Research Paper A UNIFIED FRAMEWORK FOR MULTI-OBJECTIVE TEST CASE PRIORITIZATION IN REGRESSION TESTING Lilly Raamesh

Size: px
Start display at page:

Download "Research Paper A UNIFIED FRAMEWORK FOR MULTI-OBJECTIVE TEST CASE PRIORITIZATION IN REGRESSION TESTING Lilly Raamesh"

Transcription

1 Research Paper A UNIFIED FRAMEWORK FOR MULTI-OBJECTIVE TEST CASE PRIORITIZATION IN REGRESSION TESTING Llly Raamesh Aress for Corresponence Department of I.T, St. Joseph s College of Engneerng, Ol Mamallapuram Roa, Chenna, Taml Nau 600 9, Ina ABSTRACT Testng s an ntegral part of any software evelopment. Ths paper focuses on prortzng the mult-objectve test cases n a system whle conuctng the regresson testng so as to reuce the number of test cases n a test sute an prortze them whle retanng the hghest percentage of the orgnal test sute s fault etecton effectveness. Regresson testng s an mportant process as t s to be ensure that changes that are mae have not ntrouce new faults. Regresson testng s expensve f t allows the re executon of all test cases. In ths stuaton, test case prortzaton technques am to mprove the effectveness of regresson testng by orerng the test cases n an orer that attempts to maxmze the objectve functon. In ths paper, n orer to maxmze the effectveness of the system the reucton, optmzaton an prortzaton of test cases are combne usng mnmum reunancy an maxmum relevance (mrmr) feature selecton an genetc algorthm. So, a unfe framework s ntrouce for mult objectve test case prortzaton for regresson testng. Ths paper focuses on prortzng the mult objectve test cases n a system whle conuctng the regresson testng by usng feature selecton an genetc algorthm. Feature selecton removes reunancy an selects maxmum relevance test cases. A genetc algorthm s a robust search technque, often utlze to entfy the accurate or approxmate solutons for optmzaton an search problems KEYWORDS: Genetc algorthm; mnmum reunancy an maxmum relevance; Relevancy threshol; Reunancy threshol; Mutual nformaton; Mutaton probablty; Eltst selecton genetc algorthm.. INTRODUCTION The rap evelopment of software mae testng a challengng role n software evelopment. Whle performng testng the effectveness of testng epens on the test cases that are use. A test case s a set of contons or varables uner whch a tester wll etermne f a requrement upon an applcaton s partally or fully satsfe. Usually the testng can be one wth all possble test cases to fn all the faults. But as the number of test cases s ncrease the project tme an cost s also ncrease. It s a must to reuce the number of test cases so as to have an effcent system. Regresson testng can be use to ensure that changes to a program for the purposes of ncreasng functonalty or removng faults oes not have any negatve mpact on the correctness of the software.a varety of objectve functons are applcable; one such functon nvolves rate of fault etecton-a measure of how quckly faults are etecte wthn the testng process. An mprove rate of fault etecton urng regresson testng can prove faster feeback on a system uner regresson test an let ebuggers begn ther work earler than mght otherwse be possble. To reuce the cost of regresson testng, software testers may prortze ther test cases so that those whch are more mportant, by some measure, are run earler n the regresson testng process. One potental goal of such prortzaton s to ncrease a test sutes rate of fault etecton. Ths paper focuses on prortzng the mult objectve test cases n a system whle conuctng the regresson testng so as to reuce the number of test cases n a test sute an prortze them whle retanng the hghest percentage of the orgnal test sute s fault etecton effectveness. In ths work, n orer to maxmze the effectveness of the system the reucton an prortzaton of test cases are combne usng mnmum reunancy an maxmum relevance (mrmr) feature selecton an genetc algorthm. So, a unfe framework s ntrouce for mult objectve test case prortzaton for regresson testng. Int J Av Engg Tech/Vol. VII/Issue I/Jan.-March,06/ In ths paper, the reucton, optmzaton an prortzaton are one base on the objectve functon whch consers the objectves lke memory usage, executon tme (cost), completeness (coverage) an fault coverage. The fnal objectve functon Z nclues 4 sub objectve functons {f, f, f 3, f 4} whch escrbes the objectves. The objectves set X s gven as {x, x, x 3, x 4}. Objectve functons Z = {f, f, f 3, f 4}. where the objectve functon (f ) for memory usage(x )s to select test cases from the test sute T whch satsfes () mn f (x,t), x = mu - mf for all = to n () where, mu memory use after the executon of th test case mf memory free before the executon of th test case The objectve functon (f ) for executon Tme(x ) s to select test cases from the test sute T whch satsfes () mn f (x,t), x = ft - st for all = to n () where,ft s the fnsh tme of the th test case st s the start tme of th test case The objectve functon (f 3 ) for Completeness (x 3) s to select test cases from the test sute T whch satsfes (3) max f 3 (x 3,T), x 3 = sc + pc + bc + fc for all = to n (3) where, sc s the statement coverage value of test case t pc s the path coverage value of test case t bc s the branch coverage value of test case t fc s the functon coverage value of test case t The objectve functon (f 4 ) for fault coverage (x 4) s to select test cases from the test sute T whch satsfes (4) max f 4 (x 4,T), x 4= f /N for all = to n (4) where, f s the faults etecte by the th test case N s the total number of faults n the system.. RELATED WORKS Numerous prortzaton technques have been escrbe n the lterature [3,7,8,0] have shown that at least some of these technques can sgnfcantly ncrease the rate of fault etecton of

2 test sutes. The rates of fault etecton prouce by prortzaton technques can vary sgnfcantly wth several factors relate to program attrbutes, change attrbutes, an test sute characterstcs []. Test Case Prortzaton (TC has been prmarly apple to mprove the effect of regresson testng []. Mutual Informaton has been perfectly utlze n the approach calle mrmr (mnmum Reunancy- Maxmum Relevance) [4] whch ams at obtanng maxmum classfcaton or precton performance wth a mnmal subset of varables by reucng the reunances among the selecte varables to a mnmum an to maxmze ther relevance. Even genetc algorthms were use for feature selecton []. Then mult objectve genetc algorthms were use [3] for feature selecton. The genetc algorthm performs well n test case prortzaton [,] an was expermentally teste [,3]. Hybr Genetc Algorthm (HGA) [8] was propose for obtanng the best possble number of test cases for the purpose of optmzaton. From the survey, t s entfe that the feature selecton algorthm fns a very lmte applcaton to test cases. From the test sute the relevant test cases are selecte an the reunant ones are omtte. GA s one such evolutonary algorthm. GA has emerge as a practcal, robust optmzaton technque an search metho. A GA s a search algorthm that s nspre by the way nature evolves speces usng a natural selecton of the fttest nvuals an t s prove that Genetc Algorthms performe well n test case prortzaton. Hence, base on the survey, a unfe mult objectve test case prortzaton system s evelope for regresson testng to ncrease the effectveness of the testng system. 3. Test Case Reucton Usng mnmum Reunancy Maxmum-Relevance (mrmr) Feature Selecton The mnmum Reunancy-Maxmum Relevance (mrmr) approach s use to select the maxmum relevant test cases from the test sute wth respect to the objectves whle avong the reunant ones. It uses mutual nformaton to analyze relevance an reunancy. Mutual nformaton s a basc concept n nformaton theory. The mutual nformaton (MI) of two ranom varables s a quantty that measures the mutual epenence of the two ranom varables. The mutual nformaton (MI) between the test cases an the objectve s calculate (the relevance term). Then the average MI between the test cases an the remanng test cases that are alreay selecte s compute (the reunancy term). The general feature selecton problem efne for mnmal-reunancy-maxmal-relevance (mrmr) s mofe accorng to test case reucton problem an s efne as Gven the nput ata D table as T test cases an X features (objectves) such as {x, x, x 3, x 4} an the target classfcaton varable c, the feature selecton problem s to fn from the 4-mensonal observaton space, R M, a subspace of x features, R x, that optmally characterzes c. The mrmr feature selecton algorthm for test case reucton s gven as Algorthm Int J Av Engg Tech/Vol. VII/Issue I/Jan.-March,06/ (Intalzaton): set X ntal set of 4 objectves, X={x,x,x 3,x 4 }, set T ntal set of test cases, T = { t, t,t 3 t n } an Intal test case set S { } an R { }. (Max-Relevance) Compute I (x, t ) as n (3.0)for all t ε T an x ε X select the test case t that maxmzes I(x, t ) an a t to S, S { t } repeat for all t ε T repeat for all x ε X 3. (Mn-Reunancy) Compute I(s, s j ) as n (3.)for all s, s j ε S select the test case s that maxmzes I(s, s j ) compare s an s j n terms of I(x, s ), I(x, s j ) select the s or s j wth max I an a R { s } repeat for all s ε S Repeat for all x ε X 4. Output the mrmr reuce test cases. 3.. Stages n mrmr Feature Selecton The stages n feature selecton are Input Evaluator Output 3... Input stage In the nput stage, the test sute T an the objectve set X are gven to the Evaluator. The objectve set X has 4 objectves such as memory usage, executon tme, completeness an fault Evaluator stage The evaluator stage n feature selecton uses two technques. Max-Relevance Mn-Reunancy () Max-Relevance The frst technque Max-Relevance s use to select the test cases wth relevant objectves such as maxmum fault coverage, mnmum executon tme, maxmum completeness an mnmum memory usage from the test sute. The test cases wth the most relevant features to the objectves are selecte from the test sute by the technque Maxmum Relevance. Max-Relevance (Hanchuan Peng et al 005) s to search test case wth features satsfyng Eq.(5), wth the mean value of all mutual nformaton values between nvual feature x an test sute T. max D ( X, T ), D x I ( x x T ) (5) x Ths frst technque acts as an rrelevancy flter, whch selects the subset of relevant test cases by removng rrelevant ones. The technque consers the value of the objectves that s avalable n each test case n the test sute. Then the test cases are ranke base on ther values of objectves. The rankng s one base on the mportance of the objectve to the system. In ths system the four objectves are ranke as fault coverage, executon tme, completeness an memory usage base on ther mportance to the test case prortzaton system. The objectve value s calculate base on MI between the test cases an the objectves usng Eq.(6). p( x, t ) I ( x, t ) p( x, t )log (6) p( x ) p( t )

3 P(x, t j ) s calculate as frequency of both x an t j / no of transactons P(x ) s calculate as frequency of P(x ) / no of transactons an P(t ) s calculate as frequency of P(t ) / no of transactons t j ncates the test cases n the test sute. The MI s calculate between each test case an the frst objectve. A hgher MI value between the test case an the objectve means more common nformaton content between them.if MI between the test case an the objectve larger than a threshol, enote by relevancy threshol or RLTH, these two that s the test case an the objectve are consere relevant to each other. The test cases wth the RLTH value larger than a threshol, enote by rrelevancy threshol, are selecte an the other test cases are fltere out. () Mn-Reunancy The output from the frst technque often contans test cases whch are relevant but reunant an mrmr attempts to aress ths problem by removng those reunant test cases by usng the secon technque Mn-Reunancy. The mnmal reunancy (Mn-Reunancy) conton (Hanchuanpeng 005) can be ae to select mutually exclusve features usng Eq. (7) mn R( x) x x I ( x x, x j ) (7), j x The selecte test cases by the rrelevancy flter may be reunant. The secon technque of the propose feature selecton technque flters out reunant test cases. The reunant test cases among the selecte subset of the frst technque are fltere out by the MI technque. Hence, the outcome of the propose feature selecton technque s the most relevant features wth mnmum reunancy. The reunancy flter uses the concept of MI technque whch s use to measure common nformaton between test cases. Usng Eq. (5) MI s calculate between par of test cases. Hgher MI value of two test cases means more common nformaton content between them. If MI between two tests cases larger than a threshol, enote by reunancy threshol or RTH, these two test cases are consere reunant test cases. If two test cases are reunant, the less relevant one wth lower relevance weght value, obtane from the frst stage s elmnate an the more relevant one wth hgher weght value s retane. Ths process s repeate untl no reunant test case s foun Output stage The selecte test cases by the rrelevancy flter are the fnal result of the propose feature selecton technque. The test cases from feature selecton are gven as the nput to genetc algorthm. 4. Test Case Prortzaton Usng Genetc Algorthm Genetc algorthms are use for prortzng the test cases wth mult objectves. The populaton s forme wth mult objectve test cases. The ftter soluton s foun to prortze the test cases. Only the test cases wth strong ftness values are selecte an prortze accorng to ther ftness value. The output from genetc algorthm gves the prortze set of test cases. These test cases are use for testng the target system. The basc unt n GA s the chromosome. To prortze the test cases, the steps to be followe are Chromosome generaton Chromosome selecton Chromosome crossover Chromosome mutaton Termnaton Here chromosome represents the test cases. 4.. Chromosome Generaton The mrmr feature selecton algorthm outputs the reuce test sute. In orer to obtan the esrable test case, the output s subject to genetc algorthm. The output from mrmr feature selecton algorthm forms the chromosome. 4.. Chromosome representaton In GA, the chromosomes are represente by the bnary alphabet {0, } an sometmes, epenng on the applcaton, ntegers or real numbers are use. Whatever may be the representaton, t can be use to form a soluton as a fnte length strng. A populaton T = {t, t, t 3.. t n} s forme from a set of chromosomes. Where T s the test sute contanng the test cases t, t, t 3..t n. The test cases whch forms the chromosome are represente as a strng of 4 tuple an s gven as (x,x,x 3,x 4 ). Here x means the memory usage value of the test case, x s executon tme, x 3 s coverage an x 4 s fault coverage Chromosome Selecton In the selecton stage of genetc algorthm, the test cases are chosen from a populaton for subsequent procreaton. The genetc algorthm solves the optmzaton problem by creatng a populaton of chromosomes, whch s a set of possble solutons for the problem. Frst of all, several nvual solutons are ranomly create n orer to form ntal populaton. The output from feature selecton algorthm s taken as the populaton nput for genetc algorthm. The populaton gves better solutons as the search evolves an t eventually converges. To form a new generaton, a proporton of the exstng populaton s chosen urng each consecutve generaton. A ftness base process s performe to select the ftter soluton. The ftter soluton s a measure of ftness functon. Weghte Sum Approach s use for formng ftness functon. The approach use here to solve the mult-objectve optmzaton problem s to allot a weght w to each normalze objectve functon as Eq (8) f (8) hence, the problem s change nto sngle objectve problem wth a scalar objectve functon as Eq. (9). mn z w f w f... w p f p (9) where, f s the normalze objectve functon, f an w. Here, the user s expecte to gve the weghts. Solvng a problem wth an objectve functon as n Equaton (9) for a gven weght vector w { w, w,..., wp} prouces a sngle soluton. Int J Av Engg Tech/Vol. VII/Issue I/Jan.-March,06/

4 But n real tme multple solutons are esre. Then the problem nees to be solve multple tmes wth verse weght combnatons. The man problem n ths metho s selectng a weght vector. In the propose work, n orer to calculate the ftness value for each chromosome n the populaton obtane from flockng algorthm, a number of ftness functons are use such as Eq. (0), () an (). ftness (0) E r where, E r s the vector whch s gven as, Er Er () where, E s the sum of error E r r n n ( j.e., () where, s the esre stance between the test cases an j, a s the actual stance between the test cases an j, an n s the number of test cases Ftness functon evaluaton by threshol factor Ftness evaluaton nvolves efnng an objectve or ftness functon aganst whch each test case s teste for sutablty for the envronment uner conseraton. As the genetc algorthm process precees the nvual ftness of the best test case ncreases as well as the total ftness of the test sute as a whole. The fnal ftness functon s gven by the followng Eq. (3). F ( S ) O( S ) P( S ) (3) where, O(S) s the objectve functon of genetc algorthm ftness, P(S) s a non negatve penalty functon, an s a penalty tme coeffcent, whch vares aaptvely urng the GA evoluton. The value of s selecte such that f the value s larger than the threshol value t whch s calculate as the average of all x, x, x 3 an x 4. Eltst selecton s use as a selecton metho to select the test cases for recombnaton. When usng genetc algorthm to solve complcate global optmzaton problems, only the eltst selecton genetc algorthm (ESGA) can converge to optmal global soluton. The man avantage of ths selecton s that t prouces best soluton n every generaton. Only the test cases wth strong ftness values are selecte for next generaton. In ths eltst selecton metho, the ftness value of all the test cases are calculate base on the ftness functon. Then the test cases are sorte by escenng ftness values. The sum S s calculate a ) whch s sum of all test cases ftness n populaton. The cut off value r s calculate as the average of all x, x, x 3 an x 4. When the ftness value of the test case s greater than r, the current test case s eclare as selecte, or else t s eclare as omtte. The ae penalty term s a functon of the egree of volaton of the constrants, n orer to prouce a graent towar val solutons. The penalty term for any soluton that breaches the constrants can be formulate by a quantty (s), whch measures the level of constrant volaton of soluton S. Thus, the penalty functon P epens on (S) s gven as Eq. (4). P( ( S)) A ( S) Bt (4) Where, A s a severty factor, whch efnes the slope of the penalty functon an Bt s a penalty threshol factor. So, by usng eltsm or eltst selecton, the best nvuals are retane n a generaton unchange n the next generaton Chromosome Crossover Cross over s the salent operator n GA. The two strngs partcpatng n the crossover operaton are known as parent strngs an the resultng strngs are known as chlren strngs. In crossover, two parent chromosomes are poole together to form new chromosomes calle offsprng. From the exstng chromosomes, the parents are chosen wth preference towars ftness so that offsprng s expecte to appear goo genes that make the parents ftter. The effect of cross over s usually benefcal. S {,,..., } Assume, s s sn an S { s, s,..., sn} be the two chromosomes. A ranom number s selecte from the ntegers 0 r n. S 3 an S 4 are the offsprng of crossover S S {, } an S, where 3 s f r s S S4 { s f r, s S}. Here n case of test case optmzaton t s T = {x, x, x 3, x 4 } an T = {x, x, x 3, x 4 }. By applyng the crossover operator, the genes of goo chromosomes are expecte to emerge more frequently n the populaton fnally leang to an excellent soluton. Many crossover operators exst n the GA. One pont crossover an two pont crossover are the most common ones aopte. In most crossover operators, two strngs are pcke from the pool at ranom an some porton of the strngs s exchange between the strngs. Here the unform crossover s use. The mxng rato use s 0.5, so approxmately half of the genes n the offsprng wll come from test case an the other half wll come from test case. Below s a possble set of offsprng after unform crossover. Before crossover Chromosome Chromosome Crossover pont Feature Feature Feature 3 Feature 4 Feature 5 Feature 6 Feature 7 Feature 8 Int J Av Engg Tech/Vol. VII/Issue I/Jan.-March,06/

5 After crossover: (the resultng offsprng) Chromosome 3 Feature Feature Feature 7 Feature 8 Chromosome 4 Feature 5 Feature 6 Feature 3 Feature 4 Each test case has 4 features. In case of unform cross over, snce the mxng rato use s 0.5, the frst two features from the frst test case s combne wth the last two feature of the secon test case to form the frst offsprng. Smlarly, the last two features from the frst test case s combne wth the frst two feature of the secon test case to form the secon offsprng. Thus approxmately half of the genes n the offsprng wll come from test case an the other half wll come from test case Chromosome Mutaton In mutaton, the characterstcs of chromosomes are change ranomly, thereby changng the structure of a chromosome. Normally, the mutaton s apple at the gene level. The mutaton operator s use to ntrouce change nto the chromosome populaton an t s apple to each new structure nvually. When the bts are beng cope from the current strng to the new strng, there s probablty that each bt may become mutate. A gven mutaton nvolves ranomly alterng each gene wth a small probablty calle mutaton probablty P m. Wth ths probablty, a ranom real value s generate whch s use to make a ranom change n the m-th element selecte ranomly of the chromosome. If ranom number s less than the mutaton probablty, then the bt s nverte. Ths s explane below usng an example. Here the test sute contans 6 test cases from T to T6 an the mutaton probablty P m = Test sute T T T3 T4 T5 T6 T7 T8 T9 T0 T T T3 T4 T5 T6 Mutaton probablty P m = The nvual test case ranom values are gven n Table. Table. Ranom values for test cases. Test cases Ranom Values R(T) R(T) 0.36 R(T3) R(T4) 0.00 R(T5) 0.67 R(T6) R(T7) 0.34 R(T8) 0.47 R(T9) R(T0) R(T) R(T) 0.87 R(T3) R(T4) 0.00 R(T5) R(T6) Here R(T4), R(T9) an R(T4) are havng P m the mutaton probablty value less than the specfe value So, they are omtte for the next generaton. So, the next generaton test sute contans T T T3 T5 T6 T7 T8 T0 T T T3 T5 T6 Wth ths a bt of versty to the populaton by scatterng the occasonal ponts s ntrouce resultng n better optma. In ths the weak nvual that wll never be selecte for further operatons. In mutaton urng the local search, a pont s create n the neghborhoo of the current pont aroun the current soluton. The man am of mutaton s to mantan versty n the populaton. Mutaton as new nformaton n a ranom way to the genetc search process an mutaton may cause the chromosomes of nvuals to be fferent from those of ther parent nvuals. The mutaton rate s usually less than % Termnaton Termnaton s the crteron use by the genetc algorthm to make a ecson about whether to contnue the process or to stop the process. Havng selecte the ntal populaton at ranom, the ftness functon valates the ftness of the chromosomes an selects those wth hgher potental for the proucton of new offsprng. After the applcaton of genetc operators, a new populaton s create from the current populaton. These operators are enhancng the present populaton. The whole process represents the completon of a sngle cycle by genetc algorthm. After many generatons of selecton for the ftter chromosomes, the resultant populaton s consere as ftter than the orgnal. Untl the stoppng crteron s met the steps are repeate. Here the number of generatons s use as a stoppng crteron. Fnally the genetc algorthm outputs the prortze test cases. 5. Evaluaton The esgne test case prortzaton system s teste wth 0 fferent projects. The samples of results Int J Av Engg Tech/Vol. VII/Issue I/Jan.-March,06/

6 obtane from two projects are use for performance analyss an s scusse here. In APFD metrc[7] the test cases are orere base on the test optmzaton nces an a test sutes performance are analyze. The effcacy of the orerng of the test sute s evaluate n orer to measure the performance of the optmzaton metho use n ths paper. Effcacy s measure by the rate of faults etecte. The followng metrcs s utlze to compute the level of effcacy. 5.. Average Percentage of Faults Detecte (APFD) By usng the weghte average of the number of faults entfe urng the executon of the test sute, the APFD s compute. Let T be the test sute uner evaluaton, F s the number of faults contane n the program uner test P, n s the total number of test cases, an reveal (, T ) s the poston of the frst test nt, whch reveals the fault. The formula for calculatng the APFD metrc s gven below. F reveal (, T ) APFD ( T, P ) - nf n In project, the number of test cases n=0 an the number of faults f=6. Ths can be represente n the followng Table, Table The Faults Detecte by the Test Sutes n Project Test Cases T T T3 T4 T5 T6 T7 T8 T9 T0 Faults F X X X X F X X X F3 X X X X F4 X X X F5 X X X F6 X X X Here the number of test cases s 0,.e., T, T, T3, T 4, T5, T6, T7, T8, T9. T0, an the number of faults occur urng the regresson testng s 6,.e., F, F, F3, F4, F5, F6.The optmze test suts wth test sequence T 0, T5, T9, T, T6, T, T 4, T3, T7, T8, then the APFD metrc after prortzaton s (647) Apf( T, - 0*6 *0 = 0.7 The APFD metrc before prortzaton s (5455) Apf( T, - 0*6 *0 =.68 For project the APFD metrc s calculate as follows. Number of test cases n=6 an the number of faults f=5. Ths can be represente n followng Table. Table The Faults Detecte by the Test Sutes n Project Test cases T T T3 T4 T5 T6 Faults F X X F X X F3 X X F4 X X F5 X the number of test cases s 6,.e., T, T, T 3, T 4, T 5, T 6, an the number of faults occur urng the regresson testng s 5,.e., F, F, F3, F 4, F5. The optmze test suts wth test sequencet 6, T, T 3, T 4, T 5, T, then the APFD metrc after prortzaton s ( 4 ) Apf( T, - 5*6 APFD metrc before prortzaton s ( 4 5) Apf( T, - 5*6 *6 *6 = = Fgure APFD Metrc for Both Project an Project Int J Av Engg Tech/Vol. VII/Issue I/Jan.-March,06/

7 From the Tables, an Fgure, t s observe that the optmze test cases entfy the faults at an early stage. The APFD measure of prortze test cases are hgher than the non prortze orer for both projects. In Tables an, the Fault entfe urng each test cases s lste. In Table, test case 0 can entfy more number of faults when compare to others. Thus Test case 5 wll be frst execute. From Tables an, t s observe that the propose metho entfes the severe fault n the early stage. 6. CONCLUSION Snce the sngle objectve test case system cannot solve complex problems base on the results obtane usng tratonal but latest test case prortzaton for regresson testng, the usage of mult objectve test case prortzaton system usng an unfe framework nvolvng mrmr Feature Selecton an Genetc Algorthm as one n the unfe framework valates the effcency an effcacy of the testng system by reucng the executon tme, memory usage an by ncreasng the fault etecton rate an coverage. REFERENCES. IEEE stanar glossary of software engneerng termnology, IEEE St , Aenlso a Slva Smao, Rorgo Fernanes e Mello an Lucano Jose Senger, A Technque to Reuce the Test Case Sutes for Regresson Testng Base on a Self-Organzng Neural Network Archtecture, COMPSAC 06, Proceengs of the 30th Annual Internatonal Computer Software an Applcatons Conference, Vol. 0, pp , AlrezaEnsan, EbrahmBagher, Mohsen Asa, DraganGasevc an YevgenBletsky, Goal-Orente Test Case Selecton an Prortzaton for Prouct Lne Feature Moels, pp. 9-98, Anrews, S. An Investgaton nto Mutaton Operators for Partcle Swarm Optmzaton, In Proc. Congr. Evol. Compt., pp , Arvner Kaur an Dvya Bhatt, Hybr Partcle Swarm Optmzaton for Regresson Testng, Internatonal Journal on Computer Scence an Engneerng, Vol. 3 No. 5, Bates, S. an Horwtz, S. Incremental Program Testng Usng Program Depenence Graphs, In Conference Recor of the Twenteth ACM SIGPLAN-SIGACT Symposum on Prncples of Programmng Languages, Charleston, South Carolna, ACM press, pp , Benot Baury, Franck Fleurey, Jean-Marc Jezequel an Yves Le Traon, Automatc Test Cases Optmzaton usng a Bacterologcal Aaptaton Moel: Applcaton to.net Components, 7th IEEE Internatonal Conference on Automate Software Engneerng, ASE Bergmann, K.P., Scheler, R. an Jacob, C. Cryptanalyss usng Genetc Algorthms, In: Proceengs of the 0th Annual Conference on Genetc an Evolutonary Computaton, GECCO 08, ACM New York, NY, USA, pp , Llly Raamesh an Uma, G.V. An Effcent Reucton Metho for Test Cases, Internatonal Journal of Engneerng Scence an Technology, Vol., No., pp , Llly Raamesh an Uma, G.V. Knowlege Mnng of Test Case System, Internatonal Journal on Computer Scence an Engneerng, Vol., No., pp , 009. Llly Raamesh an Uma, G.V. Relable Mnng of Automatcally Generate Test Cases from Software Requrements Specfcaton, IJCSI Internatonal Journal of Computer Scence Issues, Vol. 7, No., No. 3, 00.. Llly Raamesh an Uma, G.V. A Profcent Test Case Optmzaton System Base on Brs Flockng Algorthm an GA, European Journal of Scentfc Research, Vol. 84, No.3, pp S Elbaum, A Malshevsky, G Rothermel, 00, Incorporatng varyng test costs an fault severtes nto test case prortzaton Proceengs of the 3r Internatonal Conference on Software Engneerng. 4. Hanchuan Peng, Fuhu Long, an Chrs Dng, 005, "Feature selecton base on mutual nformaton: crtera of max-epenency, max-relevance, an mnreunancy", IEEE Transactons on Pattern Analyss an MachneIntellgence,Vol. 7, No. 8, pp C Emmanouls, A Hunter, J MacIntyre, 000, Amultobjectve evolutonary settng for feature selecton an a commonalty-base crossover operator Evolutonary Computaton, 000. Proceengs of the 000 Congress on, Changbng L, Changxu Cao, Ynguo L, Ybn Yu, 007. Hybr of genetc algorthm an partcle swarm optmzaton for multcast QoS routng. Proceengs of IEEE nternatonal conference on control an automaton, pp: Elbaum, S., Malshvesky, A.G., Rothermel, G., 00, Test case prortzaton: a famly of emprcal stues. IEEE Transactons on Software Engneerng 8 (), Gregg Rothermel, Rolan H. Untch, Chentun Chu an Mary Jean Harrol, 00, Prortzng Test Cases for Regresson Testng, IEEE Transactons on software Engneerng, VOL. 7 NO Zheng L, Mark Harman, an Robert M. Herons, 007, Search algorthm for Regresson Test Case Prortzaton, IEEE Transactons on Software Engneerng, Vol. 33, No.4. [ 0. S Elbaum, AG Malshevsky, G Rothermel,00, Test case prortzaton: A famly of emprcal stues Software Engneerng, IEEE Transactons on 8 (), S Elbaum, S Karre, G Rothermel, 003, Improvng web applcaton testng wth user sesson ata, Proceengs of the 5th Internatonal Conference on Software Engneerng, Yang, J. an Honavar, V., 998, Feature Subset Selecton Usng a Genetc Algorthm, IEEE Intellgent Systems, Vol. 3, No., pp Raymer, M.L., Punch, W.F., Gooman, E.D., Kuhn, L.A., an Jan, A.K., 000, Dmensonalty reucton usng genetc algorthms, IEEE Transactons on Evolutonary Computaton, Vol. 4, No., pp64-7. Int J Av Engg Tech/Vol. VII/Issue I/Jan.-March,06/

Efficient Load-Balanced IP Routing Scheme Based on Shortest Paths in Hose Model. Eiji Oki May 28, 2009 The University of Electro-Communications

Efficient Load-Balanced IP Routing Scheme Based on Shortest Paths in Hose Model. Eiji Oki May 28, 2009 The University of Electro-Communications Effcent Loa-Balance IP Routng Scheme Base on Shortest Paths n Hose Moel E Ok May 28, 2009 The Unversty of Electro-Communcatons Ok Lab. Semnar, May 28, 2009 1 Outlne Backgroun on IP routng IP routng strategy

More information

The Objective Function Value Optimization of Cloud Computing Resources Security

The Objective Function Value Optimization of Cloud Computing Resources Security Open Journal of Optmzaton, 2015, 4, 40-46 Publshe Onlne June 2015 n ScRes. http://www.scrp.org/journal/ojop http://x.o.org/10.4236/ojop.2015.42005 The Objectve Functon Value Optmzaton of Clou Computng

More information

Meta-heuristics for Multidimensional Knapsack Problems

Meta-heuristics for Multidimensional Knapsack Problems 2012 4th Internatonal Conference on Computer Research and Development IPCSIT vol.39 (2012) (2012) IACSIT Press, Sngapore Meta-heurstcs for Multdmensonal Knapsack Problems Zhbao Man + Computer Scence Department,

More information

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

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

More information

Unsupervised Classification Using Immune Algorithm

Unsupervised Classification Using Immune Algorithm Internatonal Journal of Computer Applcatons (975 8887) Volume 2 o.7, June 2 Unsupervse Classfcaton Usng Immune Algorthm M.T. Al-Muallm Department of Computer Engneerng & Automaton, Faculty of Mechancal

More information

Parallelism for Nested Loops with Non-uniform and Flow Dependences

Parallelism for Nested Loops with Non-uniform and Flow Dependences Parallelsm for Nested Loops wth Non-unform and Flow Dependences Sam-Jn Jeong Dept. of Informaton & Communcaton Engneerng, Cheonan Unversty, 5, Anseo-dong, Cheonan, Chungnam, 330-80, Korea. seong@cheonan.ac.kr

More information

NGPM -- A NSGA-II Program in Matlab

NGPM -- A NSGA-II Program in Matlab Verson 1.4 LIN Song Aerospace Structural Dynamcs Research Laboratory College of Astronautcs, Northwestern Polytechncal Unversty, Chna Emal: lsssswc@163.com 2011-07-26 Contents Contents... 1. Introducton...

More information

A Novel Approach for an Early Test Case Generation using Genetic Algorithm and Dominance Concept based on Use cases

A Novel Approach for an Early Test Case Generation using Genetic Algorithm and Dominance Concept based on Use cases Alekhya Varkut et al, / (IJCSIT) Internatonal Journal of Computer Scence and Informaton Technologes, Vol. 3 (3), 2012,4218-4224 A Novel Approach for an Early Test Case Generaton usng Genetc Algorthm and

More information

Support Vector Machines

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

More information

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

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

More information

Learning Depth from Single Still Images: Approximate Inference 1

Learning Depth from Single Still Images: Approximate Inference 1 Learnng Depth from Sngle Stll Images: Approxmate Inference 1 MS&E 211 course project Ashutosh Saxena, Ilya O. Ryzhov Channng Wong, Janln Wang June 7th, 2006 1 In ths report, Saxena, et. al. [1] somethng

More information

MODULE - 9 LECTURE NOTES 1 FUZZY OPTIMIZATION

MODULE - 9 LECTURE NOTES 1 FUZZY OPTIMIZATION Water Resources Systems Plannng an Management: vance Tocs Fuzzy Otmzaton MODULE - 9 LECTURE NOTES FUZZY OPTIMIZTION INTRODUCTION The moels scusse so far are crs an recse n nature. The term crs means chotonomous.e.,

More information

Maximum Variance Combined with Adaptive Genetic Algorithm for Infrared Image Segmentation

Maximum Variance Combined with Adaptive Genetic Algorithm for Infrared Image Segmentation Internatonal Conference on Logstcs Engneerng, Management and Computer Scence (LEMCS 5) Maxmum Varance Combned wth Adaptve Genetc Algorthm for Infrared Image Segmentaton Huxuan Fu College of Automaton Harbn

More information

A GENETIC ALGORITHM FOR PROCESS SCHEDULING IN DISTRIBUTED OPERATING SYSTEMS CONSIDERING LOAD BALANCING

A GENETIC ALGORITHM FOR PROCESS SCHEDULING IN DISTRIBUTED OPERATING SYSTEMS CONSIDERING LOAD BALANCING A GENETIC ALGORITHM FOR PROCESS SCHEDULING IN DISTRIBUTED OPERATING SYSTEMS CONSIDERING LOAD BALANCING M. Nkravan and M. H. Kashan Department of Electrcal Computer Islamc Azad Unversty, Shahrar Shahreqods

More information

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization Problem efntons and Evaluaton Crtera for Computatonal Expensve Optmzaton B. Lu 1, Q. Chen and Q. Zhang 3, J. J. Lang 4, P. N. Suganthan, B. Y. Qu 6 1 epartment of Computng, Glyndwr Unversty, UK Faclty

More information

Reliable and Efficient Routing Using Adaptive Genetic Algorithm in Packet Switched Networks

Reliable and Efficient Routing Using Adaptive Genetic Algorithm in Packet Switched Networks IJCSI Internatonal Journal of Computer Scence Issues, Vol. 9, Issue 1, No 3, January 2012 ISSN (Onlne): 1694-0814 www.ijcsi.org 168 Relable and Effcent Routng Usng Adaptve Genetc Algorthm n Packet Swtched

More information

An Optimal Algorithm for Prufer Codes *

An Optimal Algorithm for Prufer Codes * J. Software Engneerng & Applcatons, 2009, 2: 111-115 do:10.4236/jsea.2009.22016 Publshed Onlne July 2009 (www.scrp.org/journal/jsea) An Optmal Algorthm for Prufer Codes * Xaodong Wang 1, 2, Le Wang 3,

More information

SLAM Summer School 2006 Practical 2: SLAM using Monocular Vision

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

More information

NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS

NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS ARPN Journal of Engneerng and Appled Scences 006-017 Asan Research Publshng Network (ARPN). All rghts reserved. NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS Igor Grgoryev, Svetlana

More information

Cracking of the Merkle Hellman Cryptosystem Using Genetic Algorithm

Cracking of the Merkle Hellman Cryptosystem Using Genetic Algorithm Crackng of the Merkle Hellman Cryptosystem Usng Genetc Algorthm Zurab Kochladze 1 * & Lal Besela 2 1 Ivane Javakhshvl Tbls State Unversty, 1, I.Chavchavadze av 1, 0128, Tbls, Georga 2 Sokhum State Unversty,

More information

Load Balancing for Hex-Cell Interconnection Network

Load Balancing for Hex-Cell Interconnection Network Int. J. Communcatons, Network and System Scences,,, - Publshed Onlne Aprl n ScRes. http://www.scrp.org/journal/jcns http://dx.do.org/./jcns.. Load Balancng for Hex-Cell Interconnecton Network Saher Manaseer,

More information

Network Intrusion Detection Based on PSO-SVM

Network Intrusion Detection Based on PSO-SVM TELKOMNIKA Indonesan Journal of Electrcal Engneerng Vol.1, No., February 014, pp. 150 ~ 1508 DOI: http://dx.do.org/10.11591/telkomnka.v1.386 150 Network Intruson Detecton Based on PSO-SVM Changsheng Xang*

More information

Subspace clustering. Clustering. Fundamental to all clustering techniques is the choice of distance measure between data points;

Subspace clustering. Clustering. Fundamental to all clustering techniques is the choice of distance measure between data points; Subspace clusterng Clusterng Fundamental to all clusterng technques s the choce of dstance measure between data ponts; D q ( ) ( ) 2 x x = x x, j k = 1 k jk Squared Eucldean dstance Assumpton: All features

More information

CHAPTER 4 OPTIMIZATION TECHNIQUES

CHAPTER 4 OPTIMIZATION TECHNIQUES 48 CHAPTER 4 OPTIMIZATION TECHNIQUES 4.1 INTRODUCTION Unfortunately no sngle optmzaton algorthm exsts that can be appled effcently to all types of problems. The method chosen for any partcular case wll

More information

GSLM Operations Research II Fall 13/14

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

More information

GA-Based Learning Algorithms to Identify Fuzzy Rules for Fuzzy Neural Networks

GA-Based Learning Algorithms to Identify Fuzzy Rules for Fuzzy Neural Networks Seventh Internatonal Conference on Intellgent Systems Desgn and Applcatons GA-Based Learnng Algorthms to Identfy Fuzzy Rules for Fuzzy Neural Networks K Almejall, K Dahal, Member IEEE, and A Hossan, Member

More information

Smoothing Spline ANOVA for variable screening

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

More information

Support Vector Machines

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

More information

Programming in Fortran 90 : 2017/2018

Programming in Fortran 90 : 2017/2018 Programmng n Fortran 90 : 2017/2018 Programmng n Fortran 90 : 2017/2018 Exercse 1 : Evaluaton of functon dependng on nput Wrte a program who evaluate the functon f (x,y) for any two user specfed values

More information

CHAPTER 2 PROPOSED IMPROVED PARTICLE SWARM OPTIMIZATION

CHAPTER 2 PROPOSED IMPROVED PARTICLE SWARM OPTIMIZATION 24 CHAPTER 2 PROPOSED IMPROVED PARTICLE SWARM OPTIMIZATION The present chapter proposes an IPSO approach for multprocessor task schedulng problem wth two classfcatons, namely, statc ndependent tasks and

More information

The Codesign Challenge

The Codesign Challenge ECE 4530 Codesgn Challenge Fall 2007 Hardware/Software Codesgn The Codesgn Challenge Objectves In the codesgn challenge, your task s to accelerate a gven software reference mplementaton as fast as possble.

More information

Module Management Tool in Software Development Organizations

Module Management Tool in Software Development Organizations Journal of Computer Scence (5): 8-, 7 ISSN 59-66 7 Scence Publcatons Management Tool n Software Development Organzatons Ahmad A. Al-Rababah and Mohammad A. Al-Rababah Faculty of IT, Al-Ahlyyah Amman Unversty,

More information

GENETIC ALGORITHMS APPLIED FOR PATTERN GENERATION FOR DOWNHOLE DYNAMOMETER CARDS

GENETIC ALGORITHMS APPLIED FOR PATTERN GENERATION FOR DOWNHOLE DYNAMOMETER CARDS GENETIC ALGORITHMS APPLIED FOR PATTERN GENERATION FOR DOWNHOLE DYNAMOMETER CARDS L. Schntman 1 ; B.C.Brandao 1 ; H.Lepkson 1 ; J.A.M. Felppe de Souza 2 ; J.F.S.Correa 3 1 Unversdade Federal da Baha- Brazl

More information

Determining the Optimal Bandwidth Based on Multi-criterion Fusion

Determining the Optimal Bandwidth Based on Multi-criterion Fusion Proceedngs of 01 4th Internatonal Conference on Machne Learnng and Computng IPCSIT vol. 5 (01) (01) IACSIT Press, Sngapore Determnng the Optmal Bandwdth Based on Mult-crteron Fuson Ha-L Lang 1+, Xan-Mn

More information

S1 Note. Basis functions.

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

More information

Feature Selection for Target Detection in SAR Images

Feature Selection for Target Detection in SAR Images Feature Selecton for Detecton n SAR Images Br Bhanu, Yngqang Ln and Shqn Wang Center for Research n Intellgent Systems Unversty of Calforna, Rversde, CA 95, USA Abstract A genetc algorthm (GA) approach

More information

5 The Primal-Dual Method

5 The Primal-Dual Method 5 The Prmal-Dual Method Orgnally desgned as a method for solvng lnear programs, where t reduces weghted optmzaton problems to smpler combnatoral ones, the prmal-dual method (PDM) has receved much attenton

More information

THE FAULT LOCATION ALGORITHM BASED ON TWO CIRCUIT FUNCTIONS

THE FAULT LOCATION ALGORITHM BASED ON TWO CIRCUIT FUNCTIONS U THE FAULT LOCATION ALGORITHM BASED ON TWO CIRCUIT FUNCTIONS Z. Czaa Char of Electronc Measurement, Faculty of Electroncs, Telecommuncatons an Informatcs, Techncal Unversty of Gañsk, Polan The paper presents

More information

Histogram based Evolutionary Dynamic Image Segmentation

Histogram based Evolutionary Dynamic Image Segmentation Hstogram based Evolutonary Dynamc Image Segmentaton Amya Halder Computer Scence & Engneerng Department St. Thomas College of Engneerng & Technology Kolkata, Inda amya_halder@ndatmes.com Arndam Kar and

More information

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

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

More information

Synthesis of local thermo-physical models using genetic programming

Synthesis of local thermo-physical models using genetic programming Unversty of South Florda Scholar Commons Graduate Theses and Dssertatons Graduate School 2009 Synthess of local thermo-physcal models usng genetc programmng Yng Zhang Unversty of South Florda Follow ths

More information

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

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

More information

Kent State University CS 4/ Design and Analysis of Algorithms. Dept. of Math & Computer Science LECT-16. Dynamic Programming

Kent State University CS 4/ Design and Analysis of Algorithms. Dept. of Math & Computer Science LECT-16. Dynamic Programming CS 4/560 Desgn and Analyss of Algorthms Kent State Unversty Dept. of Math & Computer Scence LECT-6 Dynamc Programmng 2 Dynamc Programmng Dynamc Programmng, lke the dvde-and-conquer method, solves problems

More information

A Notable Swarm Approach to Evolve Neural Network for Classification in Data Mining

A Notable Swarm Approach to Evolve Neural Network for Classification in Data Mining A Notable Swarm Approach to Evolve Neural Network for Classfcaton n Data Mnng Satchdananda Dehur 1, Bjan Bhar Mshra 2 and Sung-Bae Cho 1 1 Soft Computng Laboratory, Department of Computer Scence, Yonse

More information

Outline. Type of Machine Learning. Examples of Application. Unsupervised Learning

Outline. Type of Machine Learning. Examples of Application. Unsupervised Learning Outlne Artfcal Intellgence and ts applcatons Lecture 8 Unsupervsed Learnng Professor Danel Yeung danyeung@eee.org Dr. Patrck Chan patrckchan@eee.org South Chna Unversty of Technology, Chna Introducton

More information

Imperialist Competitive Algorithm with Variable Parameters to Determine the Global Minimum of Functions with Several Arguments

Imperialist Competitive Algorithm with Variable Parameters to Determine the Global Minimum of Functions with Several Arguments Fourth Internatonal Conference Modellng and Development of Intellgent Systems October 8 - November, 05 Lucan Blaga Unversty Sbu - Romana Imperalst Compettve Algorthm wth Varable Parameters to Determne

More information

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

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

More information

Learning the Kernel Parameters in Kernel Minimum Distance Classifier

Learning the Kernel Parameters in Kernel Minimum Distance Classifier Learnng the Kernel Parameters n Kernel Mnmum Dstance Classfer Daoqang Zhang 1,, Songcan Chen and Zh-Hua Zhou 1* 1 Natonal Laboratory for Novel Software Technology Nanjng Unversty, Nanjng 193, Chna Department

More information

An Entropy-Based Approach to Integrated Information Needs Assessment

An Entropy-Based Approach to Integrated Information Needs Assessment Dstrbuton Statement A: Approved for publc release; dstrbuton s unlmted. An Entropy-Based Approach to ntegrated nformaton Needs Assessment June 8, 2004 Wllam J. Farrell Lockheed Martn Advanced Technology

More information

A Serial and Parallel Genetic Based Learning Algorithm for Bayesian Classifier to Predict Metabolic Syndrome

A Serial and Parallel Genetic Based Learning Algorithm for Bayesian Classifier to Predict Metabolic Syndrome A Seral and Parallel Genetc Based Learnng Algorthm for Bayesan Classfer to Predct Metabolc Syndrome S. Dehur Department of Informaton and Communcaton Technology Fakr Mohan Unversty, Vyasa Vhar Balasore-756019,

More information

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data A Fast Content-Based Multmeda Retreval Technque Usng Compressed Data Borko Furht and Pornvt Saksobhavvat NSF Multmeda Laboratory Florda Atlantc Unversty, Boca Raton, Florda 3343 ABSTRACT In ths paper,

More information

Feature Reduction and Selection

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

More information

PARETO BAYESIAN OPTIMIZATION ALGORITHM FOR THE MULTIOBJECTIVE 0/1 KNAPSACK PROBLEM

PARETO BAYESIAN OPTIMIZATION ALGORITHM FOR THE MULTIOBJECTIVE 0/1 KNAPSACK PROBLEM PARETO BAYESIAN OPTIMIZATION ALGORITHM FOR THE MULTIOBJECTIVE 0/ KNAPSACK PROBLEM Josef Schwarz Jří Očenáše Brno Unversty of Technology Faculty of Engneerng and Computer Scence Department of Computer Scence

More information

A Hybrid Genetic Algorithm for Routing Optimization in IP Networks Utilizing Bandwidth and Delay Metrics

A Hybrid Genetic Algorithm for Routing Optimization in IP Networks Utilizing Bandwidth and Delay Metrics A Hybrd Genetc Algorthm for Routng Optmzaton n IP Networks Utlzng Bandwdth and Delay Metrcs Anton Redl Insttute of Communcaton Networks, Munch Unversty of Technology, Arcsstr. 21, 80290 Munch, Germany

More information

An Application of Computational Intelligence Technique for Predicting Surface Roughness in End Milling of Inconel-718

An Application of Computational Intelligence Technique for Predicting Surface Roughness in End Milling of Inconel-718 An Applcaton of Computatonal Intellgence Technque for Prectng Roughness n En Mllng of Inconel-718 Abhjt Mahapatra 1 an Shbenu Shekhar Roy 2, 1 Vrtual Prototypng & Immerse Vsualzaton Laboratory, Central

More information

Wishing you all a Total Quality New Year!

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

More information

Proper Choice of Data Used for the Estimation of Datum Transformation Parameters

Proper Choice of Data Used for the Estimation of Datum Transformation Parameters Proper Choce of Data Used for the Estmaton of Datum Transformaton Parameters Hakan S. KUTOGLU, Turkey Key words: Coordnate systems; transformaton; estmaton, relablty. SUMMARY Advances n technologes and

More information

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

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

More information

Faces Recognition with Image Feature Weights and Least Mean Square Learning Approach

Faces Recognition with Image Feature Weights and Least Mean Square Learning Approach Faces Recognton wth Image Feature Weghts an Least Mean Square Learnng Approach We-L Fang, Yng-Kue Yang an Jung-Kue Pan Dept. of Electrcal Engneerng, Natonal Tawan Un. of Sc. & Technology, Tape, Tawan Emal:

More information

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

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

More information

Lecture 4: Principal components

Lecture 4: Principal components /3/6 Lecture 4: Prncpal components 3..6 Multvarate lnear regresson MLR s optmal for the estmaton data...but poor for handlng collnear data Covarance matrx s not nvertble (large condton number) Robustness

More information

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

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

More information

Unsupervised Learning

Unsupervised Learning Pattern Recognton Lecture 8 Outlne Introducton Unsupervsed Learnng Parametrc VS Non-Parametrc Approach Mxture of Denstes Maxmum-Lkelhood Estmates Clusterng Prof. Danel Yeung School of Computer Scence and

More information

Data Mining For Multi-Criteria Energy Predictions

Data Mining For Multi-Criteria Energy Predictions Data Mnng For Mult-Crtera Energy Predctons Kashf Gll and Denns Moon Abstract We present a data mnng technque for mult-crtera predctons of wnd energy. A mult-crtera (MC) evolutonary computng method has

More information

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

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

More information

Solving two-person zero-sum game by Matlab

Solving two-person zero-sum game by Matlab Appled Mechancs and Materals Onlne: 2011-02-02 ISSN: 1662-7482, Vols. 50-51, pp 262-265 do:10.4028/www.scentfc.net/amm.50-51.262 2011 Trans Tech Publcatons, Swtzerland Solvng two-person zero-sum game by

More information

3. CR parameters and Multi-Objective Fitness Function

3. CR parameters and Multi-Objective Fitness Function 3 CR parameters and Mult-objectve Ftness Functon 41 3. CR parameters and Mult-Objectve Ftness Functon 3.1. Introducton Cogntve rados dynamcally confgure the wreless communcaton system, whch takes beneft

More information

X- Chart Using ANOM Approach

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

More information

Concurrent Apriori Data Mining Algorithms

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

More information

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

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

More information

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

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

More information

A New Token Allocation Algorithm for TCP Traffic in Diffserv Network

A New Token Allocation Algorithm for TCP Traffic in Diffserv Network A New Token Allocaton Algorthm for TCP Traffc n Dffserv Network A New Token Allocaton Algorthm for TCP Traffc n Dffserv Network S. Sudha and N. Ammasagounden Natonal Insttute of Technology, Truchrappall,

More information

Comparison of Heuristics for Scheduling Independent Tasks on Heterogeneous Distributed Environments

Comparison of Heuristics for Scheduling Independent Tasks on Heterogeneous Distributed Environments Comparson of Heurstcs for Schedulng Independent Tasks on Heterogeneous Dstrbuted Envronments Hesam Izakan¹, Ath Abraham², Senor Member, IEEE, Václav Snášel³ ¹ Islamc Azad Unversty, Ramsar Branch, Ramsar,

More information

Some material adapted from Mohamed Younis, UMBC CMSC 611 Spr 2003 course slides Some material adapted from Hennessy & Patterson / 2003 Elsevier

Some material adapted from Mohamed Younis, UMBC CMSC 611 Spr 2003 course slides Some material adapted from Hennessy & Patterson / 2003 Elsevier Some materal adapted from Mohamed Youns, UMBC CMSC 611 Spr 2003 course sldes Some materal adapted from Hennessy & Patterson / 2003 Elsever Scence Performance = 1 Executon tme Speedup = Performance (B)

More information

An Iterative Solution Approach to Process Plant Layout using Mixed Integer Optimisation

An Iterative Solution Approach to Process Plant Layout using Mixed Integer Optimisation 17 th European Symposum on Computer Aded Process Engneerng ESCAPE17 V. Plesu and P.S. Agach (Edtors) 2007 Elsever B.V. All rghts reserved. 1 An Iteratve Soluton Approach to Process Plant Layout usng Mxed

More information

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

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

More information

CS 534: Computer Vision Model Fitting

CS 534: Computer Vision Model Fitting CS 534: Computer Vson Model Fttng Sprng 004 Ahmed Elgammal Dept of Computer Scence CS 534 Model Fttng - 1 Outlnes Model fttng s mportant Least-squares fttng Maxmum lkelhood estmaton MAP estmaton Robust

More information

Private Information Retrieval (PIR)

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

More information

TN348: Openlab Module - Colocalization

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

More information

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

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

More information

Improving the Accuracy of Iris Recognition System using Neural Network and Particle Swarm Optimization

Improving the Accuracy of Iris Recognition System using Neural Network and Particle Swarm Optimization Improvng the Accuracy of Irs Recognton System usng Neural Netork an Partcle Sarm Optmzaton Nuzhat Faz Shakh, Department of Computer Engneerng, M.E.S. College of Engneerng, Pune, Ina D. D. Doye, Ph.D Department

More information

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

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

More information

Degree-Constrained Minimum Spanning Tree Problem Using Genetic Algorithm

Degree-Constrained Minimum Spanning Tree Problem Using Genetic Algorithm Degree-Constraned Mnmum Spannng Tree Problem Usng Genetc Algorthm Keke Lu, Zhenxang Chen, Ath Abraham *, Wene Cao and Shan Jng Shandong Provncal Key Laboratory of Network Based Intellgent Computng Unversty

More information

K-means Optimization Clustering Algorithm Based on Hybrid PSO/GA Optimization and CS validity index

K-means Optimization Clustering Algorithm Based on Hybrid PSO/GA Optimization and CS validity index Orgnal Artcle Prnt ISSN: 3-6379 Onlne ISSN: 3-595X DOI: 0.7354/jss/07/33 K-means Optmzaton Clusterng Algorthm Based on Hybrd PSO/GA Optmzaton and CS valdty ndex K Jahanbn *, F Rahmanan, H Rezae 3, Y Farhang

More information

Cluster Analysis of Electrical Behavior

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

More information

Problem Set 3 Solutions

Problem Set 3 Solutions Introducton to Algorthms October 4, 2002 Massachusetts Insttute of Technology 6046J/18410J Professors Erk Demane and Shaf Goldwasser Handout 14 Problem Set 3 Solutons (Exercses were not to be turned n,

More information

LECTURE NOTES Duality Theory, Sensitivity Analysis, and Parametric Programming

LECTURE NOTES Duality Theory, Sensitivity Analysis, and Parametric Programming CEE 60 Davd Rosenberg p. LECTURE NOTES Dualty Theory, Senstvty Analyss, and Parametrc Programmng Learnng Objectves. Revew the prmal LP model formulaton 2. Formulate the Dual Problem of an LP problem (TUES)

More information

K-means Clustering Algorithm in Projected Spaces

K-means Clustering Algorithm in Projected Spaces K-means Clusterng Algorthm n Projecte paces Alssar NAER, Dens HAMAD.A.. -U..C.O 50 rue F. Busson, BP 699, 68 Calas, France Emal: nasser@lasl.unv-lttoral.fr Chaban NAR ebanese Unversty E.F Rue Al-Arz, rpol

More information

Identifying Efficient Kernel Function in Multiclass Support Vector Machines

Identifying Efficient Kernel Function in Multiclass Support Vector Machines Internatonal Journal of Computer Applcatons (0975 8887) Volume 8 No.8, August 0 Ientfng Effcent Kernel Functon n Multclass Support Vector Machnes R.Sangeetha Ph.D Research Scholar Department of Computer

More information

Multi-objective Optimization Using Self-adaptive Differential Evolution Algorithm

Multi-objective Optimization Using Self-adaptive Differential Evolution Algorithm Mult-objectve Optmzaton Usng Self-adaptve Dfferental Evoluton Algorthm V. L. Huang, S. Z. Zhao, R. Mallpedd and P. N. Suganthan Abstract - In ths paper, we propose a Multobjectve Self-adaptve Dfferental

More information

The Research of Support Vector Machine in Agricultural Data Classification

The Research of Support Vector Machine in Agricultural Data Classification The Research of Support Vector Machne n Agrcultural Data Classfcaton Le Sh, Qguo Duan, Xnmng Ma, Me Weng College of Informaton and Management Scence, HeNan Agrcultural Unversty, Zhengzhou 45000 Chna Zhengzhou

More information

Quality Improvement Algorithm for Tetrahedral Mesh Based on Optimal Delaunay Triangulation

Quality Improvement Algorithm for Tetrahedral Mesh Based on Optimal Delaunay Triangulation Intellgent Informaton Management, 013, 5, 191-195 Publshed Onlne November 013 (http://www.scrp.org/journal/m) http://dx.do.org/10.36/m.013.5601 Qualty Improvement Algorthm for Tetrahedral Mesh Based on

More information

Correlative features for the classification of textural images

Correlative features for the classification of textural images Correlatve features for the classfcaton of textural mages M A Turkova 1 and A V Gadel 1, 1 Samara Natonal Research Unversty, Moskovskoe Shosse 34, Samara, Russa, 443086 Image Processng Systems Insttute

More information

Chinese Word Segmentation based on the Improved Particle Swarm Optimization Neural Networks

Chinese Word Segmentation based on the Improved Particle Swarm Optimization Neural Networks Chnese Word Segmentaton based on the Improved Partcle Swarm Optmzaton Neural Networks Ja He Computatonal Intellgence Laboratory School of Computer Scence and Engneerng, UESTC Chengdu, Chna Department of

More information

An Evolvable Clustering Based Algorithm to Learn Distance Function for Supervised Environment

An Evolvable Clustering Based Algorithm to Learn Distance Function for Supervised Environment IJCSI Internatonal Journal of Computer Scence Issues, Vol. 7, Issue 5, September 2010 ISSN (Onlne): 1694-0814 www.ijcsi.org 374 An Evolvable Clusterng Based Algorthm to Learn Dstance Functon for Supervsed

More information

K-means and Hierarchical Clustering

K-means and Hierarchical Clustering Note to other teachers and users of these sldes. Andrew would be delghted f you found ths source materal useful n gvng your own lectures. Feel free to use these sldes verbatm, or to modfy them to ft your

More information

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

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

More information

COLOR HISTOGRAM SIMILARITY FOR ROBOT-ARM GUIDING

COLOR HISTOGRAM SIMILARITY FOR ROBOT-ARM GUIDING COLOR HITOGRAM IMILARITY FOR ROBOT-ARM GUIDING J.L. BUELER, J.P. URBAN, G. HERMANN, H. KIHL MIP, Unversté e Haute Alsace 68093 Mulhouse, France ABTRACT Ths paper evaluates the potental of color hstogram

More information

AN EFFICIENT AND ROBUST GENETIC ALGORITHM APPROACH FOR AUTOMATED MAP LABELING

AN EFFICIENT AND ROBUST GENETIC ALGORITHM APPROACH FOR AUTOMATED MAP LABELING AN EFFICIENT AND ROBUST GENETIC ALGORITHM APPROACH FOR AUTOMATED MAP LABELING Fan Hong * Lu Kaun 2 Zhang Zuxun Natonal Laboratory of Informaton Engneerng n Surveyng Mappng and Remote Sensng of Wuhan Unversty

More information

Biostatistics 615/815

Biostatistics 615/815 The E-M Algorthm Bostatstcs 615/815 Lecture 17 Last Lecture: The Smplex Method General method for optmzaton Makes few assumptons about functon Crawls towards mnmum Some recommendatons Multple startng ponts

More information