Improving Ranking of Search Engines Results Based on Power Links

Size: px
Start display at page:

Download "Improving Ranking of Search Engines Results Based on Power Links"

Transcription

1 IPASJ Inernaional Journal of Informaion Technology (IIJIT) Web Sie: hp:// A Publisher for Research Moivaion... edioriiji@ipasj.org Volume 2, Issue 9, Sepember 2014 ISSN Improving Ranking of Search Engines Resuls Based on Power Links Mahmoud Rokaya College of Compuer and Informaion Technology, Taif Universiy, Taif, Saudi Arabia Permanen Address: Faculy of Science, Tana Universiy, Tana, Egyp ABSTRACT Informaion rerieval (IR) involves finding some desired informaion in a sore of informaion or a daabase. Despie here are as many as mehods of informaion rerieval bu here is few mehods of rerieval which considered a cusom rerieval ha depends on he relaionships beween insered words and oher words in he same domain of he insered words. Even he mehods ha ried o rely on he relaion beween keywords, hey followed hese key words blindly wihou any analysis o he acual relaions beween hese key words or oher relaed key words. Power Link aims a finding he relaion beween conceps, ideas and problems in a specific discipline. The power link algorihm was suggesed o measure how ow erms end o appear ogeher in a given corps. This work will presen a mehod o find relaions beween erms depending on Power Link. Power link is used o exrac se of linked erms for a given query based on he relaion beween he curren query and he previous one. A ranking scheme is used o filer he se of linked erms. The power links beween he documens ha appear in he search resuls and he filered se of linked erms combined wih erms in he query is used as a measure for ranking he search resuls. Terms in he filered se are given a differen weigh depending on is ype. The resuls of experimens reflec an improving in precision for he proposed mehod comparing o he ordinary approaches. Keywords:-Co-ciaion, Co-word Analysis; Informaion rerieval; Word co-occurrence; Power Link, Informaion Rerieval, Ranking, Learning o Rank. 1. INTRODUCTION The concep of he link relaed o co-word analysis sudies. Co-word analysis is a conen analysis echnique ha uses paerns of co-occurrence of pairs of iems (i.e., words or noun phrases). Indexes based on he co-occurrence frequency of iems, such as an inclusion index and a proximiy index, are used o measure he srengh of relaionships beween iems. Based on hese indexes, iems are clusered ino groups and displayed in nework maps. Co-word analysis considers he dynamics of science as a resul of acor sraegies. Changes in he conen of a subjec area are he combined effec of a large number of individual sraegies. This echnique should allow us in principle o ideniy he acors and explain he global dynamic [9; 10; 11 and 23]. Many sudies concenraed on he imporance of a single erm or compound erm. Some sudies deermined he opic of a documen or a par in a documen based on he populariy of single erms, hose erms are called Field Associaion erms. [7; 13; 20; 19; 21 and 22]. Field associaion erms (FA erms) are he erms ha indicae each subjec maer caegory in he classificaion scheme [12]. Field means a basic and common knowledge ha can be used in human communicaion [5; 6 and 22]. All hese previous mehods depend on he absolue frequency of he individual erms or he posiion of he erm inside he documens. Using he absolue frequency means ha he frequency of a erm will reflec he lengh of he documens raher han he weighs of erms. Also depending on he frequency only, as a ool o decide he fields of he erms, wases valuable informaion ha can be derived from he co-occurrence relaions beween erms. Rokaya e. al., 2008, presened a mehod o cluser and rank he erms in a given corps based on co-ciaion analysis [17 and 22]. Cociaion analysis depends on he co-frequency of wo erms regardless he posiions of insances of each erm in a given documen. Rokaya e., al., 2010, presened he power link algorihm which defined and measured he relaion beween wo erms based on he co-frequency and he relaive posiions of differen insances. The link power become bigger for hose erms ha have nearer relaive posiions [23; 25 and 26]. All hese previous mehods depend on he absolue frequency of he individual erms or he posiion of he erm inside he documens. Using he absolue frequency means ha he frequency of a erm will reflec he lengh of he documens raher han he weighs of erms. Also depending on he frequency only wases valuable informaion ha can be derived from he co-occurrence relaions beween erms. Bu he co-occurrence calculaions should no only depends on he co-frequency bu also depends on he relaive posiions of differen insances of he wo Volume 2, Issue 9, Sepember 2014 Page 1

2 IPASJ Inernaional Journal of Informaion Technology (IIJIT) Web Sie: hp:// A Publisher for Research Moivaion... edioriiji@ipasj.org Volume 2, Issue 9, Sepember 2014 ISSN erms. Power Link ha couns and analysis he co-occurrence of key erms in a corps based on co-occurrence and relaive disribuions of erms on a given subjec will be used o measure he relaions among a seleced sample of erms. Insead of depending on populariy of single erms or populariy of web pages o deermine he imporance of resuling documens wih respec o a given query, he new mehod ranks he documens depending on he populariy of he link beween erms in a query, erms in previous query and erms in he documens. The links map for a given corps is pre-calculaed. For a given query he proper erms are exraced and he linked lis of hese erms are filered and he ranking scheme is used o calculae he power link beween he resuling documens and he combinaion lis of query erms and he filered linked se of erms. The power link in he sum of each erm is give a double weigh for he new erms, negaive weigh for he removed erms and one for coninued erms. The resuled show ha he proposed mehod performing abou 25% in precision beer han he ordinary approach [27]. The remaining pars of his work are organized as follows: secion 1 discusses he idea of his paper and compares he expeced effec of using he resuls of his sudy in rerieval procedure. Secion 2 discusses he deails of he Power Link seps used in his sudy and is resuls. Secion 3 presens an arranging scheme for resuls of queries depending on resuls of secion 2. Secion 4 presens an evaluaion experimen for he approach presened in secion 3 finally secion 5 presens he conclusion and possible fuure work. 2. RETRIEVAL SYSTEM BASED POWER LINK Similar ex searching calculaes he degree of similariy beween he user's ex inpu and he daabase exs. A ex wih a high degree of similariy becomes oupu search resul Some mehods used in search engines show resuls in arranging ha reflec he degree of similariy beween query and documens. The documen ha has a highes similariy wih he query come firs hen he documen ha has smaller similariy ill reaching he one wih he smalles similariy wih he query o be shown a las. Oher common arranging mehod is erm frequency/inverse documen frequency. This mehod considers he disribuion of words and heir frequencies, hen generaes numerical weighs for words ha signify heir imporance in individual documens. Words ha are frequen (such as " or," " o" or " wih") or ha appear in many documens are given subsanially less weigh han words ha are more relevan semanically or appear in comparaively few documens. In addiion o erm weighing. Finally pages can be ranked using link analysis ha considers he naure of each page in erms of is associaion wih oher pages namely, by he number of oher pages ha poin o i or a hub by he number of pages i poins o [2; 3; 4; 8; 14; 15; 16 and 18]. Since all hese mehods depend on he absolue frequency of words in he query and documens or link analysis, hen arranging resuls according o hese mehods ignore compleely he relaions beween words in he query and he resuls ha may be irrelevan come in he firs. Also ordinary mehods in compuing similariy beween exs and user queries use he whole words available in he queries and exs, his rend is inefficien for processing large ex in heerogeneous subjec areas. Rokaya e., al., 2008, presened an arranging scheme of search resuls,ha considers relaions beween FA erms in he query,. The sysem picks he FA erms from he query hen make a ranking of hese FA erms, depending on his ranking he query resuls arranged [22]. Depending on cofrequency o deermine he relaion beween wo erms gives a wrong implicaion, especially, when he insances of he erms are disribued over a separaed pars in he same documens. Rokaya & Alam, 2010, proposed a he power link algorihm o deermine he relaion beween wo erms depsending on he co-frequency normalized by he average disance beween differen insances of he wo erms [23]. In his paper he concep of power link will be used o ge he lis of op relaed erms o he curren query. A ranking scheme will use he query erms and he relaed erms o rank he search resuls. Fig. 1 shows a similar ex search of inpu ex file and daabase ex files and heir rerieval resuls for new mehod which considers index of words links based on Power Link 3. POWER LINKS The erm power link was proposed by Rokaya and Alam, 2010, as a mehod of building dynamic field associaion erms dicionary. Power link algorihm presened new rules o improve he qualiy of filed associaion erms (FATs) dicionary in English [24]. The origin of his concep comes from he co-word analysis researches. Co-word analysis considers he dynamics of science as a resul of acor sraegies changes in he conen of a subjec area are he combined effec of a large number of individual sraegies. This echnique should allow us in principle o ideniy he acors and explain he global dynamic [1]. Volume 2, Issue 9, Sepember 2014 Page 2

3 IPASJ Inernaional Journal of Informaion Technology (IIJIT) Web Sie: hp:// A Publisher for Research Moivaion... edioriiji@ipasj.org Volume 2, Issue 9, Sepember 2014 ISSN Figure 1: A similar ex search of inpu ex file and daabase ex files and heir rerieval resuls for ordinary ex dealing mehods and for new mehod. Fig.2 explains he phases of calculaing power links. The calculaions are a chain of subsequen calculaions which ends by calculaing he power link beween a erm and a field which based on calculaing he power link beween a erm and a documens conained in ha field. Power link beween a erm and a documen based on calculaing he power link beween his erm and oher erms conained in he documen. If any wo erms 1 and 2 belongs o a documen D i will be said ha here is a link beween 1 and 2. The power of his link is measured by he funcion LT ( 1, 2) where where D is he number of differen erms in he documen D, cr ( 1, 2 ) is he co-occurrence frequency of 1 and 2 in he documen D and average L( 1i, 2 j ) represens he average disance beween any insans 1 i and 2 j of he erms 1 i, j D cr( 1, 2 ) LT ( 1, 2 ) (1), average L( 1 j, 2 j ) i, j and 2 in he documen D. For more deails see Rokaya and Alam, To esimae he power like beween wo erms 1 and 2 over a given corps, he funcion LCORPS 1, ) is defined. where: LCORPS ( 2 ( 1, 2 ) average LT ( 1, 2 D corps ) (2) This funcion saes ha he erms 1 and 2 will end o appear nearer ogeher if he value of his funcion reasonably high. To give a hreshold many values were experimenally has been ried around he mean value for he power link. This means ha he hreshold is no unique and i is dynamic. In fac i is dependen on he given corps. For he experimens he mean value was 31.5 so he algorihm is acivaed wih values around his mean o cover he inerval (mean-std, mean+std), where STD is he sandard deviaion of he mean value. Volume 2, Issue 9, Sepember 2014 Page 3

4 IPASJ Inernaional Journal of Informaion Technology (IIJIT) Web Sie: hp:// A Publisher for Research Moivaion... edioriiji@ipasj.org Volume 2, Issue 9, Sepember 2014 ISSN Field Docum w, w, 1 2 Candidae erm W Power Link Power Link beween a Figure2. Power link overview Power Link beween a 4. POWER LINK ANALYSIS Figure 3 summarizes he seps of he power link analysis; he inpus of he sysem are documens and lis of erms, he oupus of he sysem are clusers of erms and he power links map beween erms. The analysis goes hrough seps, namely, power link marix, normalized marix and he linking marix. These ge heir names according o he oupu of he sep. The nex subsecions explains he meaning and deails of each sep. 4.1 Power Link Marix The corpus (7850 aricle, 36.7 MB) was go from WWW newspapers and Nuriion sies. This corpus was chosen o be disribued over 11 sub-fields of he field Nuriion. A folder for each sub-field was esablished and he documens for his sub-field are sored in ha folder. A random sample of hese documens (281) was chosen o represen he daabase ha will be used in he Power Link and he whole corpus will be used in he evaluaion experimens. The erms exraced from his corpus auomaically were 1572 erms. 4.2 Normalized Power Link Marix Figure3. Overview of power link analysis seps To generae he power links marix. a C code o calculae he weigh for each erm in he lis in every documen in he corpus. The comparison beween every erm and every oken was made according o sem of each. The following formula was used o calculae he weigh W for a erm x in a documen k is derived from he classic known xk formula TF*IDF of Salon. The power link beween wo erms is calculaed using formula (2). The second sep is o presen he resuls o anoher C code ha calculae he Normalized Power Links. The inpu of his program is he erms lis and heir Power Links in he corpus. The oupu of he program is A symmeric marix, he cell in row x and column y represens he correlaion facor r beween each wo erms in he lis. Since each erm is presened in he power link marix by a row hen o unify he effec of numbers in his marix, i is needed o normalize he number in he marix o be wihin a specific inerval. The bes inerval is [1, -1] and he bes known measure o be used is he Volume 2, Issue 9, Sepember 2014 Page 4

5 IPASJ Inernaional Journal of Informaion Technology (IIJIT) Web Sie: hp:// A Publisher for Research Moivaion... edioriiji@ipasj.org Volume 2, Issue 9, Sepember 2014 ISSN correlaion facor. Hence correlaion facor beween erms is used and replaced in he cell corresponding o he same erms. 4.3 Linking Marix The linking marix is a symmeric marix. The cell in row X and column Y represen he cosine beween vecors X and Y in he normalized power marix. If he angle beween correlaion vecors of keyword x and keyword y was less han a given hreshold hen here is a link beween x and y. A hreshold o deermine if here is a link is used. The value of his hreshold is dynamic. For a given corps many rials is done o deermine he bes hreshold value. Tile, Auhors, Body Paragraphs, Secions Headings and References 4.4 Clusers and Links Map The Normalized Power Link marix is presened o a saisical program and wards mehod is used o produce he clusers. The final sep is o arrange he erms according o number of links hen he sum of power links hen according o he oal frequency. Table 1 shows a sample of he arranged erms according o his scheme. In his able erms beauy nuriion and spors nuriion has he same number of links and belong o he same cluser bu he sum of power links of beauy nuriion is greaer han he sum of co-occurrence frequencies of spors nuriion so beauy nuriion ge a higher rank han spors nuriion. Comparing ranking of erms Table 1 in conras of ranking in Table 2 ha depend only on he oal frequency, we will find ha he ranking is differen since he oal frequency does no reflec he acual disribuion of he word among he whole documens, also he relaions beween erms canno be refleced using he oal frequency of he individual erms only. This shows ha he new mehod is more efficien o achieve he correc ranking o erms based on Power Link 5. RANKING SCHEME The deails of his scheme can be summarized as follows: When a user eners a new query, he erms in he curren query is compared o he erms in he previous query o deermine which erms are removed ( TR se), coninued ( TC se) and added ( TN se). These ses are saved and labeled for more processing laer. Le G be he union of erms ha have links wih erms from he ses TC, TR, and TN. Suppose, for simpliciy, ha G 1, 2,..., 10. Table1: Terms ranking using Power Link Table 2: Terms ranking using oal frequency Term No. links Of sum of power links Toal frequency Term Toal frequency nuriion viamins supplemens 4157 viamins nuriion food 2187 supplemens supplemens 1032 viamins supplemens nuriion healh 1024 nuriion facs nuriion facs 969 nuriion healh beauy nuriion 925 spors nuriion nuriion die 903 beauy nuriion spors nuriion 803 nuriion informaion nuriion sofware 787 Volume 2, Issue 9, Sepember 2014 Page 5

6 IPASJ Inernaional Journal of Informaion Technology (IIJIT) Web Sie: hp:// A Publisher for Research Moivaion... edioriiji@ipasj.org Volume 2, Issue 9, Sepember 2014 ISSN nuriion food nuriion info 632 proein viamins 591 nuriion die nuriion whey 576 opimum nuriion proein 512 nuriion info nuriion informaion 405 nuriion whey opimum nuriion 395 nuriion sofware nuriion 338 By checking he disribuion of elemens of G over classes, one can rerieve o which class each erm in G belongs. Suppose, as appear in Fig. 4, he erms of G are disribued as follows: 1, 2, 3, 4 C1, 5, 6, 7, 8 C2 and 9, 10 C 3. The doed line beween wo erms, in Fig. 4, indicaes ha here is a link beween hese erms. If a erm has no links, his erm is called an isolaed erm. All isolaed erms are eliminaed from he resuling group FG. In Fig. 4, he erms 4 and 8 have no links wih oher erms, hence 4 and 8 are eliminaed from FG. Also, he erms 9 and 10 has a links wih erms ouside heir own class bu boh erms has no links wih oher elemens from G in heir own class. So, boh elemens are removed from he filered se FG. Now reurning o he original ses TR, TN and TC, erms in FG are classified ino hree ses. LTN is he se of elemens in FG and have a sronger link o TN, LTC is he se of elemens in FG and have a sronger link o TC and LTR is he se of elemens in FG and have a sronger link o TR. The erm "sronger" means ha he sum of power links beween a given erm and a se is he maximum among oher groups. Now, by knowing he ses ( TR, TC, TN ) and ( LTR, LTC, LTN ) one can wrie he equaion of calculaing he ranking facor ( RF ) for a given documens D ha appears in he search resuls for he curren query Q Prev ious Normalize d Linked C2 Que G={T TLN, TLC, C1 C1 G 9 C Figure.4 Overview of Ranking Scheme Volume 2, Issue 9, Sepember 2014 Page 6

7 IPASJ Inernaional Journal of Informaion Technology (IIJIT) Web Sie: hp:// A Publisher for Research Moivaion... edioriiji@ipasj.org Volume 2, Issue 9, Sepember 2014 ISSN RF Q, D * LT(, 2) * LT ( 1, 2) * (3) 1 LT ( 1, 2) TC LTC, D TN LTN, D TR LTR D , 2 Where, and belong o [-1,1]. In our experimens, he values assigned o, and were 0.5, 1 and -0.5 respecively. Example: Consider he query: "Viamins organic", assume ha he previous query of ha query was: "Organic minerals". Applying he conceps of ranking scheme we ge: TR ={ minerals }, TC ={ organic } and TN ={ Viamins }. Now we search he links map o rerieve he se of links G which has links wih he elemen in he se{ minerals, organic, organic}. G ={ subsances, plans, animals, inorganic, elemens }. By rerieving he class of each erm, one found ha {plans, animals} in one class and {subsances, inorganic, elemens} in anoher class and here are links beween all of hem. So he calculaions should consider all hese erms and FG = G ={ subsances, plans, animals, inorganic, elemens }. By calculaing he power link beween each elemen and he ses TR, TC and TN we found ha LTN = {plans, animals}, LTR ={subsances, elemens} and LTC ={inorganic}. Now he documens ha a big power link wih erms {Viamins, Plans, animals} will ge a high prioriy o come a he op of he resuls where documens ha have a big power link wih he erms {minerals, subsances, elemens} will come a he ail of he resuls. This shows ha he rank of a given documens will depend on he links map of erms ha his documen conains and also will depend on he user decision o refine he search by adding or removing erms. The removed and heir linked erms will give a negaive weigh for documens ha conain hese erms and will affec heir appearance order in he search resuls as expeced from such scheme. 6. EXPERIMENTS AND RESULTS. In his circumsance, one asks himself how o es his mehod, why i is expeced o give beer resuls han oher mehods. One of he keys of his issue is he relaion beween he se of erms in he query Q, erms in he se G and erms in he se FG. FG is a funcion is in Q and G, G iself is a funcion in Q and PQ FG F 1( G ) and FG F2 ( Q, PQ). The parameers of boh funcions F1 and F2 are he links map and he cluser. The F qualiy of he links map and he clusers leads direcly o he qualiy of he funcions 1 and F 2. So, i is needed o design experimens o check he qualiy of linking and clusering processes. From he oher hand i is imporan o check he validiy of he ranking process iself. This discussion leads us direcly o wo ses of experimens (a) Experimens o check he qualiy of links and clusers (b) Experimens o evaluae ranking process. 6.1 Experimens o check he qualiy of links and clusers Assuming ha a human would be able o idenify he clusers and links map for a given erm. If he se of linked erms for each erm derived by he auomaic sysem has a high overlap wih he human derived ses and if he classes derived by he sysem have a high overlap wih he classes derived by he human, he auomaic mehod should regarded as effecive. In all experimens, wo manually exraced ses are generaed. In boh cases he user is asked o classify he given erms in disjoin classes and deermine which erms should be linked or appear in he linked lis of a given erm. The evaluaion akes he following form: A user walks o he sysem and picks a se of erms. The erms are disribued randomly in ses and he user is asked o pick one of hem. The user is asked o classify hese erms in a specific number of disjoin classes. Also he user is asked o lis he linked erms o each erm in his se. Anoher manual classificaion is prepared by anoher user. The curren user is asked o compare his own resuls o he oher user resuls and refine his resuls if he wans or o approve his resuls. In he second case, he sysem generaes he clusers and he linked lis for each erm using our proposed mehod o ge he auomaic one. In boh cases, he user saisfacion is measured by he number of common clusers and commen linked liss for each erm beween his own resuls and he arge se (manually or auomaically derived). A random classificaion and derivaion of linked liss is done by randomly disribuing he erms in a disjoin classes and he lis of linked ses are derived for each ermed randomly based on he number of common characers Volume 2, Issue 9, Sepember 2014 Page 7

8 IPASJ Inernaional Journal of Informaion Technology (IIJIT) Web Sie: hp:// A Publisher for Research Moivaion... edioriiji@ipasj.org Volume 2, Issue 9, Sepember 2014 ISSN in each erm. If wo erms have a common hree characers hey should be added o he lis of each oher regardless he order of he characers in each erm. This mehod is called he random mehod Iniial: Anoher mehod depends on arranging he erms in each group in ascending manner. To ge he clusers of he erms, he oal number of erms is couned; he number of erms in each class is he oal number of erms divided by he number of required clusers. Le he number of erms in each class o be r, he firs r in he ordered se represens he firs class, he second r in he ordered se represen he second class and so on. To ge he linked lis for each group for a given erm. In he ordered group consider ha he nex erm of he las erm is he firs erm. The linked lis for a given erm is he r / 2 previous erms and he r / 2 nex erms in he ordered group. This mehod is called iniial mehod. Fify groups were chosen for he evaluaion process. Table 3. Evaluaion of power link clusering and linking Evaluaion for Deriving Clusers Evaluaion for Deriving Linked Liss Overlap beween manual clusers: 85.7 % Overlap beween manual Linking: 83.6 % Algorihm Cluser1 Cluser2 Average Linked Lis1 Linked Lis2 Average Power link 83.92% 72.26% 78.09% 73.92% 79.26% 76.59% Random 53.74% 48.36% 51.05% 51.74% 42.36% 47.05% Iniial 60.42% 54.67% 57.55% 58.34% 51.61% 54.98% The overlapping beween he wo manual clusers and he linked liss were 85.7 % and 83.6 % respecively which were expeced. Table 3 summarizes he resuls of he experimens which represens he overlapping for clusers and linked liss beween he auomaic and he manual mehods. From his able, he auomaic mehod does beer han he random and he iniial mehods. The resuls for he power link mehod were 83.92% and 72.26%, he average is 78.09% for clusers. The resuls for he power link mehod were 73.92% and 79.26%, he average is 76.59% for clusers. These resuls proof ha he proposed mehod is fine and gave a considered performance han he iniial and random mehods. 6.2 Experimens o evaluae ranking process For comparison beween ordinary approach and he new one. The precision was calculaed according o he following equaions. No. of relevan documens among he firs op resuls Precision (4) Number of firs op resuls Ten differen users are asked o use he new mehod and oher mehods in he search process. Each user eners 10 subsequen queries in a specific subjec. Each ime he user adds and removes some erms o refine he resuls. The search resuls for every query are saved in a separaed folder. For every query he firs 100 resuls are considered o be he se D ha he arranging scheme will be applied on i. Afer geing he arranged se he number of relevan documens among he firs 50 resuls of he se D was couned before and afer he arranging process. In his experimen, number of firs op resuls is equal o 50. For his experimen, 10 queries are designed and presened o each user. Each query was designed o reflec one and only one subjec in he field Nuriion. Since of he users is an exper in Nuriion field, each user was asked o refine his queries gradually by adding new erms and removing some erms. In each sep, user saisfacion is measured using he precision measure in formula (4). The experimens were done over a corps consiss of 9740 aricles exraced from newspaper, Nuriion secion. (56.7 MB). Figure 5 shows he comparison beween he precision of he ordinary and he new approach. In his figure each poin represens he average of each user resuls. The number of relevan documens increased for all users wih differen raio. Also he average of relevan number of documens afer applying he arranging scheme was documens and he average of relevan number of documens before applying he arranging scheme was documens. These resuls show ha based on he proposed arranging scheme and ranking process for he erms a beer arranging of search resuls be achieved. Volume 2, Issue 9, Sepember 2014 Page 8

9 IPASJ Inernaional Journal of Informaion Technology (IIJIT) Web Sie: hp:// A Publisher for Research Moivaion... edioriiji@ipasj.org Volume 2, Issue 9, Sepember 2014 ISSN Figure 5: The resul of comparison beween he precision for he firs fify resuls before and afer applying he arranging scheme using he absolue frequency and TF*IDF frequency The average precision for he new approach was 78.37%whereas he precision for he ordinary approach was 53.32%. This means ha he new approach achieved a beer precision han he ordinary approach by 25.05% The comparison beween he precision of he ordinary and he new approach. show ha he average of relevan number of documens afer applying he arranging scheme was documens and he average of relevan number of documens before applying he arranging scheme was documens. These resuls show ha based on he proposed arranging scheme and ranking process for he erms a beer arranging of search resuls can be achieved. The average precision for he new approach was 78.37%whereas he precision for he ordinary approach was 53.32%. This means ha he new approach achieved a beer precision han he ordinary approach by 25.05% 7. CONCLUSION AND RECOMMENDATIONS In his work Power Link was used o develop a mehod o rank erms in Nuriion field. From he experimenal resuls i is clear ha he ranks of erms using frequency is oally differen from using ranking using Power Link, since he frequency does no reflec he acual disribuion of he word among he whole daa. Also ranking was inroduced o he search engine o achieve a beer rerieval ha considers he relaions beween erms. The new approach using Power Link performing abou 25% in precision beer han he ordinary approach. Also he ranking algorihm refines he ranking of subsequen query resuls depending of he feedback of he user which can be followed hrough adding and removing or oally changing he erms included in he query. REFERENCES [1] Bursein, J., Kukich, K., Wolff, S., Lu, C., Chodorow, M., Harder, L., Harris. M. D., (1998). Auomaed scoring using a hybrid feaure idenificaion echnique. In ACL/COLING 98, Proceedings of he 36h Annual Meeing of he Associaion for Compuaional Linguisics [2] Hofmann, T. (2000). Learning probabilisic models of he Web. In Proceedings of he 23rd ACM SIGIR, pp [3] Lempel, R., & Moran, S. (2000). The sochasic approach for link-srucure analysis (SALSA) and he TKC effec. In Proceedings of he 9h Inernaional WWW Conference, Amserdam, The Neherlands, pp [4] Hofmann, T. (2000). Learning probabilisic models of he Web. In Proceedings of he 23rd ACM SIGIR, pp [5] Lempel, R., & Moran, S. (2000). The sochasic approach for link-srucure analysis (SALSA) and he TKC effec. In Proceedings of he 9h Inernaional WWW Conference, Amserdam, The Neherlands, pp [6] Charles T. M., Ber R. B., (2000), Donald H. Kraf. Tex informaion rerieval sysems. Academic Press. London. [7] Fukea, M., Lee, S., Tsuji, T., Okada, M., Aoe, J. I., (2000). A documen classificaion mehod by using field associaion words. Informaion Science, 126, [8] Ng, Y., Zheng, X., & Jordan, I. (2001). Sable algorihms for link analysis. In Proceedings 24h Annual Inl. ACM SIGIR Conference, New Orleans, Louisiana, U.S, pp [9] Ding, Y., Gobinda G., Foo S., (2001). Bibliomeric carography of informaion rerieval research by using Power Link. Informaion Processing and Managemen, 37, Volume 2, Issue 9, Sepember 2014 Page 9

10 IPASJ Inernaional Journal of Informaion Technology (IIJIT) Web Sie: hp:// A Publisher for Research Moivaion... edioriiji@ipasj.org Volume 2, Issue 9, Sepember 2014 ISSN [10] Panel, P., Lin, D. (2002). Discovering word senses from ex. In ACM SIGKDD Conference on Knowledge Discovery and Daa Mining, Edmonon, Canada. [11] Ruhven, I. and Lalmas, M., van Rijsbergen, C. J., (2002). Combining and selecing characerisics of informaion use. Journal of he American Sociey for Informaion Science and Technology, 53, 5, CI24 [12] Lee, S., Shishibori, M., Sumiomo, S., Aoe, J. I., (2002). Exracion of field-coheren passages. Informaion Processing and Managemen, 38, [13] Alam El-S., M. Fukea, K. Moria, Aoe, J. I., (2003). Documens similariy measuremen using field associaion erms. Informaion Processing and Managemen, 39, [14] Chakrabari, S. (2003). Mining he Web: Analysis of Hyperex and Semi Srucured Daa Mining he Web: Analysis of Hyperex and Semi Srucured Daa. Morgan Kaufmann. [15] Tomlin, A. (2003). A new paradigm for ranking pages on he WWW. In Proceedings of he 12h Inernaional World Wide Wed Conference, Budapes, Hungary, pp [16] C. Tomlin, I. Michell, A. Bayen, and M. Oishi, Compuaional Techniques for he Verificaion and Conrol of Hybrid Sysems, Proceedings of he IEEE, Volume 91, Number 7, pp , July [17] Chakrabari, S. (2003). Mining he Web: Analysis of Hyperex and Semi Srucured Daa Mining he Web: Analysis of Hyperex and Semi Srucured Daa. Morgan Kaufmann. [18] Gull A., (2006). On Two Web Informaion rerieval Boosing Tools: Clusering and Ranking, PhD hesis, Degli Sudi di Pisa. Universiy. [19] Alam, El-S. Elmarhomy G., Moria K., Fukea, M., Aoe J. I., (2006). Auomaic Building of New Field Associaion Word Candidaes Using Search Engine. Informaion Processing & Managemen Journal, 42, 4, [20] Elmarhomy G., Alam, El-S. Fukea, M., Moria K., Sumiomo, T., Aoe J. I., (2006). Auomaic Deleion of Unnecessary Field Associaion Word Using Morphological Analysis. Journal of Compuer and Mahemaics, 83, 3, [21] Mahmoud Rokaya, Elsayed Alam, Masao Fukea, Tshering C. Dorji and Jun-ichi Aoe, Ranking of field associaion erms using Co-word analysis, Third Inernaional Compuer Engineering conference, Cairo Universiy, December 26-27, 2007 CI19- [22] Mahmoud Rokaya, Elsayed Alam, Masao Fukea, Tshering C. Dorji and Jun-ichi Aoe, Ranking of field associaion erms using Co-word analysis, Informaion Processing & Managemen, Volume 44, Issue 2, March 2008, Pages [23] Mahmoud Rokaya and Alam, E-S. (2010) Building of field associaion erms based on links, In. J. Compuer Applicaions in Technology, Vol. 38, No. 4, pp [24] Mahmoud Rokaya and Abdallah Nahla, (2011), Building a Muli-lingual Field Associaion Terms Dicionary, Inernaional Journal of Compuer Science and Nework Securiy, Vol. 11 No. 3 pp , [25] Mahmoud Rokaya, AbdAllah Nahla, Sulan Aljahdali, (2012), Conex-Sensiive Spell Checking Based on Field Associaion Terms. IJCSNS Inernaional Journal Of Compuer Science And Nework Securiy. Vol. 12 No. 3 pp , [26] Mahmoud Rokaya, Auomaic Summarizaion based on Field Coheren Passages. Inernaional Journal of Compuer Applicaions 79(9):38-44, Ocober Published by Foundaion of Compuer Science, New York, USA [27] Mahmoud Rokaya, (2013), Auomaic Tex Exracion Based on Field Associaion Terms and Power Links, Inernaional Journal of Compuer and Informaion Technology (IJCIT). Volume 2, Issue 9, Sepember 2014 Page 10

Handling uncertainty in semantic information retrieval process

Handling uncertainty in semantic information retrieval process Handling uncerainy in semanic informaion rerieval process Chkiwa Mounira 1, Jedidi Anis 1 and Faiez Gargouri 1 1 Mulimedia, InfoRmaion sysems and Advanced Compuing Laboraory Sfax Universiy, Tunisia m.chkiwa@gmail.com,

More information

A Matching Algorithm for Content-Based Image Retrieval

A Matching Algorithm for Content-Based Image Retrieval A Maching Algorihm for Conen-Based Image Rerieval Sue J. Cho Deparmen of Compuer Science Seoul Naional Universiy Seoul, Korea Absrac Conen-based image rerieval sysem rerieves an image from a daabase using

More information

Analysis of Various Types of Bugs in the Object Oriented Java Script Language Coding

Analysis of Various Types of Bugs in the Object Oriented Java Script Language Coding Indian Journal of Science and Technology, Vol 8(21), DOI: 10.17485/ijs/2015/v8i21/69958, Sepember 2015 ISSN (Prin) : 0974-6846 ISSN (Online) : 0974-5645 Analysis of Various Types of Bugs in he Objec Oriened

More information

STEREO PLANE MATCHING TECHNIQUE

STEREO PLANE MATCHING TECHNIQUE STEREO PLANE MATCHING TECHNIQUE Commission III KEY WORDS: Sereo Maching, Surface Modeling, Projecive Transformaion, Homography ABSTRACT: This paper presens a new ype of sereo maching algorihm called Sereo

More information

IntentSearch:Capturing User Intention for One-Click Internet Image Search

IntentSearch:Capturing User Intention for One-Click Internet Image Search JOURNAL OF L A T E X CLASS FILES, VOL. 6, NO. 1, JANUARY 2010 1 InenSearch:Capuring User Inenion for One-Click Inerne Image Search Xiaoou Tang, Fellow, IEEE, Ke Liu, Jingyu Cui, Suden Member, IEEE, Fang

More information

Learning in Games via Opponent Strategy Estimation and Policy Search

Learning in Games via Opponent Strategy Estimation and Policy Search Learning in Games via Opponen Sraegy Esimaion and Policy Search Yavar Naddaf Deparmen of Compuer Science Universiy of Briish Columbia Vancouver, BC yavar@naddaf.name Nando de Freias (Supervisor) Deparmen

More information

Lecture 18: Mix net Voting Systems

Lecture 18: Mix net Voting Systems 6.897: Advanced Topics in Crypography Apr 9, 2004 Lecure 18: Mix ne Voing Sysems Scribed by: Yael Tauman Kalai 1 Inroducion In he previous lecure, we defined he noion of an elecronic voing sysem, and specified

More information

Win, Yuzana; Masada, Tomonari. Citation. Issue Date Right. this work in other works.

Win, Yuzana; Masada, Tomonari. Citation. Issue Date Right. this work in other works. NAOSITE: Nagasaki Universiy's Ac Tile Exploring Technical Phrase Frames f Auhor(s) Ciaion Win, Yuzana; Masada, Tomonari 05 IEEE 9h Inernaional Confer Neworking and Applicaions Worksho Issue Dae 05-04-7

More information

Feature Selection for Web Page Classification Using Swarm Optimization

Feature Selection for Web Page Classification Using Swarm Optimization Feaure Selecion for Web Page Classificaion Using Swarm Opimizaion B. Leela Devi, A. Sankar Absrac The web s increased populariy has included a huge amoun of informaion, due o which auomaed web page classificaion

More information

Image segmentation. Motivation. Objective. Definitions. A classification of segmentation techniques. Assumptions for thresholding

Image segmentation. Motivation. Objective. Definitions. A classification of segmentation techniques. Assumptions for thresholding Moivaion Image segmenaion Which pixels belong o he same objec in an image/video sequence? (spaial segmenaion) Which frames belong o he same video sho? (emporal segmenaion) Which frames belong o he same

More information

Video Content Description Using Fuzzy Spatio-Temporal Relations

Video Content Description Using Fuzzy Spatio-Temporal Relations Proceedings of he 4s Hawaii Inernaional Conference on Sysem Sciences - 008 Video Conen Descripion Using Fuzzy Spaio-Temporal Relaions rchana M. Rajurkar *, R.C. Joshi and Sananu Chaudhary 3 Dep of Compuer

More information

LOW-VELOCITY IMPACT LOCALIZATION OF THE COMPOSITE TUBE USING A NORMALIZED CROSS-CORRELATION METHOD

LOW-VELOCITY IMPACT LOCALIZATION OF THE COMPOSITE TUBE USING A NORMALIZED CROSS-CORRELATION METHOD 21 s Inernaional Conference on Composie Maerials Xi an, 20-25 h Augus 2017 LOW-VELOCITY IMPACT LOCALIZATION OF THE COMPOSITE TUBE USING A NORMALIZED CROSS-CORRELATION METHOD Hyunseok Kwon 1, Yurim Park

More information

CAMERA CALIBRATION BY REGISTRATION STEREO RECONSTRUCTION TO 3D MODEL

CAMERA CALIBRATION BY REGISTRATION STEREO RECONSTRUCTION TO 3D MODEL CAMERA CALIBRATION BY REGISTRATION STEREO RECONSTRUCTION TO 3D MODEL Klečka Jan Docoral Degree Programme (1), FEEC BUT E-mail: xkleck01@sud.feec.vubr.cz Supervised by: Horák Karel E-mail: horak@feec.vubr.cz

More information

Difficulty-aware Hybrid Search in Peer-to-Peer Networks

Difficulty-aware Hybrid Search in Peer-to-Peer Networks Difficuly-aware Hybrid Search in Peer-o-Peer Neworks Hanhua Chen, Hai Jin, Yunhao Liu, Lionel M. Ni School of Compuer Science and Technology Huazhong Univ. of Science and Technology {chenhanhua, hjin}@hus.edu.cn

More information

Implementing Ray Casting in Tetrahedral Meshes with Programmable Graphics Hardware (Technical Report)

Implementing Ray Casting in Tetrahedral Meshes with Programmable Graphics Hardware (Technical Report) Implemening Ray Casing in Terahedral Meshes wih Programmable Graphics Hardware (Technical Repor) Marin Kraus, Thomas Erl March 28, 2002 1 Inroducion Alhough cell-projecion, e.g., [3, 2], and resampling,

More information

Real Time Integral-Based Structural Health Monitoring

Real Time Integral-Based Structural Health Monitoring Real Time Inegral-Based Srucural Healh Monioring The nd Inernaional Conference on Sensing Technology ICST 7 J. G. Chase, I. Singh-Leve, C. E. Hann, X. Chen Deparmen of Mechanical Engineering, Universiy

More information

Shortest Path Algorithms. Lecture I: Shortest Path Algorithms. Example. Graphs and Matrices. Setting: Dr Kieran T. Herley.

Shortest Path Algorithms. Lecture I: Shortest Path Algorithms. Example. Graphs and Matrices. Setting: Dr Kieran T. Herley. Shores Pah Algorihms Background Seing: Lecure I: Shores Pah Algorihms Dr Kieran T. Herle Deparmen of Compuer Science Universi College Cork Ocober 201 direced graph, real edge weighs Le he lengh of a pah

More information

Sam knows that his MP3 player has 40% of its battery life left and that the battery charges by an additional 12 percentage points every 15 minutes.

Sam knows that his MP3 player has 40% of its battery life left and that the battery charges by an additional 12 percentage points every 15 minutes. 8.F Baery Charging Task Sam wans o ake his MP3 player and his video game player on a car rip. An hour before hey plan o leave, he realized ha he forgo o charge he baeries las nigh. A ha poin, he plugged

More information

Visually Summarizing the Web using Internal Images and Keyphrases

Visually Summarizing the Web using Internal Images and Keyphrases Visually Summarizing he Web using Inernal Images and Keyphrases M.V.Gedam, S. A. Taale Deparmen of compuer engineering, PUNE Universiy Vidya Praishhan s College of Engg., India Absrac Visual summarizaion

More information

Design Alternatives for a Thin Lens Spatial Integrator Array

Design Alternatives for a Thin Lens Spatial Integrator Array Egyp. J. Solids, Vol. (7), No. (), (004) 75 Design Alernaives for a Thin Lens Spaial Inegraor Array Hala Kamal *, Daniel V azquez and Javier Alda and E. Bernabeu Opics Deparmen. Universiy Compluense of

More information

Gauss-Jordan Algorithm

Gauss-Jordan Algorithm Gauss-Jordan Algorihm The Gauss-Jordan algorihm is a sep by sep procedure for solving a sysem of linear equaions which may conain any number of variables and any number of equaions. The algorihm is carried

More information

Who thinks who knows who? Socio-Cognitive Analysis of an Network

Who thinks who knows who? Socio-Cognitive Analysis of an  Network Who hinks who knows who? Socio-Cogniive Analysis of an Email Nework Nishih Pahak Deparmen of Compuer Science Universiy of Minnesoa Minneapolis, MN, USA npahak@cs.umn.edu Sandeep Mane Deparmen of Compuer

More information

A time-space consistency solution for hardware-in-the-loop simulation system

A time-space consistency solution for hardware-in-the-loop simulation system Inernaional Conference on Advanced Elecronic Science and Technology (AEST 206) A ime-space consisency soluion for hardware-in-he-loop simulaion sysem Zexin Jiang a Elecric Power Research Insiue of Guangdong

More information

MORPHOLOGICAL SEGMENTATION OF IMAGE SEQUENCES

MORPHOLOGICAL SEGMENTATION OF IMAGE SEQUENCES MORPHOLOGICAL SEGMENTATION OF IMAGE SEQUENCES B. MARCOTEGUI and F. MEYER Ecole des Mines de Paris, Cenre de Morphologie Mahémaique, 35, rue Sain-Honoré, F 77305 Fonainebleau Cedex, France Absrac. In image

More information

The Impact of Product Development on the Lifecycle of Defects

The Impact of Product Development on the Lifecycle of Defects The Impac of Produc Developmen on he Lifecycle of Rudolf Ramler Sofware Compeence Cener Hagenberg Sofware Park 21 A-4232 Hagenberg, Ausria +43 7236 3343 872 rudolf.ramler@scch.a ABSTRACT This paper invesigaes

More information

Relevance Ranking using Kernels

Relevance Ranking using Kernels Relevance Ranking using Kernels Jun Xu 1, Hang Li 1, and Chaoliang Zhong 2 1 Microsof Research Asia, 4F Sigma Cener, No. 49 Zhichun Road, Beijing, China 100190 2 Beijing Universiy of Poss and Telecommunicaions,

More information

An efficient approach to improve throughput for TCP vegas in ad hoc network

An efficient approach to improve throughput for TCP vegas in ad hoc network Inernaional Research Journal of Engineering and Technology (IRJET) e-issn: 395-0056 Volume: 0 Issue: 03 June-05 www.irje.ne p-issn: 395-007 An efficien approach o improve hroughpu for TCP vegas in ad hoc

More information

Nonparametric CUSUM Charts for Process Variability

Nonparametric CUSUM Charts for Process Variability Journal of Academia and Indusrial Research (JAIR) Volume 3, Issue June 4 53 REEARCH ARTICLE IN: 78-53 Nonparameric CUUM Chars for Process Variabiliy D.M. Zombade and V.B. Ghue * Dep. of aisics, Walchand

More information

Performance Evaluation of Implementing Calls Prioritization with Different Queuing Disciplines in Mobile Wireless Networks

Performance Evaluation of Implementing Calls Prioritization with Different Queuing Disciplines in Mobile Wireless Networks Journal of Compuer Science 2 (5): 466-472, 2006 ISSN 1549-3636 2006 Science Publicaions Performance Evaluaion of Implemening Calls Prioriizaion wih Differen Queuing Disciplines in Mobile Wireless Neworks

More information

Open Access Research on an Improved Medical Image Enhancement Algorithm Based on P-M Model. Luo Aijing 1 and Yin Jin 2,* u = div( c u ) u

Open Access Research on an Improved Medical Image Enhancement Algorithm Based on P-M Model. Luo Aijing 1 and Yin Jin 2,* u = div( c u ) u Send Orders for Reprins o reprins@benhamscience.ae The Open Biomedical Engineering Journal, 5, 9, 9-3 9 Open Access Research on an Improved Medical Image Enhancemen Algorihm Based on P-M Model Luo Aijing

More information

COSC 3213: Computer Networks I Chapter 6 Handout # 7

COSC 3213: Computer Networks I Chapter 6 Handout # 7 COSC 3213: Compuer Neworks I Chaper 6 Handou # 7 Insrucor: Dr. Marvin Mandelbaum Deparmen of Compuer Science York Universiy F05 Secion A Medium Access Conrol (MAC) Topics: 1. Muliple Access Communicaions:

More information

Time Expression Recognition Using a Constituent-based Tagging Scheme

Time Expression Recognition Using a Constituent-based Tagging Scheme Track: Web Conen Analysis, Semanics and Knowledge Time Expression Recogniion Using a Consiuen-based Tagging Scheme Xiaoshi Zhong and Erik Cambria School of Compuer Science and Engineering Nanyang Technological

More information

Robust Multi-view Face Detection Using Error Correcting Output Codes

Robust Multi-view Face Detection Using Error Correcting Output Codes Robus Muli-view Face Deecion Using Error Correcing Oupu Codes Hongming Zhang,2, Wen GaoP P, Xilin Chen 2, Shiguang Shan 2, and Debin Zhao Deparmen of Compuer Science and Engineering, Harbin Insiue of Technolog

More information

Hidden Markov Model and Chapman Kolmogrov for Protein Structures Prediction from Images

Hidden Markov Model and Chapman Kolmogrov for Protein Structures Prediction from Images Hidden Markov Model and Chapman Kolmogrov for Proein Srucures Predicion from Images Md.Sarwar Kamal 1, Linkon Chowdhury 2, Mohammad Ibrahim Khan 2, Amira S. Ashour 3, João Manuel R.S. Tavares 4, Nilanjan

More information

Motion Level-of-Detail: A Simplification Method on Crowd Scene

Motion Level-of-Detail: A Simplification Method on Crowd Scene Moion Level-of-Deail: A Simplificaion Mehod on Crowd Scene Absrac Junghyun Ahn VR lab, EECS, KAIST ChocChoggi@vr.kais.ac.kr hp://vr.kais.ac.kr/~zhaoyue Recen echnological improvemen in characer animaion

More information

Evaluation and Improvement of Region-based Motion Segmentation

Evaluation and Improvement of Region-based Motion Segmentation Evaluaion and Improvemen of Region-based Moion Segmenaion Mark Ross Universiy Koblenz-Landau, Insiue of Compuaional Visualisics, Universiässraße 1, 56070 Koblenz, Germany Email: ross@uni-koblenz.de Absrac

More information

IAJIT First Online Publication

IAJIT First Online Publication An Improved Feaure Exracion and Combinaion of Muliple Classifiers for Query-by- ming Naha Phiwma and Parinya Sanguansa 2 Deparmen of Compuer Science, Suan Dusi Rajabha Universiy, Thailand 2 Faculy of Engineering

More information

MATH Differential Equations September 15, 2008 Project 1, Fall 2008 Due: September 24, 2008

MATH Differential Equations September 15, 2008 Project 1, Fall 2008 Due: September 24, 2008 MATH 5 - Differenial Equaions Sepember 15, 8 Projec 1, Fall 8 Due: Sepember 4, 8 Lab 1.3 - Logisics Populaion Models wih Harvesing For his projec we consider lab 1.3 of Differenial Equaions pages 146 o

More information

Occlusion-Free Hand Motion Tracking by Multiple Cameras and Particle Filtering with Prediction

Occlusion-Free Hand Motion Tracking by Multiple Cameras and Particle Filtering with Prediction 58 IJCSNS Inernaional Journal of Compuer Science and Nework Securiy, VOL.6 No.10, Ocober 006 Occlusion-Free Hand Moion Tracking by Muliple Cameras and Paricle Filering wih Predicion Makoo Kao, and Gang

More information

Definition and examples of time series

Definition and examples of time series Definiion and examples of ime series A ime series is a sequence of daa poins being recorded a specific imes. Formally, le,,p be a probabiliy space, and T an index se. A real valued sochasic process is

More information

Managing XML Versions and Replicas in a P2P Context

Managing XML Versions and Replicas in a P2P Context Managing XML Versions and Replicas in a P2P Conex Deise de Brum Saccol1 1,2, Nina Edelweiss 2, Renaa de Maos Galane 2,4, Carlo Zaniolo 3 2 Insiuo de Informáica - Universidade Federal do Rio Grande do Sul

More information

The Beer Dock: Three and a Half Implementations of the Beer Distribution Game

The Beer Dock: Three and a Half Implementations of the Beer Distribution Game The Beer Dock 2002-08-13 17:55:44-0700 The Beer Dock: Three and a Half Implemenaions of he Beer Disribuion Game Michael J. Norh[1] and Charles M. Macal Argonne Naional Laboraory, Argonne, Illinois Absrac

More information

Web System for the Remote Control and Execution of an IEC Application

Web System for the Remote Control and Execution of an IEC Application Web Sysem for he Remoe Conrol and Execuion of an IEC 61499 Applicaion Oana ROHAT, Dan POPESCU Faculy of Auomaion and Compuer Science, Poliehnica Universiy, Splaiul Independenței 313, Bucureși, 060042,

More information

Design and Application of Computer-aided English Online Examination System NONG DeChang 1, a

Design and Application of Computer-aided English Online Examination System NONG DeChang 1, a 3rd Inernaional Conference on Maerials Engineering, Manufacuring Technology and Conrol (ICMEMTC 2016) Design and Applicaion of Compuer-aided English Online Examinaion Sysem NONG DeChang 1, a 1,2 Guangxi

More information

Data Structures and Algorithms. The material for this lecture is drawn, in part, from The Practice of Programming (Kernighan & Pike) Chapter 2

Data Structures and Algorithms. The material for this lecture is drawn, in part, from The Practice of Programming (Kernighan & Pike) Chapter 2 Daa Srucures and Algorihms The maerial for his lecure is drawn, in par, from The Pracice of Programming (Kernighan & Pike) Chaper 2 1 Moivaing Quoaion Every program depends on algorihms and daa srucures,

More information

Why not experiment with the system itself? Ways to study a system System. Application areas. Different kinds of systems

Why not experiment with the system itself? Ways to study a system System. Application areas. Different kinds of systems Simulaion Wha is simulaion? Simple synonym: imiaion We are ineresed in sudying a Insead of experimening wih he iself we experimen wih a model of he Experimen wih he Acual Ways o sudy a Sysem Experimen

More information

STRING DESCRIPTIONS OF DATA FOR DISPLAY*

STRING DESCRIPTIONS OF DATA FOR DISPLAY* SLAC-PUB-383 January 1968 STRING DESCRIPTIONS OF DATA FOR DISPLAY* J. E. George and W. F. Miller Compuer Science Deparmen and Sanford Linear Acceleraor Cener Sanford Universiy Sanford, California Absrac

More information

Voltair Version 2.5 Release Notes (January, 2018)

Voltair Version 2.5 Release Notes (January, 2018) Volair Version 2.5 Release Noes (January, 2018) Inroducion 25-Seven s new Firmware Updae 2.5 for he Volair processor is par of our coninuing effors o improve Volair wih new feaures and capabiliies. For

More information

A Fast Stereo-Based Multi-Person Tracking using an Approximated Likelihood Map for Overlapping Silhouette Templates

A Fast Stereo-Based Multi-Person Tracking using an Approximated Likelihood Map for Overlapping Silhouette Templates A Fas Sereo-Based Muli-Person Tracking using an Approximaed Likelihood Map for Overlapping Silhouee Templaes Junji Saake Jun Miura Deparmen of Compuer Science and Engineering Toyohashi Universiy of Technology

More information

A new algorithm for small object tracking based on super-resolution technique

A new algorithm for small object tracking based on super-resolution technique A new algorihm for small objec racking based on super-resoluion echnique Yabunayya Habibi, Dwi Rana Sulisyaningrum, and Budi Seiyono Ciaion: AIP Conference Proceedings 1867, 020024 (2017); doi: 10.1063/1.4994427

More information

EECS 487: Interactive Computer Graphics

EECS 487: Interactive Computer Graphics EECS 487: Ineracive Compuer Graphics Lecure 7: B-splines curves Raional Bézier and NURBS Cubic Splines A represenaion of cubic spline consiss of: four conrol poins (why four?) hese are compleely user specified

More information

Less Pessimistic Worst-Case Delay Analysis for Packet-Switched Networks

Less Pessimistic Worst-Case Delay Analysis for Packet-Switched Networks Less Pessimisic Wors-Case Delay Analysis for Packe-Swiched Neworks Maias Wecksén Cenre for Research on Embedded Sysems P O Box 823 SE-31 18 Halmsad maias.wecksen@hh.se Magnus Jonsson Cenre for Research

More information

Wheelchair-user Detection Combined with Parts-based Tracking

Wheelchair-user Detection Combined with Parts-based Tracking Wheelchair-user Deecion Combined wih Pars-based Tracking Ukyo Tanikawa 1, Yasuomo Kawanishi 1, Daisuke Deguchi 2,IchiroIde 1, Hiroshi Murase 1 and Ryo Kawai 3 1 Graduae School of Informaion Science, Nagoya

More information

Partition-based document identifier assignment (PBDIA) algorithm. (long queries)

Partition-based document identifier assignment (PBDIA) algorithm. (long queries) ( ) Pariion-based documen idenifier assignmen (PBDIA) algorihm PBDIA (long queries) (parallel IR) :,,,, d-gap Compressing an invered file can grealy improve query performance of an informaion rerieval

More information

Who Thinks Who Knows Who? Socio-cognitive Analysis of Networks. Technical Report

Who Thinks Who Knows Who? Socio-cognitive Analysis of  Networks. Technical Report Who Thinks Who Knows Who? Socio-cogniive Analysis of Email Neworks Technical Repor Deparmen of Compuer Science and Engineering Universiy of Minnesoa 4-192 EECS Building 200 Union Sree SE Minneapolis, MN

More information

An Adaptive Spatial Depth Filter for 3D Rendering IP

An Adaptive Spatial Depth Filter for 3D Rendering IP JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE, VOL.3, NO. 4, DECEMBER, 23 175 An Adapive Spaial Deph Filer for 3D Rendering IP Chang-Hyo Yu and Lee-Sup Kim Absrac In his paper, we presen a new mehod

More information

FIELD PROGRAMMABLE GATE ARRAY (FPGA) AS A NEW APPROACH TO IMPLEMENT THE CHAOTIC GENERATORS

FIELD PROGRAMMABLE GATE ARRAY (FPGA) AS A NEW APPROACH TO IMPLEMENT THE CHAOTIC GENERATORS FIELD PROGRAMMABLE GATE ARRAY (FPGA) AS A NEW APPROACH TO IMPLEMENT THE CHAOTIC GENERATORS Mohammed A. Aseeri and M. I. Sobhy Deparmen of Elecronics, The Universiy of Ken a Canerbury Canerbury, Ken, CT2

More information

IROS 2015 Workshop on On-line decision-making in multi-robot coordination (DEMUR 15)

IROS 2015 Workshop on On-line decision-making in multi-robot coordination (DEMUR 15) IROS 2015 Workshop on On-line decision-making in muli-robo coordinaion () OPTIMIZATION-BASED COOPERATIVE MULTI-ROBOT TARGET TRACKING WITH REASONING ABOUT OCCLUSIONS KAROL HAUSMAN a,, GREGORY KAHN b, SACHIN

More information

MOTION TRACKING is a fundamental capability that

MOTION TRACKING is a fundamental capability that TECHNICAL REPORT CRES-05-008, CENTER FOR ROBOTICS AND EMBEDDED SYSTEMS, UNIVERSITY OF SOUTHERN CALIFORNIA 1 Real-ime Moion Tracking from a Mobile Robo Boyoon Jung, Suden Member, IEEE, Gaurav S. Sukhame,

More information

Utility-Based Hybrid Memory Management

Utility-Based Hybrid Memory Management Uiliy-Based Hybrid Memory Managemen Yang Li Saugaa Ghose Jongmoo Choi Jin Sun Hui Wang Onur Mulu Carnegie Mellon Universiy Dankook Universiy Beihang Universiy ETH Zürich While he memory fooprins of cloud

More information

Audio Engineering Society. Convention Paper. Presented at the 119th Convention 2005 October 7 10 New York, New York USA

Audio Engineering Society. Convention Paper. Presented at the 119th Convention 2005 October 7 10 New York, New York USA Audio Engineering Sociey Convenion Paper Presened a he 119h Convenion 2005 Ocober 7 10 New Yor, New Yor USA This convenion paper has been reproduced from he auhor's advance manuscrip, wihou ediing, correcions,

More information

Research Article Auto Coloring with Enhanced Character Registration

Research Article Auto Coloring with Enhanced Character Registration Compuer Games Technology Volume 2008, Aricle ID 35398, 7 pages doi:0.55/2008/35398 Research Aricle Auo Coloring wih Enhanced Characer Regisraion Jie Qiu, Hock Soon Seah, Feng Tian, Quan Chen, Zhongke Wu,

More information

An HTTP Web Traffic Model Based on the Top One Million Visited Web Pages

An HTTP Web Traffic Model Based on the Top One Million Visited Web Pages An HTTP Web Traffic Model Based on he Top One Million Visied Web Pages Rasin Pries, Zsol Magyari, Phuoc Tran-Gia Universiy of Würzburg, Insiue of Compuer Science, Germany Email: {pries,rangia}@informaik.uni-wuerzburg.de

More information

Image Based Computer-Aided Manufacturing Technology

Image Based Computer-Aided Manufacturing Technology Sensors & Transducers 03 by IFSA hp://www.sensorsporal.com Image Based Compuer-Aided Manufacuring Technology Zhanqi HU Xiaoqin ZHANG Jinze LI Wei LI College of Mechanical Engineering Yanshan Universiy

More information

Vulnerability Evaluation of Multimedia Subsystem Based on Complex Network

Vulnerability Evaluation of Multimedia Subsystem Based on Complex Network JOURAL OF MULTIMDIA, VOL. 8, O. 4, AUGUST 23 439 Vulnerabiliy valuaion of Mulimedia Subsysem Based on Complex ewor Xiaoling Tang Insiue of Higher ducaion Research, Jilin Business and Technology College,

More information

Improving the Efficiency of Dynamic Service Provisioning in Transport Networks with Scheduled Services

Improving the Efficiency of Dynamic Service Provisioning in Transport Networks with Scheduled Services Improving he Efficiency of Dynamic Service Provisioning in Transpor Neworks wih Scheduled Services Ralf Hülsermann, Monika Jäger and Andreas Gladisch Technologiezenrum, T-Sysems, Goslarer Ufer 35, D-1585

More information

Video-Based Face Recognition Using Probabilistic Appearance Manifolds

Video-Based Face Recognition Using Probabilistic Appearance Manifolds Video-Based Face Recogniion Using Probabilisic Appearance Manifolds Kuang-Chih Lee Jeffrey Ho Ming-Hsuan Yang David Kriegman klee10@uiuc.edu jho@cs.ucsd.edu myang@honda-ri.com kriegman@cs.ucsd.edu Compuer

More information

A Bayesian Approach to Video Object Segmentation via Merging 3D Watershed Volumes

A Bayesian Approach to Video Object Segmentation via Merging 3D Watershed Volumes A Bayesian Approach o Video Objec Segmenaion via Merging 3D Waershed Volumes Yu-Pao Tsai 1,3, Chih-Chuan Lai 1,2, Yi-Ping Hung 1,2, and Zen-Chung Shih 3 1 Insiue of Informaion Science, Academia Sinica,

More information

Simple Network Management Based on PHP and SNMP

Simple Network Management Based on PHP and SNMP Simple Nework Managemen Based on PHP and SNMP Krasimir Trichkov, Elisavea Trichkova bsrac: This paper aims o presen simple mehod for nework managemen based on SNMP - managemen of Cisco rouer. The paper

More information

A Face Detection Method Based on Skin Color Model

A Face Detection Method Based on Skin Color Model A Face Deecion Mehod Based on Skin Color Model Dazhi Zhang Boying Wu Jiebao Sun Qinglei Liao Deparmen of Mahemaics Harbin Insiue of Technology Harbin China 150000 Zhang_dz@163.com mahwby@hi.edu.cn sunjiebao@om.com

More information

Rao-Blackwellized Particle Filtering for Probing-Based 6-DOF Localization in Robotic Assembly

Rao-Blackwellized Particle Filtering for Probing-Based 6-DOF Localization in Robotic Assembly MITSUBISHI ELECTRIC RESEARCH LABORATORIES hp://www.merl.com Rao-Blackwellized Paricle Filering for Probing-Based 6-DOF Localizaion in Roboic Assembly Yuichi Taguchi, Tim Marks, Haruhisa Okuda TR1-8 June

More information

Reinforcement Learning by Policy Improvement. Making Use of Experiences of The Other Tasks. Hajime Kimura and Shigenobu Kobayashi

Reinforcement Learning by Policy Improvement. Making Use of Experiences of The Other Tasks. Hajime Kimura and Shigenobu Kobayashi Reinforcemen Learning by Policy Improvemen Making Use of Experiences of The Oher Tasks Hajime Kimura and Shigenobu Kobayashi Tokyo Insiue of Technology, JAPAN genfe.dis.iech.ac.jp, kobayasidis.iech.ac.jp

More information

M(t)/M/1 Queueing System with Sinusoidal Arrival Rate

M(t)/M/1 Queueing System with Sinusoidal Arrival Rate 20 TUTA/IOE/PCU Journal of he Insiue of Engineering, 205, (): 20-27 TUTA/IOE/PCU Prined in Nepal M()/M/ Queueing Sysem wih Sinusoidal Arrival Rae A.P. Pan, R.P. Ghimire 2 Deparmen of Mahemaics, Tri-Chandra

More information

Using UMLS-based Re-Weighting Terms as a Query Expansion Strategy. Weizhong Zhu, Xuheng Xu, Xiaohua Hu, Il-Yeol Song, and Robert B.

Using UMLS-based Re-Weighting Terms as a Query Expansion Strategy. Weizhong Zhu, Xuheng Xu, Xiaohua Hu, Il-Yeol Song, and Robert B. Using UMLS-base Re-Weighing Terms as a Expansion Sraegy Weizhong Zhu, Xuheng Xu, Xiaohua Hu, Il-Yeol Song, an Rober B Allen Absrac Search engines have significanly improve he efficiency of bio-meical lieraure

More information

On the Emotion of Users in App Reviews

On the Emotion of Users in App Reviews On he Emoion of Users in App Reviews Daniel Marens Universiy of Hamburg Hamburg, Germany marens@informaik.uni-hamburg.de Timo Johann Universiy of Hamburg Hamburg, Germany johann@informaik.uni-hamburg.de

More information

MoBAN: A Configurable Mobility Model for Wireless Body Area Networks

MoBAN: A Configurable Mobility Model for Wireless Body Area Networks MoBAN: A Configurable Mobiliy Model for Wireless Body Area Neworks Majid Nabi 1, Marc Geilen 1, Twan Basen 1,2 1 Deparmen of Elecrical Engineering, Eindhoven Universiy of Technology, he Neherlands 2 Embedded

More information

COMP26120: Algorithms and Imperative Programming

COMP26120: Algorithms and Imperative Programming COMP26120 ecure C3 1/48 COMP26120: Algorihms and Imperaive Programming ecure C3: C - Recursive Daa Srucures Pee Jinks School of Compuer Science, Universiy of Mancheser Auumn 2011 COMP26120 ecure C3 2/48

More information

A New Semantic Cache Management Method in Mobile Databases

A New Semantic Cache Management Method in Mobile Databases Journal o Compuer Science 1 (3): 351-354, 25 ISSN 1549-3636 Science Publicaions, 25 A New Semanic Cache Managemen Mehod in Mobile Daabases Shengei Shi, Jianzhong Li and Chaokun Wang School o Compuer Science

More information

PART 1 REFERENCE INFORMATION CONTROL DATA 6400 SYSTEMS CENTRAL PROCESSOR MONITOR

PART 1 REFERENCE INFORMATION CONTROL DATA 6400 SYSTEMS CENTRAL PROCESSOR MONITOR . ~ PART 1 c 0 \,).,,.,, REFERENCE NFORMATON CONTROL DATA 6400 SYSTEMS CENTRAL PROCESSOR MONTOR n CONTROL DATA 6400 Compuer Sysems, sysem funcions are normally handled by he Monior locaed in a Peripheral

More information

Michiel Helder and Marielle C.T.A Geurts. Hoofdkantoor PTT Post / Dutch Postal Services Headquarters

Michiel Helder and Marielle C.T.A Geurts. Hoofdkantoor PTT Post / Dutch Postal Services Headquarters SHORT TERM PREDICTIONS A MONITORING SYSTEM by Michiel Helder and Marielle C.T.A Geurs Hoofdkanoor PTT Pos / Duch Posal Services Headquarers Keywords macro ime series shor erm predicions ARIMA-models faciliy

More information

Coded Caching with Multiple File Requests

Coded Caching with Multiple File Requests Coded Caching wih Muliple File Requess Yi-Peng Wei Sennur Ulukus Deparmen of Elecrical and Compuer Engineering Universiy of Maryland College Park, MD 20742 ypwei@umd.edu ulukus@umd.edu Absrac We sudy a

More information

A Hierarchical Object Recognition System Based on Multi-scale Principal Curvature Regions

A Hierarchical Object Recognition System Based on Multi-scale Principal Curvature Regions A Hierarchical Objec Recogniion Sysem Based on Muli-scale Principal Curvaure Regions Wei Zhang, Hongli Deng, Thomas G Dieerich and Eric N Morensen School of Elecrical Engineering and Compuer Science Oregon

More information

Robot localization under perceptual aliasing conditions based on laser reflectivity using particle filter

Robot localization under perceptual aliasing conditions based on laser reflectivity using particle filter Robo localizaion under percepual aliasing condiions based on laser refleciviy using paricle filer DongXiang Zhang, Ryo Kurazume, Yumi Iwashia, Tsuomu Hasegawa Absrac Global localizaion, which deermines

More information

CENG 477 Introduction to Computer Graphics. Modeling Transformations

CENG 477 Introduction to Computer Graphics. Modeling Transformations CENG 477 Inroducion o Compuer Graphics Modeling Transformaions Modeling Transformaions Model coordinaes o World coordinaes: Model coordinaes: All shapes wih heir local coordinaes and sies. world World

More information

Test - Accredited Configuration Engineer (ACE) Exam - PAN-OS 6.0 Version

Test - Accredited Configuration Engineer (ACE) Exam - PAN-OS 6.0 Version Tes - Accredied Configuraion Engineer (ACE) Exam - PAN-OS 6.0 Version ACE Exam Quesion 1 of 50. Which of he following saemens is NOT abou Palo Alo Neworks firewalls? Sysem defauls may be resored by performing

More information

Hyelim Oh. School of Computing, National University of Singapore, 13 Computing Drive, Singapore SINGAPORE

Hyelim Oh. School of Computing, National University of Singapore, 13 Computing Drive, Singapore SINGAPORE RESEARCH ARTICLE FREE VERSUS FOR-A-FEE: THE IMPACT OF A PAYWALL ON THE PATTERN AND EFFECTIVENESS OF WORD-OF-MOUTH VIA SOCIAL MEDIA Hyelim Oh School of Compuing, Naional Universiy of Singapore, 13 Compuing

More information

Joint Feature Learning With Robust Local Ternary Pattern for Face Recognition

Joint Feature Learning With Robust Local Ternary Pattern for Face Recognition Join Feaure Learning Wih Robus Local Ternary Paern for Face Recogniion Yuvaraju.M 1, Shalini.S 1 Assisan Professor, Deparmen of Elecrical and Elecronics Engineering, Anna Universiy Regional Campus, Coimbaore,

More information

(Structural Time Series Models for Describing Trend in All India Sunflower Yield Using SAS

(Structural Time Series Models for Describing Trend in All India Sunflower Yield Using SAS (Srucural Time Series Models for Describing Trend in All India Sunflower Yield Using SAS Himadri Ghosh, Prajneshu and Savia Wadhwa I.A.S.R.I., Library Avenue, New Delhi-110 01 him_adri@iasri.res.in, prajnesh@iasri.res.in,

More information

Assignment 2. Due Monday Feb. 12, 10:00pm.

Assignment 2. Due Monday Feb. 12, 10:00pm. Faculy of rs and Science Universiy of Torono CSC 358 - Inroducion o Compuer Neworks, Winer 218, LEC11 ssignmen 2 Due Monday Feb. 12, 1:pm. 1 Quesion 1 (2 Poins): Go-ack n RQ In his quesion, we review how

More information

Improved TLD Algorithm for Face Tracking

Improved TLD Algorithm for Face Tracking Absrac Improved TLD Algorihm for Face Tracking Huimin Li a, Chaojing Yu b and Jing Chen c Chongqing Universiy of Poss and Telecommunicaions, Chongqing 400065, China a li.huimin666@163.com, b 15023299065@163.com,

More information

An Improved Square-Root Nyquist Shaping Filter

An Improved Square-Root Nyquist Shaping Filter An Improved Square-Roo Nyquis Shaping Filer fred harris San Diego Sae Universiy fred.harris@sdsu.edu Sridhar Seshagiri San Diego Sae Universiy Seshigar.@engineering.sdsu.edu Chris Dick Xilinx Corp. chris.dick@xilinx.com

More information

4 Error Control. 4.1 Issues with Reliable Protocols

4 Error Control. 4.1 Issues with Reliable Protocols 4 Error Conrol Jus abou all communicaion sysems aemp o ensure ha he daa ges o he oher end of he link wihou errors. Since i s impossible o build an error-free physical layer (alhough some shor links can

More information

Landmarks: A New Model for Similarity-Based Pattern Querying in Time Series Databases

Landmarks: A New Model for Similarity-Based Pattern Querying in Time Series Databases Lmarks: A New Model for Similariy-Based Paern Querying in Time Series Daabases Chang-Shing Perng Haixun Wang Sylvia R. Zhang D. So Parker perng@cs.ucla.edu hxwang@cs.ucla.edu Sylvia Zhang@cle.com so@cs.ucla.edu

More information

Modelling urban travel time variability with the Burr regression technique

Modelling urban travel time variability with the Burr regression technique Ausralasian Transpor Research Forum 2011 Proceedings 28-30 Sepember 2011, Adelaide, Ausralia Publicaion websie: hp://www.parec.org/arf.aspx Modelling urban ravel ime variabiliy wih he Burr regression echnique

More information

NEWTON S SECOND LAW OF MOTION

NEWTON S SECOND LAW OF MOTION Course and Secion Dae Names NEWTON S SECOND LAW OF MOTION The acceleraion of an objec is defined as he rae of change of elociy. If he elociy changes by an amoun in a ime, hen he aerage acceleraion during

More information

Weighted Voting in 3D Random Forest Segmentation

Weighted Voting in 3D Random Forest Segmentation Weighed Voing in 3D Random Fores Segmenaion M. Yaqub,, P. Mahon 3, M. K. Javaid, C. Cooper, J. A. Noble NDORMS, Universiy of Oxford, IBME, Deparmen of Engineering Science, Universiy of Oxford, 3 MRC Epidemiology

More information

CONTEXT MODELS FOR CRF-BASED CLASSIFICATION OF MULTITEMPORAL REMOTE SENSING DATA

CONTEXT MODELS FOR CRF-BASED CLASSIFICATION OF MULTITEMPORAL REMOTE SENSING DATA ISPRS Annals of he Phoogrammery, Remoe Sensing and Spaial Informaion Sciences, Volume I-7, 2012 XXII ISPRS Congress, 25 Augus 01 Sepember 2012, Melbourne, Ausralia CONTEXT MODELS FOR CRF-BASED CLASSIFICATION

More information

Computer representations of piecewise

Computer representations of piecewise Edior: Gabriel Taubin Inroducion o Geomeric Processing hrough Opimizaion Gabriel Taubin Brown Universiy Compuer represenaions o piecewise smooh suraces have become vial echnologies in areas ranging rom

More information

MIC2569. Features. General Description. Applications. Typical Application. CableCARD Power Switch

MIC2569. Features. General Description. Applications. Typical Application. CableCARD Power Switch CableCARD Power Swich General Descripion is designed o supply power o OpenCable sysems and CableCARD hoss. These CableCARDs are also known as Poin of Disribuion (POD) cards. suppors boh Single and Muliple

More information

FUZZY HUMAN/MACHINE RELIABILITY USING VHDL

FUZZY HUMAN/MACHINE RELIABILITY USING VHDL FUZZY HUMN/MCHINE RELIBILITY USING VHDL Carlos. Graciós M. 1, lejandro Díaz S. 2, Efrén Gorroiea H. 3 (1) Insiuo Tecnológico de Puebla v. Tecnológico 420. Col. Maravillas, C. P. 72220, Puebla, Pue. México

More information