Investigating methods for improving Bagged k-nn classifiers

Size: px
Start display at page:

Download "Investigating methods for improving Bagged k-nn classifiers"

Transcription

1 Ivestigatig methods for improvig Bagged k-nn classifiers Fuad M. Alkoot Telecommuicatio & Navigatio Istitute, P.A.A.E.T. P.O.Box 4575, Alsalmia, Kuwait Abstract- We experimet with baggig knn classifiers usig a optimal distace metric. The aim is to establish whether baggig knn is useful whe a better metric is used. We experimet o real world data sets, at differet traiig set sizes. Our experimets also ivolve Modified baggig, which was proposed by us, to see the effect of prior kowledge o the baggig performace uder the ew distace measure. Results idicate the optimal metric improves the performace of baggig as well as the sigle classifier. Key-Words: - baggig, fusio, classifier combiig, earest eighbor 1 Itroductio I order to improve the accuracy of classifiers researchers have foud that fusig (combiig) the decisios of more tha oe classifier would yield superior results over the best sigle classifier. The papers [1,2,12,13,14,15,17,20,21,22] are a sample showig the use of classifier fusio to improve classificatio accuracy. Baggig [6], proposed by Breima, is a method of geeratig multiple versios of a predictor or classifier, via bootstrappig ad the usig these to get a aggregated decisio. The multiple versios of classifiers are formed by makig bootstrap [11] replicas of the traiig set, ad these are the used to trai additioal classifiers. Breima postulates that the ecessary precoditio for baggig to improve accuracy beig the classifier istability.by istability we mea that a perturbatio of the learig set causes sigificat chages i the classifier output. Baggig has bee successfully applied to practical cases to improve the performace of ustable classifiers. A sample of such papers icludes [10, 8]. May authors have ivestigated its merits ad compared baggig to boostig or other methods [4,7,9,16,18]. I [6] Breima argued that baggig would ot improve a earest eighbor (NN) classifier, because it is stable. He cofirmed this experimetally by showig that, whe baggig NN classifiers, good results were achieved o 3 data sets out of 6. But, whe baggig decisio trees, better error rate o all 6 data sets was observed. Most research to date has bee directed towards applyig baggig to ustable classifiers, such as decisio trees ad eural etworks. Our previous work [3] o baggig k-nn uder small sample size showed that although regular baggig could ot outperform the sigle classifier, modified baggig which is implemeted with some modificatios to the baggig method, may outperform the sigle classifier. The improvemets were mostly at medium traiig set sizes, while at large traiig set sizes it had a similar performace to regular baggig ad the sigle classifier. Eve at the medium set size, for few data types, we did ot always achieve a sigificat improvemet. More ivestigatio is required to fid the reasos behid this variable performace. We also aim to further improve the performace of bagged k-nn classifiers, beyod what we achieved through modified baggig, ad fid the methods, coditios ad data properties that lead to the successful performace. There we used the Euclidea distace as the metric to fid the closest k samples. However, the limitatio of the Euclidea metric is that it does esure that the k earest eighbors are draw from a regio with a costat a posteriori class probability distributio. This may lead to suboptimal performaces. If a more robust distace metric is used the sigle classifier may outperform all baggig methods, or o the cotrary baggig may gai more from the optimal metric tha the sigle classifier. However, if we use a distace metric that improves the sigle classifier but is data depedet, we will be usig a method that creates diverse ad hece ISSN: Page 351 ISBN:

2 ustable classifiers. Ad sice baggig works best o ustable classifiers we may ed up with knn that ca be improved via baggig. We experimet with baggig usig the optimal distace metric proposed by Short ad Fukuaga [19]. I the ext sectio we will overview the ew metric. I sectio 3 we preset the differet baggig methods. Sectio 4 cotais the experimetal methodology. The results are preseted i sectio 5. The paper is brought to coclusio i sectio 6. 2 The optimal distace metric Short ad Fukuaga [19] showed that the variace of fiite sample size estimates may be miimized by a proper choice of the metric. The use of such a metric should lead to performace improvemet. The optimal distace metric is defied as follows. For a give test sample x 0 _ the distace to a poit X e is defied as ; T d x, X ) = V ( x X ) (1) ( 0 e x0 0 e Where V is the average gradiet directio of the a posteriori probability of class ω i at poit x 0. Its estimate V V x = x 0 m is i= 1 i 2 ( ) ( Mi( x0) M0( x0 )) 0 (2) where i is the umber of samples out of that belog to class i. m is the umber of classes. The local sample class i mea M i x ) ad local sample ( 0 mixture mea 0 ( x 0 ) are give as 1 M i ( x0 ) = ( X1 x0) (3) M i xj w i 0 ) = ( X j x0 ) j= 1 M 0 ( x (4) For k-nearest Neighbors we fid the k closest samples to x 0, the usig their labels we decide which class x 0 belogs to by the majority votig. The ecessary precoditio is that this distace measure is applied oly to the samples close to x 0 Hece, iitially the closest samples are foud usig the Euclidea distace, ad the from amog these samples the closest k are foud accordig to equatio 1. We automatically select to be 3k rouded to the closest iteger. 2 3 Baggig ad modified baggig procedures Whe a data set is small, the proportios of traiig patters from the differet classes may be urepresetative. The probability of drawig a traiig set with samples from some class completely missig becomes o egligible. Whe this occurs, baggig may eve become couterproductive. For this reaso we set out to ivestigate the effect of bootstrap cotrol as suggested i [3]. Three modificatios of the stadard baggig method are cosidered. We ame the stadard procedure as method 1 ad its modified versios as methods 2-4. The methods which exploit icreasig amouts of prior kowledge ca be summarized as follows. Method 1 Give a learig set, each bootstrap set is created by samplig from the learig set radomly with replacemet. The cardiality of each boot set is the same as the size of the traiig set. Method 2 Whe bootstrap sets are created from the learig set we check the ratio of the umber of samples per class i the bootstrap set. This ratio is compared to the ratio of samples per class i the learig set. If the differece betwee the compared ratios is larger tha a certai class populatio bias tolerace threshold we reject the bootstrap set. The bias tolerace threshold used is set at 10%. Method 3 This method is similar to method 2 except that the bootstrap set ratio is compared to the ratio i the full set. By full set we mea the set cotaiig all samples, learig ad test samples. This full set ratio simulates a prior kowledge of the class distributio i the sample space. Method 4 Here we oly require that all classes be represeted i the bootstrap set, without eforcig a certai ratio of samples per class. This is doe by rejectig ay bootstrap set that does ot represet all classes. ISSN: Page 352 ISBN:

3 4 Methodology I this project we experimet with baggig [6] k-nn classifiers. The experimets are simulated usig Matlab o several Petium based persoal computers. Table 1, Characteristics of used data sets Data ame No. of samples No. of features No of classes Wiscosi Breast Cacer, BCW Ioosphere Iris Wie Four real data sets from the UCI repository [5] are used. Traiig ad test sets are geerated from the origial data set. For each of the data sets a sigle traiig set is radomly take from the origial sample space, i.e. the full data set. The K-NN classifier built usig this origial learig set is referred to as the sigle classifier. The remaiig samples are used as a test set. N Bootsets are geerated usig the traiig set. The decisio of the N boot sets are aggregated to classify the test set. As suggested by Breima we may start with N = 25 as the umber of aggregated k-nn classifiers. The experimets are the repeated for varyig N, umber of compoet k-nn classifiers, to have a overview of the effect of the umber of classifiers o system performace. These results are referred to as the bagged classifier results. We compare these results to those obtaied from the sigle classifier, ad to those obtaied from other baggig methods of creatig bootstrap sets, as outlied i sectio 3, for two types of learig sets. I the first case the learig set is created by radomly takig samples from the full data set. This results i a set that may cotai some but ot all classes. The secod type of learig set is referred to as a modified learig set. It is costructed usig Method 3 which was metioed as a techique to create ubiased bootstrap sets. This results i a set that is represetative of all the classes, with class populatio ratios similar to those of the full set. The modified learig set simulates a ubiased sample space. To obtai ustable k-nn classifiers, we propose usig a optimal distace metric proposed by Short ad Fukuaga [19], as explaied i sectio 2. We repeat the experimets usig the Euclidea metric, i order to make a direct compariso ad asses the merits of baggig i cojuctio with the optimal metric. I our previous experimets, for each set size, the umber of earest eighbors, k, is foud automatically as the square root of the umber of traiig sets rouded to the closest iteger. I this paper 10 values of k are used for each traiig set size, to see the effect of k o the baggig performace uder the ew metric. The above is repeated for the four traiig set sizes icludig 10, 20, 40 ad 80 samples. The experimets are repeated for differet data sets to fid which leads to improved performace. The data sets used are obtaied from the UCI repository, ad the characteristics are show i table 1. We repeat the experimets for varyig feature set sizes. Where we radomly choose a subset of the full feature set. We experimet with 3 feature set sizes icludig 100, 80 ad 50 percet of the features. The radomly selected features are the same for the learig set ad the bootstrap sets. All experimets are repeated 100 times the averaged to achieve statistically reliable results. 5 Results We experimets with baggig knn classifiers usig a optimal distace metric. The aim is to establish whether baggig knn is useful whe the proposed metric is used. Our results, o 4 data sets, idicate that both the sigle classifier ad baggig results improve due to this metric, with the exceptio of small learig sets. Figures show baggig results for the BCW data set. Each figure shows the classificatio rate of a baggig method i compariso to the sigle classifier usig the Euclidea ad optimal metrics. For each value of k we ca compare the performaces at differet umber of fused classifiers, ragig from 3 to 25 bootstrap sets. The values of the x-axis represet the umber of fused bootstrap sets, whe multiplied by 2 ad added to 1. Therefore, 12 represets 25 bootstrap sets, while 5 represets 11. ISSN: Page 353 ISBN:

4 Results usig regular baggig method 1, show that at the smallest set size optimal metric baggig is almost ever superior. At set size 2 optimal baggig improves but it still is ot superior, with the exceptio at large values of k=9 ad 10 whe regular learig set is used ad at k greater tha 4 whe modified learig set is used. At set sizes 3 ad 4 optimal metric baggig is superior at all k except at k=5 ad 9 usig size 3 ad k=5, 7 ad 9 usig size 4, whe regular learig set is used. However if modified learig is used the optimal metric sigle classifier outperforms optimal metric baggig at all odd values of k. at the largest two sizes the optimal metric outperforms Euclidea regardless of type of classifier system. For all sizes the baggig performace improves as the umber of fused classifiers icreases. optimal baggig outperforms all. It is at this size that we begi to see the advatage of baggig whe method 2 is used i cojuctio with a optimal metric. This is most obvious at k=7, where the optimal metric yields a superior baggig performace while baggig usig the Euclidea metric yields worse performace tha the sigle classifier. Also, at size 4, the optimal metric always outperforms the Euclidea. However, at odd k, the sigle classifier outperforms baggig as k icreases. The differece reaches a sigificat level at k=9. Figure 2 BCW data results whe baggig method 4 is used with modified learig set usig Sum fusio strategy at set size 2 Figure 1 BCW data results whe baggig method 3 is used with regular learig set usig Sum fusio strategy at set size 2 Usig baggig method 2, at the smallest set size, Euclidea is best at k=4, 8 ad 9, otherwise, optimal is either better or equal to Euclidea. Optimal metric sigle classifier outperforms optimal baggig oly at k=1, 3 ad 10, for regular learig set ad at k=7 ad 10 for modified learig set. At set size 2, Euclidea is best at k=7 ad 8 usig regular learig set. However, at k=8 usig regular learig, ad at k=7 ad 8 usig optimal learig, whe the umber of fused classifiers icreases optimal baggig outperforms Euclidea baggig ad outperforms all. At this size, the sigle classifier outperforms baggig at odd values of k. At size 3, the optimal metric sigle classifier outperforms baggig at k=5 ad 9 oly. Otherwise, Usig baggig method 3, at the smallest set size, baggig outperforms the sigle at small values of k. It improves as umber of fused classifiers icreases. The superiority of the optimal is ot obvious at this size where the two metrics show a equal performace. At set size 2 optimal metric outperforms Euclidea ad optimal metric baggig shows the best performace. Ad exceptio is at k=3 usig regular learig set, where baggig reaches the sigle classifier oly at higher umber of fused classifiers. At the third set size, optimal metric baggig outperforms all, especially at larger umber of fused classifiers. However, usig modified learig set the sigle classifier usig a optimal metric outperforms baggig, although isigificatly, at k= 5 ad 9. This is also true at the fourth set size. ISSN: Page 354 ISBN:

5 Figure 3 BCW data results whe baggig method 3 is used with modified learig set usig Sum fusio strategy at set size 2 At the fourth baggig method, the smallest set size performace is similar to baggig method 3. However, usig a modified learig set the sigle classifier outperforms baggig. This is because bootstrap sets created usig baggig method 4 do ot cotai a correct represetatio of the sample space. At set sizes 2, 3 ad 4, baggig ad the sigle classifier show a mixed performace at odd values of k. At eve values of k baggig clearly outperforms the sigle classifier, especially as the umber of fused classifiers icreases. We ca coclude that baggig methods 2 usig a optimal metric outperforms the sigle classifier usig either learig set type at large traiig set sizes. A exceptio is whe k is the closest odd value to the square root of the umber of traiig samples. Baggig method 3 outperforms the sigle classifier, as method 2 did, i additio to the few cases where method 2 failed. At the smallest set sizes 1 ad 2 the two metrics show a mixed performace, ad the optimal metric looses its clear advatage over the Euclidea. 6 Coclusios Experimets o combiig k-nn classifiers usig baggig are coducted. Four differet baggig methods are experimeted uder two types of learig sets. I our experimets we varied the umber of combied classifiers, the umber of earest eighbors, the fusio method ad the learig set size. The experimets icluded four data sets obtaied from the UCI repository. Results of all data sets show the advatage of the optimal metric over the Euclidea for the sigle classifier at most set sizes ad values of earest eighbor k. Baggig gaied from the optimal metric, ad o three of the data types was able to outperform the optimal metric sigle classifier. Whe baggig usig the Euclidea metric was ot able to outperform the sigle classifier, the optimal metric baggig was able to outperform the sigle classifier. We foud that at small traiig set size baggig Euclidea may outperform the optimal metric. Therefore, we recommed the optimal metric at set sizes above 20 samples. We ca coclude that modified baggig methods 2 ad 3, usig the optimal metric, have the highest probability of achievig the best performace. Ackowledgmets This research was supported by the Public Authority for applied Educatio ad Traiig of Kuwait uder grat umber TR Refereces 1. F. M. Alkoot ad J. Kittler. Moderatig k classifiers. Patter Aalysis ad Applicatios, 5(3): , F. M. Alkoot ad J. Kittler. Modified product fusio. Patter Recogitio Letters, 23(8): , Fuad M. Alkoot ad Josef Kittler, Populatio Bias Cotrol for Baggig k-nn Experts, I Proceedigs Sesor Fusio: Architectures, Algorithms, ad Applicatios V, Orlado, Florida, 17-20/April SPIE Volume 4385, pp E. Bauer ad R. Kohavi. A empirical compariso of votig classificatio algorithms : Baggig, boostig ad variats. Machie Learig, pages 1-38, C.L. Blake, E. Keogh, C.J. Merz. UCI repository of machie learig databases, Departmet of Iformatio ad Computer Sciece, Uiversity of Califoria, Irvie, CA, ISSN: Page 355 ISBN:

6 6. L. Breima. Baggig predictors. Machie Learig, 24: , L. Breima. Bias, variace ad arcig classifiers. Techical Report 460, Statistics Departةet, Uiversity of Califoria at Berkeley, P. dechazal ad B. Celler. Improvig ecg diagostic classificatio by combiig multiple eural etworks. I Computers i Cardiology, volume 24, pages 473{476. IEEE, T. Dietterich. A experimetal compariso of three methods for costructig esembles of decisio trees: Baggig, boostig, ad radomizatio. Machie Learig, pages 1-22, B. Draper ad K. Baek. Baggig i computer visio. I Proceedigs of the IEEE Computer Society Coferece o Computer Visio ad Patter Recogitio, pages IEEE Comp Soc, Los Alamos, CA, USA, B. Efro ad R. Tibshirai. A Itroductio to the Bootstrap. Chapma ad Hall, T.K. Ho, J.J. Hull, ad S.N. Srihari. Decisio combiatio i multiple classifier systems. IEEE Trasactios o Patter Aalysis ad Machie Itelligece, 16(1):66 75, J. Kittler ad F. M. Alkoot. Sum versus vote fusio i multiple classifier systems. IEEE Tras o PAMI, 25(1): , J. Kittler, M. Hatef, R. Dui, ad J. Matas. O combiig classifiers. IEEE Tras Patter Aalysis ad Machie Itelligece, 20(3): , J. Kittler. Combiig classifiers: A theoretical framework. Patter Aalysis ad Applicatios, 1:18 27, J. Quila. Baggig, boostig ad c4.5. I Proceedigs of the 13th Natioal Coferece o Artificial Itelligece, volume 1, pages 725{730, Portlad, OR, USA,, AAAI, Melo Park, CA, USA 17. G. Rogova. Combiig the results of several eural etwork classifiers. Neural Networks, 7(5): , R. E. Schapire. A brief itroductio to boostig. I Proceedigs of the Sixteeth Iteratioal Joit Coferece o Artificial Itelligece, Robert Short ad Keiosuke Fukuaga. A ew earest eighbor distace measure. I IEEE coferece, pages 81 to 86, D.H. Wolpert. Stacked geeralizatio. Neural Networks, 5(2): , K Woods, W P Kegelmeyer, ad K Bowyer. Combiatio of multiple experts usig local accuracy estimates. IEEE Tras PAMI, 19: , L. Xu, A. Krzyzak, ad C.Y. Sue. Methods of combiig multiple classifiers ad their applicatios to hadwritig recogitio. IEEE Tras. SMC, 22(3): ,1992. ISSN: Page 356 ISBN:

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 new algorithm to build feed forward neural networks.

A new algorithm to build feed forward neural networks. A ew algorithm to build feed forward eural etworks. Amit Thombre Cetre of Excellece, Software Techologies ad Kowledge Maagemet, Tech Mahidra, Pue, Idia Abstract The paper presets a ew algorithm to build

More information

Analysis of Documents Clustering Using Sampled Agglomerative Technique

Analysis of Documents Clustering Using Sampled Agglomerative Technique Aalysis of Documets Clusterig Usig Sampled Agglomerative Techique Omar H. Karam, Ahmed M. Hamad, ad Sheri M. Moussa Abstract I this paper a clusterig algorithm for documets is proposed that adapts a samplig-based

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

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

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

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

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

Dynamic Programming and Curve Fitting Based Road Boundary Detection

Dynamic Programming and Curve Fitting Based Road Boundary Detection Dyamic Programmig ad Curve Fittig Based Road Boudary Detectio SHYAM PRASAD ADHIKARI, HYONGSUK KIM, Divisio of Electroics ad Iformatio Egieerig Chobuk Natioal Uiversity 664-4 Ga Deokji-Dog Jeoju-City Jeobuk

More information

DATA MINING II - 1DL460

DATA MINING II - 1DL460 DATA MINING II - 1DL460 Sprig 2017 A secod course i data miig http://www.it.uu.se/edu/course/homepage/ifoutv2/vt17/ Kjell Orsbor Uppsala Database Laboratory Departmet of Iformatio Techology, Uppsala Uiversity,

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

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

. Written in factored form it is easy to see that the roots are 2, 2, i,

. Written in factored form it is easy to see that the roots are 2, 2, i, CMPS A Itroductio to Programmig Programmig Assigmet 4 I this assigmet you will write a java program that determies the real roots of a polyomial that lie withi a specified rage. Recall that the roots (or

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

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

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

Alpha Individual Solutions MAΘ National Convention 2013

Alpha Individual Solutions MAΘ National Convention 2013 Alpha Idividual Solutios MAΘ Natioal Covetio 0 Aswers:. D. A. C 4. D 5. C 6. B 7. A 8. C 9. D 0. B. B. A. D 4. C 5. A 6. C 7. B 8. A 9. A 0. C. E. B. D 4. C 5. A 6. D 7. B 8. C 9. D 0. B TB. 570 TB. 5

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

Lecture 13: Validation

Lecture 13: Validation Lecture 3: Validatio Resampli methods Holdout Cross Validatio Radom Subsampli -Fold Cross-Validatio Leave-oe-out The Bootstrap Bias ad variace estimatio Three-way data partitioi Itroductio to Patter Recoitio

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

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

Heuristic Approaches for Solving the Multidimensional Knapsack Problem (MKP)

Heuristic Approaches for Solving the Multidimensional Knapsack Problem (MKP) Heuristic Approaches for Solvig the Multidimesioal Kapsack Problem (MKP) R. PARRA-HERNANDEZ N. DIMOPOULOS Departmet of Electrical ad Computer Eg. Uiversity of Victoria Victoria, B.C. CANADA Abstract: -

More information

Performance Comparisons of PSO based Clustering

Performance Comparisons of PSO based Clustering Performace Comparisos of PSO based Clusterig Suresh Chadra Satapathy, 2 Guaidhi Pradha, 3 Sabyasachi Pattai, 4 JVR Murthy, 5 PVGD Prasad Reddy Ail Neeruoda Istitute of Techology ad Scieces, Sagivalas,Vishaapatam

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

Using The Central Limit Theorem for Belief Network Learning

Using The Central Limit Theorem for Belief Network Learning Usig The Cetral Limit Theorem for Belief Network Learig Ia Davidso, Mioo Amiia Computer Sciece Dept, SUNY Albay Albay, NY, USA,. davidso@cs.albay.edu Abstract. Learig the parameters (coditioal ad margial

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

Feature classification for multi-focus image fusion

Feature classification for multi-focus image fusion Iteratioal Joural of the Physical Scieces Vol. 6(0), pp. 4838-4847, 3 September, 0 Available olie at http://www.academicjourals.org/ijps DOI: 0.5897/IJPS.73 ISSN 99-950 0 Academic Jourals Full Legth Research

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

Improving Template Based Spike Detection

Improving Template Based Spike Detection Improvig Template Based Spike Detectio Kirk Smith, Member - IEEE Portlad State Uiversity petra@ee.pdx.edu Abstract Template matchig algorithms like SSE, Covolutio ad Maximum Likelihood are well kow for

More information

( n+1 2 ) , position=(7+1)/2 =4,(median is observation #4) Median=10lb

( n+1 2 ) , position=(7+1)/2 =4,(median is observation #4) Median=10lb Chapter 3 Descriptive Measures Measures of Ceter (Cetral Tedecy) These measures will tell us where is the ceter of our data or where most typical value of a data set lies Mode the value that occurs most

More information

Administrative UNSUPERVISED LEARNING. Unsupervised learning. Supervised learning 11/25/13. Final project. No office hours today

Administrative UNSUPERVISED LEARNING. Unsupervised learning. Supervised learning 11/25/13. Final project. No office hours today Admiistrative Fial project No office hours today UNSUPERVISED LEARNING David Kauchak CS 451 Fall 2013 Supervised learig Usupervised learig label label 1 label 3 model/ predictor label 4 label 5 Supervised

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

Our second algorithm. Comp 135 Machine Learning Computer Science Tufts University. Decision Trees. Decision Trees. Decision Trees.

Our second algorithm. Comp 135 Machine Learning Computer Science Tufts University. Decision Trees. Decision Trees. Decision Trees. Comp 135 Machie Learig Computer Sciece Tufts Uiversity Fall 2017 Roi Khardo Some of these slides were adapted from previous slides by Carla Brodley Our secod algorithm Let s look at a simple dataset for

More information

A PREDICTION MODEL FOR USER S SHARE ANALYSIS IN DUAL- SIM ENVIRONMENT

A PREDICTION MODEL FOR USER S SHARE ANALYSIS IN DUAL- SIM ENVIRONMENT GSJ: Computer Sciece ad Telecommuicatios 03 No.3(39) ISSN 5-3 A PRDICTION MODL FOR USR S SHAR ANALYSIS IN DUAL- SIM NVIRONMNT Thakur Sajay, Jai Parag Orietal Uiversity, Idore, Idia sajaymca00@yahoo.com

More information

Effect of control points distribution on the orthorectification accuracy of an Ikonos II image through rational polynomial functions

Effect of control points distribution on the orthorectification accuracy of an Ikonos II image through rational polynomial functions Effect of cotrol poits distributio o the orthorectificatio accuracy of a Ikoos II image through ratioal polyomial fuctios Marcela do Valle Machado 1, Mauro Homem Atues 1 ad Paula Debiasi 1 1 Federal Rural

More information

Bayesian approach to reliability modelling for a probability of failure on demand parameter

Bayesian approach to reliability modelling for a probability of failure on demand parameter Bayesia approach to reliability modellig for a probability of failure o demad parameter BÖRCSÖK J., SCHAEFER S. Departmet of Computer Architecture ad System Programmig Uiversity Kassel, Wilhelmshöher Allee

More information

Probabilistic Fuzzy Time Series Method Based on Artificial Neural Network

Probabilistic Fuzzy Time Series Method Based on Artificial Neural Network America Joural of Itelliget Systems 206, 6(2): 42-47 DOI: 0.5923/j.ajis.2060602.02 Probabilistic Fuzzy Time Series Method Based o Artificial Neural Network Erol Egrioglu,*, Ere Bas, Cagdas Haka Aladag

More information

Data diverse software fault tolerance techniques

Data diverse software fault tolerance techniques Data diverse software fault tolerace techiques Complemets desig diversity by compesatig for desig diversity s s limitatios Ivolves obtaiig a related set of poits i the program data space, executig the

More information

Fire Recognition in Video. Walter Phillips III Mubarak Shah Niels da Vitoria Lobo.

Fire Recognition in Video. Walter Phillips III Mubarak Shah Niels da Vitoria Lobo. Fire Recogitio i Video Walter Phillips III Mubarak Shah Niels da Vitoria Lobo {wrp65547,shah,iels}@cs.ucf.edu Computer Visio Laboratory Departmet of Computer Sciece Uiversity of Cetral Florida Orlado,

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

On (K t e)-saturated Graphs

On (K t e)-saturated Graphs Noame mauscript No. (will be iserted by the editor O (K t e-saturated Graphs Jessica Fuller Roald J. Gould the date of receipt ad acceptace should be iserted later Abstract Give a graph H, we say a graph

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

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

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

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

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

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

On-line cursive letter recognition using sequences of local minima/maxima. Robert Powalka

On-line cursive letter recognition using sequences of local minima/maxima. Robert Powalka O-lie cursive letter recogitio usig sequeces of local miima/maxima Summary Robert Powalka 19 th August 1993 This report presets the desig ad implemetatio of a o-lie cursive letter recogizer usig sequeces

More information

UNIT 4 Section 8 Estimating Population Parameters using Confidence Intervals

UNIT 4 Section 8 Estimating Population Parameters using Confidence Intervals UNIT 4 Sectio 8 Estimatig Populatio Parameters usig Cofidece Itervals To make ifereces about a populatio that caot be surveyed etirely, sample statistics ca be take from a SRS of the populatio ad used

More information

Improving Information Retrieval System Security via an Optimal Maximal Coding Scheme

Improving Information Retrieval System Security via an Optimal Maximal Coding Scheme Improvig Iformatio Retrieval System Security via a Optimal Maximal Codig Scheme Dogyag Log Departmet of Computer Sciece, City Uiversity of Hog Kog, 8 Tat Chee Aveue Kowloo, Hog Kog SAR, PRC dylog@cs.cityu.edu.hk

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

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

COSC 1P03. Ch 7 Recursion. Introduction to Data Structures 8.1

COSC 1P03. Ch 7 Recursion. Introduction to Data Structures 8.1 COSC 1P03 Ch 7 Recursio Itroductio to Data Structures 8.1 COSC 1P03 Recursio Recursio I Mathematics factorial Fiboacci umbers defie ifiite set with fiite defiitio I Computer Sciece sytax rules fiite defiitio,

More information

Lecture 6. Lecturer: Ronitt Rubinfeld Scribes: Chen Ziv, Eliav Buchnik, Ophir Arie, Jonathan Gradstein

Lecture 6. Lecturer: Ronitt Rubinfeld Scribes: Chen Ziv, Eliav Buchnik, Ophir Arie, Jonathan Gradstein 068.670 Subliear Time Algorithms November, 0 Lecture 6 Lecturer: Roitt Rubifeld Scribes: Che Ziv, Eliav Buchik, Ophir Arie, Joatha Gradstei Lesso overview. Usig the oracle reductio framework for approximatig

More information

Neuro Fuzzy Model for Human Face Expression Recognition

Neuro Fuzzy Model for Human Face Expression Recognition IOSR Joural of Computer Egieerig (IOSRJCE) ISSN : 2278-0661 Volume 1, Issue 2 (May-Jue 2012), PP 01-06 Neuro Fuzzy Model for Huma Face Expressio Recogitio Mr. Mayur S. Burage 1, Prof. S. V. Dhopte 2 1

More information

Chapter 1. Introduction to Computers and C++ Programming. Copyright 2015 Pearson Education, Ltd.. All rights reserved.

Chapter 1. Introduction to Computers and C++ Programming. Copyright 2015 Pearson Education, Ltd.. All rights reserved. Chapter 1 Itroductio to Computers ad C++ Programmig Copyright 2015 Pearso Educatio, Ltd.. All rights reserved. Overview 1.1 Computer Systems 1.2 Programmig ad Problem Solvig 1.3 Itroductio to C++ 1.4 Testig

More information

CS 683: Advanced Design and Analysis of Algorithms

CS 683: Advanced Design and Analysis of Algorithms CS 683: Advaced Desig ad Aalysis of Algorithms Lecture 6, February 1, 2008 Lecturer: Joh Hopcroft Scribes: Shaomei Wu, Etha Feldma February 7, 2008 1 Threshold for k CNF Satisfiability I the previous lecture,

More information

FEATURES VECTOR FOR PERSONAL IDENTIFICATION BASED ON IRIS TEXTURE

FEATURES VECTOR FOR PERSONAL IDENTIFICATION BASED ON IRIS TEXTURE FEATURES VECTOR FOR PERSONAL IDENTIFICATION BASED ON IRIS TEXTURE R. P. Moreo Departameto de Egeharia Elétrica EESC - USP Av. Trabalhador Sãocarlese, 400 São Carlos / SP Brasil raphael@digmotor.com.br

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

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

Identification of the Swiss Z24 Highway Bridge by Frequency Domain Decomposition Brincker, Rune; Andersen, P.

Identification of the Swiss Z24 Highway Bridge by Frequency Domain Decomposition Brincker, Rune; Andersen, P. Aalborg Uiversitet Idetificatio of the Swiss Z24 Highway Bridge by Frequecy Domai Decompositio Bricker, Rue; Aderse, P. Published i: Proceedigs of IMAC 2 Publicatio date: 22 Documet Versio Publisher's

More information

ENGI 4421 Probability and Statistics Faculty of Engineering and Applied Science Problem Set 1 Descriptive Statistics

ENGI 4421 Probability and Statistics Faculty of Engineering and Applied Science Problem Set 1 Descriptive Statistics ENGI 44 Probability ad Statistics Faculty of Egieerig ad Applied Sciece Problem Set Descriptive Statistics. If, i the set of values {,, 3, 4, 5, 6, 7 } a error causes the value 5 to be replaced by 50,

More information

Descriptive Statistics Summary Lists

Descriptive Statistics Summary Lists Chapter 209 Descriptive Statistics Summary Lists Itroductio This procedure is used to summarize cotiuous data. Large volumes of such data may be easily summarized i statistical lists of meas, couts, stadard

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

Searching a Russian Document Collection Using English, Chinese and Japanese Queries

Searching a Russian Document Collection Using English, Chinese and Japanese Queries Searchig a Russia Documet Collectio Usig Eglish, Chiese ad Japaese Queries Fredric C. Gey (gey@ucdata.berkeley.edu) UC Data Archive & Techical Assistace Uiversity of Califoria, Berkeley, CA 94720 USA ABSTRACT.

More information

Performance Evaluation of Mutation / Non- Mutation Based Classification With Missing Data

Performance Evaluation of Mutation / Non- Mutation Based Classification With Missing Data Performace Evaluatio of Mutatio / No- Mutatio Based Classificatio With Missig Data N.C. Viod Research Scholar, Maomaiam Sudaraar Uiversity, Tiruelveli, Tamil Nadu, Idia Dr. M. Puithavalli Research Supervisor,

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

IMP: Superposer Integrated Morphometrics Package Superposition Tool

IMP: Superposer Integrated Morphometrics Package Superposition Tool IMP: Superposer Itegrated Morphometrics Package Superpositio Tool Programmig by: David Lieber ( 03) Caisius College 200 Mai St. Buffalo, NY 4208 Cocept by: H. David Sheets, Dept. of Physics, Caisius College

More information

Empirical Validate C&K Suite for Predict Fault-Proneness of Object-Oriented Classes Developed Using Fuzzy Logic.

Empirical Validate C&K Suite for Predict Fault-Proneness of Object-Oriented Classes Developed Using Fuzzy Logic. Empirical Validate C&K Suite for Predict Fault-Proeess of Object-Orieted Classes Developed Usig Fuzzy Logic. Mohammad Amro 1, Moataz Ahmed 1, Kaaa Faisal 2 1 Iformatio ad Computer Sciece Departmet, Kig

More information

Morgan Kaufmann Publishers 26 February, COMPUTER ORGANIZATION AND DESIGN The Hardware/Software Interface. Chapter 5

Morgan Kaufmann Publishers 26 February, COMPUTER ORGANIZATION AND DESIGN The Hardware/Software Interface. Chapter 5 Morga Kaufma Publishers 26 February, 28 COMPUTER ORGANIZATION AND DESIGN The Hardware/Software Iterface 5 th Editio Chapter 5 Set-Associative Cache Architecture Performace Summary Whe CPU performace icreases:

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

EMPIRICAL ANALYSIS OF FAULT PREDICATION TECHNIQUES FOR IMPROVING SOFTWARE PROCESS CONTROL

EMPIRICAL ANALYSIS OF FAULT PREDICATION TECHNIQUES FOR IMPROVING SOFTWARE PROCESS CONTROL Iteratioal Joural of Iformatio Techology ad Kowledge Maagemet July-December 2012, Volume 5, No. 2, pp. 371-375 EMPIRICAL ANALYSIS OF FAULT PREDICATION TECHNIQUES FOR IMPROVING SOFTWARE PROCESS CONTROL

More information

A Martingale Framework for Concept Change Detection in Time-Varying Data Streams

A Martingale Framework for Concept Change Detection in Time-Varying Data Streams A Martigale Framework for Cocept Chage Detectio i Time-Varyig Data Streams She-Shyag Ho sho@gmu.edu Departmet of Computer Sciece, George Maso Uiversity, 4400 Uiversity Drive, Fairfax, VA 22030 USA Abstract

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

Model Enhancement in Data Mining: Calibration, ROC Analysis, Model Combination and Mimetic Models

Model Enhancement in Data Mining: Calibration, ROC Analysis, Model Combination and Mimetic Models Model Ehacemet i Miig: Calibratio, ROC Aalysis, Model Combiatio ad Mimetic Models José Herádez-Orallo Dpto. de Sistemas Iformáticos y Computació, Uiversidad Politécica de Valecia, jorallo@dsic.upv.es Rome,

More information

Efficient Eye Location for Biomedical Imaging using Two-level Classifier Scheme

Efficient Eye Location for Biomedical Imaging using Two-level Classifier Scheme 828 Iteratioal Joural of Cotrol, Automatio, ad Systems, vol. 6, o. 6, pp. 828-835, December 2008 Efficiet Eye Locatio for Biomedical Imagig usig Two-level Classifier Scheme Mi Youg Nam, Xi Wag, ad Phill

More information

Appendix D. Controller Implementation

Appendix D. Controller Implementation COMPUTER ORGANIZATION AND DESIGN The Hardware/Software Iterface 5 th Editio Appedix D Cotroller Implemetatio Cotroller Implemetatios Combiatioal logic (sigle-cycle); Fiite state machie (multi-cycle, pipelied);

More information

EFFECT OF QUERY FORMATION ON WEB SEARCH ENGINE RESULTS

EFFECT OF QUERY FORMATION ON WEB SEARCH ENGINE RESULTS Iteratioal Joural o Natural Laguage Computig (IJNLC) Vol. 2, No., February 203 EFFECT OF QUERY FORMATION ON WEB SEARCH ENGINE RESULTS Raj Kishor Bisht ad Ila Pat Bisht 2 Departmet of Computer Sciece &

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

Random Graphs and Complex Networks T

Random Graphs and Complex Networks T Radom Graphs ad Complex Networks T-79.7003 Charalampos E. Tsourakakis Aalto Uiversity Lecture 3 7 September 013 Aoucemet Homework 1 is out, due i two weeks from ow. Exercises: Probabilistic iequalities

More information

New Results on Energy of Graphs of Small Order

New Results on Energy of Graphs of Small Order Global Joural of Pure ad Applied Mathematics. ISSN 0973-1768 Volume 13, Number 7 (2017), pp. 2837-2848 Research Idia Publicatios http://www.ripublicatio.com New Results o Eergy of Graphs of Small Order

More information

APPLICATION NOTE PACE1750AE BUILT-IN FUNCTIONS

APPLICATION NOTE PACE1750AE BUILT-IN FUNCTIONS APPLICATION NOTE PACE175AE BUILT-IN UNCTIONS About This Note This applicatio brief is iteded to explai ad demostrate the use of the special fuctios that are built ito the PACE175AE processor. These powerful

More information

Lecture 5. Counting Sort / Radix Sort

Lecture 5. Counting Sort / Radix Sort Lecture 5. Coutig Sort / Radix Sort T. H. Corme, C. E. Leiserso ad R. L. Rivest Itroductio to Algorithms, 3rd Editio, MIT Press, 2009 Sugkyukwa Uiversity Hyuseug Choo choo@skku.edu Copyright 2000-2018

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

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

Unsupervised Discretization Using Kernel Density Estimation

Unsupervised Discretization Using Kernel Density Estimation Usupervised Discretizatio Usig Kerel Desity Estimatio Maregle Biba, Floriaa Esposito, Stefao Ferilli, Nicola Di Mauro, Teresa M.A Basile Departmet of Computer Sciece, Uiversity of Bari Via Oraboa 4, 7025

More information

Analysis Metrics. Intro to Algorithm Analysis. Slides. 12. Alg Analysis. 12. Alg Analysis

Analysis Metrics. Intro to Algorithm Analysis. Slides. 12. Alg Analysis. 12. Alg Analysis Itro to Algorithm Aalysis Aalysis Metrics Slides. Table of Cotets. Aalysis Metrics 3. Exact Aalysis Rules 4. Simple Summatio 5. Summatio Formulas 6. Order of Magitude 7. Big-O otatio 8. Big-O Theorems

More information

The isoperimetric problem on the hypercube

The isoperimetric problem on the hypercube The isoperimetric problem o the hypercube Prepared by: Steve Butler November 2, 2005 1 The isoperimetric problem We will cosider the -dimesioal hypercube Q Recall that the hypercube Q is a graph whose

More information

1. The lines intersect. There is one solution, the point where they intersect. The system is called a consistent system.

1. The lines intersect. There is one solution, the point where they intersect. The system is called a consistent system. Commo Core Math 3 Notes Uit Day Systems I. Systems of Liear Equatios A system of two liear equatios i two variables is two equatios cosidered together. To solve a system is to fid all the ordered pairs

More information

Lower Bounds for Sorting

Lower Bounds for Sorting Liear Sortig Topics Covered: Lower Bouds for Sortig Coutig Sort Radix Sort Bucket Sort Lower Bouds for Sortig Compariso vs. o-compariso sortig Decisio tree model Worst case lower boud Compariso Sortig

More information

Polynomial Functions and Models. Learning Objectives. Polynomials. P (x) = a n x n + a n 1 x n a 1 x + a 0, a n 0

Polynomial Functions and Models. Learning Objectives. Polynomials. P (x) = a n x n + a n 1 x n a 1 x + a 0, a n 0 Polyomial Fuctios ad Models 1 Learig Objectives 1. Idetify polyomial fuctios ad their degree 2. Graph polyomial fuctios usig trasformatios 3. Idetify the real zeros of a polyomial fuctio ad their multiplicity

More information

Assignment Problems with fuzzy costs using Ones Assignment Method

Assignment Problems with fuzzy costs using Ones Assignment Method IOSR Joural of Mathematics (IOSR-JM) e-issn: 8-8, p-issn: 9-6. Volume, Issue Ver. V (Sep. - Oct.06), PP 8-89 www.iosrjourals.org Assigmet Problems with fuzzy costs usig Oes Assigmet Method S.Vimala, S.Krisha

More information

Fuzzy Rule Selection by Data Mining Criteria and Genetic Algorithms

Fuzzy Rule Selection by Data Mining Criteria and Genetic Algorithms Fuzzy Rule Selectio by Data Miig Criteria ad Geetic Algorithms Hisao Ishibuchi Dept. of Idustrial Egieerig Osaka Prefecture Uiversity 1-1 Gakue-cho, Sakai, Osaka 599-8531, JAPAN E-mail: hisaoi@ie.osakafu-u.ac.jp

More information

Elementary Educational Computer

Elementary Educational Computer Chapter 5 Elemetary Educatioal Computer. Geeral structure of the Elemetary Educatioal Computer (EEC) The EEC coforms to the 5 uits structure defied by vo Neuma's model (.) All uits are preseted i a simplified

More information

Arithmetic Sequences

Arithmetic Sequences . Arithmetic Sequeces COMMON CORE Learig Stadards HSF-IF.A. HSF-BF.A.1a HSF-BF.A. HSF-LE.A. Essetial Questio How ca you use a arithmetic sequece to describe a patter? A arithmetic sequece is a ordered

More information

A METHOD OF GENERATING RULES FOR A KERNEL FUZZY CLASSIFIER

A METHOD OF GENERATING RULES FOR A KERNEL FUZZY CLASSIFIER Proceedigs of the Sixth Iteratioal Coferece o Machie Learig ad Cyberetics, Hog Kog, 9- August 7 A METHOD OF GENERATING RULES FOR A KERNEL FUZZY CLASSIFIER AI-MIN YANG,, XIN-GUANG LI, LING-MIN JIANG,YONG-MEI

More information

Clustering and Classifying Diabetic Data Sets Using K-Means Algorithm

Clustering and Classifying Diabetic Data Sets Using K-Means Algorithm Article ca be accessed olie at http://www.publishigidia.com Clusterig ad Classifyig Diabetic Data Sets Usig K-Meas Algorithm M. Kothaiayaki*, P. Thagaraj** Abstract The k-meas algorithm is well kow for

More information

Parallel Polygon Approximation Algorithm Targeted at Reconfigurable Multi-Ring Hardware

Parallel Polygon Approximation Algorithm Targeted at Reconfigurable Multi-Ring Hardware Parallel Polygo Approximatio Algorithm Targeted at Recofigurable Multi-Rig Hardware M. Arif Wai* ad Hamid R. Arabia** *Califoria State Uiversity Bakersfield, Califoria, USA **Uiversity of Georgia, Georgia,

More information

Turkish Fingerspelling Recognition System Using Axis of Least Inertia Based Fast Alignment

Turkish Fingerspelling Recognition System Using Axis of Least Inertia Based Fast Alignment Turkish Figerspellig ecogitio System Usig Axis of Least Iertia Based Fast Aligmet Oğuz Altu, Sogül Albayrak, Ali Ekici, ad Behzat Bükü Yıldız Techical Uiversity, Computer Egieerig Departmet, Yıldız, İstabul,

More information

The Magma Database file formats

The Magma Database file formats The Magma Database file formats Adrew Gaylard, Bret Pikey, ad Mart-Mari Breedt Johaesburg, South Africa 15th May 2006 1 Summary Magma is a ope-source object database created by Chris Muller, of Kasas City,

More information