Description of NTU Approach to NTCIR3 Multilingual Information Retrieval

Size: px
Start display at page:

Download "Description of NTU Approach to NTCIR3 Multilingual Information Retrieval"

Transcription

1 Proceedngs of the Thrd NTCIR Workshop Descrpton of NTU Approach to NTCIR3 Multlngual Informaton Retreval Wen-Cheng Ln and Hsn-Hs Chen Department of Computer Scence and Informaton Engneerng Natonal Tawan Unversty Tape, TAIWAN E-mal: Abstract Ths paper deals wth Chnese, Englsh and Japanese multlngual nformaton retreval. Several mergng strateges, ncludng raw-score mergng, round-robn mergng, normalzed-score mergng, and normalzedby-top-k mergng, were nvestgated. Expermental results show that centralzed approach s better than dstrbuted approach. In dstrbuted approach, normalzed-by-top-k wth consderaton of translaton penalty outperforms the other mergng strateges. Keywords: Mergng Strategy, Multlngual Informaton Retreval, Query Translaton 1. Introducton Multlngual Informaton Retreval [7] uses a query n one language to retreve documents n dfferent languages. In addton to language translaton ssue, how to conduct a ranked lst that contans documents n dfferent languages from several text collectons s also crtcal. There are two possble archtectures n MLIR say, centralzed and dstrbuted. In a centralzed archtecture, a huge collecton that contans documents n dfferent languages s used. In a dstrbuted archtecture, documents n dfferent languages are ndexed and retreved separately, and all the results are merged nto a multlngual ranked lst. Several mergng strateges have been proposed. Raw-score mergng selects documents based on ther orgnal smlarty scores. Normalzed-score mergng normalzes the smlarty score of each document and sorts all the documents by ther normalzed scores. For each topc, the smlarty score of each document s dvded by the maxmum score n ths topc. Roundrobn mergng nterleaves the results n the ntermedate runs. In ths paper, we adopted dstrbuted archtecture and proposed mergng strateges to merge the result lsts. The rest of ths paper s organzed as follows. Secton 2 descrbes the ndexng method. Secton 3 shows the query translaton process. Secton 4 descrbes our mergng strateges. Secton 5 shows the experment results. Secton 6 concludes the remark. 2. Indexng The document set used n NTCIR3 MLIR task conssts of Chnese, Englsh and Japanese documents. The numbers of documents n Chnese, Englsh, and Japanese document sets are 381,681, 22,927 and 236,664, respectvely. The partcpants can use two or all of these three document collectons as the target language sets. We used all of these three document collectons to conduct X CJE experments. The IR model we used s the basc vector space model. Documents and queres are represented as term vectors, and cosne vector smlarty formula s used to measure the smlarty of a query and a document. Approprate terms are extracted from each document n ndexng stage. In the experments, the <HEADLINE> and <TEXT> sectons were used for ndexng. For Englsh, all words were retaned, and all letters were transformed to lower case. The Japanese documents were frst segmented by ChaSen [6]. All words n the above two sectons were used as ndex terms. For Chnese, we used Chnese character bgrams to ndex Chnese documents. The term weghtng functon for all document sets s tf*df. 3. Query Translaton In the experment, the Japanese queres were used as source queres and translated nto target languages,.e., Englsh and Chnese. We used CO model [1], whch s a hybrd dctonary- and corpus-based 2003 Natonal Insttute of Informatcs

2 The Thrd NTCIR Workshop, Sep Oct method, to translate queres. Snce we dd not have a Japanese-Chnese dctonary, we used Englsh as an ntermedate language n the ntal study. The Japanese queres were translated nto Englsh, and then the translated Englsh queres were further translated nto Chnese. The Japanese queres were translated nto Englsh n the way as follows: (a) The Japanese query was segmented by ChaSen. (b) For each Japanese query term, we found ts Englsh translaton equvalents by lookng up a Japanese-Englsh dctonary. (c) By usng co-occurrence nformaton traned from TREC6 text collecton [4], we selected the best Englsh translaton equvalent for each source query term. We adopted mutual nformaton (MI) [2] to measure the co-occurrence strength between words. For a query term, we compared the MI values of all the translaton equvalent pars (x, y), where x s the translaton equvalent of ths term, and y s the translaton equvalent of another query term wthn a sentence. The word par (x, y j ) wth the hghest MI value s extracted, and the translaton equvalent x s regarded as the best translaton equvalent of ths query term. Selecton s carred out based on the order of the query terms. Translated Englsh queres were translated nto Chnese usng the same method except that Englsh queres dd not need to be segmented. The MI values of Chnese words were traned from Academa Snca Balanced Corpus (ASBC) [5]. 4. Mergng Strateges There are two possble archtectures n MLIR,.e., centralzed and dstrbuted. In a centralzed archtecture, document collectons n dfferent languages are vewed as a sngle document collecton and are ndexed n one huge ndex fle. The advantage of centralzed archtecture s that t avods the mergng problem. It needs only one retrevng phase to produce a result lst that contans relevant documents n dfferent languages. One of problems of a centralzed archtecture s that ndex terms may be over weghted. In other words, the total number of documents ncreases, but the number of occurrences of a term does not. In tf*df scheme, the df of a term s ncreased and t s over-weghted. Ths phenomenon s clear n small text collecton. For example, the N n df formula s 22,927 when Englsh document s used. However, ths value s ncreased to 641,272,.e., about tmes larger, f the three document collectons are merged together. Comparatvely, the weghts of Chnese ndex terms are ncreased only 1.68 tmes due to the sze of N. The ncrements of weghts are unbalance for document collectons n dfferent sze. Thus, IR system may prefer documents n small document collecton. The second archtecture s a dstrbuted MLIR. Documents n dfferent languages are ndexed and retreved separately. The ranked lsts of all monolngual and cross-lngual runs are merged nto one multlngual ranked lst. How to merge result lsts s a problem. Recent works have proposed varous approaches to deal wth the mergng problem. A smple mergng method s raw-score mergng, whch sorts all results by ther orgnal smlarty scores and then selects the top ranked documents. Raw-score mergng s based on the assumpton that the smlarty scores across collectons are comparable. However, the collecton-dependent statstcs n document or query weghts nvaldates ths assumpton [3, 8]. Another approach, roundrobn mergng, nterleaves the results based on the rank. Ths approach assumes that each collecton has approxmately the same number of relevant documents and the dstrbuton of relevant documents s smlar across the result lsts. Actually, dfferent collectons do not contan equal numbers of relevant documents. Thus, the performance of round-robn mergng may be poor. The thrd approach s normalzed-score mergng. For each topc, the smlarty score of each document s dvded by the maxmum score n ths topc. After adjustng scores, all results are put nto a pool and sorted by the normalzed score. Ths approach maps the smlarty scores of dfferent result lsts nto the same range, from 0 to 1, and makes the scores more comparable. But t has a problem. If the maxmum score s much hgher than the second one n the same result lst, the normalzed-score of the document at rank 2 would be made lower even f ts orgnal score s hgh. Thus, the fnal rank of ths document would be lower than that of the top ranked documents wth very low but smlar orgnal scores n another result lst. Smlarty score reflects the degree of smlarty between a document and a query. A document wth hgh smlarty score seems to be more relevant to the desred query. But, f the query s not formulated well, e.g., napproprate translaton of a query, a document wth hgh score stll does not meet the user s nformaton need. When mergng results, such documents that have ncorrect hgh scores should not be ncluded n the fnal result lst. Thus, we have to consder the effectveness of each ndvdual run n the mergng stage. The basc dea of our mergng strategy s that adjustng the smlarty scores of documents n each result lst to make them more comparable and to reflect ther confdence. The smlarty scores are adjusted by the followng formula. S ˆ 1 j = Sj W (1) S k

3 Proceedngs of the Thrd NTCIR Workshop where S j s the orgnal smlarty score of the document at rank j n the ranked lst of Ŝ j S k topc, s the adjusted smlarty score of the document at rank j n the ranked lst of topc, s the average smlarty score of top k documents, and W s the weght of query n a cross-lngual run. We dvde the weght adjustng process nto two steps. Frst, we use a modfed score normalzaton method to normalze the smlarty scores. The orgnal score of each document s dvded by the average score of top k documents nstead of the maxmum score. We call ths normalzed-by-top-k. Second, the normalzed score multples a weght that reflects the retreval effectveness of the desred topc n each text collecton. Because of not knowng the retreval performance n advance, we have to guess the performance of each run. For each language par, the queres are translated nto target language and then system retreves the target language documents. A good translaton should have better performance. We can predct the retreval performance based on the translaton performance. There are two factors affectng the translaton performance,.e., the degree of translaton ambguty and the number of unknown words. For each query, we compute the average number of translaton equvalents of query terms and the number of unknown words n each language par, and use them to compute the weghts of each crosslngual run. The weght can be determned by the followng three formulas: 2 51 T U + W = c1 + c2 c3 1 (2) 50 n 1 U + W = c1 + c2 c3 1 (3) T n 1 U + W = c + c c 1 (4) T n where W s the weght of query n a cross-lngual run, T s the average number of translaton equvalents of query terms n query, U s the number of unknown words n query, n s the number of query terms n query, and c 1, c 2 and c 3 are tunable parameters, and c 1 +c 2 +c 3 =1. In the experment, the Japanese queres were translated nto Englsh, and then the translated Englsh queres were further translated nto Chnese. Some Japanese query terms have no Englsh translaton, and therefore they cannot be translated nto Englsh and also Chnese. The unknown words n Japanese-Englsh translaton are also unknown n Englsh-Chnese translaton. Thus, the number of unknown words n Japanese-Englsh-Chnese translaton s the sum of those n Japanese-Englsh translaton and Englsh-Chnese translaton. 5. Results We submtted three J CJE multlngual runs and one E E monolngual run. All runs use descrpton feld only. The Englsh monolngual run, NTU-E-E- D-01, uses offcal Englsh topcs to retreve Englsh documents. The three multlngual runs use Japanese topcs as source queres. The Japanese topcs were translated nto Englsh and Chnese by CO Model descrbed n Secton 3. The source Japanese topcs and the translated Englsh and Chnese topcs were used to retreve Japanese, Englsh and Chnese documents, respectvely. Then, we merged these three result lsts. We used dfferent mergng strateges for the three multlngual runs. 1. NTU-J-CJE-D-01 Frst, we used formula (1) to adjust the smlarty score of each document. We used the average smlarty score of top 10 documents for normalzaton. The weght W was determned by formula (2). The values of c 1, c 2 and c 3 were set to 0.1, 0.4 and 0.5, respectvely. Then all results were put n a pool and sorted by the adjusted score. The top 1000 documents were selected as the fnal results. 2. NTU-J-CJE-D-02 The mergng strategy s the same as run NTU-J- CJE-D-01 except that the weght W was determned by formula (3). 3. NTU-J-CJE-D-03 The smlarty scores were adjusted by multplyng a constant weght. The smlarty scores n Japanese-Englsh run multpled 1.5; the smlarty scores n Japanese-Chnese run multpled 0.5; the smlarty scores n monolngual Japanese run were not changed. These values were traned from the experments usng dry-run data. The results of our offcal runs are shown n Table 1. Table 2 shows the unoffcal evaluaton of ntermedate monolngual (.e., Japanese to Japanese) and cross-lngual runs (.e., Japanese to Englsh and Japanese to Englsh). The relevant assessment of each language s extracted from multlngual assessment fle. The performance of run NTU-J- CJE-D-02 s slghtly better than that of run NTU-J- CJE-01. The weght W of run NTU-J-CJE-D-02 s smaller than that of run NTU-J-CJE-D-01 for most queres. But t seems not small enough for Japanese- Chnese cross-lngual run. Snce the Chnese translatons of Japanese queres are not translated well, the performance of Japanese-Chnese crosslngual run s worse. When mergng results, the

4 The Thrd NTCIR Workshop, Sep Oct Table 1. The results of offcal runs Run # Topc Scorng Mode Average Precson Recall NTU-E-E-D Rgd / 444 Relax / 741 NTU-J-CJE-D Rgd / 4053 Relax / 6648 NTU-J-CJE-D Rgd / 4053 Relax / 6648 NTU-J-CJE-D Rgd / 4053 Relax / 6648 Table 2. The results of ntermedate runs Run # Topc Scorng Mode Average Precson Recall ntu-fr-j-j-d 45 Rgd / 1659 ntu-fr-j-e-d 40 Rgd /456 ntu-fr-j-c-d 48 Rgd /1938 Japanese-Chnese cross-lngual run should have lower weght. The performances of the offcal multlngual runs do not dffer too much. The best run s NTU-J-CJE-D-03 whose average precson s The weghts traned from dry-run experments stll perform well n the formal-run. In order to compare the effectveness of dfferent mergng strateges, we also conducted several unoffcal runs shown as follows. 1. ntu-fr-j-cje-d-01 The mergng strategy s the same as run NTU-J- CJE-D-01, but the values of parameters c 1, c 2 and c 3 were set to 0, 0.6 and 0.4, respectvely. 2. ntu-fr-j-cje-d-02 The mergng strategy s the same as run NTU-J- CJE-D-02, but the values of parameters c 1, c 2 and c 3 were set to 0, 0.6 and 0.4, respectvely. 3. ntu-fr-j-cje-d-04 The mergng strategy s the same as run ntu-fr-jcje-d-01 except that the weght W was determned by formula (4). 4. ntu-fr-j-cje-d-raw-score We used raw-score mergng to merge result lsts. 5. ntu-fr-j-cje-d-normalzed-score The result lsts were merged by normalzedscore mergng strategy. The maxmum smlarty score was used for normalzaton. 6. ntu-fr-j-cje-d-normalzed-top10 In ths run, we used the modfed normalzedscore mergng method. We dd not consder the performance drop caused by query translaton. That s, the weght W n formula (1) was 1 for every sub run. 7. ntu-fr-j-cje-d-round-robn We used round-robn mergng to merge result lsts. 8. ntu-fr-j-cje-d-centralzed Ths run adopted centralzed archtecture. All document collectons were ndexed n one ndex fle. The topcs contaned orgnal Japanese query terms, translated Englsh query terms and translated Chnese query terms. The results of unoffcal runs are shown n Table 3. We used the rgd relevant set to evaluate the unoffcal runs. In the offcal evaluaton, the Japanese documents wthout text were removed from the ranked lst. We dd not remove those Japanese documents when evaluatng our unoffcal runs n Table 1. Therefore, the results of unoffcal runs cannot be compared to the offcal runs. We reevaluated the offcal runs wthout removng the Japanese documents wthout text. The new results of runs NTU-J-CJE-D-01, NTU-J-CJE-D-02 and NTU- J-CJE-D-03 are shown n the last three rows n Table 3. Table 3 shows that the performances of ntu-fr-jcje-d-01, ntu-fr-j-cje-d-02, and ntu-fr-j-cje-d-04 are smlar to those of offcal runs even the values of parameters c 1, c 2 and c 3 are changed. The performance of raw-score mergng s good. Ths s probably because we use the same IR model and term weghtng scheme for all text collectons. Comparatvely, the performances of normalzedscore, round-robn and normalzed-by-top-k mergng are poor, especally round-robn mergng strategy. Normalzd-by-top-k s better than normalzed score mergng. When consderng the translaton penalty, the performance of normalzed-by-top-k s ncreased and s better than the other mergng strateges. It shows that translaton penalty s helpful. The best run s ntu-fr-j-cje-d-centralzed, whch ndexes all documents n dfferent languages together. In ths run, most of the top ranked documents are n Japanese or n Englsh n most topcs. Table 2 shows that the performances of Japanese monolngual

5 Proceedngs of the Thrd NTCIR Workshop Table 3. The results of unoffcal runs Run Average Precson Recall ntu-fr-j-cje-d / 4053 ntu-fr-j-cje-d / 4053 ntu-fr-j-cje-d / 4053 ntu-fr-j-cje-d-raw-score / 4053 ntu-fr-j-cje-d-normalzed-score / 4053 ntu-fr-j-cje-d-normalzed-top / 4053 ntu-fr-j-cje-d-round-robn / 4053 ntu-fr-j-cje-d-centralzed / 4053 NTU-J-CJE-D / 4053 NTU-J-CJE-D / 4053 NTU-J-CJE-D / 4053 Table 4. The results of unoffcal runs usng new Japanese-Chnese run Run Average Precson Recall ntu-fr-j-c-d /1938 ntu-fr-j-cje-d / 4053 ntu-fr-j-cje-d / 4053 ntu-fr-j-cje-d / 4053 ntu-fr-j-cje-d-raw-score / 4053 ntu-fr-j-cje-d-normalzed-score / 4053 ntu-fr-j-cje-d-normalzed-top / 4053 ntu-fr-j-cje-d-round-robn / 4053 ntu-fr-j-cje-d-centralzed / 4053 Table 5. Normalzed-by-top-k wth translaton penalty (C 1 =0, C 2 =0.4, C 3 =0.6) Run Average Precson Recall ntu-fr-j-cje-d / 4053 ntu-fr-j-cje-d / 4053 ntu-fr-j-cje-d / 4053 retreval and Japanese-Englsh cross-lngual retreval are much better than that of Japanese-Chnese crosslngual retreval. Therefore, the fnal result lst should not contan too many Chnese documents. The over-weghtng phenomenon n centralzed archtecture ncreases the scores of Japanese and Englsh documents, so that more Japanese and Englsh documents are ncluded n the result lst of run ntu-fr-j-cje-d-centralzed. Ths makes the performance better. In the ntal experments, we use Englsh as a pvot language to derve Chnese translaton equvalents of Japanese query terms. Expermental results show that the performance of Japanese- Chnese cross-lngual run s very bad. In the further tests, we translated Japanese queres nto Chnese drectly by usng BtEx onlne Japanese-Chnese dctonary ( Table 4 lsts the performances of new Japanese-Chnese crosslngual run and multlngual runs. The performance of the new Japanese-Chnese cross-lngual run s mproved only a lttle,.e., from to The major reason s that many query terms have no translaton. After analyss, there are 351 dstnct query terms n the descrpton feld of Japanese queres. Among these, total 232 terms have no translaton. The remanng query terms have only one translaton. Furthermore, our system dd not return any documents n the new Japanese-Chnese cross-lngual run for topcs 16, 19 and 23. Ths s because all the translated Chnese terms of these three topcs are ungrams and our system uses bgrams as ndex terms. In such a case, no relevant document s proposed. The performance of centralzed archtecture s stll the best. When consderng the translaton penalty, normalzed-by-top-k (.e., runs ntu-fr-j-cje-d-02-2 and ntu-fr-j-cje-d-04-2) s better than the other mergng strateges. Compared to the old translaton scheme, the performances of all mergng strateges

6 The Thrd NTCIR Workshop, Sep Oct except raw-score and normalzed-by-top-k wth translaton penalty are ncreased when the Japanese queres are translated nto Chnese by usng BtEx onlne dctonary. Snce the Japanese query terms have only one Chnese translaton, emphaszng the degree of translaton ambguty part n formulas 2-4 ncreases the mergng weght of Japanese-Chnese cross-lngual run. That decreases the performance of normalzed-by-top-k wth translaton penalty. Thus, we adjusted the values of parameters c 1, c 2 and c 3 to 0, 0.4 and 0.6, respectvely. Table 5 shows that the performances are mproved. In summary, the translaton penalty s an mportant factor n mergng, and we should also consder the qualty factor of dctonares (e.g., ts coverage). [5] Huang, C.R. and Chen, K.J., Academc Snca Balanced Corpus. Techncal Report 95-02/ Academc Snca, Tape, Tawan. [6] Matsumoto, Y., Ktauch, A., Yamashta, T., and Hrano, Y., Japanese Morphologcal Analyss System ChaSen verson 2.0 Manual. Techncal Report NAIST-IS-TR99009, Nara Insttute of Scence and Technology Techncal Report. [7] Oard, D.W. and Dorr, B.J., A Survey of Multlngual Text Retreval. Techncal Report UMIACS-TR-96-19, Unversty of Maryland, Insttute for Advanced Computer Studes. [8] Voorhees, E.M., Gupta, N.K., and Johnson-Lard, B., The Collecton Fuson Problem. In proceedngs of the Thrd Text REtreval Conference (TREC-3), Gathersburg, Maryland, November, NIST Publcaton, Concludng Remarks Ths paper consders the two archtectures n MLIR. The centralzed approach performed well n all the experments. However, the centralzed archtecture s not sutable n practce, especally for very huge corpora. Centralzed archtecture needs spendng more tme to ndex and to retreve documents n all languages. Dstrbuted archtecture s more flexble. It s easy to add or delete corpora n dfferent languages and employ dfferent retreval systems n dstrbuted archtecture. Mergng problem s crtcal n dstrbuted archtecture. Ths paper proposed several mergng strateges to ntegrate the result lsts of collectons n dfferent languages. The expermental results showed that the performance of normalzed-by-top-k wth translaton penalty was better than raw-score mergng, normalzed-score mergng and round-robn mergng. References [1] Chen, H.H., Ban, G.W., and Ln, W.C., Resolvng translaton ambguty and target polysemy n cross-language nformaton retreval. In Proceedngs of 37 th Annual Meetng of the Assocaton for Computatonal Lngustcs, Maryland, June Assocaton for Computatonal Lngustcs, [2] Church, K., Gale, W., Hanks, P., and Hndle, D., Parsng, Word Assocatons and Typcal Predcate- Argument Relatons. In Proceedngs of Internatonal Workshop on Parsng Technologes, Pttsburgh, PA, August Carnege Mellon Unversty, Pttsburgh, PA, [3] Dumas, S.T., LSI meets TREC: A Status Report. In proceedngs of the Frst Text REtreval Conference (TREC-1), Gathersburg, Maryland, November, NIST Publcaton, [4] Harman, D.K., TREC-6 Proceedngs. Gathersburg, Maryland. Natonal Insttute of Standards and Technology.

Merging Results by Using Predicted Retrieval Effectiveness

Merging Results by Using Predicted Retrieval Effectiveness Mergng Results by Usng Predcted Retreval Effectveness Introducton Wen-Cheng Ln and Hsn-Hs Chen Departent of Coputer Scence and Inforaton Engneerng Natonal Tawan Unversty Tape, TAIWAN densln@nlg.cse.ntu.edu.tw;

More information

UB at GeoCLEF Department of Geography Abstract

UB at GeoCLEF Department of Geography   Abstract UB at GeoCLEF 2006 Mguel E. Ruz (1), Stuart Shapro (2), June Abbas (1), Slva B. Southwck (1) and Davd Mark (3) State Unversty of New York at Buffalo (1) Department of Lbrary and Informaton Studes (2) Department

More information

Performance Evaluation of Information Retrieval Systems

Performance Evaluation of Information Retrieval Systems Why System Evaluaton? Performance Evaluaton of Informaton Retreval Systems Many sldes n ths secton are adapted from Prof. Joydeep Ghosh (UT ECE) who n turn adapted them from Prof. Dk Lee (Unv. of Scence

More information

Term Weighting Classification System Using the Chi-square Statistic for the Classification Subtask at NTCIR-6 Patent Retrieval Task

Term Weighting Classification System Using the Chi-square Statistic for the Classification Subtask at NTCIR-6 Patent Retrieval Task Proceedngs of NTCIR-6 Workshop Meetng, May 15-18, 2007, Tokyo, Japan Term Weghtng Classfcaton System Usng the Ch-square Statstc for the Classfcaton Subtask at NTCIR-6 Patent Retreval Task Kotaro Hashmoto

More information

Combining Multiple Resources, Evidence and Criteria for Genomic Information Retrieval

Combining Multiple Resources, Evidence and Criteria for Genomic Information Retrieval Combnng Multple Resources, Evdence and Crtera for Genomc Informaton Retreval Luo S 1, Je Lu 2 and Jame Callan 2 1 Department of Computer Scence, Purdue Unversty, West Lafayette, IN 47907, USA ls@cs.purdue.edu

More information

Query Clustering Using a Hybrid Query Similarity Measure

Query Clustering Using a Hybrid Query Similarity Measure Query clusterng usng a hybrd query smlarty measure Fu. L., Goh, D.H., & Foo, S. (2004). WSEAS Transacton on Computers, 3(3), 700-705. Query Clusterng Usng a Hybrd Query Smlarty Measure Ln Fu, Don Hoe-Lan

More information

Cross-Language Information Retrieval

Cross-Language Information Retrieval Feature Artcle: Cross-Language Informaton Retreval 19 Cross-Language Informaton Retreval Jan-Yun Ne 1 Abstract A research group n Unversty of Montreal has worked on the problem of cross-language nformaton

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

Federated Search of Text-Based Digital Libraries in Hierarchical Peer-to-Peer Networks

Federated Search of Text-Based Digital Libraries in Hierarchical Peer-to-Peer Networks Federated Search of Text-Based Dgtal Lbrares n Herarchcal Peer-to-Peer Networks Je Lu School of Computer Scence Carnege Mellon Unversty Pttsburgh, PA 15213 jelu@cs.cmu.edu Jame Callan School of Computer

More information

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration Improvement of Spatal Resoluton Usng BlockMatchng Based Moton Estmaton and Frame Integraton Danya Suga and Takayuk Hamamoto Graduate School of Engneerng, Tokyo Unversty of Scence, 6-3-1, Nuku, Katsuska-ku,

More information

School of Engineering and Technology, Department of Computer Science, Pondicherry University Pondicherry-India.

School of Engineering and Technology, Department of Computer Science, Pondicherry University Pondicherry-India. IEEE-Internatonal Conference on Recent Trends n Informaton Technology, ICRTIT 2 MIT, Anna Unversty, Chenna. June 3-5, 2 Performance Evaluaton of Multlngual Informaton Retreval (MLIR) System over Informaton

More information

Cross-lingual Pseudo Relevance Feedback Based on Weak Relevant Topic Alignment

Cross-lingual Pseudo Relevance Feedback Based on Weak Relevant Topic Alignment Cross-lngual Pseudo Relevance Feedback Based on Weak Relevant opc Algnment WANG Xu-wen Insttute of Medcal Informaton & Lbrary, Chnese Academy of Medcal Scences, Beng 100020 wang.xuwen@mcams.ac.cn ZHANG

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

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

Document Representation and Clustering with WordNet Based Similarity Rough Set Model

Document Representation and Clustering with WordNet Based Similarity Rough Set Model IJCSI Internatonal Journal of Computer Scence Issues, Vol. 8, Issue 5, No 3, September 20 ISSN (Onlne): 694-084 www.ijcsi.org Document Representaton and Clusterng wth WordNet Based Smlarty Rough Set Model

More information

Learning-Based Top-N Selection Query Evaluation over Relational Databases

Learning-Based Top-N Selection Query Evaluation over Relational Databases Learnng-Based Top-N Selecton Query Evaluaton over Relatonal Databases Lang Zhu *, Wey Meng ** * School of Mathematcs and Computer Scence, Hebe Unversty, Baodng, Hebe 071002, Chna, zhu@mal.hbu.edu.cn **

More information

A Binarization Algorithm specialized on Document Images and Photos

A Binarization Algorithm specialized on Document Images and Photos A Bnarzaton Algorthm specalzed on Document mages and Photos Ergna Kavalleratou Dept. of nformaton and Communcaton Systems Engneerng Unversty of the Aegean kavalleratou@aegean.gr Abstract n ths paper, a

More information

Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers

Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers IOSR Journal of Electroncs and Communcaton Engneerng (IOSR-JECE) e-issn: 78-834,p- ISSN: 78-8735.Volume 9, Issue, Ver. IV (Mar - Apr. 04), PP 0-07 Content Based Image Retreval Usng -D Dscrete Wavelet wth

More information

Using Fuzzy Logic to Enhance the Large Size Remote Sensing Images

Using Fuzzy Logic to Enhance the Large Size Remote Sensing Images Internatonal Journal of Informaton and Electroncs Engneerng Vol. 5 No. 6 November 015 Usng Fuzzy Logc to Enhance the Large Sze Remote Sensng Images Trung Nguyen Tu Huy Ngo Hoang and Thoa Vu Van Abstract

More information

Semantic Image Retrieval Using Region Based Inverted File

Semantic Image Retrieval Using Region Based Inverted File Semantc Image Retreval Usng Regon Based Inverted Fle Dengsheng Zhang, Md Monrul Islam, Guoun Lu and Jn Hou 2 Gppsland School of Informaton Technology, Monash Unversty Churchll, VIC 3842, Australa E-mal:

More information

Optimizing Document Scoring for Query Retrieval

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

More information

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

Information Retrieval

Information Retrieval Anmol Bhasn abhasn[at]cedar.buffalo.edu Moht Devnan mdevnan[at]cse.buffalo.edu Sprng 2005 #$ "% &'" (! Informaton Retreval )" " * + %, ##$ + *--. / "#,0, #'",,,#$ ", # " /,,#,0 1"%,2 '",, Documents are

More information

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

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

More information

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

SEMANTIC SEARCH OF INTERNET INFORMATION RESOURCES ON BASE OF ONTOLOGIES AND MULTILINGUISTIC THESAURUSES. Anatoly Gladun, Julia Rogushina

SEMANTIC SEARCH OF INTERNET INFORMATION RESOURCES ON BASE OF ONTOLOGIES AND MULTILINGUISTIC THESAURUSES. Anatoly Gladun, Julia Rogushina 48 SEMANTIC SEARCH OF INTERNET INFORMATION RESOURCES ON BASE OF ONTOLOGIES AND MULTILINGUISTIC THESAURUSES Anatoly Gladun, Jula Rogushna Abstract: the approaches to the analyss of varous nformaton resources

More information

Online Text Mining System based on M2VSM

Online Text Mining System based on M2VSM FR-E2-1 SCIS & ISIS 2008 Onlne Text Mnng System based on M2VSM Yasufum Takama 1, Takash Okada 1, Toru Ishbash 2 1. Tokyo Metropoltan Unversty, 2. Tokyo Metropoltan Insttute of Technology 6-6 Asahgaoka,

More information

Complex Numbers. Now we also saw that if a and b were both positive then ab = a b. For a second let s forget that restriction and do the following.

Complex Numbers. Now we also saw that if a and b were both positive then ab = a b. For a second let s forget that restriction and do the following. Complex Numbers The last topc n ths secton s not really related to most of what we ve done n ths chapter, although t s somewhat related to the radcals secton as we wll see. We also won t need the materal

More information

Selecting Query Term Alterations for Web Search by Exploiting Query Contexts

Selecting Query Term Alterations for Web Search by Exploiting Query Contexts Selectng Query Term Alteratons for Web Search by Explotng Query Contexts Guhong Cao Stephen Robertson Jan-Yun Ne Dept. of Computer Scence and Operatons Research Mcrosoft Research at Cambrdge Dept. of Computer

More information

Related-Mode Attacks on CTR Encryption Mode

Related-Mode Attacks on CTR Encryption Mode Internatonal Journal of Network Securty, Vol.4, No.3, PP.282 287, May 2007 282 Related-Mode Attacks on CTR Encrypton Mode Dayn Wang, Dongda Ln, and Wenlng Wu (Correspondng author: Dayn Wang) Key Laboratory

More information

Scheduling Remote Access to Scientific Instruments in Cyberinfrastructure for Education and Research

Scheduling Remote Access to Scientific Instruments in Cyberinfrastructure for Education and Research Schedulng Remote Access to Scentfc Instruments n Cybernfrastructure for Educaton and Research Je Yn 1, Junwe Cao 2,3,*, Yuexuan Wang 4, Lanchen Lu 1,3 and Cheng Wu 1,3 1 Natonal CIMS Engneerng and Research

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

A Method of Hot Topic Detection in Blogs Using N-gram Model

A Method of Hot Topic Detection in Blogs Using N-gram Model 84 JOURNAL OF SOFTWARE, VOL. 8, NO., JANUARY 203 A Method of Hot Topc Detecton n Blogs Usng N-gram Model Xaodong Wang College of Computer and Informaton Technology, Henan Normal Unversty, Xnxang, Chna

More information

CSCI 5417 Information Retrieval Systems Jim Martin!

CSCI 5417 Information Retrieval Systems Jim Martin! CSCI 5417 Informaton Retreval Systems Jm Martn! Lecture 11 9/29/2011 Today 9/29 Classfcaton Naïve Bayes classfcaton Ungram LM 1 Where we are... Bascs of ad hoc retreval Indexng Term weghtng/scorng Cosne

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

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

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

Steps for Computing the Dissimilarity, Entropy, Herfindahl-Hirschman and. Accessibility (Gravity with Competition) Indices

Steps for Computing the Dissimilarity, Entropy, Herfindahl-Hirschman and. Accessibility (Gravity with Competition) Indices Steps for Computng the Dssmlarty, Entropy, Herfndahl-Hrschman and Accessblty (Gravty wth Competton) Indces I. Dssmlarty Index Measurement: The followng formula can be used to measure the evenness between

More information

KIDS Lab at ImageCLEF 2012 Personal Photo Retrieval

KIDS Lab at ImageCLEF 2012 Personal Photo Retrieval KD Lab at mageclef 2012 Personal Photo Retreval Cha-We Ku, Been-Chan Chen, Guan-Bn Chen, L-J Gaou, Rong-ng Huang, and ao-en Wang Knowledge, nformaton, and Database ystem Laboratory Department of Computer

More information

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching A Fast Vsual Trackng Algorthm Based on Crcle Pxels Matchng Zhqang Hou hou_zhq@sohu.com Chongzhao Han czhan@mal.xjtu.edu.cn Ln Zheng Abstract: A fast vsual trackng algorthm based on crcle pxels matchng

More information

Virtual Machine Migration based on Trust Measurement of Computer Node

Virtual Machine Migration based on Trust Measurement of Computer Node Appled Mechancs and Materals Onlne: 2014-04-04 ISSN: 1662-7482, Vols. 536-537, pp 678-682 do:10.4028/www.scentfc.net/amm.536-537.678 2014 Trans Tech Publcatons, Swtzerland Vrtual Machne Mgraton based on

More information

Keywords - Wep page classification; bag of words model; topic model; hierarchical classification; Support Vector Machines

Keywords - Wep page classification; bag of words model; topic model; hierarchical classification; Support Vector Machines (IJCSIS) Internatonal Journal of Computer Scence and Informaton Securty, Herarchcal Web Page Classfcaton Based on a Topc Model and Neghborng Pages Integraton Wongkot Srura Phayung Meesad Choochart Haruechayasak

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

An Image Fusion Approach Based on Segmentation Region

An Image Fusion Approach Based on Segmentation Region Rong Wang, L-Qun Gao, Shu Yang, Yu-Hua Cha, and Yan-Chun Lu An Image Fuson Approach Based On Segmentaton Regon An Image Fuson Approach Based on Segmentaton Regon Rong Wang, L-Qun Gao, Shu Yang 3, Yu-Hua

More information

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

Load-Balanced Anycast Routing

Load-Balanced Anycast Routing Load-Balanced Anycast Routng Chng-Yu Ln, Jung-Hua Lo, and Sy-Yen Kuo Department of Electrcal Engneerng atonal Tawan Unversty, Tape, Tawan sykuo@cc.ee.ntu.edu.tw Abstract For fault-tolerance and load-balance

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

Deep Classification in Large-scale Text Hierarchies

Deep Classification in Large-scale Text Hierarchies Deep Classfcaton n Large-scale Text Herarches Gu-Rong Xue Dkan Xng Qang Yang 2 Yong Yu Dept. of Computer Scence and Engneerng Shangha Jao-Tong Unversty {grxue, dkxng, yyu}@apex.sjtu.edu.cn 2 Hong Kong

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

Syntactic Tree-based Relation Extraction Using a Generalization of Collins and Duffy Convolution Tree Kernel

Syntactic Tree-based Relation Extraction Using a Generalization of Collins and Duffy Convolution Tree Kernel Syntactc Tree-based Relaton Extracton Usng a Generalzaton of Collns and Duffy Convoluton Tree Kernel Mahdy Khayyaman Seyed Abolghasem Hassan Abolhassan Mrroshandel Sharf Unversty of Technology Sharf Unversty

More information

Helsinki University Of Technology, Systems Analysis Laboratory Mat Independent research projects in applied mathematics (3 cr)

Helsinki University Of Technology, Systems Analysis Laboratory Mat Independent research projects in applied mathematics (3 cr) Helsnk Unversty Of Technology, Systems Analyss Laboratory Mat-2.08 Independent research projects n appled mathematcs (3 cr) "! #$&% Antt Laukkanen 506 R ajlaukka@cc.hut.f 2 Introducton...3 2 Multattrbute

More information

A Unified Framework for Semantics and Feature Based Relevance Feedback in Image Retrieval Systems

A Unified Framework for Semantics and Feature Based Relevance Feedback in Image Retrieval Systems A Unfed Framework for Semantcs and Feature Based Relevance Feedback n Image Retreval Systems Ye Lu *, Chunhu Hu 2, Xngquan Zhu 3*, HongJang Zhang 2, Qang Yang * School of Computng Scence Smon Fraser Unversty

More information

Lobachevsky State University of Nizhni Novgorod. Polyhedron. Quick Start Guide

Lobachevsky State University of Nizhni Novgorod. Polyhedron. Quick Start Guide Lobachevsky State Unversty of Nzhn Novgorod Polyhedron Quck Start Gude Nzhn Novgorod 2016 Contents Specfcaton of Polyhedron software... 3 Theoretcal background... 4 1. Interface of Polyhedron... 6 1.1.

More information

Experiments in Text Categorization Using Term Selection by Distance to Transition Point

Experiments in Text Categorization Using Term Selection by Distance to Transition Point Experments n Text Categorzaton Usng Term Selecton by Dstance to Transton Pont Edgar Moyotl-Hernández, Héctor Jménez-Salazar Facultad de Cencas de la Computacón, B. Unversdad Autónoma de Puebla, 14 Sur

More information

A KIND OF ROUTING MODEL IN PEER-TO-PEER NETWORK BASED ON SUCCESSFUL ACCESSING RATE

A KIND OF ROUTING MODEL IN PEER-TO-PEER NETWORK BASED ON SUCCESSFUL ACCESSING RATE A KIND OF ROUTING MODEL IN PEER-TO-PEER NETWORK BASED ON SUCCESSFUL ACCESSING RATE 1 TAO LIU, 2 JI-JUN XU 1 College of Informaton Scence and Technology, Zhengzhou Normal Unversty, Chna 2 School of Mathematcs

More information

An Efficient Garbage Collection for Flash Memory-Based Virtual Memory Systems

An Efficient Garbage Collection for Flash Memory-Based Virtual Memory Systems S. J and D. Shn: An Effcent Garbage Collecton for Flash Memory-Based Vrtual Memory Systems 2355 An Effcent Garbage Collecton for Flash Memory-Based Vrtual Memory Systems Seunggu J and Dongkun Shn, Member,

More information

Hierarchical clustering for gene expression data analysis

Hierarchical clustering for gene expression data analysis Herarchcal clusterng for gene expresson data analyss Gorgo Valentn e-mal: valentn@ds.unm.t Clusterng of Mcroarray Data. Clusterng of gene expresson profles (rows) => dscovery of co-regulated and functonally

More information

Relevance Feedback Document Retrieval using Non-Relevant Documents

Relevance Feedback Document Retrieval using Non-Relevant Documents Relevance Feedback Document Retreval usng Non-Relevant Documents TAKASHI ONODA, HIROSHI MURATA and SEIJI YAMADA Ths paper reports a new document retreval method usng non-relevant documents. From a large

More information

Synthesizer 1.0. User s Guide. A Varying Coefficient Meta. nalytic Tool. Z. Krizan Employing Microsoft Excel 2007

Synthesizer 1.0. User s Guide. A Varying Coefficient Meta. nalytic Tool. Z. Krizan Employing Microsoft Excel 2007 Syntheszer 1.0 A Varyng Coeffcent Meta Meta-Analytc nalytc Tool Employng Mcrosoft Excel 007.38.17.5 User s Gude Z. Krzan 009 Table of Contents 1. Introducton and Acknowledgments 3. Operatonal Functons

More information

Improving the Quality of Information Retrieval Using Syntactic Analysis of Search Query

Improving the Quality of Information Retrieval Using Syntactic Analysis of Search Query Improvng the Qualty of Informaton Retreval Usng Syntactc Analyss of Search Query Nadezhda Yarushkna 1[0000-0002-5718-8732], Aleksey Flppov 1[0000-0003-0008-5035], and Mara Grgorcheva 1[0000-0001-7492-5178]

More information

Classic Term Weighting Technique for Mining Web Content Outliers

Classic Term Weighting Technique for Mining Web Content Outliers Internatonal Conference on Computatonal Technques and Artfcal Intellgence (ICCTAI'2012) Penang, Malaysa Classc Term Weghtng Technque for Mnng Web Content Outlers W.R. Wan Zulkfel, N. Mustapha, and A. Mustapha

More information

An Iterative Implicit Feedback Approach to Personalized Search

An Iterative Implicit Feedback Approach to Personalized Search An Iteratve Implct Feedback Approach to Personalzed Search Yuanhua Lv 1, Le Sun 2, Junln Zhang 2, Jan-Yun Ne 3, Wan Chen 4, and We Zhang 2 1, 2 Insttute of Software, Chnese Academy of Scences, Beng, 100080,

More information

Arabic Text Classification Using N-Gram Frequency Statistics A Comparative Study

Arabic Text Classification Using N-Gram Frequency Statistics A Comparative Study Arabc Text Classfcaton Usng N-Gram Frequency Statstcs A Comparatve Study Lala Khresat Dept. of Computer Scence, Math and Physcs Farlegh Dcknson Unversty 285 Madson Ave, Madson NJ 07940 Khresat@fdu.edu

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

An Improved Image Segmentation Algorithm Based on the Otsu Method

An Improved Image Segmentation Algorithm Based on the Otsu Method 3th ACIS Internatonal Conference on Software Engneerng, Artfcal Intellgence, Networkng arallel/dstrbuted Computng An Improved Image Segmentaton Algorthm Based on the Otsu Method Mengxng Huang, enjao Yu,

More information

CS47300: Web Information Search and Management

CS47300: Web Information Search and Management CS47300: Web Informaton Search and Management Prof. Chrs Clfton 15 September 2017 Materal adapted from course created by Dr. Luo S, now leadng Albaba research group Retreval Models Informaton Need Representaton

More information

Web Document Classification Based on Fuzzy Association

Web Document Classification Based on Fuzzy Association Web Document Classfcaton Based on Fuzzy Assocaton Choochart Haruechayasa, Me-Lng Shyu Department of Electrcal and Computer Engneerng Unversty of Mam Coral Gables, FL 33124, USA charuech@mam.edu, shyu@mam.edu

More information

Using Language Models for Flat Text Queries in XML Retrieval

Using Language Models for Flat Text Queries in XML Retrieval Usng Language Models for Flat ext Queres n XML Retreval aul Oglve, Jame Callan Language echnoes Insttute School of Computer Scence Carnege Mellon Unversty ttsburgh, A USA {pto,callan}@cs.cmu.edu ABSRAC

More information

Background Removal in Image indexing and Retrieval

Background Removal in Image indexing and Retrieval Background Removal n Image ndexng and Retreval Y Lu and Hong Guo Department of Electrcal and Computer Engneerng The Unversty of Mchgan-Dearborn Dearborn Mchgan 4818-1491, U.S.A. Voce: 313-593-508, Fax:

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

Reducing Frame Rate for Object Tracking

Reducing Frame Rate for Object Tracking Reducng Frame Rate for Object Trackng Pavel Korshunov 1 and We Tsang Oo 2 1 Natonal Unversty of Sngapore, Sngapore 11977, pavelkor@comp.nus.edu.sg 2 Natonal Unversty of Sngapore, Sngapore 11977, oowt@comp.nus.edu.sg

More information

Video Proxy System for a Large-scale VOD System (DINA)

Video Proxy System for a Large-scale VOD System (DINA) Vdeo Proxy System for a Large-scale VOD System (DINA) KWUN-CHUNG CHAN #, KWOK-WAI CHEUNG *# #Department of Informaton Engneerng *Centre of Innovaton and Technology The Chnese Unversty of Hong Kong SHATIN,

More information

Hermite Splines in Lie Groups as Products of Geodesics

Hermite Splines in Lie Groups as Products of Geodesics Hermte Splnes n Le Groups as Products of Geodescs Ethan Eade Updated May 28, 2017 1 Introducton 1.1 Goal Ths document defnes a curve n the Le group G parametrzed by tme and by structural parameters n the

More information

A Novel Adaptive Descriptor Algorithm for Ternary Pattern Textures

A Novel Adaptive Descriptor Algorithm for Ternary Pattern Textures A Novel Adaptve Descrptor Algorthm for Ternary Pattern Textures Fahuan Hu 1,2, Guopng Lu 1 *, Zengwen Dong 1 1.School of Mechancal & Electrcal Engneerng, Nanchang Unversty, Nanchang, 330031, Chna; 2. School

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

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

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

More information

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

Keyword-based Document Clustering

Keyword-based Document Clustering Keyword-based ocument lusterng Seung-Shk Kang School of omputer Scence Kookmn Unversty & AIrc hungnung-dong Songbuk-gu Seoul 36-72 Korea sskang@kookmn.ac.kr Abstract ocument clusterng s an aggregaton of

More information

TECHNIQUE OF FORMATION HOMOGENEOUS SAMPLE SAME OBJECTS. Muradaliyev A.Z.

TECHNIQUE OF FORMATION HOMOGENEOUS SAMPLE SAME OBJECTS. Muradaliyev A.Z. TECHNIQUE OF FORMATION HOMOGENEOUS SAMPLE SAME OBJECTS Muradalyev AZ Azerbajan Scentfc-Research and Desgn-Prospectng Insttute of Energetc AZ1012, Ave HZardab-94 E-mal:aydn_murad@yahoocom Importance of

More information

BioTechnology. An Indian Journal FULL PAPER. Trade Science Inc.

BioTechnology. An Indian Journal FULL PAPER. Trade Science Inc. [Type text] [Type text] [Type text] ISSN : 0974-74 Volume 0 Issue BoTechnology 04 An Indan Journal FULL PAPER BTAIJ 0() 04 [684-689] Revew on Chna s sports ndustry fnancng market based on market -orented

More information

The Effect of Similarity Measures on The Quality of Query Clusters

The Effect of Similarity Measures on The Quality of Query Clusters The effect of smlarty measures on the qualty of query clusters. Fu. L., Goh, D.H., Foo, S., & Na, J.C. (2004). Journal of Informaton Scence, 30(5) 396-407 The Effect of Smlarty Measures on The Qualty of

More information

Recommended Items Rating Prediction based on RBF Neural Network Optimized by PSO Algorithm

Recommended Items Rating Prediction based on RBF Neural Network Optimized by PSO Algorithm Recommended Items Ratng Predcton based on RBF Neural Network Optmzed by PSO Algorthm Chengfang Tan, Cayn Wang, Yuln L and Xx Q Abstract In order to mtgate the data sparsty and cold-start problems of recommendaton

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

Virtual Memory. Background. No. 10. Virtual Memory: concept. Logical Memory Space (review) Demand Paging(1) Virtual Memory

Virtual Memory. Background. No. 10. Virtual Memory: concept. Logical Memory Space (review) Demand Paging(1) Virtual Memory Background EECS. Operatng System Fundamentals No. Vrtual Memory Prof. Hu Jang Department of Electrcal Engneerng and Computer Scence, York Unversty Memory-management methods normally requres the entre process

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

Intrinsic Plagiarism Detection Using Character n-gram Profiles

Intrinsic Plagiarism Detection Using Character n-gram Profiles Intrnsc Plagarsm Detecton Usng Character n-gram Profles Efstathos Stamatatos Unversty of the Aegean 83200 - Karlovass, Samos, Greece stamatatos@aegean.gr Abstract: The task of ntrnsc plagarsm detecton

More information

Parallel matrix-vector multiplication

Parallel matrix-vector multiplication Appendx A Parallel matrx-vector multplcaton The reduced transton matrx of the three-dmensonal cage model for gel electrophoress, descrbed n secton 3.2, becomes excessvely large for polymer lengths more

More information

Under-Sampling Approaches for Improving Prediction of the Minority Class in an Imbalanced Dataset

Under-Sampling Approaches for Improving Prediction of the Minority Class in an Imbalanced Dataset Under-Samplng Approaches for Improvng Predcton of the Mnorty Class n an Imbalanced Dataset Show-Jane Yen and Yue-Sh Lee Department of Computer Scence and Informaton Engneerng, Mng Chuan Unversty 5 The-Mng

More information

An Indian Journal FULL PAPER ABSTRACT KEYWORDS. Trade Science Inc.

An Indian Journal FULL PAPER ABSTRACT KEYWORDS. Trade Science Inc. [Type text] [Type text] [Type text] ISSN : 97-735 Volume Issue 9 BoTechnology An Indan Journal FULL PAPER BTAIJ, (9), [333-3] Matlab mult-dmensonal model-based - 3 Chnese football assocaton super league

More information

Advanced Computer Networks

Advanced Computer Networks Char of Network Archtectures and Servces Department of Informatcs Techncal Unversty of Munch Note: Durng the attendance check a stcker contanng a unque QR code wll be put on ths exam. Ths QR code contans

More information

Federated Search of Text Search Engines in Uncooperative Environments

Federated Search of Text Search Engines in Uncooperative Environments 1 Federated Search of Text Search Engnes n Uncooperatve Envronments Luo S Thess Proposal Language Technology Insttute School of Computer Scence Carnege Mellon Unversty ls@cs.cmu.edu Thess Commttee: Jame

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

LRD: Latent Relation Discovery for Vector Space Expansion and Information Retrieval

LRD: Latent Relation Discovery for Vector Space Expansion and Information Retrieval LRD: Latent Relaton Dscovery for Vector Space Expanson and Informaton Retreval Techncal Report KMI-06-09 March, 006 Alexandre Gonçalves, Janhan Zhu, Dawe Song, Vctora Uren, Roberto Pacheco In Proc. of

More information

Fast Computation of Shortest Path for Visiting Segments in the Plane

Fast Computation of Shortest Path for Visiting Segments in the Plane Send Orders for Reprnts to reprnts@benthamscence.ae 4 The Open Cybernetcs & Systemcs Journal, 04, 8, 4-9 Open Access Fast Computaton of Shortest Path for Vstng Segments n the Plane Ljuan Wang,, Bo Jang

More information

A Fuzzy Image Matching Algorithm with Linguistic Spatial Queries

A Fuzzy Image Matching Algorithm with Linguistic Spatial Queries Fuzzy Matchng lgorthm wth Lngustc Spatal Queres TZUNG-PEI HONG, SZU-PO WNG, TIEN-HIN WNG, EEN-HIN HIEN epartment of Electrcal Engneerng, Natonal Unversty of Kaohsung Insttute of Informaton Management,

More information

A Generation Model to Unify Topic Relevance and Lexicon-based Sentiment for Opinion Retrieval

A Generation Model to Unify Topic Relevance and Lexicon-based Sentiment for Opinion Retrieval A Generaton Model to Unfy Topc Relevance and Lexcon-based Sentment for Opnon Retreval Mn Zhang State key lab of Intellgent Tech.& Sys, Dept. of Computer Scence, Tsnghua Unversty, Bejng, 00084, Chna 86-0-6279-2595

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

Spatial Data Dynamic Balancing Distribution Method Based on the Minimum Spatial Proximity for Parallel Spatial Database

Spatial Data Dynamic Balancing Distribution Method Based on the Minimum Spatial Proximity for Parallel Spatial Database JOURNAL OF SOFTWARE, VOL. 6, NO. 7, JULY 211 1337 Spatal Data Dynamc Balancng Dstrbuton Method Based on the Mnmum Spatal Proxmty for Parallel Spatal Database Yan Zhou College of Automaton Unversty of Electrc

More information

Application of Grey-based Taguchi methods on Determining. Process Parameter of linear motion guide with Multiple. Performance Characteristics

Application of Grey-based Taguchi methods on Determining. Process Parameter of linear motion guide with Multiple. Performance Characteristics Proceedngs of the th WSEAS Internatonal Conference on APPLIED MATHEMATICS, Dallas, Texas, USA, March -, Applcaton of Grey-based Taguch methods on Determnng Process Parameter of lnear moton gude wth Multple

More information

SURFACE PROFILE EVALUATION BY FRACTAL DIMENSION AND STATISTIC TOOLS USING MATLAB

SURFACE PROFILE EVALUATION BY FRACTAL DIMENSION AND STATISTIC TOOLS USING MATLAB SURFACE PROFILE EVALUATION BY FRACTAL DIMENSION AND STATISTIC TOOLS USING MATLAB V. Hotař, A. Hotař Techncal Unversty of Lberec, Department of Glass Producng Machnes and Robotcs, Department of Materal

More information