Regularized Orthogonal Local Fisher Discriminant Analysis

Size: px
Start display at page:

Download "Regularized Orthogonal Local Fisher Discriminant Analysis"

Transcription

1 Regularized Orthogoal Local Fisher Discrimiat Aalysis Shuhua Xu Departmet of Maths Uiversity of Shaoxig City South Road, Shaoxig P.R Chia Joural of Digital Iformatio Maagemet ABSRAC: Aimig at deficiecies of the ability for preservig local oliear structure of recetly proposed Regularized Orthogoal Liear Discrimiat Aalysis () for dimesioality reductio, a kid of dimesioality reductio algorithm amed Regularized Orthogoal Local Fisher Discrimiat Aalysis () is proposed i the paper, which is origiated from. he algorithm itroduce the idea of local structure preservig i Local Fisher Discrimiat Aalysis (LFDA) o the basic of, followig properties of ad stregtheig the ability for capturig local structure iformatio of data with oliear structures. Experimets o real face datasets demostrate the effectiveess of our proposed algorithm. Categories ad Subject Descriptors: G.4: [Mathematical aalysis]: Noliear equatios; I..2: [Symbolic ad algebraic algorithms] Geeral erms: Fisher Discrimiat Aalysis, Noliear equatios Keywords: Dimesioality Reductio, Regularized Orthogoal Liear Discrimiat Aalysis, Local Noliear Structure, Local Fisher Discrimiat Aalysis Received: 8 October 2, Revised 2 December 2, Accepted 2 December 2. Itroductio I applicatios of data miig, high-dimesioal data lead to too much redudat feature iformatio ad icrease the computatioal complexity of disposig. Hece dimesioality reductio is ecessary. he purpose of dimesioality reductio is to fid a low-dimesioal represetatio of the high-dimesioal data at miimum cost i the process of preservig certai features. he most well-kow iitial dimesioality reductio methods are Pricipal Compoet Aalysis (PCA) [] ad Liear Discrimiat Aalysis (LDA) [2]. As supervised dimesioality reductio, LDA searches the projectio axes o which the ot-same-class poits are far from each other while requirig the same-class poits to be close to each other. herefore, LDA ecodes discrimiatig iformatio i a liearly separable space ad is successfully applied ito face recogitio. However, it is much expesive to attai plety of class labeled samples i practical applicatios of face recogitio, which cause that the total scatter matrix ca be sigular i LDA sice the data poits are from a very high-dimesioal space ad thus usually the umber of the data samples is much smaller tha the data dimesio. his is kow as the udersampled problem. o solve the udersampled problem i LDA applicatio, extesios of LDA ca be proposed i the literature. he two-stage LDA is proposed i [3-5], which is to apply a itermediate dimesioality reductio stage to reduce the data dimesioality. Although this method is simple, some importat iformatio is removed i the itermediate dimesioality reductio stage. he regularized LDA () is proposed i [6-], which is to cosider regularizatio by addig the perturbatio to the total scatter matrix. he methods based 54 Joural of Digital Iformatio Maagemet Volume Number 2 April 3

2 o pseudoiverse [] are applied to avoid the sigularity problem, icludig orthogoal LDA (OLDA) [2-3], ull space LDA (NLDA) [4-6], ucorrelated LDA [7], QR/ GSVD-based LDA [8-]. OLDA obtais easily the optimal trasformatio matrix by oly orthogoal trasformatios without computig ay eige-decompositio ad matrix iverse. Moreover, OLDA is implemeted by usig several QR factorizatios ad is a fast oe. I above exteds of LDA for the udersampled problem, is a efficiet method with little computatio. he major problem of the is to choose a appropriate regularizatio parameter. Usually these algorithms select the regularizatio parameter from a give parameter cadidate set by usig cross-validatio for classificatio. But how to choose a appropriate cadidate set is ot clear. herefore, up to ow, there is o cocrete mathematical theory available i selectig a appropriate regularizatio parameter i practical applicatios of the. For fillig this gap, Chig et al proposed Regularized Orthogoal Liear Discrimiat Aalysis () [2]. derives from the mathematical relatioship betwee OLDA ad ad fids a mathematical criterio for selectig the regularizatio parameter from the relatio. However, the performace of teds to be degraded o o-liear data because that is origiated from LDA which works very well if the samples i each class follow Gaussia distributios with a liear covariace structure. o overcome this drawback, Local FDA (LFDA) [22-23] has bee proposed, which combies the ideas of FDA ad LPP to maximize betwee-class reparability while preserve withi-class local structure. LFDA ca provide more separate embeddig tha FDA. Ispired by LFDA, a kid of Regularized Orthogoal Local Fisher Discrimiat Aalysis () is proposed for dimesioality reductio. he algorithm itroduces the idea of LFDA ito, preservig local structure iformatio of samples ad calculatig the regular parameter automatically. herefore ca be applied i highdimesioal data with o-liear structure. Experimets o YaleB ad AR demostrate the proposed algorithm is valid. he rest of the paper is orgaized as follows: Sectio 2 reviews LDA, LFDA ad. Our is itroduced i Sectio 3. I Sectio 4, we compare with some related works. he experimetal results ad aalyses are preseted. Fially, we provide some cocludig remarks ad future work i Sectio Related works 2. Liear Discrimiat Aalysis (LDA) Give samples X = {x i x i R d } i =, cotaiig C classes. deotes the umber of samples. he goal of LDA is to seek a projectio matrix such that the betwee-class scatter is maximized ad the withi-class scatter is miimized i projected data. he objective fuctio of LDA is as follows: = arg max tr (( S w ) ( S b )) Where S b deotes the betwee-class scatter matrix ad S w deotes the withi-class scatter matrix S b ad S w are defied as follow: S b = (x ij x ) (x i x ) C i = j= S w = (x ij x i ) (x ij x i ) Where x ij deotes the j th sample i the i th class. x = x i = i deotes the average of all samples X, i x = x ij deotes the average of samples i the i th j = i i class. i ( i C) deotes the umber of samples i the i th class. Equatio () may be further trasformed ito followig geeralized eigevalue problem: () (2) (3) S b t m = (4) λ m S w t m, m =,..., l (l < d ) Get the projectig matrix = [t, t 2,..., t l ]. 2.2 Local Fisher Discrimiat Aalysis (LFDA) LFDA is a localized variat of Fisher discrimiat aalysis. LFDA takes local structure of the data ito accout so the multimodaldata ca be embedded appropriately. LFDA redefie S (lb) ad S (lw) as follows: where S (lb) = S (lw) = 2 2 i, j = i, j = (lb) (x i )(x i ) (lw) (x i )(x i ) (lb) = Ai, j (/ / ) if y = y y i i j / if y i y j (lw) = A i, j (/ y ) if y i = y i j if y i y j (5) (6) (7) (8) x A i, j = exp i 2 ( ) (9) δ i δ j k δ i = x i x i () Where x k i is the k th earest eighbor of x i, A i, j deotes the affiity weight of x i ad x j, the parameter represets the local scalig aroud x i. he objective fuctio of LFDA is defied as follows: = arg max tr (( S (lw) ) ( S (lb) )) () Joural of Digital Iformatio Maagemet Volume Number 2 April 3 55

3 2.3 Regularized Orthogoal Liear Discrimiat Aalysis () O the base of [7], the objective fuctio of is as follows: = arg max tr (( S w + λi) ( S b )) (2) s.t. = I Where, the appropriate regularizatio parameter λ is selected accordig to [2]. 3. Regularized Orthogoal Local Fisher Discrimiat Aalysis () 3. Basic idea () is a efficiet algorithm for the udersampled problem. However, the mai task of the regularized LDA is to choose a appropriate regularizatio parameter λ. If is λ large, iformatio o the scatter matrix is lost. While if it is too small, the regularizatio may ot be sufficietly effective. Usually existig methods select the regularizatio parameterfrom a cadidate set of the regularizatio parameter give with the cross-validatio method. It has bee show i [] that the matrix computatios ivolved i the regularized LDA ca be simplified so that the cross-validatio procedure ca be performed efficietly. However, for methods, it is ot clear how to choose a appropriate cadidate set. makes the aalysis of the relatioship betwee OLDA ad.by meas of this relatioship, fid a mathematical criterio for selectig the regularizatio parameter i. Cosequetly develops a ew regularized orthogoal liear discrimiat aalysis method, i which o cadidate set of regularizatio parameter is eeded. (2) I may practical applicatios of data miig, itrisical low dimesioal data ofte lie i a very high dimesioal space. It is importat to explicitly take ito accout the structure of the maifold o which the data may possibly reside. LPP is to fid the optimal liear approximatios to the eige fuctios of the Laplace Beltrami operator o the maifold, sharig may of the data represetatio properties of oliear dimesioality reductio such as Laplacia Eige maps or Locally Liear Embeddig. LPP keeps earby data pairs i the origial space close i the embeddig space, by which oliear data ca be embedded without losig its local structure. LFDA combies the idea of LPP ad FDA, iheritig merits of them. As above aalyses, o the base of, the idea of local preservig i LFDA is itroduced. his will overcome the poor ability of for capturig the local structure ad iherit characteristics of them. 3.2 Objective fuctio O the base of Equatio (2), the objective fuctio of is defied as follows: = arg max tr ((λ ( S (lb) ) + ( S (lw) )) ( S (lb) )) (3) s.t. = I Where, accordig to [], the regularizatio parameter λ is solved with followig steps: () Give samples X = {x i x i R d } i =, cotaiig k class face. Firstly, R ad Q are gotte via QR-decompositio as follows: X = Q R (4) Where Q R d is colum orthogoal. (2) X R, X 2 R (k ) ad X 2 R ( k) are computed as follows: [X X 2 X 3 ] = R ϑ ϑ ϑ ρ k Where ρ be the permutatio matrix obtaied by exchagig the ( ) i = j = j + colum (for i = 2,., k), but otherwise leavig the order of the remaiig colums uchaged. ϑ i (i = 2,., k) ad ϑ are calculated as follows: ϑ i = i I 2 k (3) calculate th-colum of I ad i th i / i i / i i i =,., k ϑ = I / i [X X 2 ] = Q 2 k R, / i (8) Where R, R q (k ) ad R (γ q ) ( k) are of full row rak. (4) calculate λ λ = ε (6) (9) (+) (+) (+) 2 (+ R, 2 2 [ε + 2 ( + 2 ) ( q + R, 2 F )]) (+) Where ε deotes error, deotes the pseudo iverse of. 3.3 Algorithm steps Iput: samples X = {x i x i R d } i = with C class, error ε >. Output:the colum orthogoal projectio matrix R d l. Steps: () calculate W (lb) W (lw) usig Equatio (7) ad Equatio (8) (7) 56 Joural of Digital Iformatio Maagemet Volume Number 2 April 3

4 (2) calculate Q usig Equatio (4). (3) calculate X, X 2 ad X 3 usig Equatio (5). (4) calculate R,, R, 2 ad usig Equatio (8). (5) calculate λ usig Equatio (9). (6) trasform Equatio (2) ito followig geeralized matrix problem:, S (lb) t m = β m (λ S (lb) + S (lw) ) t m, m =,..., l ad calculate = [t, t 2,..., t l ]. 4. Experimetal results ad aalysis 4. Experimetal Datasets ad Settigs Face datasets are typical high-dimesioal data with oliear structures. I the experimet, YaleB ad AR are selected ad are describe as follows: ) YaleB cotais 244 frot-view face images of 38 idividuals. For each idividual, about 64 pictures were take uder various laboratory-cotrolled lightig coditios. I our experimets, he cropped images with the resolutio of are used. A group of samples i YaleB are show i Figure. 2) AR database cotais over face images of 26 idividuals. For each idividual, 26 pictures were take i two sessios (separated by two weeks) ad each sectio cotais 3 images. hese images iclude frot view of faces with differet expressios, illumiatios ad occlusios. I the experimet, them are resized to A group of samples i AR are show i Figure 2. ad are compared with ad the Nearest Neighbor Classifier is adopted i order to verify the performace of our algorithm. images are selected radomly from a group face ad remais for test samples. Moreover, the regularizatio parameter λ i is set to. ad the eighbor parameter k i is set to Experimetal Results Experimets are made uder differet ad differet reduced dimesios. All experimets are repeated twety times ad average recogitio accuracy rates are gotte. Reduced dimesios are selected with the certai icremet ad correspodig average recogitio accuracies are calculated. Experimetal results are show i Figure 3- Figure 4 Recogitio accuracy (%) Recogitio accuracy (%) Dimesio (a) = Dimesio (b) = Figure 3. Experimetal results o YaleB with Figure. A group of samples i YaleB Figure 2. A group of samples i AR Joural of Digital Iformatio Maagemet Volume Number 2 April 3 57

5 Recogitio accuracy (%) Recogitio accuracy (%) Dimesio (a) = 5 Dimesio (a) = Figure 4. Experimetal results o AR with From above Figure 3- Figure 4, i the term of the relatio of recogitio accuracy ad reduced dimesios, coclusios ca be draw as follows: () With icrease i reduced dimesio, the recogitio accuracy rate of all algorithms promote rapidly firstly ad go smoothly, which shows that these algorithms ca get most recogitio accuracy rates i low dimesio.he reasos is that they is origiated from LDA with the merit. (2) is superior to ad i AR ad YaleB with oliear structures, which is illustrated by that ifuses efficietly the characteristics of preservig local structure i LFDA while ad fail to capture local structures. Moreover, i the term of the relatio of recogitio accuracy ad the umber of traiig samples, some followig coclusios are draw: ) As experimets o YaleB show, the most recogitio accuracy rate of is respectively higher tha that of ad whe is set to. he gap betwee them becomes larger whe is set to. his illumiate that more traiig samples is helpful for to capture the local structure feature. 2) he performace of is better uder = tha that uder =, which shows that more traiig samples make it for with the power ability for capturig local structure features to be more applied o AR with power exteral disturb, icludig illumiatios ad occlusios. 5. Coclusio I the paper, Regularized Orthogoal Local Fisher Discrimiat Aalysis () for dimesioality reductio is proposed. Aimig at the deficiecy o the ability for capturig local structures iformatio, itroduce the idea of preservig local structures i Local Fisher Discrimiat Aalysis (LFDA) o the base of, iheritig merits of ad promote the ability for local learig. Experimetal results o YaleB ad AR show the proposed algorithm fuse efficietly LFDA ad. However, for, the local structure preservig is based o the approximatio of liearizatio istead of istict geometrical structure. How to fuse other oliear algorithm i is our ext work. 6. Ackowledgemets he research is supported by NSF of Zhejiag provice (grat No. LQ2F7, Y22544). Refereces [] Fukuaga, K. (9). Itroductio to Statistical Patter Recogitio, 2 d ed., Academic Press, Bosto, USA. [2] Duda, R. O., Hart, P. E., Stork. D. G. ().Patter Classificatio, secod ed., Joh Wiley & Sos, New York. [3] Howlad, P., Park, H. (4). Geeralizig discrimiat aalysis usig the geeralized sigular value decompositio. IEEE rasactios o Patter Aalysis ad Machie Itelligece, 26 (8) [4] Swets, D. L.,Weg, J. J. (996). Usig discrimiat eigefeatures for image retrieval, IEEE rasactios o Patter Aalysis ad Machie Itelligece, 8 (8) [5] Ye, J. P., Li, Q. (5). A two-stage liear discrimiat aalysis via QR-decompositio. IEEE rasactios o Patter Aalysis ad Machie Itelligece, 27(6) [6] Jerome, H. F. (989). Regularized discrimiat aalysis. Joural of the America Statistical Associatio, 84 (5) [7] Dai, D. Q., Yue, P. C. (3). Regularized discrimiat aalysis ad its applicatio to face recogitio. Patter Recogitio, 36 (3) [8] Guo,Y. Q., Hastie,. (7). Regularized liear discrimiat aalysis ad its applicatio i microarray. Biostatistics, 8 () Joural of Digital Iformatio Maagemet Volume Number 2 April 3

6 [9] Ye, P., Xiog,., Li, Q., Jaarda,R., Bi, B., Cherkassky V., Kambhamettu, C. (6). Efficiet model selectio for regularized liear discrimiat aalysis. I: Proc. of the 5 th ACM iteratioal coferece o Iformatio ad kowledge maagemet (CIKM 6), p ACM, November. [] Jiepig, Y., ie, W. (6). Regularized discrimiat aalysis for high dimesioal, low sample size data. I: Proc. of Proceedigs of the 2 th ACM SIGKDD Iteratioal Coferece o Kowledge discovery ad Data Miig (KDD 6), p ACM, August. [] Golub, G. H., VaLoa, C. F. (996). Matrix Computatios, third ed.. he Johs Hopkis Uiversity Press, Baltimore, MD. [2] Chu, D. L, Goh, S.. (). A ew ad fast orthogoal liear discrimiat aalysis o udersampled problems. SIAM Joural o Scietific Computig, 32 (4) [3] Ye, J. P. (5). Characterizatio of a family of algorithms for geeralized discrimiat aalysis o udersampled problems. Joural of Machie Learig Research, 6 (4) [4] Che, L. F., Liao, H. Y., Ko, M.., Li, J. C., Yu, G. J. (). A ew LDA-based face recogitio system which ca solve the small sample size problem. Patter Recogitio, 33 () [5] Chu, D., hye, G. S. (). A ew ad fast implemetatio for ull space based liear discrimiat aalysis. Patter Recogitio, 43 (4) [6] Rui, H., Qigsha, L., Haqig, L., Sogde, M. (2). Solvig the small sample size problem of LDA. I: Proc. of the Iteratioal Coferece o Patter Recogitio (ICPR 2), p IEEE Computer Society, April. [7] Chu, D. L., Goh, S.., Hug, Y. S. (). Characterizatio of all solutios for udersampled ucorrelated liear discrimiat aalysis problems. SIAM Joural o Matrix Aalysis ad Applicatios, 32 (2) [8] Peg, H., Moogu, J., Haesu, P. (3). Structure preservig dimesio reductio for clustered text data based o the geeralized sigular value decompositio. SIAM Joural o Matrix Aalysis ad Applicatios 25 () [9] Haesu, P., Drake, B. L., Sagmi, L., Park, C. H. (7). Fast Liear Discrimiat Aalysis Usig QR Decompositio ad Regularizatio. echical Report G- CSE-7-2, Georgia Istitute of echology. [] Ye, J. P., Jaarda, R., Park, C. H., Park, H. (4). A optimizatio criterio for geeralized discrimiat aalysis o udersampled problems. IEEE rasactios o Patter Aalysis ad Machie Itelligece, 26 (8) [2] Chiga, W. K, Chub, D., Liaoc, L. Z, Wagb, X. Y (2). Regularized Orthogoal Liear Discrimiat Aalysis. Patter Recogitio, 45 (7) [22] Masashi, S. (6). Local Fisher discrimiat aalysis for supervised dimesioality reductio. I: Proc. of the 23 rd iteratioal coferece o Machie learig (ICML 6), p ACM, Apr. [23] Masashi, S. (7). Dimesioality reductio of multimodal labeled data by local Fisher discrimiat aalysis. Joural of Machie Learig Research, 8 (5) Author Biography Shuhua XU was bor i Jiagxi, Chia, i 977. She received her M.S. degree from Guizhou Uiversity, Guizhou, Chia, i 4. Now she is a istructor of the School of Mathematics Sciece ad physics Sciece. Her research iterests iclude optimizatio theory ad applicatio, machie learig theory ad patter recogitio. Joural of Digital Iformatio Maagemet Volume Number 2 April 3 59

Eigenimages. Digital Image Processing: Bernd Girod, Stanford University -- Eigenimages 1

Eigenimages. Digital Image Processing: Bernd Girod, Stanford University -- Eigenimages 1 Eigeimages Uitary trasforms Karhue-Loève trasform ad eigeimages Sirovich ad Kirby method Eigefaces for geder recogitio Fisher liear discrimat aalysis Fisherimages ad varyig illumiatio Fisherfaces vs. eigefaces

More information

Pattern Recognition Systems Lab 1 Least Mean Squares

Pattern Recognition Systems Lab 1 Least Mean Squares Patter Recogitio Systems Lab 1 Least Mea Squares 1. Objectives This laboratory work itroduces the OpeCV-based framework used throughout the course. I this assigmet a lie is fitted to a set of poits usig

More information

Eigenimages. Digital Image Processing: Bernd Girod, 2013 Stanford University -- Eigenimages 1

Eigenimages. Digital Image Processing: Bernd Girod, 2013 Stanford University -- Eigenimages 1 Eigeimages Uitary trasforms Karhue-Loève trasform ad eigeimages Sirovich ad Kirby method Eigefaces for geder recogitio Fisher liear discrimat aalysis Fisherimages ad varyig illumiatio Fisherfaces vs. eigefaces

More information

Ones Assignment Method for Solving Traveling Salesman Problem

Ones Assignment Method for Solving Traveling Salesman Problem Joural of mathematics ad computer sciece 0 (0), 58-65 Oes Assigmet Method for Solvig Travelig Salesma Problem Hadi Basirzadeh Departmet of Mathematics, Shahid Chamra Uiversity, Ahvaz, Ira Article history:

More information

Dimensionality Reduction PCA

Dimensionality Reduction PCA Dimesioality Reductio PCA Machie Learig CSE446 David Wadde (slides provided by Carlos Guestri) Uiversity of Washigto Feb 22, 2017 Carlos Guestri 2005-2017 1 Dimesioality reductio Iput data may have thousads

More information

A New Morphological 3D Shape Decomposition: Grayscale Interframe Interpolation Method

A New Morphological 3D Shape Decomposition: Grayscale Interframe Interpolation Method A ew Morphological 3D Shape Decompositio: Grayscale Iterframe Iterpolatio Method D.. Vizireau Politehica Uiversity Bucharest, Romaia ae@comm.pub.ro R. M. Udrea Politehica Uiversity Bucharest, Romaia mihea@comm.pub.ro

More information

A SOFTWARE MODEL FOR THE MULTILAYER PERCEPTRON

A SOFTWARE MODEL FOR THE MULTILAYER PERCEPTRON A SOFTWARE MODEL FOR THE MULTILAYER PERCEPTRON Roberto Lopez ad Eugeio Oñate Iteratioal Ceter for Numerical Methods i Egieerig (CIMNE) Edificio C1, Gra Capitá s/, 08034 Barceloa, Spai ABSTRACT I this work

More information

3D Model Retrieval Method Based on Sample Prediction

3D Model Retrieval Method Based on Sample Prediction 20 Iteratioal Coferece o Computer Commuicatio ad Maagemet Proc.of CSIT vol.5 (20) (20) IACSIT Press, Sigapore 3D Model Retrieval Method Based o Sample Predictio Qigche Zhag, Ya Tag* School of Computer

More information

A Semi- Non-Negative Matrix Factorization and Principal Component Analysis Unified Framework for Data Clustering

A Semi- Non-Negative Matrix Factorization and Principal Component Analysis Unified Framework for Data Clustering A Semi- No-Negative Matrix Factorizatio ad Pricipal Compoet Aalysis Uified Framework for Data Clusterig V.Yuvaraj, N.SivaKumar Assistat Professor, Departmet of Computer Sciece, K.S.G college of Arts ad

More information

arxiv: v2 [cs.ds] 24 Mar 2018

arxiv: v2 [cs.ds] 24 Mar 2018 Similar Elemets ad Metric Labelig o Complete Graphs arxiv:1803.08037v [cs.ds] 4 Mar 018 Pedro F. Felzeszwalb Brow Uiversity Providece, RI, USA pff@brow.edu March 8, 018 We cosider a problem that ivolves

More information

Dimension Reduction and Manifold Learning. Xin Zhang

Dimension Reduction and Manifold Learning. Xin Zhang Dimesio Reductio ad Maifold Learig Xi Zhag eeizhag@scut.edu.c Cotet Motivatio of maifold learig Pricipal compoet aalysis ad its etesio Maifold learig Global oliear maifold learig (IsoMap) Local oliear

More information

An Efficient Algorithm for Graph Bisection of Triangularizations

An Efficient Algorithm for Graph Bisection of Triangularizations A Efficiet Algorithm for Graph Bisectio of Triagularizatios Gerold Jäger Departmet of Computer Sciece Washigto Uiversity Campus Box 1045 Oe Brookigs Drive St. Louis, Missouri 63130-4899, USA jaegerg@cse.wustl.edu

More information

An Efficient Algorithm for Graph Bisection of Triangularizations

An Efficient Algorithm for Graph Bisection of Triangularizations Applied Mathematical Scieces, Vol. 1, 2007, o. 25, 1203-1215 A Efficiet Algorithm for Graph Bisectio of Triagularizatios Gerold Jäger Departmet of Computer Sciece Washigto Uiversity Campus Box 1045, Oe

More information

Improving Face Recognition Rate by Combining Eigenface Approach and Case-based Reasoning

Improving Face Recognition Rate by Combining Eigenface Approach and Case-based Reasoning Improvig Face Recogitio Rate by Combiig Eigeface Approach ad Case-based Reasoig Haris Supic, ember, IAENG Abstract There are may approaches to the face recogitio. This paper presets a approach that combies

More information

An Improved Shuffled Frog-Leaping Algorithm for Knapsack Problem

An Improved Shuffled Frog-Leaping Algorithm for Knapsack Problem A Improved Shuffled Frog-Leapig Algorithm for Kapsack Problem Zhoufag Li, Ya Zhou, ad Peg Cheg School of Iformatio Sciece ad Egieerig Hea Uiversity of Techology ZhegZhou, Chia lzhf1978@126.com Abstract.

More information

Chapter 3 Classification of FFT Processor Algorithms

Chapter 3 Classification of FFT Processor Algorithms Chapter Classificatio of FFT Processor Algorithms The computatioal complexity of the Discrete Fourier trasform (DFT) is very high. It requires () 2 complex multiplicatios ad () complex additios [5]. As

More information

Fuzzy Minimal Solution of Dual Fully Fuzzy Matrix Equations

Fuzzy Minimal Solution of Dual Fully Fuzzy Matrix Equations Iteratioal Coferece o Applied Mathematics, Simulatio ad Modellig (AMSM 2016) Fuzzy Miimal Solutio of Dual Fully Fuzzy Matrix Equatios Dequa Shag1 ad Xiaobi Guo2,* 1 Sciece Courses eachig Departmet, Gasu

More information

A Study on the Performance of Cholesky-Factorization using MPI

A Study on the Performance of Cholesky-Factorization using MPI A Study o the Performace of Cholesky-Factorizatio usig MPI Ha S. Kim Scott B. Bade Departmet of Computer Sciece ad Egieerig Uiversity of Califoria Sa Diego {hskim, bade}@cs.ucsd.edu Abstract Cholesky-factorizatio

More information

LU Decomposition Method

LU Decomposition Method SOLUTION OF SIMULTANEOUS LINEAR EQUATIONS LU Decompositio Method Jamie Traha, Autar Kaw, Kevi Marti Uiversity of South Florida Uited States of America kaw@eg.usf.edu http://umericalmethods.eg.usf.edu Itroductio

More information

Text Feature Selection based on Feature Dispersion Degree and Feature Concentration Degree

Text Feature Selection based on Feature Dispersion Degree and Feature Concentration Degree Available olie at www.ijpe-olie.com vol. 13, o. 7, November 017, pp. 1159-1164 DOI: 10.3940/ijpe.17.07.p19.11591164 Text Feature Selectio based o Feature Dispersio Degree ad Feature Cocetratio Degree Zhifeg

More information

Solving Fuzzy Assignment Problem Using Fourier Elimination Method

Solving Fuzzy Assignment Problem Using Fourier Elimination Method Global Joural of Pure ad Applied Mathematics. ISSN 0973-768 Volume 3, Number 2 (207), pp. 453-462 Research Idia Publicatios http://www.ripublicatio.com Solvig Fuzzy Assigmet Problem Usig Fourier Elimiatio

More information

LDA-based Non-negative Matrix Factorization for Supervised Face Recognition

LDA-based Non-negative Matrix Factorization for Supervised Face Recognition 1294 JOURNAL OF SOFTWARE, VOL. 9, NO. 5, MAY 2014 LDA-based No-egative Matrix Factorizatio for Supervised Face Recogitio Yu Xue a, Chog Sze Tog b, Jig Yu Yua c a School of Physics ad Telecommuicatio Egieerig,

More information

Research Article An Improved Metric Learning Approach for Degraded Face Recognition

Research Article An Improved Metric Learning Approach for Degraded Face Recognition Mathematical Problems i Egieerig, Article ID 74978, 10 pages http://dxdoiorg/101155/014/74978 Research Article A Improved Metric Learig Approach for Degraded Face Recogitio Guofeg Zou, 1 Yuayua Zhag, 1

More information

Pruning and Summarizing the Discovered Time Series Association Rules from Mechanical Sensor Data Qing YANG1,a,*, Shao-Yu WANG1,b, Ting-Ting ZHANG2,c

Pruning and Summarizing the Discovered Time Series Association Rules from Mechanical Sensor Data Qing YANG1,a,*, Shao-Yu WANG1,b, Ting-Ting ZHANG2,c Advaces i Egieerig Research (AER), volume 131 3rd Aual Iteratioal Coferece o Electroics, Electrical Egieerig ad Iformatio Sciece (EEEIS 2017) Pruig ad Summarizig the Discovered Time Series Associatio Rules

More information

Algorithms for Disk Covering Problems with the Most Points

Algorithms for Disk Covering Problems with the Most Points Algorithms for Disk Coverig Problems with the Most Poits Bi Xiao Departmet of Computig Hog Kog Polytechic Uiversity Hug Hom, Kowloo, Hog Kog csbxiao@comp.polyu.edu.hk Qigfeg Zhuge, Yi He, Zili Shao, Edwi

More information

Analysis of Server Resource Consumption of Meteorological Satellite Application System Based on Contour Curve

Analysis of Server Resource Consumption of Meteorological Satellite Application System Based on Contour Curve Advaces i Computer, Sigals ad Systems (2018) 2: 19-25 Clausius Scietific Press, Caada Aalysis of Server Resource Cosumptio of Meteorological Satellite Applicatio System Based o Cotour Curve Xiagag Zhao

More information

New Fuzzy Color Clustering Algorithm Based on hsl Similarity

New Fuzzy Color Clustering Algorithm Based on hsl Similarity IFSA-EUSFLAT 009 New Fuzzy Color Clusterig Algorithm Based o hsl Similarity Vasile Ptracu Departmet of Iformatics Techology Tarom Compay Bucharest Romaia Email: patrascu.v@gmail.com Abstract I this paper

More information

BASED ON ITERATIVE ERROR-CORRECTION

BASED ON ITERATIVE ERROR-CORRECTION A COHPARISO OF CRYPTAALYTIC PRICIPLES BASED O ITERATIVE ERROR-CORRECTIO Miodrag J. MihaljeviC ad Jova Dj. GoliC Istitute of Applied Mathematics ad Electroics. Belgrade School of Electrical Egieerig. Uiversity

More information

Adaptive Resource Allocation for Electric Environmental Pollution through the Control Network

Adaptive Resource Allocation for Electric Environmental Pollution through the Control Network Available olie at www.sciecedirect.com Eergy Procedia 6 (202) 60 64 202 Iteratioal Coferece o Future Eergy, Eviromet, ad Materials Adaptive Resource Allocatio for Electric Evirometal Pollutio through the

More information

Journal of Chemical and Pharmaceutical Research, 2013, 5(12): Research Article

Journal of Chemical and Pharmaceutical Research, 2013, 5(12): Research Article Available olie www.jocpr.com Joural of Chemical ad Pharmaceutical Research, 2013, 5(12):745-749 Research Article ISSN : 0975-7384 CODEN(USA) : JCPRC5 K-meas algorithm i the optimal iitial cetroids based

More information

ISSN (Print) Research Article. *Corresponding author Nengfa Hu

ISSN (Print) Research Article. *Corresponding author Nengfa Hu Scholars Joural of Egieerig ad Techology (SJET) Sch. J. Eg. Tech., 2016; 4(5):249-253 Scholars Academic ad Scietific Publisher (A Iteratioal Publisher for Academic ad Scietific Resources) www.saspublisher.com

More information

On Spectral Theory Of K-n- Arithmetic Mean Idempotent Matrices On Posets

On Spectral Theory Of K-n- Arithmetic Mean Idempotent Matrices On Posets Iteratioal Joural of Sciece, Egieerig ad echology Research (IJSER), Volume 5, Issue, February 016 O Spectral heory Of -- Arithmetic Mea Idempotet Matrices O Posets 1 Dr N Elumalai, ProfRMaikada, 3 Sythiya

More information

Higher-order iterative methods free from second derivative for solving nonlinear equations

Higher-order iterative methods free from second derivative for solving nonlinear equations Iteratioal Joural of the Phsical Scieces Vol 6(8, pp 887-89, 8 April, Available olie at http://wwwacademicjouralsorg/ijps DOI: 5897/IJPS45 ISSN 99-95 Academic Jourals Full Legth Research Paper Higher-order

More information

Characterizing graphs of maximum principal ratio

Characterizing graphs of maximum principal ratio Characterizig graphs of maximum pricipal ratio Michael Tait ad Josh Tobi November 9, 05 Abstract The pricipal ratio of a coected graph, deoted γg, is the ratio of the maximum ad miimum etries of its first

More information

Cubic Polynomial Curves with a Shape Parameter

Cubic Polynomial Curves with a Shape Parameter roceedigs of the th WSEAS Iteratioal Coferece o Robotics Cotrol ad Maufacturig Techology Hagzhou Chia April -8 00 (pp5-70) Cubic olyomial Curves with a Shape arameter MO GUOLIANG ZHAO YANAN Iformatio ad

More information

ANN WHICH COVERS MLP AND RBF

ANN WHICH COVERS MLP AND RBF ANN WHICH COVERS MLP AND RBF Josef Boští, Jaromír Kual Faculty of Nuclear Scieces ad Physical Egieerig, CTU i Prague Departmet of Software Egieerig Abstract Two basic types of artificial eural etwors Multi

More information

Fundamentals of Media Processing. Shin'ichi Satoh Kazuya Kodama Hiroshi Mo Duy-Dinh Le

Fundamentals of Media Processing. Shin'ichi Satoh Kazuya Kodama Hiroshi Mo Duy-Dinh Le Fudametals of Media Processig Shi'ichi Satoh Kazuya Kodama Hiroshi Mo Duy-Dih Le Today's topics Noparametric Methods Parze Widow k-nearest Neighbor Estimatio Clusterig Techiques k-meas Agglomerative Hierarchical

More information

A Novel Feature Extraction Algorithm for Haar Local Binary Pattern Texture Based on Human Vision System

A Novel Feature Extraction Algorithm for Haar Local Binary Pattern Texture Based on Human Vision System A Novel Feature Extractio Algorithm for Haar Local Biary Patter Texture Based o Huma Visio System Liu Tao 1,* 1 Departmet of Electroic Egieerig Shaaxi Eergy Istitute Xiayag, Shaaxi, Chia Abstract The locality

More information

Designing a learning system

Designing a learning system CS 75 Machie Learig Lecture Desigig a learig system Milos Hauskrecht milos@cs.pitt.edu 539 Seott Square, x-5 people.cs.pitt.edu/~milos/courses/cs75/ Admiistrivia No homework assigmet this week Please try

More information

CHAPTER IV: GRAPH THEORY. Section 1: Introduction to Graphs

CHAPTER IV: GRAPH THEORY. Section 1: Introduction to Graphs CHAPTER IV: GRAPH THEORY Sectio : Itroductio to Graphs Sice this class is called Number-Theoretic ad Discrete Structures, it would be a crime to oly focus o umber theory regardless how woderful those topics

More information

Neural Networks A Model of Boolean Functions

Neural Networks A Model of Boolean Functions Neural Networks A Model of Boolea Fuctios Berd Steibach, Roma Kohut Freiberg Uiversity of Miig ad Techology Istitute of Computer Sciece D-09596 Freiberg, Germay e-mails: steib@iformatik.tu-freiberg.de

More information

The content is identical to the content of the published paper, but without the final typesetting by the publisher.

The content is identical to the content of the published paper, but without the final typesetting by the publisher. This documet cotais the publisher s pdf-versio of the refereed paper: Efficiet Trackig of the Domiat Eigespace of a Normalized Kerel Matrix by Geert Gis, Ilse Smets, ad Ja Va Impe which has bee archived

More information

Numerical Methods Lecture 6 - Curve Fitting Techniques

Numerical Methods Lecture 6 - Curve Fitting Techniques Numerical Methods Lecture 6 - Curve Fittig Techiques Topics motivatio iterpolatio liear regressio higher order polyomial form expoetial form Curve fittig - motivatio For root fidig, we used a give fuctio

More information

Accuracy Improvement in Camera Calibration

Accuracy Improvement in Camera Calibration Accuracy Improvemet i Camera Calibratio FaJie L Qi Zag ad Reihard Klette CITR, Computer Sciece Departmet The Uiversity of Aucklad Tamaki Campus, Aucklad, New Zealad fli006, qza001@ec.aucklad.ac.z r.klette@aucklad.ac.z

More information

Study on effective detection method for specific data of large database LI Jin-feng

Study on effective detection method for specific data of large database LI Jin-feng Iteratioal Coferece o Automatio, Mechaical Cotrol ad Computatioal Egieerig (AMCCE 205) Study o effective detectio method for specific data of large database LI Ji-feg (Vocatioal College of DogYig, Shadog

More information

New HSL Distance Based Colour Clustering Algorithm

New HSL Distance Based Colour Clustering Algorithm The 4th Midwest Artificial Itelligece ad Cogitive Scieces Coferece (MAICS 03 pp 85-9 New Albay Idiaa USA April 3-4 03 New HSL Distace Based Colour Clusterig Algorithm Vasile Patrascu Departemet of Iformatics

More information

Image based Cats and Possums Identification for Intelligent Trapping Systems

Image based Cats and Possums Identification for Intelligent Trapping Systems Volume 159 No, February 017 Image based Cats ad Possums Idetificatio for Itelliget Trappig Systems T. A. S. Achala Perera School of Egieerig Aucklad Uiversity of Techology New Zealad Joh Collis School

More information

Optimization for framework design of new product introduction management system Ma Ying, Wu Hongcui

Optimization for framework design of new product introduction management system Ma Ying, Wu Hongcui 2d Iteratioal Coferece o Electrical, Computer Egieerig ad Electroics (ICECEE 2015) Optimizatio for framework desig of ew product itroductio maagemet system Ma Yig, Wu Hogcui Tiaji Electroic Iformatio Vocatioal

More information

Creating Exact Bezier Representations of CST Shapes. David D. Marshall. California Polytechnic State University, San Luis Obispo, CA , USA

Creating Exact Bezier Representations of CST Shapes. David D. Marshall. California Polytechnic State University, San Luis Obispo, CA , USA Creatig Exact Bezier Represetatios of CST Shapes David D. Marshall Califoria Polytechic State Uiversity, Sa Luis Obispo, CA 93407-035, USA The paper presets a method of expressig CST shapes pioeered by

More information

Second-Order Domain Decomposition Method for Three-Dimensional Hyperbolic Problems

Second-Order Domain Decomposition Method for Three-Dimensional Hyperbolic Problems Iteratioal Mathematical Forum, Vol. 8, 013, o. 7, 311-317 Secod-Order Domai Decompositio Method for Three-Dimesioal Hyperbolic Problems Youbae Ju Departmet of Applied Mathematics Kumoh Natioal Istitute

More information

A New Bit Wise Technique for 3-Partitioning Algorithm

A New Bit Wise Technique for 3-Partitioning Algorithm Special Issue of Iteratioal Joural of Computer Applicatios (0975 8887) o Optimizatio ad O-chip Commuicatio, No.1. Feb.2012, ww.ijcaolie.org A New Bit Wise Techique for 3-Partitioig Algorithm Rajumar Jai

More information

Criterion in selecting the clustering algorithm in Radial Basis Functional Link Nets

Criterion in selecting the clustering algorithm in Radial Basis Functional Link Nets WSEAS TRANSACTIONS o SYSTEMS Ag Sau Loog, Og Hog Choo, Low Heg Chi Criterio i selectig the clusterig algorithm i Radial Basis Fuctioal Lik Nets ANG SAU LOONG 1, ONG HONG CHOON 2 & LOW HENG CHIN 3 Departmet

More information

Learning to Shoot a Goal Lecture 8: Learning Models and Skills

Learning to Shoot a Goal Lecture 8: Learning Models and Skills Learig to Shoot a Goal Lecture 8: Learig Models ad Skills How do we acquire skill at shootig goals? CS 344R/393R: Robotics Bejami Kuipers Learig to Shoot a Goal The robot eeds to shoot the ball i the goal.

More information

A Note on Least-norm Solution of Global WireWarping

A Note on Least-norm Solution of Global WireWarping A Note o Least-orm Solutio of Global WireWarpig Charlie C. L. Wag Departmet of Mechaical ad Automatio Egieerig The Chiese Uiversity of Hog Kog Shati, N.T., Hog Kog E-mail: cwag@mae.cuhk.edu.hk Abstract

More information

Fast Fourier Transform (FFT) Algorithms

Fast Fourier Transform (FFT) Algorithms Fast Fourier Trasform FFT Algorithms Relatio to the z-trasform elsewhere, ozero, z x z X x [ ] 2 ~ elsewhere,, ~ e j x X x x π j e z z X X π 2 ~ The DFS X represets evely spaced samples of the z- trasform

More information

Task scenarios Outline. Scenarios in Knowledge Extraction. Proposed Framework for Scenario to Design Diagram Transformation

Task scenarios Outline. Scenarios in Knowledge Extraction. Proposed Framework for Scenario to Design Diagram Transformation 6-0-0 Kowledge Trasformatio from Task Scearios to View-based Desig Diagrams Nima Dezhkam Kamra Sartipi {dezhka, sartipi}@mcmaster.ca Departmet of Computig ad Software McMaster Uiversity CANADA SEKE 08

More information

Mapping Publishing and Mapping Adaptation in the Middleware of Railway Information Grid System

Mapping Publishing and Mapping Adaptation in the Middleware of Railway Information Grid System Mappig Publishig ad Mappig Adaptatio i the Middleware of Railway Iformatio Grid ystem You Gamei, Liao Huamig, u Yuzhog Istitute of Computig Techology, Chiese Academy of cieces, Beijig 00080 gameiu@ict.ac.c

More information

Exact Minimum Lower Bound Algorithm for Traveling Salesman Problem

Exact Minimum Lower Bound Algorithm for Traveling Salesman Problem Exact Miimum Lower Boud Algorithm for Travelig Salesma Problem Mohamed Eleiche GeoTiba Systems mohamed.eleiche@gmail.com Abstract The miimum-travel-cost algorithm is a dyamic programmig algorithm to compute

More information

The Counterchanged Crossed Cube Interconnection Network and Its Topology Properties

The Counterchanged Crossed Cube Interconnection Network and Its Topology Properties WSEAS TRANSACTIONS o COMMUNICATIONS Wag Xiyag The Couterchaged Crossed Cube Itercoectio Network ad Its Topology Properties WANG XINYANG School of Computer Sciece ad Egieerig South Chia Uiversity of Techology

More information

Sectio 4, a prototype project of settig field weight with AHP method is developed ad the experimetal results are aalyzed. Fially, we coclude our work

Sectio 4, a prototype project of settig field weight with AHP method is developed ad the experimetal results are aalyzed. Fially, we coclude our work 200 2d Iteratioal Coferece o Iformatio ad Multimedia Techology (ICIMT 200) IPCSIT vol. 42 (202) (202) IACSIT Press, Sigapore DOI: 0.7763/IPCSIT.202.V42.0 Idex Weight Decisio Based o AHP for Iformatio Retrieval

More information

Force Network Analysis using Complementary Energy

Force Network Analysis using Complementary Energy orce Network Aalysis usig Complemetary Eergy Adrew BORGART Assistat Professor Delft Uiversity of Techology Delft, The Netherlads A.Borgart@tudelft.l Yaick LIEM Studet Delft Uiversity of Techology Delft,

More information

Lip Contour Extraction Based on Support Vector Machine

Lip Contour Extraction Based on Support Vector Machine Lip Cotour Extractio Based o Support Vector Machie Author Pa, Xiaosheg, Kog, Jiagpig, Liew, Ala Wee-Chug Published 008 Coferece Title CISP 008 : Proceedigs, First Iteratioal Cogress o Image ad Sigal Processig

More information

Bayesian Network Structure Learning from Attribute Uncertain Data

Bayesian Network Structure Learning from Attribute Uncertain Data Bayesia Network Structure Learig from Attribute Ucertai Data Wetig Sog 1,2, Jeffrey Xu Yu 3, Hog Cheg 3, Hogya Liu 4, Ju He 1,2,*, ad Xiaoyog Du 1,2 1 Key Labs of Data Egieerig ad Kowledge Egieerig, Miistry

More information

FACE RECOGNITION BY EMBEDDING OF DT-CWT COEFFICIENT USING SOM AND ENSEMBLE BASED CLASSIFIER

FACE RECOGNITION BY EMBEDDING OF DT-CWT COEFFICIENT USING SOM AND ENSEMBLE BASED CLASSIFIER GAURI AGRAWAL AND SANJAY KUMAR MAURYA: FACE RECOGNITION BY EMBEDDING OF DT-CWT COEFFICIENT USING SOM AND ENSEMBLE BASED CLASSIFIER DOI: 0.297/ijivp.206.082 FACE RECOGNITION BY EMBEDDING OF DT-CWT COEFFICIENT

More information

Load balanced Parallel Prime Number Generator with Sieve of Eratosthenes on Cluster Computers *

Load balanced Parallel Prime Number Generator with Sieve of Eratosthenes on Cluster Computers * Load balaced Parallel Prime umber Geerator with Sieve of Eratosthees o luster omputers * Soowook Hwag*, Kyusik hug**, ad Dogseug Kim* *Departmet of Electrical Egieerig Korea Uiversity Seoul, -, Rep. of

More information

Lecture 18. Optimization in n dimensions

Lecture 18. Optimization in n dimensions Lecture 8 Optimizatio i dimesios Itroductio We ow cosider the problem of miimizig a sigle scalar fuctio of variables, f x, where x=[ x, x,, x ]T. The D case ca be visualized as fidig the lowest poit of

More information

An Anomaly Detection Method Based On Deep Learning

An Anomaly Detection Method Based On Deep Learning Sed Orders for Reprits to reprits@bethamsciece.ae 734 The Ope Automatio ad Cotrol Systems Joural, 05, 7, 734-739 A Aomaly Detectio Method Based O Deep Learig Ope Access Hog-li Deg *, Tao yag ad Jiag-i

More information

An improved support vector machine based on particle swarm optimization in laser ultrasonic defect detection

An improved support vector machine based on particle swarm optimization in laser ultrasonic defect detection A improved support vector machie based o particle swarm optimizatio i laser ultrasoic defect detectio School of Sciece, North Uiversity of Chia, aiyua, Shaxi 35, Chia xut98@63.com,hhp9@63.com,xywag@6.com,43497@qq.com

More information

Investigating methods for improving Bagged k-nn classifiers

Investigating methods for improving Bagged k-nn classifiers Ivestigatig methods for improvig Bagged k-nn classifiers Fuad M. Alkoot Telecommuicatio & Navigatio Istitute, P.A.A.E.T. P.O.Box 4575, Alsalmia, 22046 Kuwait Abstract- We experimet with baggig knn classifiers

More information

INTERSECTION CORDIAL LABELING OF GRAPHS

INTERSECTION CORDIAL LABELING OF GRAPHS INTERSECTION CORDIAL LABELING OF GRAPHS G Meea, K Nagaraja Departmet of Mathematics, PSR Egieerig College, Sivakasi- 66 4, Virudhuagar(Dist) Tamil Nadu, INDIA meeag9@yahoocoi Departmet of Mathematics,

More information

Harris Corner Detection Algorithm at Sub-pixel Level and Its Application Yuanfeng Han a, Peijiang Chen b * and Tian Meng c

Harris Corner Detection Algorithm at Sub-pixel Level and Its Application Yuanfeng Han a, Peijiang Chen b * and Tian Meng c Iteratioal Coferece o Computatioal Sciece ad Egieerig (ICCSE 015) Harris Corer Detectio Algorithm at Sub-pixel Level ad Its Applicatio Yuafeg Ha a, Peijiag Che b * ad Tia Meg c School of Automobile, Liyi

More information

BOOLEAN MATHEMATICS: GENERAL THEORY

BOOLEAN MATHEMATICS: GENERAL THEORY CHAPTER 3 BOOLEAN MATHEMATICS: GENERAL THEORY 3.1 ISOMORPHIC PROPERTIES The ame Boolea Arithmetic was chose because it was discovered that literal Boolea Algebra could have a isomorphic umerical aspect.

More information

Euclidean Distance Based Feature Selection for Fault Detection Prediction Model in Semiconductor Manufacturing Process

Euclidean Distance Based Feature Selection for Fault Detection Prediction Model in Semiconductor Manufacturing Process Vol.133 (Iformatio Techology ad Computer Sciece 016), pp.85-89 http://dx.doi.org/10.1457/astl.016. Euclidea Distace Based Feature Selectio for Fault Detectio Predictio Model i Semicoductor Maufacturig

More information

Evaluation of Support Vector Machine Kernels for Detecting Network Anomalies

Evaluation of Support Vector Machine Kernels for Detecting Network Anomalies Evaluatio of Support Vector Machie Kerels for Detectig Network Aomalies Prera Batta, Maider Sigh, Zhida Li, Qigye Dig, ad Ljiljaa Trajković Commuicatio Networks Laboratory http://www.esc.sfu.ca/~ljilja/cl/

More information

Web Text Feature Extraction with Particle Swarm Optimization

Web Text Feature Extraction with Particle Swarm Optimization 32 IJCSNS Iteratioal Joural of Computer Sciece ad Network Security, VOL.7 No.6, Jue 2007 Web Text Feature Extractio with Particle Swarm Optimizatio Sog Liagtu,, Zhag Xiaomig Istitute of Itelliget Machies,

More information

What are we going to learn? CSC Data Structures Analysis of Algorithms. Overview. Algorithm, and Inputs

What are we going to learn? CSC Data Structures Analysis of Algorithms. Overview. Algorithm, and Inputs What are we goig to lear? CSC316-003 Data Structures Aalysis of Algorithms Computer Sciece North Carolia State Uiversity Need to say that some algorithms are better tha others Criteria for evaluatio Structure

More information

Ensemble-based Feature Selection Criteria

Ensemble-based Feature Selection Criteria Esemble-based Feature Selectio Criteria Terry Wideatt 1, Matthew Prior 1, Niv Effro 2, Natha Itrator 2 1 Cetre for Visio, Speech ad Sigal Proc (CVSSP), Uiversity of Surrey, Guildford, Surrey, Uited Kigdom

More information

CSCI 5090/7090- Machine Learning. Spring Mehdi Allahyari Georgia Southern University

CSCI 5090/7090- Machine Learning. Spring Mehdi Allahyari Georgia Southern University CSCI 5090/7090- Machie Learig Sprig 018 Mehdi Allahyari Georgia Souther Uiversity Clusterig (slides borrowed from Tom Mitchell, Maria Floria Balca, Ali Borji, Ke Che) 1 Clusterig, Iformal Goals Goal: Automatically

More information

The Closest Line to a Data Set in the Plane. David Gurney Southeastern Louisiana University Hammond, Louisiana

The Closest Line to a Data Set in the Plane. David Gurney Southeastern Louisiana University Hammond, Louisiana The Closest Lie to a Data Set i the Plae David Gurey Southeaster Louisiaa Uiversity Hammod, Louisiaa ABSTRACT This paper looks at three differet measures of distace betwee a lie ad a data set i the plae:

More information

Text Categorization Based on Regularized Linear Classification Methods

Text Categorization Based on Regularized Linear Classification Methods Iformatio Retrieval, 4, 5 3, 200 c 200 Kluwer Academic Publishers. Maufactured i The Netherlads. Text Categorizatio Based o Regularized Liear Classificatio Methods TONG ZHANG tzhag@watso.ibm.com FRANK

More information

Designing a learning system

Designing a learning system CS 75 Itro to Machie Learig Lecture Desigig a learig system Milos Hauskrecht milos@pitt.edu 539 Seott Square, -5 people.cs.pitt.edu/~milos/courses/cs75/ Admiistrivia No homework assigmet this week Please

More information

BAYESIAN WITH FULL CONDITIONAL POSTERIOR DISTRIBUTION APPROACH FOR SOLUTION OF COMPLEX MODELS. Pudji Ismartini

BAYESIAN WITH FULL CONDITIONAL POSTERIOR DISTRIBUTION APPROACH FOR SOLUTION OF COMPLEX MODELS. Pudji Ismartini Proceedig of Iteratioal Coferece O Research, Implemetatio Ad Educatio Of Mathematics Ad Scieces 014, Yogyakarta State Uiversity, 18-0 May 014 BAYESIAN WIH FULL CONDIIONAL POSERIOR DISRIBUION APPROACH FOR

More information

MATHEMATICAL METHODS OF ANALYSIS AND EXPERIMENTAL DATA PROCESSING (Or Methods of Curve Fitting)

MATHEMATICAL METHODS OF ANALYSIS AND EXPERIMENTAL DATA PROCESSING (Or Methods of Curve Fitting) MATHEMATICAL METHODS OF ANALYSIS AND EXPERIMENTAL DATA PROCESSING (Or Methods of Curve Fittig) I this chapter, we will eamie some methods of aalysis ad data processig; data obtaied as a result of a give

More information

Copyright 2016 Ramez Elmasri and Shamkant B. Navathe

Copyright 2016 Ramez Elmasri and Shamkant B. Navathe Copyright 2016 Ramez Elmasri ad Shamkat B. Navathe CHAPTER 19 Query Optimizatio Copyright 2016 Ramez Elmasri ad Shamkat B. Navathe Itroductio Query optimizatio Coducted by a query optimizer i a DBMS Goal:

More information

Copyright 2016 Ramez Elmasri and Shamkant B. Navathe

Copyright 2016 Ramez Elmasri and Shamkant B. Navathe Copyright 2016 Ramez Elmasri ad Shamkat B. Navathe CHAPTER 18 Strategies for Query Processig Copyright 2016 Ramez Elmasri ad Shamkat B. Navathe Itroductio DBMS techiques to process a query Scaer idetifies

More information

Our Learning Problem, Again

Our Learning Problem, Again Noparametric Desity Estimatio Matthew Stoe CS 520, Sprig 2000 Lecture 6 Our Learig Problem, Agai Use traiig data to estimate ukow probabilities ad probability desity fuctios So far, we have depeded o describig

More information

A Very Simple Approach for 3-D to 2-D Mapping

A Very Simple Approach for 3-D to 2-D Mapping A Very Simple Approach for -D to -D appig Sadipa Dey (1 Ajith Abraham ( Sugata Sayal ( Sadipa Dey (1 Ashi Software Private Limited INFINITY Tower II 10 th Floor Plot No. - 4. Block GP Salt Lake Electroics

More information

Image Analysis. Segmentation by Fitting a Model

Image Analysis. Segmentation by Fitting a Model Image Aalysis Segmetatio by Fittig a Model Christophoros Nikou cikou@cs.uoi.gr Images take from: D. Forsyth ad J. Poce. Computer Visio: A Moder Approach, Pretice Hall, 2003. Computer Visio course by Svetlaa

More information

Introduction. Nature-Inspired Computing. Terminology. Problem Types. Constraint Satisfaction Problems - CSP. Free Optimization Problem - FOP

Introduction. Nature-Inspired Computing. Terminology. Problem Types. Constraint Satisfaction Problems - CSP. Free Optimization Problem - FOP Nature-Ispired Computig Hadlig Costraits Dr. Şima Uyar September 2006 Itroductio may practical problems are costraied ot all combiatios of variable values represet valid solutios feasible solutios ifeasible

More information

AN OPTIMIZATION NETWORK FOR MATRIX INVERSION

AN OPTIMIZATION NETWORK FOR MATRIX INVERSION 397 AN OPTIMIZATION NETWORK FOR MATRIX INVERSION Ju-Seog Jag, S~ Youg Lee, ad Sag-Yug Shi Korea Advaced Istitute of Sciece ad Techology, P.O. Box 150, Cheogryag, Seoul, Korea ABSTRACT Iverse matrix calculatio

More information

A Polynomial Interval Shortest-Route Algorithm for Acyclic Network

A Polynomial Interval Shortest-Route Algorithm for Acyclic Network A Polyomial Iterval Shortest-Route Algorithm for Acyclic Network Hossai M Akter Key words: Iterval; iterval shortest-route problem; iterval algorithm; ucertaity Abstract A method ad algorithm is preseted

More information

Pseudocode ( 1.1) Analysis of Algorithms. Primitive Operations. Pseudocode Details. Running Time ( 1.1) Estimating performance

Pseudocode ( 1.1) Analysis of Algorithms. Primitive Operations. Pseudocode Details. Running Time ( 1.1) Estimating performance Aalysis of Algorithms Iput Algorithm Output A algorithm is a step-by-step procedure for solvig a problem i a fiite amout of time. Pseudocode ( 1.1) High-level descriptio of a algorithm More structured

More information

Improvement of the Orthogonal Code Convolution Capabilities Using FPGA Implementation

Improvement of the Orthogonal Code Convolution Capabilities Using FPGA Implementation Improvemet of the Orthogoal Code Covolutio Capabilities Usig FPGA Implemetatio Naima Kaabouch, Member, IEEE, Apara Dhirde, Member, IEEE, Saleh Faruque, Member, IEEE Departmet of Electrical Egieerig, Uiversity

More information

Performance Plus Software Parameter Definitions

Performance Plus Software Parameter Definitions Performace Plus+ Software Parameter Defiitios/ Performace Plus Software Parameter Defiitios Chapma Techical Note-TG-5 paramete.doc ev-0-03 Performace Plus+ Software Parameter Defiitios/2 Backgroud ad Defiitios

More information

Evaluation scheme for Tracking in AMI

Evaluation scheme for Tracking in AMI A M I C o m m u i c a t i o A U G M E N T E D M U L T I - P A R T Y I N T E R A C T I O N http://www.amiproject.org/ Evaluatio scheme for Trackig i AMI S. Schreiber a D. Gatica-Perez b AMI WP4 Trackig:

More information

Lecture 1: Introduction and Strassen s Algorithm

Lecture 1: Introduction and Strassen s Algorithm 5-750: Graduate Algorithms Jauary 7, 08 Lecture : Itroductio ad Strasse s Algorithm Lecturer: Gary Miller Scribe: Robert Parker Itroductio Machie models I this class, we will primarily use the Radom Access

More information

Data Structures and Algorithms. Analysis of Algorithms

Data Structures and Algorithms. Analysis of Algorithms Data Structures ad Algorithms Aalysis of Algorithms Outlie Ruig time Pseudo-code Big-oh otatio Big-theta otatio Big-omega otatio Asymptotic algorithm aalysis Aalysis of Algorithms Iput Algorithm Output

More information

Lecture 2: Spectra of Graphs

Lecture 2: Spectra of Graphs Spectral Graph Theory ad Applicatios WS 20/202 Lecture 2: Spectra of Graphs Lecturer: Thomas Sauerwald & He Su Our goal is to use the properties of the adjacecy/laplacia matrix of graphs to first uderstad

More information

Image Segmentation EEE 508

Image Segmentation EEE 508 Image Segmetatio Objective: to determie (etract) object boudaries. It is a process of partitioig a image ito distict regios by groupig together eighborig piels based o some predefied similarity criterio.

More information

Lecture Notes 6 Introduction to algorithm analysis CSS 501 Data Structures and Object-Oriented Programming

Lecture Notes 6 Introduction to algorithm analysis CSS 501 Data Structures and Object-Oriented Programming Lecture Notes 6 Itroductio to algorithm aalysis CSS 501 Data Structures ad Object-Orieted Programmig Readig for this lecture: Carrao, Chapter 10 To be covered i this lecture: Itroductio to algorithm aalysis

More information