A Powerful Feature Selection approach based on Mutual Information

Size: px
Start display at page:

Download "A Powerful Feature Selection approach based on Mutual Information"

Transcription

1 6 IJCN Internatonal Journal of Computer cence and Network ecurty, VOL.8 No.4, Aprl 008 A Powerful Feature electon approach based on Mutual Informaton Al El Akad, Abdelall El Ouardgh, and Drss Aboutadne GCM-LRIT, Faculty of cences, Mohammed V Unversty, Rabat, Morocco MCE, GCM-LRIT, Faculty of Economc cences, Hassan I Unversty, ettat, Morocco GCM-LRIT, Faculty of cences, Mohammed V Unversty, Rabat, Morocco ummary Feature selecton ams to reduce the dmensonalty of patterns for classfcatory analyss by selectng the most nformatve nstead of rrelevant and/or redundant features. In ths paper we propose a novel feature selecton measure based on mutual nformaton and takes nto consderaton the nteracton between features. The proposed measure s used to determne relevant features from the orgnal feature set for a pattern recognton problem. We use a upport Vector Machne (VM classfer to compare the performance of our measure wth recently proposed nformaton theoretc crtera. Very good performances are obtaned when applyng ths method on handwrtten dgtal recognton data. Key words: Feature selecton, Feature nteracton, Mutual Informaton, Interacton Gan, Handwrtten Dgt recognton. Introducton Feature selecton s a very mportant step n classfcaton snce the ncluson of rrelevant and redundant features often degrade the performance of a classfcaton algorthm both n speed and predcton accuracy. In the case of a pattern recognton problem, the obectve of feature selecton s to fnd the smallest subset of features that maxmzes the pattern recognton ablty. Ideally, ths can be acheved by examnng all possble subsets and fndng the one that satsfes the above crteron. Ths approach s known as exhaustve feature selecton. Even wth a moderate number of features, the exhaustve selecton s mpractcal because of ts computatonal requrements. Other feature selecton methods were developed to reduce computatonal complexty by compromsng performance. All feature selecton methods need to use an evaluaton functon together wth a search procedure to obtan the optmal feature set. The evaluaton functon measures how good a specfc subset can be n dscrmnatng between classes and can be dvded nto two man groups: flters and wrappers. Flters measure the relevance of feature subsets ndependently of any classfer, whereas wrappers use the classfer s performance as the evaluaton measure. earch procedures on the other hand, are methods that only consder small porton of all possble subsets. In ths paper, our obectve s to develop an evaluaton functon that can be used wth any search procedure. We wll consder flter evaluaton measures because they are faster than wrapper and can handle large datasets []. A varety of flter-based measures have already been proposed n the lterature. The most popular fall under the followng three categores: dstance measures, consstency measures and nformaton measures. Ths paper wll focus on the nformaton measure that s based on the concept of mutual nformaton. The drawback of the recently proposed nformaton measures s that they don t take nto consderaton the nteracton between features. Indeed, a sngle feature can be consdered rrelevant based on ts correlaton wth the class; but when combned wth other features, t becomes very relevant. Unntentonal removal of these features can result n a loss of useful nformaton and thus may cause poor classfcaton performance. Ths s studed n [3] as attrbute nteracton. We wll propose a new nformaton based evaluaton functon called IGF (Interacton Gan for Feature electon that overcomes the drawbacks of the other functons. Our proposed method wll be used to determne the relevant features from the orgnal feature set for a pattern recognton problem and wll be compared wth three recently proposed nformaton theoretc crtera. The rest of the paper s organzed as the follows: ome nformaton theoretc notons for feature selecton and the state of the art about the recently proposed nformaton theoretc crtera for feature selecton are addressed n the secton two. ecton three presents our proposed evaluaton functon based on Interacton Gan (IGF. Expermental results on handwrtten dgtal recognton data and comparson n term of classfcaton accuracy between our proposed method and three recently proposed nformaton theoretc crtera s presented n secton four. The last secton summarzes the fndng and gves some perspectves that can follow up on ths work. Manuscrpt receved Aprl 8, 008. Manuscrpt revsed Aprl 0, 008.

2 IJCN Internatonal Journal of Computer cence and Network ecurty, VOL.8 No.4, Aprl Informaton theoretc for Feature electon. Defntons and measurements ( Mutual nformaton and condtonal mutual nformaton: The frst goal of a predcton model s to mnmze the uncertanty on the dependent varable. A good formalzaton of the uncertanty of a random varable s gven by hannon and Weaver s [4] nformaton theory. Whle frst developed for bnary varables, t has been extended to contnuous varables. Let and Y be two random varables (they can have real or vector values. We denote μ the ont probablty densty functon of, Y and Y. We recall that the margnal densty functons are gven by: ( x = μ, Y y dy ( y = μ, Y y dx μ ( μ ( Y Let us now recall some elements of nformaton theory. The uncertanty on Y s gven by ts entropy defned as: μ H( = ( ylog μ ( y dy (3 Y Y If we get knowledge on Y ndrectly by knowng, the resultng uncertanty on Y knowng s gven by ts condtonal entropy, that s: H( Y / = μ ( x μy ( y / = xlog μy ( y / = x dydx (4 The ont uncertanty of the (, Y par s gven by the ont entropy, defned as: μ H, = y log y dxdy (5 (, Y μ, Y The mutual nformaton between and Y can be consdered as a measure of the amount of knowledge on Y provded by (or conversely on the amount of knowledge on provded by Y. Therefore, t can be defned as [5]: I( ; = H( H( Y / (6 Whch s exactly the reducton of the uncertanty of Y when s known. If Y s the dependant varable n a predcton context, the mutual nformaton s thus partcularly suted to measure the pertnence of n a model for Y [6]. Usng the propertes of the entropy, the mutual nformaton can be rewrtten nto: I( ; = H( + H( H(, (7 That s, accordng to the prevously recalled defntons, nto [7]: μ, Y y I( ; = μ Y y log dxdy (8, μ ( x μ ( y The condtonal mutual nformaton s defned as: I( ; Y / = H ( / H ( / Y, (9 = I / Y, I( / ( Y Ths value quantfes how much nformaton s shared between and Y, gven the value of. Another way to see t, as t s decomposed above, s as the dfference between the nformaton requred to descrbe gven, and the nformaton to descrbe gven both and Y. If Y and carry the same nformaton about, the two terms on the rght are equal, and the condtonal mutual nformaton s zero. On the opposte, f both Y and brng nformaton, and f those nformatons are complementary, the dfference s large. ( Feature nteracton and Interacton Gan: Feature selecton s one effectve mean to remove rrelevant features [8]. Optmal feature selecton requres an exponentally large search space ( O ( * N, where N s the number of features [9]. Researchers often resort to varous approxmatons to determne relevant features (e.g., relevance s determned by correlaton between ndvdual features and the class [0], []. However, a sngle feature can be consdered rrelevant based on ts correlaton wth the class; but when combned wth other features, t becomes very relevant. An llustraton of feature nteracton s gven by the well-known OR problem [], [3]: We see that and have null mutual nformaton wth the output, once they are taken ndvdually (.e I ( ; = 0, I ( ; = 0. However, when they are taken together, the mutual nformaton Y

3 8 IJCN Internatonal Journal of Computer cence and Network ecurty, VOL.8 No.4, Aprl 008 I (, ; = H( > 0 of the subset s postve. Interacton explans why an apparently rrelevant combnaton of varables can eventually perform effcently n a learnng task. To decde, whether there s nteracton between two attrbutes, [4] propose an heurstc test, called nteracton gan. It s based on the well-known dea of nformaton gan. Informaton gan can be regarded as a measure of the strength of a -way nteracton between an attrbute and the class Y. In ths sprt, we can generalze t to 3-way nteractons by ntroducng the nteracton gan [4]: I( ; ; = I(, ; I( ; I( ; (0 Interacton gan can be understood as the dfference between the actual decrease n entropy acheved by the ont attrbute and the expected decrease n entropy wth the assumpton of ndependence between attrbutes and. The hgher the nteracton gan, the more nformaton was ganed by onng the attrbutes n the Cartesan product, n comparson wth the nformaton ganed from sngle attrbutes. It s qute easy to see that when nteracton gan s negatve, context decreased the amount of dependence. When the nteracton gan s postve, context ncreased the amount of dependence. When the nteracton gan s zero, context dd not affect the dependence between the two attrbutes. Interacton gan s dentcal to the noton of nteracton nformaton [3] and mutual nformaton among three random varables [4], [5]. In the followng secton, we wll proceed to a crtcal survey of nformaton theoretc approaches exstng n lterature, by stressng when and where the noton of nteracton s taken nto account.. tate of the Art As mutual nformaton can measure relevance, ths quantty s currently used n lterature for performng feature selecton. One of the man reasons for adoptng t s ts low complexty computatonal complexty cost ( O ( d * N where d s the number of varables and N s the number of samples n the case of dscrete varables. The followng sectons wll sketch three state-of-the-art flter approaches that use ths quantty. ( Varable Rankng (RANK: The rankng method returns a rankng of varables on the bass of ther ndvdual mutual nformaton wth the output. Ths means that, gven n nput varables, the method frst computes n tmes the quantty I( ;, = Kn, then ranks the varables accordng to ths quantty and eventually dscards the least relevant ones [6]. The man advantage of the method s ts rapdty of executon. Indeed, only n computatons of mutual nformaton are requred for a resultng complexty ( O ( n* * N. The man drawback derves from the fact that possble redundances between varables s not taken nto account. Indeed, two redundant varables, yet hghly relevant taken ndvdually, wll be both well ranked. As a result, a model that uses these two varables s dangerously prone to an ncreased varance wthout any gan n terms of bas reducton. On the contrary, two varables can be complementary to the output (.e. hghly relevant together whle each of them appears to be poorly relevant once taken ndvdually. As a consequence, these varables could be badly ranked, or worse elmnated, by the rankng flter. Although the varable rankng algorthm s reputed to be fast, t may be poorly effcent as t only reles on ndvdual relevance. Recently, new algorthms that combne relevance and redundancy analyss offer a good compromse between accuracy and computatonal load as the Fast Correlaton Based Flter [6]. Also, some heurstc search methods such as the best frst search (also known as the forward selecton can be combned effcently wth nformaton theoretc crtera n order to select the best varable gven a prevously selected subset. In the next sectons, two theoretc crtera exstng n the lterature and that can be easly combned wth the forward selecton, are presented. ( Mnmum Redundancy - Maxmum Relevance crteron (MRMR: The mnmum redundancy - maxmum relevance crteron [7] conssts n selectng the varable among the not yet selected features that maxmzes u z where u s a relevance term and z s a redundancy term. More precsely, u s the relevance of to the output Y alone, and z s the mean redundancy of to each varable already selected. u = I( ; ( z = I( ; d ( MRMR = arg max ( u z (3 At each step, ths method selects the varable whch has the best compromse relevance-redundancy. Ths selecton crteron s fast and effcent. At step d of the forward search, the search algorthm computes n d evaluatons

4 IJCN Internatonal Journal of Computer cence and Network ecurty, VOL.8 No.4, Aprl where each evaluaton requres the estmaton of d + b-varate denstes (one for each already selected varables plus one wth the output. It has been shown n [7] that the MRMR crteron s an optmal frst order approxmaton of the condtonal relevance crteron. Furthermore, MRMR avods the estmaton of multvarate denstes by usng multple b-varate denstes. Note that, although the method ams to address the ssue of redundancy between varables through the term z, t s not able to take nto account the nteractons between varables. ( Condtonal Mutual Informaton Maxmzaton Crteron (CMIM: Ths approach [8] proposes to select the feature whose mnmal condtonal relevance I ( ; Y / among the selected features, s maxmal. Ths requres the computaton of the mutual nformaton of and the output Y, condtonal on each feature prevously selected. Then, the mnmal value s retaned and the feature that has a maxmal mnmal condtonal relevance s selected. The varable returned accordng to the CMIM crteron s: CMIM = arg max ( mn ( I( ; Y / (4 Ths selecton crteron s powerful. It selects relevant varables, t avods redundancy, t avods estmatng hgh dmensonal multvarate denstes and unlke the prevous method, t does not gnore varable nteracton. However, t wll not necessary select an nteractng varable wth the already selected varables. Indeed, a varable that has a hgh nteracton wth an already selected varable wll be characterzed by a hgh condtonal mutual nformaton wth that varable but not necessarly by a hgh mnmal condtonal nformaton. In terms of complexty, note that at th the d step of the forward search, the algorthm computes n d evaluatons where each evaluaton followng CMIM requres the estmaton of d tr-varate denstes (one for each prevously selected varable. 3. Interacton Gan Based Feature electon (IGF The new proposed evaluaton measure for a gven feature wll be based on the ndvdual Mutual Informaton and a compromse between features redundancy and features nteracton. The compromse s made by the mean of Interacton Gan. In formal notaton, the varable returned accordng to the IGF crteron s: IGF = arg max ( I( ; + I( ; ; (5 d The man advantage n usng ths crteron for selectng varables s that an nteractng varable of an already selected one has a much hgher probablty to be selected than wth other crtera. The relevance of each feature can be ndcated by ts Mutual Informaton wth class labels I( ;. The second term makes a compromse between redundancy and nteracton. A negatve Interacton Gan ndcates that the features are redundant and a postve one ndcates that the features work well together. 4. Expermental Results In ths secton, we perform comprehensve experments on handwrtten dgtal recognton dataset to compare the IGF selecton algorthm wth the three state of the art approaches dscussed above: The Rankng algorthm, the Mnmum Redundancy Maxmum Relevance crteron and the Condtonal Mutual Informaton Maxmzaton crteron. 4. Dataset Descrpton We have used the dataset of handwrtten numeral recognton from UCI Machne Learnng Repostory [9]. It conssts of 649 features on handwrtten numerals ( 0 9. These 649 features dstrbute over the followng feature sets: 76 Fourer coeffcents of the character shapes, 6 profle correlatons, 64 Karhunen-Love coeffcents, 40 pxel averages n x3 wndows, 47 Zernke moments, 6 morphologcal features. There are 00 patterns per class (for a total of,000 patterns. 4. Classfer Descrpton VM (upport Vector Machne s a relatvely new and promsng classfcaton method [0]. It s a margn classfer that draws an optmal hyper-plane n the feature vector space; ths defnes a boundary that maxmzes the margn between data samples n two classes, therefore leadng to good generalzaton propertes. A key factor n VM s to use kernels to construct nonlnear decson boundary. In ths expermentaton, we used the Weka [] verson of LIBVM [] whch allow us to drectly construct a multclass VM wth exponental kernel. 4.3 Assessment measure We assessed classfcaton performance usng K-fold cross valdaton. In ths assessment method the orgnal sample s parttoned nto k sub-samples. Of the k sub-samples, a

5 0 IJCN Internatonal Journal of Computer cence and Network ecurty, VOL.8 No.4, Aprl 008 sngle sub-sample s retaned as the valdaton data for testng the model, and the remanng k sub-samples are used as tranng data. The cross-valdaton process s then repeated k tmes (the folds, wth each of the k sub-samples used exactly once as the valdaton data. The k results from the folds then can be averaged (or otherwse combned to produce a sngle estmaton. Cross valdaton accuracy provdes more realstc assessment of classfers whch generalze well to unseen data. We used 0-fold cross valdaton [3], [4]. 4.4 Results Each selecton method stops after those thrty varables have been selected. Then, the evaluaton of the selecton s done by usng a 0-fold cross valdaton wth a VM learnng algorthm. The accuracy of classfcaton (recognton rate relatvely to the step by step ntroducton of the varables s computed and the evoluton of the recognton rate usng dfferent feature selecton algorthm s reported n the fg.. Fg. Evoluton of the 0-fold cross valdaton accuracy of the VM learnng algorthm The above graph show the strength of our proposed measure compared wth the three well known feature selecton algorthms. In addton IGF s better than the other algorthm by at least % of the recognton rate. The analyss of ths graph allowed us to take out the followng results: The measures based on the mutual nformaton can be used for performng feature selecton for the problem of pattern recognton; The analyss of the nteracton between features must be taken nto consderaton when selectng features for pattern recognton. 4. Concluson and future work In ths paper, we proposed a new evaluaton functon, called IGF, based on the concept of mutual nformaton and nteracton gan. The functon takes nto consderaton the nteracton between features. When the functon was used wth the stepwse selecton procedure n the problem of pattern recognton, t mproves classfcaton accuracy wth a lesser number of features compared to the other methods. The man advantage of the proposal measure s that t takes nto account dfferent features nteracton wthout ncreasng the computatonal complexty. Further experments wll focus on other pattern recognton problems. Moreover, other search strateges than the forward selecton n order to valdate the crteron n a wder range of domans. References [] Dash, M., Lu, H. Feature selecton for classfcaton. Intellgent Data Analyss pp 3-56 (997. [] Isabelle Guyon Andr Elsseeff, An Introducton to Varable and Feature electon Journal of Machne Learnng Research 3 pp 57-8 (003. [3] Aleks Jakuln and Ivan Bratko. Analyzng attrbute dependences. In PKDD, 003. [4] C.E. hannon, W. Weaver, The Mathematcal Theory of Communcaton, Unversty of Illnos Press, Urbana, IL, 949. [5] T.M. Cover, J.A. Thomas, Elements of Informaton Theory,Wley, New York, 99. [6] Yu, L., Lu, H.: Effcent feature selecton va analyss of relevance and redundancy. Journal of Machne Learnng Research 5 ( [7] C.H. Chen, tatstcal Pattern Recognton, partan Books, Washngton, DC, 973. [8] A. L. Blum and P. Langley. electon of relevant features and examples n machne learnng. Artfcal Intellgence, 97:457, 997. [9] H. Almuallm and T. G. Detterch. Learnng boolean concepts n the presence of many rrelevant features. Artfcal Intellgence, 69(- :79305, 994. [0] M. A. Hall. Correlaton-based feature selecton for dscrete and numerc class machne learnng. In ICML, 000. [] L. Yu and H. Lu. Feature selecton for hghdmensonal data: a fast correlaton-based flter soluton. In ICML, 003. [3] Kohav, R., John, G.H.: Wrappers for feature subset selecton. Artfcal Intellgence 97(- ( [3] McGll, W.J.: Multvarate nformaton transmsson. Psychometrka 9 ( [4] Jakuln, A.: Attrbute nteractons n machne learnng. Master s thess, Unversty of Lublana, Faculty of Computer and Informaton cence (003. [5] Yeung, R.W.: A new outlook on hannon s nformaton measures. IEEE Transactons on Informaton Theory 37 ( [6] Duch, W., Wnarsk, T., Besada, J., Kachel, A.: Feature selecton and rankng flters. In: Internatonal Conference on Artfcal Neural Networks (ICANN and Internatonal

6 IJCN Internatonal Journal of Computer cence and Network ecurty, VOL.8 No.4, Aprl 008 Conference on Neural Informaton Processng (ICONIP. ( [7] Peng, H., Long, F.: An effcent max-dependency algorthm for gene selecton. In: 36th ymposum on the Interface: Computatonal Bology and Bonformatcs. (004. [8] Fleuret, F.: Fast bnary feature selecton wth condtonal mutual nformaton. Journal of Machne Learnng Research 5 ( [9] C.L. Blake and C.J. Merz. UCI repostory of machne learnng databases, 998. [0] Vapnk V, The Nature of tatstcal Learnng Theory, New York: prnger, 995. [] Ian H. Wtten and Ebe Frank. Data mnng:practcal machne learnng tools and technques wth Java mplementatons. Morgan Kaufman, an Francsco, CA, UA, [] Yasser EL-Manzalawy (005. WLVM. URLhttp:// yasser/wlsvm/. [3] Moore, A.W. and Lee, M.., Effcent algorthms for mnmzng cross valdaton error. In: Proceedngs of Eleventh Internatonal Conference on Machne Learnng, Morgan Kaufmann, New Brunswck, New Jersey, 90-98, (994. [4] Thomas G. Detterch Approxmate tatstcal Tests for Comparng upervsed Classfcaton Learnng Algorthms Neural Computaton 0, (998. [5] T. Mtchell, Machne Learnng McGraw-Hll (997.

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

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

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

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

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

Support Vector Machines

Support Vector Machines Support Vector Machnes Decson surface s a hyperplane (lne n 2D) n feature space (smlar to the Perceptron) Arguably, the most mportant recent dscovery n machne learnng In a nutshell: map the data to a predetermned

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

Support Vector Machines

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

More information

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

Classification / Regression Support Vector Machines

Classification / Regression Support Vector Machines Classfcaton / Regresson Support Vector Machnes Jeff Howbert Introducton to Machne Learnng Wnter 04 Topcs SVM classfers for lnearly separable classes SVM classfers for non-lnearly separable classes SVM

More information

Feature Selection as an Improving Step for Decision Tree Construction

Feature Selection as an Improving Step for Decision Tree Construction 2009 Internatonal Conference on Machne Learnng and Computng IPCSIT vol.3 (2011) (2011) IACSIT Press, Sngapore Feature Selecton as an Improvng Step for Decson Tree Constructon Mahd Esmael 1, Fazekas Gabor

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

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

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

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

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

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

More information

Outline. Discriminative classifiers for image recognition. Where in the World? A nearest neighbor recognition example 4/14/2011. CS 376 Lecture 22 1

Outline. Discriminative classifiers for image recognition. Where in the World? A nearest neighbor recognition example 4/14/2011. CS 376 Lecture 22 1 4/14/011 Outlne Dscrmnatve classfers for mage recognton Wednesday, Aprl 13 Krsten Grauman UT-Austn Last tme: wndow-based generc obect detecton basc ppelne face detecton wth boostng as case study Today:

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

Face Recognition University at Buffalo CSE666 Lecture Slides Resources:

Face Recognition University at Buffalo CSE666 Lecture Slides Resources: Face Recognton Unversty at Buffalo CSE666 Lecture Sldes Resources: http://www.face-rec.org/algorthms/ Overvew of face recognton algorthms Correlaton - Pxel based correspondence between two face mages Structural

More information

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

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

More information

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

Smoothing Spline ANOVA for variable screening

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

More information

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

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

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

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

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

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

Relevance Assignment and Fusion of Multiple Learning Methods Applied to Remote Sensing Image Analysis

Relevance Assignment and Fusion of Multiple Learning Methods Applied to Remote Sensing Image Analysis Assgnment and Fuson of Multple Learnng Methods Appled to Remote Sensng Image Analyss Peter Bajcsy, We-Wen Feng and Praveen Kumar Natonal Center for Supercomputng Applcaton (NCSA), Unversty of Illnos at

More information

ISSN: International Journal of Engineering and Innovative Technology (IJEIT) Volume 1, Issue 4, April 2012

ISSN: International Journal of Engineering and Innovative Technology (IJEIT) Volume 1, Issue 4, April 2012 Performance Evoluton of Dfferent Codng Methods wth β - densty Decodng Usng Error Correctng Output Code Based on Multclass Classfcaton Devangn Dave, M. Samvatsar, P. K. Bhanoda Abstract A common way to

More information

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

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

More information

Optimizing Document Scoring for Query Retrieval

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

More information

Lecture 5: Multilayer Perceptrons

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

More information

BOOSTING CLASSIFICATION ACCURACY WITH SAMPLES CHOSEN FROM A VALIDATION SET

BOOSTING CLASSIFICATION ACCURACY WITH SAMPLES CHOSEN FROM A VALIDATION SET 1 BOOSTING CLASSIFICATION ACCURACY WITH SAMPLES CHOSEN FROM A VALIDATION SET TZU-CHENG CHUANG School of Electrcal and Computer Engneerng, Purdue Unversty, West Lafayette, Indana 47907 SAUL B. GELFAND School

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

Using Neural Networks and Support Vector Machines in Data Mining

Using Neural Networks and Support Vector Machines in Data Mining Usng eural etworks and Support Vector Machnes n Data Mnng RICHARD A. WASIOWSKI Computer Scence Department Calforna State Unversty Domnguez Hlls Carson, CA 90747 USA Abstract: - Multvarate data analyss

More information

Human Face Recognition Using Generalized. Kernel Fisher Discriminant

Human Face Recognition Using Generalized. Kernel Fisher Discriminant Human Face Recognton Usng Generalzed Kernel Fsher Dscrmnant ng-yu Sun,2 De-Shuang Huang Ln Guo. Insttute of Intellgent Machnes, Chnese Academy of Scences, P.O.ox 30, Hefe, Anhu, Chna. 2. Department of

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

X- Chart Using ANOM Approach

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

More information

An 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

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 Robust Method for Estimating the Fundamental Matrix

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

More information

TN348: Openlab Module - Colocalization

TN348: Openlab Module - Colocalization TN348: Openlab Module - Colocalzaton Topc The Colocalzaton module provdes the faclty to vsualze and quantfy colocalzaton between pars of mages. The Colocalzaton wndow contans a prevew of the two mages

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

Associative Based Classification Algorithm For Diabetes Disease Prediction

Associative Based Classification Algorithm For Diabetes Disease Prediction Internatonal Journal of Engneerng Trends and Technology (IJETT) Volume-41 Number-3 - November 016 Assocatve Based Classfcaton Algorthm For Dabetes Dsease Predcton 1 N. Gnana Deepka, Y.surekha, 3 G.Laltha

More information

12/2/2009. Announcements. Parametric / Non-parametric. Case-Based Reasoning. Nearest-Neighbor on Images. Nearest-Neighbor Classification

12/2/2009. Announcements. Parametric / Non-parametric. Case-Based Reasoning. Nearest-Neighbor on Images. Nearest-Neighbor Classification Introducton to Artfcal Intellgence V22.0472-001 Fall 2009 Lecture 24: Nearest-Neghbors & Support Vector Machnes Rob Fergus Dept of Computer Scence, Courant Insttute, NYU Sldes from Danel Yeung, John DeNero

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

Machine Learning. Support Vector Machines. (contains material adapted from talks by Constantin F. Aliferis & Ioannis Tsamardinos, and Martin Law)

Machine Learning. Support Vector Machines. (contains material adapted from talks by Constantin F. Aliferis & Ioannis Tsamardinos, and Martin Law) Machne Learnng Support Vector Machnes (contans materal adapted from talks by Constantn F. Alfers & Ioanns Tsamardnos, and Martn Law) Bryan Pardo, Machne Learnng: EECS 349 Fall 2014 Support Vector Machnes

More information

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

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

More information

CAN COMPUTERS LEARN FASTER? Seyda Ertekin Computer Science & Engineering The Pennsylvania State University

CAN COMPUTERS LEARN FASTER? Seyda Ertekin Computer Science & Engineering The Pennsylvania State University CAN COMPUTERS LEARN FASTER? Seyda Ertekn Computer Scence & Engneerng The Pennsylvana State Unversty sertekn@cse.psu.edu ABSTRACT Ever snce computers were nvented, manknd wondered whether they mght be made

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

CLASSIFICATION OF ULTRASONIC SIGNALS

CLASSIFICATION OF ULTRASONIC SIGNALS The 8 th Internatonal Conference of the Slovenan Socety for Non-Destructve Testng»Applcaton of Contemporary Non-Destructve Testng n Engneerng«September -3, 5, Portorož, Slovena, pp. 7-33 CLASSIFICATION

More information

SVM-based Learning for Multiple Model Estimation

SVM-based Learning for Multiple Model Estimation SVM-based Learnng for Multple Model Estmaton Vladmr Cherkassky and Yunqan Ma Department of Electrcal and Computer Engneerng Unversty of Mnnesota Mnneapols, MN 55455 {cherkass,myq}@ece.umn.edu Abstract:

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

Yan et al. / J Zhejiang Univ-Sci C (Comput & Electron) in press 1. Improving Naive Bayes classifier by dividing its decision regions *

Yan et al. / J Zhejiang Univ-Sci C (Comput & Electron) in press 1. Improving Naive Bayes classifier by dividing its decision regions * Yan et al. / J Zhejang Unv-Sc C (Comput & Electron) n press 1 Journal of Zhejang Unversty-SCIENCE C (Computers & Electroncs) ISSN 1869-1951 (Prnt); ISSN 1869-196X (Onlne) www.zju.edu.cn/jzus; www.sprngerlnk.com

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

NAG Fortran Library Chapter Introduction. G10 Smoothing in Statistics

NAG Fortran Library Chapter Introduction. G10 Smoothing in Statistics Introducton G10 NAG Fortran Lbrary Chapter Introducton G10 Smoothng n Statstcs Contents 1 Scope of the Chapter... 2 2 Background to the Problems... 2 2.1 Smoothng Methods... 2 2.2 Smoothng Splnes and Regresson

More information

Determining Fuzzy Sets for Quantitative Attributes in Data Mining Problems

Determining Fuzzy Sets for Quantitative Attributes in Data Mining Problems Determnng Fuzzy Sets for Quanttatve Attrbutes n Data Mnng Problems ATTILA GYENESEI Turku Centre for Computer Scence (TUCS) Unversty of Turku, Department of Computer Scence Lemmnkäsenkatu 4A, FIN-5 Turku

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

Solitary and Traveling Wave Solutions to a Model. of Long Range Diffusion Involving Flux with. Stability Analysis

Solitary and Traveling Wave Solutions to a Model. of Long Range Diffusion Involving Flux with. Stability Analysis Internatonal Mathematcal Forum, Vol. 6,, no. 7, 8 Soltary and Travelng Wave Solutons to a Model of Long Range ffuson Involvng Flux wth Stablty Analyss Manar A. Al-Qudah Math epartment, Rabgh Faculty of

More information

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

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

More information

Three supervised learning methods on pen digits character recognition dataset

Three supervised learning methods on pen digits character recognition dataset Three supervsed learnng methods on pen dgts character recognton dataset Chrs Flezach Department of Computer Scence and Engneerng Unversty of Calforna, San Dego San Dego, CA 92093 cflezac@cs.ucsd.edu Satoru

More information

Simulation: Solving Dynamic Models ABE 5646 Week 11 Chapter 2, Spring 2010

Simulation: Solving Dynamic Models ABE 5646 Week 11 Chapter 2, Spring 2010 Smulaton: Solvng Dynamc Models ABE 5646 Week Chapter 2, Sprng 200 Week Descrpton Readng Materal Mar 5- Mar 9 Evaluatng [Crop] Models Comparng a model wth data - Graphcal, errors - Measures of agreement

More information

Support Vector Machines. CS534 - Machine Learning

Support Vector Machines. CS534 - Machine Learning Support Vector Machnes CS534 - Machne Learnng Perceptron Revsted: Lnear Separators Bnar classfcaton can be veed as the task of separatng classes n feature space: b > 0 b 0 b < 0 f() sgn( b) Lnear Separators

More information

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

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

More information

A Statistical Model Selection Strategy Applied to Neural Networks

A Statistical Model Selection Strategy Applied to Neural Networks A Statstcal Model Selecton Strategy Appled to Neural Networks Joaquín Pzarro Elsa Guerrero Pedro L. Galndo joaqun.pzarro@uca.es elsa.guerrero@uca.es pedro.galndo@uca.es Dpto Lenguajes y Sstemas Informátcos

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

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

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

More information

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 NOTE ON FUZZY CLOSURE OF A FUZZY SET

A NOTE ON FUZZY CLOSURE OF A FUZZY SET (JPMNT) Journal of Process Management New Technologes, Internatonal A NOTE ON FUZZY CLOSURE OF A FUZZY SET Bhmraj Basumatary Department of Mathematcal Scences, Bodoland Unversty, Kokrajhar, Assam, Inda,

More information

Concurrent Apriori Data Mining Algorithms

Concurrent Apriori Data Mining Algorithms Concurrent Apror Data Mnng Algorthms Vassl Halatchev Department of Electrcal Engneerng and Computer Scence York Unversty, Toronto October 8, 2015 Outlne Why t s mportant Introducton to Assocaton Rule Mnng

More information

Fuzzy Modeling of the Complexity vs. Accuracy Trade-off in a Sequential Two-Stage Multi-Classifier System

Fuzzy Modeling of the Complexity vs. Accuracy Trade-off in a Sequential Two-Stage Multi-Classifier System Fuzzy Modelng of the Complexty vs. Accuracy Trade-off n a Sequental Two-Stage Mult-Classfer System MARK LAST 1 Department of Informaton Systems Engneerng Ben-Guron Unversty of the Negev Beer-Sheva 84105

More information

Random Kernel Perceptron on ATTiny2313 Microcontroller

Random Kernel Perceptron on ATTiny2313 Microcontroller Random Kernel Perceptron on ATTny233 Mcrocontroller Nemanja Djurc Department of Computer and Informaton Scences, Temple Unversty Phladelpha, PA 922, USA nemanja.djurc@temple.edu Slobodan Vucetc Department

More information

The Study of Remote Sensing Image Classification Based on Support Vector Machine

The Study of Remote Sensing Image Classification Based on Support Vector Machine Sensors & Transducers 03 by IFSA http://www.sensorsportal.com The Study of Remote Sensng Image Classfcaton Based on Support Vector Machne, ZHANG Jan-Hua Key Research Insttute of Yellow Rver Cvlzaton and

More information

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

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

More information

Journal of Process Control

Journal of Process Control Journal of Process Control (0) 738 750 Contents lsts avalable at ScVerse ScenceDrect Journal of Process Control j ourna l ho me pag e: wwwelsevercom/locate/jprocont Decentralzed fault detecton and dagnoss

More information

Journal of Chemical and Pharmaceutical Research, 2014, 6(6): Research Article. A selective ensemble classification method on microarray data

Journal of Chemical and Pharmaceutical Research, 2014, 6(6): Research Article. A selective ensemble classification method on microarray data Avalable onlne www.ocpr.com Journal of Chemcal and Pharmaceutcal Research, 2014, 6(6):2860-2866 Research Artcle ISSN : 0975-7384 CODEN(USA) : JCPRC5 A selectve ensemble classfcaton method on mcroarray

More information

Private Information Retrieval (PIR)

Private Information Retrieval (PIR) 2 Levente Buttyán Problem formulaton Alce wants to obtan nformaton from a database, but she does not want the database to learn whch nformaton she wanted e.g., Alce s an nvestor queryng a stock-market

More information

For instance, ; the five basic number-sets are increasingly more n A B & B A A = B (1)

For instance, ; the five basic number-sets are increasingly more n A B & B A A = B (1) Secton 1.2 Subsets and the Boolean operatons on sets If every element of the set A s an element of the set B, we say that A s a subset of B, or that A s contaned n B, or that B contans A, and we wrte A

More information

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

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

More information

Optimal Workload-based Weighted Wavelet Synopses

Optimal Workload-based Weighted Wavelet Synopses Optmal Workload-based Weghted Wavelet Synopses Yoss Matas School of Computer Scence Tel Avv Unversty Tel Avv 69978, Israel matas@tau.ac.l Danel Urel School of Computer Scence Tel Avv Unversty Tel Avv 69978,

More information

A User Selection Method in Advertising System

A User Selection Method in Advertising System Int. J. Communcatons, etwork and System Scences, 2010, 3, 54-58 do:10.4236/jcns.2010.31007 Publshed Onlne January 2010 (http://www.scrp.org/journal/jcns/). A User Selecton Method n Advertsng System Shy

More information

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

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

More information

GSLM Operations Research II Fall 13/14

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

More information

Network Coding as a Dynamical System

Network Coding as a Dynamical System Network Codng as a Dynamcal System Narayan B. Mandayam IEEE Dstngushed Lecture (jont work wth Dan Zhang and a Su) Department of Electrcal and Computer Engneerng Rutgers Unversty Outlne. Introducton 2.

More information

Incremental Learning with Support Vector Machines and Fuzzy Set Theory

Incremental Learning with Support Vector Machines and Fuzzy Set Theory The 25th Workshop on Combnatoral Mathematcs and Computaton Theory Incremental Learnng wth Support Vector Machnes and Fuzzy Set Theory Yu-Mng Chuang 1 and Cha-Hwa Ln 2* 1 Department of Computer Scence and

More information

A Hill-climbing Landmarker Generation Algorithm Based on Efficiency and Correlativity Criteria

A Hill-climbing Landmarker Generation Algorithm Based on Efficiency and Correlativity Criteria A Hll-clmbng Landmarker Generaton Algorthm Based on Effcency and Correlatvty Crtera Daren Ler, Irena Koprnska, and Sanjay Chawla School of Informaton Technologes, Unversty of Sydney Madsen Buldng F09,

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

CHAPTER 3 SEQUENTIAL MINIMAL OPTIMIZATION TRAINED SUPPORT VECTOR CLASSIFIER FOR CANCER PREDICTION

CHAPTER 3 SEQUENTIAL MINIMAL OPTIMIZATION TRAINED SUPPORT VECTOR CLASSIFIER FOR CANCER PREDICTION 48 CHAPTER 3 SEQUENTIAL MINIMAL OPTIMIZATION TRAINED SUPPORT VECTOR CLASSIFIER FOR CANCER PREDICTION 3.1 INTRODUCTION The raw mcroarray data s bascally an mage wth dfferent colors ndcatng hybrdzaton (Xue

More information

An improvement direction for filter selection techniques using information theory measures and quadratic optimization

An improvement direction for filter selection techniques using information theory measures and quadratic optimization (IJARAI) Internatonal Journal of Advanced Research n Artfcal Intellgence, An mprovement drecton for flter selecton technques usng nformaton theory measures and quadratc optmzaton Waad Bouaguel LARODEC,

More information

Adaptive Virtual Support Vector Machine for the Reliability Analysis of High-Dimensional Problems

Adaptive Virtual Support Vector Machine for the Reliability Analysis of High-Dimensional Problems Proceedngs of the ASME 2 Internatonal Desgn Engneerng Techncal Conferences & Computers and Informaton n Engneerng Conference IDETC/CIE 2 August 29-3, 2, Washngton, D.C., USA DETC2-47538 Adaptve Vrtual

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

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

User Authentication Based On Behavioral Mouse Dynamics Biometrics

User Authentication Based On Behavioral Mouse Dynamics Biometrics User Authentcaton Based On Behavoral Mouse Dynamcs Bometrcs Chee-Hyung Yoon Danel Donghyun Km Department of Computer Scence Department of Computer Scence Stanford Unversty Stanford Unversty Stanford, CA

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

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

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

More information

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

BAYESIAN MULTI-SOURCE DOMAIN ADAPTATION

BAYESIAN MULTI-SOURCE DOMAIN ADAPTATION BAYESIAN MULTI-SOURCE DOMAIN ADAPTATION SHI-LIANG SUN, HONG-LEI SHI Department of Computer Scence and Technology, East Chna Normal Unversty 500 Dongchuan Road, Shangha 200241, P. R. Chna E-MAIL: slsun@cs.ecnu.edu.cn,

More information

Hybridization of Expectation-Maximization and K-Means Algorithms for Better Clustering Performance

Hybridization of Expectation-Maximization and K-Means Algorithms for Better Clustering Performance BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 16, No 2 Sofa 2016 Prnt ISSN: 1311-9702; Onlne ISSN: 1314-4081 DOI: 10.1515/cat-2016-0017 Hybrdzaton of Expectaton-Maxmzaton

More information

Wishing you all a Total Quality New Year!

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

More information