dashed lne, dash-dot lne and dash-dot-dot lne respectvely. Indeed, for ncreasng number of hstogram bns and hstogram resoluton levels prunng rate s approxmately 55% as shown n Fg. 4. The frst hstogram resoluton level representaton yelds the most robust performance of prunng around 55%. For the target database wth ncreasng number of hstogram bns the best prunng rate s n the range 55.21% to 39.35% across dfferent hstogram resoluton levels. That s, the hstogram representaton wth hgher number of hstogram bns yelds good prunng rate, however t s computatonally domneerng.

10 5.5 Performance Analyss Fg. 5. Performance Analyss Many dfferent measures for evaluatng the performance of QBH systems have been proposed [14] [9] [8]. The measures requre a collecton of tranng and testng samples for each test scenaro and parameter combnatons. The Mean Recprocal Rank (MRR) s defned as: n 1 1 MRR n (13) rank ( t ) 1 MRR s a metrc for estmatng any system that generates lst of potental responses to a query. Recprocal rank of a query outcome s the multplcatve nverse of the rank of the frst accurate response. That s, the MRR s estmated as the average of the recprocal ranks of outcomes for a sample of queres. The recprocal value of the MRR refers to the harmonc mean of the ranks. In other words frequency of the system estmatng one of the frst ranks s calculated through MRR [15]. We obtaned MRR n the range 16.41% to 21.34% for dfferent hstogram resoluton levels. The proposed strategy reveals that the MRR ncreases wth ncrease n hstogram resoluton level as portrayed n Fg. 5. In other words, frequency of occupyng top fve ranks ncreases as hstogram resoluton level ncreases. Smlarly for each test scenaro and parameter combnaton the Mean of Accuracy (MoA) s defned as: n 1 n rank( t ) MoA n (14) 1 n 1 It demonstrates the average rank at whch the target was found for each query. We obtaned MoA n the range 68.84% to 83.21% wth hstogram resoluton levels one to fve. From Fg. 5, t s found that the MoA decreases wth ncrease n hstogram

11 resoluton level. Ths ndcates average rank of the retreved song decreases wth hgher hstogram resoluton levels. The Top X Ht Rate s defned as percentage of successful queres and t can be shown mathematcally as: Top( X ) #{ rank ( ): rank ( ) X}/ N (15) where X symbolze top most songs and N ndcates total number of songs. The mpact of Top X Ht Rate for dfferent hstogram resoluton level s portrayed n Fg. 5. The top X Ht Rate vared from 65.78% to 78.90% for dfferent hstogram resoluton levels. From the Fg. 5, X value 10 was found to be the best, at whch system obtaned retreval accuracy n the range 65.78% to wth ncreasng hstogram resoluton level. Comparng fgures 3, 4 and 5, the MRH based representatons emprcally yeld relatvely better performance n terms of MRR, MoA and Top X Ht Rate. 6 Concluson In ths work, we have attempted to explot advantages of MRA technque to progressvely reduce search space for QBH applcatons. In these knds of applcatons, ntal result set conssts of songs that have some specfc patterns; subsequent steps perform relatvely slow search n the small space to retreve all songs whose hstogram shape matches wth query. MRH analyss s employed as database flterng procedure to support teratve search n the database to produce effectve musc retrevals. The results obtaned from exhaustve expermentaton are encouragng. Exhaustve exploraton of the possblty of combnng equal area bn hstogram and MRA s to be consdered as part of further nvestgaton. References 1. A.Adds, G.Armano, and E.Vargu:. Usng the progressve flterng approach to deal wth nput mbalance n large-scale taxonomes. In Proc. of In Large-Scale Herarchcal Classfcaton Workshop of ECIR, (2010). 2. A.Ghas, J.Logan, D.Chamberln, and B.C.Smth:. Query by hummng-muscal nformaton retreval n an audo database. In Proc. ACM Multmeda, pages , (1995). 3. A.K.Trpathy, N.Chhatre, N.Surendranath, and M.Kals:. Query by hummng system. Internatonal Journal of Recent Trends n Engneerng, 2(5): , (2009). 4. Georges-Perre Bonneau, Gershon Elber, Stefane Hahmann, and Basle Sauvage:. Multresoluton analyss. In Lela De Floran and Mchele Spagnuolo, edtors, Shape Analyss and Structurng, Mathematcs+Vsualzaton, chapter 3, pages Sprnger, Jan (2008). 5. C.C.Lu and P.J.Tsa:. Content-based retreval of mp3 musc objects. ACM, pages , (2001).

12 6. C.Francu and C.G.Nevll-Mannng:. Dstance metrcs and ndexng strateges for a dgtal lbrary of popular musc. In Proc. of IEEE Internatonal Conference on Multmeda and Expo, (2000). 7. J.S.R.Jang and H.R.Lee:. Herarchcal flterng method for content based musc retreval va acoustc nput. In Proc. of the 9th ACM Multmeda Conference, Ottawa, ON, Canada, pages , (2001). 8. J.S.R.Jang and H.R.Lee:. An ntal study on progressve flterng based on dynamc programmng for query by sngng/hummng. In Proc. of 7th IEEE Pacfc-Rm Conf. Multmeda, Zhejang, Chna, pages , November (2006). 9. J.S.R.Jang and H.R.Lee:. A general framework of progressve flterng and ts applcaton to query by sngng/hummng. IEEE Transactons on Audo, Speech and Language Processng, 16(2), Feb (2008). 10. J.S.R.Jang and M.Y.Gao:. A query-by-sngng system based on dynamc programmng. In Proc. of Internatonal Workshop on Intellgent System Resolutons (8 th Bellman Contnuum), Hsnchu, Tawan, R.O.C., pages 85-89, (2000). 11. L.Fu and X.Y.Xue:. A new effcent approach to query by hummng. Internatonal Computer Musc Conference, ICMC, Mam, USA, (2004). 12. L.Lu, H.You, and H.J.Zhang:. A new approach to query by hummng n musc retreval. In Proc. of IEEE Internatonal Conference on Multmeda and Expo (ICME), pages , (2001). 13. M.A.Raju, B.Sundaram, and P.Rao:. Tansen: a query-by-hummng based musc retreval system. In Proc. of the Natonal Conference on Communcatons (NCC), (2003). 14. N.Adams, D.Marquez, and G.Wake_eld:. Iteratve deepenng for melody algnment and retreval. In Proc. of Internatonal Symp. Musc Inf. Retreval (ISMIR), pages , (2005). 15. Trsladev C. Nagav and Nagappa U. Bhajantr:. Perceptve analyss of query by sngng system through query excerpton. In Proc. of the 2nd Internatonal CCSEIT-2012, Avnashlngam Unversty, Combatore, Inda., October (2012). Forthcomng. 16. N.H.Adams, M.A.Bartsch, J.B.Shfrn, and G.H.Wake_eld:. Tme seres algnment for musc nformaton retreval. In Proc. of 5th ISMIR, pages , (2004). 17. S.Chu, E.Keogh, D.Hart, and M.Pazzan:. Iteratve deepenng dynamc tme warpng for tme seres. In Proc. of 2nd SIAM Internatonal Conference on Data Mnng, CD-ROM, (2002). 18. W.Jeon and C.Ma:. Effcent search of musc ptch contours usng wavelet transforms and segmented dynamc tme warpng. In Proc. of IEEE Internatonal Conference on Acoustcs, Speech and Sgnal Processng (ICASSP), pages , (2011). 19. X.Wu and M.L:. A top-down approach to melody match n ptch contour for query by hummng. In Proc. of 5th Internatonal Symposum on Chnese Spoken Language Processng, Sngapore, (2006). 20. Y.Zhu and D.Shasha:. Warpng ndexes wth envelope transforms for query by hummng. In Proc. of SIGMOD, San Dego, CA., (2003). 21. Z.Wang and B.Zhang:. Quotent space model of herarchcal query-by-hummng system. In Proc. of IEEE Internatonal Conference on Granular Computng, 2: , (2005).

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

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

More information

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

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

Term Weighting Classification System Using the Chi-square Statistic for the Classification Subtask at NTCIR-6 Patent Retrieval Task

Term Weighting Classification System Using the Chi-square Statistic for the Classification Subtask at NTCIR-6 Patent Retrieval Task Proceedngs of NTCIR-6 Workshop Meetng, May 15-18, 2007, Tokyo, Japan Term Weghtng Classfcaton System Usng the Ch-square Statstc for the Classfcaton Subtask at NTCIR-6 Patent Retreval Task Kotaro Hashmoto

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

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

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

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

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

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

Cluster Analysis of Electrical Behavior

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

More information

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

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

More information

Related-Mode Attacks on CTR Encryption Mode

Related-Mode Attacks on CTR Encryption Mode Internatonal Journal of Network Securty, Vol.4, No.3, PP.282 287, May 2007 282 Related-Mode Attacks on CTR Encrypton Mode Dayn Wang, Dongda Ln, and Wenlng Wu (Correspondng author: Dayn Wang) Key Laboratory

More information

A Deflected Grid-based Algorithm for Clustering Analysis

A Deflected Grid-based Algorithm for Clustering Analysis A Deflected Grd-based Algorthm for Clusterng Analyss NANCY P. LIN, CHUNG-I CHANG, HAO-EN CHUEH, HUNG-JEN CHEN, WEI-HUA HAO Department of Computer Scence and Informaton Engneerng Tamkang Unversty 5 Yng-chuan

More information

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

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

More information

A fast algorithm for color image segmentation

A fast algorithm for color image segmentation Unersty of Wollongong Research Onlne Faculty of Informatcs - Papers (Arche) Faculty of Engneerng and Informaton Scences 006 A fast algorthm for color mage segmentaton L. Dong Unersty of Wollongong, lju@uow.edu.au

More information

Available online at Available online at Advanced in Control Engineering and Information Science

Available online at   Available online at   Advanced in Control Engineering and Information Science Avalable onlne at wwwscencedrectcom Avalable onlne at wwwscencedrectcom Proceda Proceda Engneerng Engneerng 00 (2011) 15000 000 (2011) 1642 1646 Proceda Engneerng wwwelsevercom/locate/proceda Advanced

More information

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

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

More information

Novel Pattern-based Fingerprint Recognition Technique Using 2D Wavelet Decomposition

Novel Pattern-based Fingerprint Recognition Technique Using 2D Wavelet Decomposition Mathematcal Methods for Informaton Scence and Economcs Novel Pattern-based Fngerprnt Recognton Technque Usng D Wavelet Decomposton TUDOR BARBU Insttute of Computer Scence of the Romanan Academy T. Codrescu,,

More information

A Multi-step Strategy for Shape Similarity Search In Kamon Image Database

A Multi-step Strategy for Shape Similarity Search In Kamon Image Database A Mult-step Strategy for Shape Smlarty Search In Kamon Image Database Paul W.H. Kwan, Kazuo Torach 2, Kesuke Kameyama 2, Junbn Gao 3, Nobuyuk Otsu 4 School of Mathematcs, Statstcs and Computer Scence,

More information

SLAM Summer School 2006 Practical 2: SLAM using Monocular Vision

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

More information

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

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

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

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

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

Music/Voice Separation using the Similarity Matrix. Zafar Rafii & Bryan Pardo

Music/Voice Separation using the Similarity Matrix. Zafar Rafii & Bryan Pardo Musc/Voce Separaton usng the Smlarty Matrx Zafar Raf & Bryan Pardo Introducton Muscal peces are often characterzed by an underlyng repeatng structure over whch varyng elements are supermposed Propellerheads

More information

Local Quaternary Patterns and Feature Local Quaternary Patterns

Local Quaternary Patterns and Feature Local Quaternary Patterns Local Quaternary Patterns and Feature Local Quaternary Patterns Jayu Gu and Chengjun Lu The Department of Computer Scence, New Jersey Insttute of Technology, Newark, NJ 0102, USA Abstract - Ths paper presents

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

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

Query Clustering Using a Hybrid Query Similarity Measure

Query Clustering Using a Hybrid Query Similarity Measure Query clusterng usng a hybrd query smlarty measure Fu. L., Goh, D.H., & Foo, S. (2004). WSEAS Transacton on Computers, 3(3), 700-705. Query Clusterng Usng a Hybrd Query Smlarty Measure Ln Fu, Don Hoe-Lan

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

Mining User Similarity Using Spatial-temporal Intersection

Mining User Similarity Using Spatial-temporal Intersection www.ijcsi.org 215 Mnng User Smlarty Usng Spatal-temporal Intersecton Ymn Wang 1, Rumn Hu 1, Wenhua Huang 1 and Jun Chen 1 1 Natonal Engneerng Research Center for Multmeda Software, School of Computer,

More information

MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION

MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION Paulo Quntlano 1 & Antono Santa-Rosa 1 Federal Polce Department, Brasla, Brazl. E-mals: quntlano.pqs@dpf.gov.br and

More information

Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach

Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach Angle Estmaton and Correcton of Hand Wrtten, Textual and Large areas of Non-Textual Document Images: A Novel Approach D.R.Ramesh Babu Pyush M Kumat Mahesh D Dhannawat PES Insttute of Technology Research

More information

A Clustering Algorithm for Key Frame Extraction Based on Density Peak

A Clustering Algorithm for Key Frame Extraction Based on Density Peak Journal of Computer and Communcatons, 2018, 6, 118-128 http://www.scrp.org/ournal/cc ISSN Onlne: 2327-5227 ISSN Prnt: 2327-5219 A Clusterng Algorthm for Key Frame Extracton Based on Densty Peak Hong Zhao

More information

Fuzzy C-Means Initialized by Fixed Threshold Clustering for Improving Image Retrieval

Fuzzy C-Means Initialized by Fixed Threshold Clustering for Improving Image Retrieval Fuzzy -Means Intalzed by Fxed Threshold lusterng for Improvng Image Retreval NAWARA HANSIRI, SIRIPORN SUPRATID,HOM KIMPAN 3 Faculty of Informaton Technology Rangst Unversty Muang-Ake, Paholyotn Road, Patumtan,

More information

Corner-Based Image Alignment using Pyramid Structure with Gradient Vector Similarity

Corner-Based Image Alignment using Pyramid Structure with Gradient Vector Similarity Journal of Sgnal and Informaton Processng, 013, 4, 114-119 do:10.436/jsp.013.43b00 Publshed Onlne August 013 (http://www.scrp.org/journal/jsp) Corner-Based Image Algnment usng Pyramd Structure wth Gradent

More information

USING GRAPHING SKILLS

USING GRAPHING SKILLS Name: BOLOGY: Date: _ Class: USNG GRAPHNG SKLLS NTRODUCTON: Recorded data can be plotted on a graph. A graph s a pctoral representaton of nformaton recorded n a data table. t s used to show a relatonshp

More information

Feature Reduction and Selection

Feature Reduction and Selection Feature Reducton and Selecton Dr. Shuang LIANG School of Software Engneerng TongJ Unversty Fall, 2012 Today s Topcs Introducton Problems of Dmensonalty Feature Reducton Statstc methods Prncpal Components

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

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

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

More information

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

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

Hybrid Non-Blind Color Image Watermarking

Hybrid Non-Blind Color Image Watermarking Hybrd Non-Blnd Color Image Watermarkng Ms C.N.Sujatha 1, Dr. P. Satyanarayana 2 1 Assocate Professor, Dept. of ECE, SNIST, Yamnampet, Ghatkesar Hyderabad-501301, Telangana 2 Professor, Dept. of ECE, AITS,

More information

Vectorization of Image Outlines Using Rational Spline and Genetic Algorithm

Vectorization of Image Outlines Using Rational Spline and Genetic Algorithm 01 Internatonal Conference on Image, Vson and Computng (ICIVC 01) IPCSIT vol. 50 (01) (01) IACSIT Press, Sngapore DOI: 10.776/IPCSIT.01.V50.4 Vectorzaton of Image Outlnes Usng Ratonal Splne and Genetc

More information

Intelligent Information Acquisition for Improved Clustering

Intelligent Information Acquisition for Improved Clustering Intellgent Informaton Acquston for Improved Clusterng Duy Vu Unversty of Texas at Austn duyvu@cs.utexas.edu Mkhal Blenko Mcrosoft Research mblenko@mcrosoft.com Prem Melvlle IBM T.J. Watson Research Center

More information

Collaboratively Regularized Nearest Points for Set Based Recognition

Collaboratively Regularized Nearest Points for Set Based Recognition Academc Center for Computng and Meda Studes, Kyoto Unversty Collaboratvely Regularzed Nearest Ponts for Set Based Recognton Yang Wu, Mchhko Mnoh, Masayuk Mukunok Kyoto Unversty 9/1/013 BMVC 013 @ Brstol,

More information

1. Introduction. Abstract

1. Introduction. Abstract Image Retreval Usng a Herarchy of Clusters Danela Stan & Ishwar K. Seth Intellgent Informaton Engneerng Laboratory, Department of Computer Scence & Engneerng, Oaland Unversty, Rochester, Mchgan 48309-4478

More information

Signature and Lexicon Pruning Techniques

Signature and Lexicon Pruning Techniques Sgnature and Lexcon Prunng Technques Srnvas Palla, Hansheng Le, Venu Govndaraju Centre for Unfed Bometrcs and Sensors Unversty at Buffalo {spalla2, hle, govnd}@cedar.buffalo.edu Abstract Handwrtten word

More information

A Gradient Difference based Technique for Video Text Detection

A Gradient Difference based Technique for Video Text Detection A Gradent Dfference based Technque for Vdeo Text Detecton Palaahnakote Shvakumara, Trung Quy Phan and Chew Lm Tan School of Computng, Natonal Unversty of Sngapore {shva, phanquyt, tancl }@comp.nus.edu.sg

More information

6.854 Advanced Algorithms Petar Maymounkov Problem Set 11 (November 23, 2005) With: Benjamin Rossman, Oren Weimann, and Pouya Kheradpour

6.854 Advanced Algorithms Petar Maymounkov Problem Set 11 (November 23, 2005) With: Benjamin Rossman, Oren Weimann, and Pouya Kheradpour 6.854 Advanced Algorthms Petar Maymounkov Problem Set 11 (November 23, 2005) Wth: Benjamn Rossman, Oren Wemann, and Pouya Kheradpour Problem 1. We reduce vertex cover to MAX-SAT wth weghts, such that the

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

A Novel Term_Class Relevance Measure for Text Categorization

A Novel Term_Class Relevance Measure for Text Categorization A Novel Term_Class Relevance Measure for Text Categorzaton D S Guru, Mahamad Suhl Department of Studes n Computer Scence, Unversty of Mysore, Mysore, Inda Abstract: In ths paper, we ntroduce a new measure

More information

Image Representation & Visualization Basic Imaging Algorithms Shape Representation and Analysis. outline

Image Representation & Visualization Basic Imaging Algorithms Shape Representation and Analysis. outline mage Vsualzaton mage Vsualzaton mage Representaton & Vsualzaton Basc magng Algorthms Shape Representaton and Analyss outlne mage Representaton & Vsualzaton Basc magng Algorthms Shape Representaton and

More information

A Gradient Difference based Technique for Video Text Detection

A Gradient Difference based Technique for Video Text Detection 2009 10th Internatonal Conference on Document Analyss and Recognton A Gradent Dfference based Technque for Vdeo Text Detecton Palaahnakote Shvakumara, Trung Quy Phan and Chew Lm Tan School of Computng,

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

Can We Beat the Prefix Filtering? An Adaptive Framework for Similarity Join and Search

Can We Beat the Prefix Filtering? An Adaptive Framework for Similarity Join and Search Can We Beat the Prefx Flterng? An Adaptve Framework for Smlarty Jon and Search Jannan Wang Guolang L Janhua Feng Department of Computer Scence and Technology, Tsnghua Natonal Laboratory for Informaton

More information

Virtual Machine Migration based on Trust Measurement of Computer Node

Virtual Machine Migration based on Trust Measurement of Computer Node Appled Mechancs and Materals Onlne: 2014-04-04 ISSN: 1662-7482, Vols. 536-537, pp 678-682 do:10.4028/www.scentfc.net/amm.536-537.678 2014 Trans Tech Publcatons, Swtzerland Vrtual Machne Mgraton based on

More information

Structural Analysis of Musical Signals for Indexing and Thumbnailing

Structural Analysis of Musical Signals for Indexing and Thumbnailing Structural Analyss of Muscal Sgnals for Indexng and Thumbnalng We Cha Barry Vercoe MIT Meda Laboratory {chawe, bv}@meda.mt.edu Abstract A muscal pece typcally has a repettve structure. Analyss of ths structure

More information

Classifier Selection Based on Data Complexity Measures *

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

More information

A Similarity Measure Method for Symbolization Time Series

A Similarity Measure Method for Symbolization Time Series Research Journal of Appled Scences, Engneerng and Technology 5(5): 1726-1730, 2013 ISSN: 2040-7459; e-issn: 2040-7467 Maxwell Scentfc Organzaton, 2013 Submtted: July 27, 2012 Accepted: September 03, 2012

More information

Detection of an Object by using Principal Component Analysis

Detection of an Object by using Principal Component Analysis Detecton of an Object by usng Prncpal Component Analyss 1. G. Nagaven, 2. Dr. T. Sreenvasulu Reddy 1. M.Tech, Department of EEE, SVUCE, Trupath, Inda. 2. Assoc. Professor, Department of ECE, SVUCE, Trupath,

More information

Boundary-Based Time Series Sorting

Boundary-Based Time Series Sorting JOURNAL OF ELECTRONIC SCIENCE AND TECHNOLOGY OF CHINA, VOL. 6, NO. 3, SEPTEMBER 2008 323 Boundary-Based Tme Seres Sortng Jun-Ku L, Yuan-Zhen Wang, and Ha-Bo L Abstract In many applcatons, t s desrable

More information

An Image Compression Algorithm based on Wavelet Transform and LZW

An Image Compression Algorithm based on Wavelet Transform and LZW An Image Compresson Algorthm based on Wavelet Transform and LZW Png Luo a, Janyong Yu b School of Chongqng Unversty of Posts and Telecommuncatons, Chongqng, 400065, Chna Abstract a cylpng@63.com, b y27769864@sna.cn

More information

Life Tables (Times) Summary. Sample StatFolio: lifetable times.sgp

Life Tables (Times) Summary. Sample StatFolio: lifetable times.sgp Lfe Tables (Tmes) Summary... 1 Data Input... 2 Analyss Summary... 3 Survval Functon... 5 Log Survval Functon... 6 Cumulatve Hazard Functon... 7 Percentles... 7 Group Comparsons... 8 Summary The Lfe Tables

More information

S1 Note. Basis functions.

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

More information

Reducing Frame Rate for Object Tracking

Reducing Frame Rate for Object Tracking Reducng Frame Rate for Object Trackng Pavel Korshunov 1 and We Tsang Oo 2 1 Natonal Unversty of Sngapore, Sngapore 11977, pavelkor@comp.nus.edu.sg 2 Natonal Unversty of Sngapore, Sngapore 11977, oowt@comp.nus.edu.sg

More information

Overview. Basic Setup [9] Motivation and Tasks. Modularization 2008/2/20 IMPROVED COVERAGE CONTROL USING ONLY LOCAL INFORMATION

Overview. Basic Setup [9] Motivation and Tasks. Modularization 2008/2/20 IMPROVED COVERAGE CONTROL USING ONLY LOCAL INFORMATION Overvew 2 IMPROVED COVERAGE CONTROL USING ONLY LOCAL INFORMATION Introducton Mult- Smulator MASIM Theoretcal Work and Smulaton Results Concluson Jay Wagenpfel, Adran Trachte Motvaton and Tasks Basc Setup

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

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

Object-Based Techniques for Image Retrieval

Object-Based Techniques for Image Retrieval 54 Zhang, Gao, & Luo Chapter VII Object-Based Technques for Image Retreval Y. J. Zhang, Tsnghua Unversty, Chna Y. Y. Gao, Tsnghua Unversty, Chna Y. Luo, Tsnghua Unversty, Chna ABSTRACT To overcome the

More information

A Multiresolution Symbolic Representation of Time Series

A Multiresolution Symbolic Representation of Time Series A Multresoluton Symbolc Representaton of Tme Seres Vasleos Megalookonomou 1 Qang Wang 1 Guo L 1 Chrstos Faloutsos 2 1 Department of Computer & Informaton Scences 2 Department of Computer Scence Temple

More information

Lobachevsky State University of Nizhni Novgorod. Polyhedron. Quick Start Guide

Lobachevsky State University of Nizhni Novgorod. Polyhedron. Quick Start Guide Lobachevsky State Unversty of Nzhn Novgorod Polyhedron Quck Start Gude Nzhn Novgorod 2016 Contents Specfcaton of Polyhedron software... 3 Theoretcal background... 4 1. Interface of Polyhedron... 6 1.1.

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

Sequential search. Building Java Programs Chapter 13. Sequential search. Sequential search

Sequential search. Building Java Programs Chapter 13. Sequential search. Sequential search Sequental search Buldng Java Programs Chapter 13 Searchng and Sortng sequental search: Locates a target value n an array/lst by examnng each element from start to fnsh. How many elements wll t need to

More information

Performance Evaluation of Information Retrieval Systems

Performance Evaluation of Information Retrieval Systems Why System Evaluaton? Performance Evaluaton of Informaton Retreval Systems Many sldes n ths secton are adapted from Prof. Joydeep Ghosh (UT ECE) who n turn adapted them from Prof. Dk Lee (Unv. of Scence

More information

VISUAL SELECTION OF SURFACE FEATURES DURING THEIR GEOMETRIC SIMULATION WITH THE HELP OF COMPUTER TECHNOLOGIES

VISUAL SELECTION OF SURFACE FEATURES DURING THEIR GEOMETRIC SIMULATION WITH THE HELP OF COMPUTER TECHNOLOGIES UbCC 2011, Volume 6, 5002981-x manuscrpts OPEN ACCES UbCC Journal ISSN 1992-8424 www.ubcc.org VISUAL SELECTION OF SURFACE FEATURES DURING THEIR GEOMETRIC SIMULATION WITH THE HELP OF COMPUTER TECHNOLOGIES

More information

An Indian Journal FULL PAPER ABSTRACT KEYWORDS. Trade Science Inc.

An Indian Journal FULL PAPER ABSTRACT KEYWORDS. Trade Science Inc. [Type text] [Type text] [Type text] ISSN : 97-735 Volume Issue 9 BoTechnology An Indan Journal FULL PAPER BTAIJ, (9), [333-3] Matlab mult-dmensonal model-based - 3 Chnese football assocaton super league

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

Comparison Study of Textural Descriptors for Training Neural Network Classifiers

Comparison Study of Textural Descriptors for Training Neural Network Classifiers Comparson Study of Textural Descrptors for Tranng Neural Network Classfers G.D. MAGOULAS (1) S.A. KARKANIS (1) D.A. KARRAS () and M.N. VRAHATIS (3) (1) Department of Informatcs Unversty of Athens GR-157.84

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

Brushlet Features for Texture Image Retrieval

Brushlet Features for Texture Image Retrieval DICTA00: Dgtal Image Computng Technques and Applcatons, 1 January 00, Melbourne, Australa 1 Brushlet Features for Texture Image Retreval Chbao Chen and Kap Luk Chan Informaton System Research Lab, School

More information

Evaluation of an Enhanced Scheme for High-level Nested Network Mobility

Evaluation of an Enhanced Scheme for High-level Nested Network Mobility IJCSNS Internatonal Journal of Computer Scence and Network Securty, VOL.15 No.10, October 2015 1 Evaluaton of an Enhanced Scheme for Hgh-level Nested Network Moblty Mohammed Babker Al Mohammed, Asha Hassan.

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

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

Decision Strategies for Rating Objects in Knowledge-Shared Research Networks

Decision Strategies for Rating Objects in Knowledge-Shared Research Networks Decson Strateges for Ratng Objects n Knowledge-Shared Research etwors ALEXADRA GRACHAROVA *, HAS-JOACHM ER **, HASSA OUR ELD ** OM SUUROE ***, HARR ARAKSE *** * nsttute of Control and System Research,

More information

Content Based Retrieval

Content Based Retrieval 2010 2nd Internatonal Conference on Sgnal rocessng Systems (ICSS) A Novel Commercal Break Detecton and Automatc Annotaton of TV rograms for Abstract In ths paper, we present a novel approach for automatc

More information

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

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

More information

Using Fuzzy Logic to Enhance the Large Size Remote Sensing Images

Using Fuzzy Logic to Enhance the Large Size Remote Sensing Images Internatonal Journal of Informaton and Electroncs Engneerng Vol. 5 No. 6 November 015 Usng Fuzzy Logc to Enhance the Large Sze Remote Sensng Images Trung Nguyen Tu Huy Ngo Hoang and Thoa Vu Van Abstract

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

Mathematics 256 a course in differential equations for engineering students

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

More information

Key-Selective Patchwork Method for Audio Watermarking

Key-Selective Patchwork Method for Audio Watermarking Internatonal Journal of Dgtal Content Technology and ts Applcatons Volume 4, Number 4, July 2010 Key-Selectve Patchwork Method for Audo Watermarkng 1 Ch-Man Pun, 2 Jng-Jng Jang 1, Frst and Correspondng

More information

Enhancement of Infrequent Purchased Product Recommendation Using Data Mining Techniques

Enhancement of Infrequent Purchased Product Recommendation Using Data Mining Techniques Enhancement of Infrequent Purchased Product Recommendaton Usng Data Mnng Technques Noraswalza Abdullah, Yue Xu, Shlomo Geva, and Mark Loo Dscplne of Computer Scence Faculty of Scence and Technology Queensland

More information

Load-Balanced Anycast Routing

Load-Balanced Anycast Routing Load-Balanced Anycast Routng Chng-Yu Ln, Jung-Hua Lo, and Sy-Yen Kuo Department of Electrcal Engneerng atonal Tawan Unversty, Tape, Tawan sykuo@cc.ee.ntu.edu.tw Abstract For fault-tolerance and load-balance

More information

BRDPHHC: A Balance RDF Data Partitioning Algorithm based on Hybrid Hierarchical Clustering

BRDPHHC: A Balance RDF Data Partitioning Algorithm based on Hybrid Hierarchical Clustering 015 IEEE 17th Internatonal Conference on Hgh Performance Computng and Communcatons (HPCC), 015 IEEE 7th Internatonal Symposum on Cyberspace Safety and Securty (CSS), and 015 IEEE 1th Internatonal Conf

More information

BioTechnology. An Indian Journal FULL PAPER. Trade Science Inc.

BioTechnology. An Indian Journal FULL PAPER. Trade Science Inc. [Type text] [Type text] [Type text] ISSN : 0974-74 Volume 0 Issue BoTechnology 04 An Indan Journal FULL PAPER BTAIJ 0() 04 [684-689] Revew on Chna s sports ndustry fnancng market based on market -orented

More information

SCALABLE AND VISUALIZATION-ORIENTED CLUSTERING FOR EXPLORATORY SPATIAL ANALYSIS

SCALABLE AND VISUALIZATION-ORIENTED CLUSTERING FOR EXPLORATORY SPATIAL ANALYSIS SCALABLE AND VISUALIZATION-ORIENTED CLUSTERING FOR EXPLORATORY SPATIAL ANALYSIS J.H.Guan, F.B.Zhu, F.L.Ban a School of Computer, Spatal Informaton & Dgtal Engneerng Center, Wuhan Unversty, Wuhan, 430079,

More information

Data Mining: Model Evaluation

Data Mining: Model Evaluation Data Mnng: Model Evaluaton Aprl 16, 2013 1 Issues: Evaluatng Classfcaton Methods Accurac classfer accurac: predctng class label predctor accurac: guessng value of predcted attrbutes Speed tme to construct

More information

A CALCULATION METHOD OF DEEP WEB ENTITIES RECOGNITION

A CALCULATION METHOD OF DEEP WEB ENTITIES RECOGNITION A CALCULATION METHOD OF DEEP WEB ENTITIES RECOGNITION 1 FENG YONG, DANG XIAO-WAN, 3 XU HONG-YAN School of Informaton, Laonng Unversty, Shenyang Laonng E-mal: 1 fyxuhy@163.com, dangxaowan@163.com, 3 xuhongyan_lndx@163.com

More information