Recommendations of Personal Web Pages Based on User Navigational Patterns
|
|
- Norman Barker
- 5 years ago
- Views:
Transcription
1 nternatonal Journal of Machne Learnng and Computng, Vol. 4, No. 4, August 2014 Recommendatons of Personal Web Pages Based on User Navgatonal Patterns Yn-Fu Huang and Ja-ang Jhang Abstract n ths paper, we propose a web recommendaton system where user navgatonal patterns can be extracted from web logs. Frst, the recommendaton system dscovers user concepts from web logs step-by-step, and then extracts the navgaton patterns among these concepts. hese navgatonal patterns are then used to generate recommendaton web pages by matchng the navgaton behavor of a user personal knowledge base. he pages n a recommendaton lst are ranked accordng to ther hub scores whch are computed based on page connectvty nformaton. he expermental results show that the web pages recommended by our system are of better qualty and acceptable for humans from varous domans, based on human evaluators rankng as well as qualty-value-based performance measures. ndex erms nformaton retreval, recommendaton system, web mnng, web search.. NRODUCON As more and more nformaton s avalable on the nternet, web search has become an essental tool for users. However, sometmes a user query s ambguous and cannot clearly descrbe what he/she wants. For example, f the keyword specfed n a user query s apple, t cannot ndcate frut or computer scence explctly. n ths paper, we propose a soluton to ths problem by constructng a web recommendaton system whch ntegrates personal knowledge bases over dfferent domans to help users to extract desred nformaton. A web recommendaton system s an onlne nformaton system that recommends relevant tems to users. he recommended tems could be products, moves, or even on-lne resources such as web pages. ypcally, a web recommendaton system s composed of an off-lne module and on-lne module. he off-lne module dscovers user navgaton patterns from web logs, whle the on-lne module matches the navgaton behavor of a current user wth dscovered navgaton patterns to produce a recommendaton lst. n recent years, many recommendaton systems have been developed to facltate web search. However, the common problem wth these recommendaton systems s that they generally requre a great amount of documents collected from the vsted webstes by users and the nformaton from user. BASC CONCEPS Some technques and approaches are used n our work. Here, we would brefly revew them n the followng subsectons. A. Query Classfcaton he classfcaton/categorzaton of web queres s usually an nvestgated ssue n computer scence. he task s to assgn a web query to one or more predefned categores, based on ts topcs. he mportance of query classfcaton was emphaszed by many servces provded by web search. A drect applcaton s to provde better web pages for users wth mult-category nterests. For example, a user ssung a web query apple mght expect to browse the web pages related to frut apple, or he/she may prefer to look over the products or news related to the company Apple. Onlne advertsement servces rely on query classfcaton results to promote products more accurately. Web pages can be grouped together accordng to the categores predcted by a query classfcaton algorthm. However, the computaton of query classfcaton s non-trval. Dfferent from document classfcaton tasks, the queres submtted by web users are usually short and ambguous, and ther meanngs are evolvng over tme. herefore, query classfcaton s much more dffcult than tradtonal document classfcaton tasks [2]-[4]. Manuscrpt receved February 13, 2014; revsed May 12, hs work was supported by Natonal Scence Councl of R.O.C under Grant NSC E MY3. Yn-Fu Huang s wth Natonal Yunln Unversty of Scence and echnology, Yunln, awan 640 (e-mal: huangyf@yuntech.edu.tw). Ja-ang Jhang s wth ornado echnologes Co., Ltd, ape, awan 106 (e-mal: @yuntech.edu.tw). DO: /JMLC.2014.V4.429 nteractons. n ths paper, we propose a novel approach nstead of collectng a huge amount of data. n general, a user sesson has more than one query to be fulflled [1]. hus, the queres of a user sesson n web logs can be clustered based on the probabltes n dfferent domans, and these clusters are called concepts. n other words, a concept s a sesson wth coherent nformaton, whch s constructed dynamcally and not pre-defned. hen, these concepts are augmented wth ther connected neghborhoods and fnally generate navgaton patterns. Next, the navgaton patterns already captured are compared wth the semantc graph n a personal knowledge base. Fnally, we recommend the most relevant web pages n the matched clusters. he remander of the paper s organzed as follows. Frst, related basc concepts and personal knowledge bases are ntroduced n Secton. hen, Secton descrbes each component n the system archtecture. Secton V dscusses the expermental results. Fnally, we make conclusons n Secton V. B. Fuzzy Clusterng Clusterng s the task of assgnng a set of obects nto groups (called clusters) so that the obects n the same cluster 307
2 nternatonal Journal of Machne Learnng and Computng, Vol. 4, No. 4, August 2014 are more smlar (n some sense or another) to each other than to those n other clusters. ypcally, clusterng technques come n two notons: hard and soft. n hard clusterng [5], data s dvded nto dstnct clusters, where each data element belongs to exactly one cluster. n soft clusterng (or fuzzy clusterng) [6], each data element has a certan probablty of belongng to each of the clusters, as shown n Fg. 1. One can thnk of hard clusterng as a specal case of soft clusterng where these probabltes only take values 0 or 1. C. Lnk Analyss Algorthm Fg. 1. Fuzzy clusterng. he analyss of hyperlnks has been nstrumental n the development of web search. here are several algorthms of the lnk analyss; e.g., the PageRank algorthm and HS (.e., Hypertext nduced opc Selecton) algorthm are two popular algorthms. PageRank consders the hyperlnk weght normalzaton and the balance dstrbuton of random surfers as the ctaton score [7]. HS makes the dfferentaton between hubs and authortes, and estmates them n a mutually renforcng way. D. Personal Knowledge Base A personal knowledge base (PKB) s knowledge repostory used to store the personal knowledge of an ndvdual. A PKB dffers from a tradtonal database where t contans subectve materal partcular to the owner. mportantly, a PKB conssts prmarly of knowledge, rather than nformaton; n other words, t s not a collecton of documents or other sources that an ndvdual has encountered, but rather an expresson of the dstlled knowledge that the owner has extracted from those sources [8]. A. Overvew. SYSEM ARCHECURE he archtecture of the web recommendaton system, as shown n Fg. 2, conssts of fve components: 1) preprocessor, 2) query classfcaton, 3) concept dentfcaton, 4) HS algorthm, and 5) recommendaton engne. Snce dfferent users have ther own nterests n dfferent domans such as scence, art, sports et al., the recommendaton system dscovers user concepts from web logs step-by-step, and then extracts the navgaton patterns among these concepts. Afterwards, the recommendaton engne dentfes the navgaton behavor of a current user by hs/her personal knowledge base [9] and matches the behavor wth the dscovered navgaton patterns. f navgaton patterns are found, the engne would recommend a lst of web-pages for hs/her browsng. B. Preprocessor Frst, the preprocessor parses or splts up web logs nto three fles: 1) query fle, 2) user vstng fle, and 3) page connectvty nformaton. All of these fle records nformaton regardng users request to web logs. he query fle collects all of queres recorded n web logs. he user fle ncludes anonymous user Ds, queres ssued by users, and URLs clcked on search results. he page connectvty nformaton records the connectvty of these URLs n web logs. C. Query Classfcaton ypcally, the queres ssued by users consst of a few words. Snce these queres are usually very short and ambguous, how to nterpret the queres n terms of multple domans s the maor problem of concept dentfcaton. Here, we use the taxonomy-brdgng algorthm [3] to solve ths problem, whch classfes a user query Q k nto a set of n categores {C 1, C 2,, C n }. As a result, we can represent a query as a vector Q k = (p(c k1 ), p(c k2 ),, p(c kn )) where p(c k ) s the probablty of query Q k belongng to category C. An example of the target categores s llustrated n Fg. 3. Because no data are provded to defne the contents and semantcs of a category and query, a straghtforward method s to submt them to a search engne for extractng related pages. he extracted pages can help determne the meanngs of the categores and queres. n [3], Shen et al. connect the target categores and queres by takng ntermedate categores as a brdge. As llustrated n Fg. 4, the squares n the left part denote the queres to be classfed; the tree n the rght part represents a herarchy organzed by the target categores; the tree n the mddle part s an exstng ntermedate taxonomy used n the Open Drectory Proect (ODP) [10]. he thckness of the dotted lnes reflects the smlarly relatonshp between two nodes. For example, gven a target category C and a query q k, we can udge the smlarty between them by the dstrbutons of ther relatonshp to the ntermedate category C and C. For the followng formula used n the taxonomy-brdgng algorthm, p( C q) s the condtonal probablty of a target category C, gven a query q. Smlarly, p( C C ) and p(q C ) are the condtonal probabltes of a target category C and a query q respectvely, gven an ntermedate category C. p( C ) s the pror probablty of a ntermedate category C, whch can be estmated from the web pages n the ntermedate categores C. f a target category C s represented by a set of words (w 1, w 2,, w n ) where each word w k appears n k tmes, p( as n k 1 n p( w C ) k k C C k ) can be calculated. Fnally, p(q C ) can be calculated n the same way as p( C C ). hus, the formula can be 308
3 nternatonal Journal of Machne Learnng and Computng, Vol. 4, No. 4, August 2014 Fg. 2. System archtecture. expressed as follows: represented by a set of queres {Amercan League, Boston Red Sox, Oakland Athletcs,, Maor League Baseball}. p(c q) C p(c C ) where p(q C ) p(c ) p(q) 1) Query Clusterng As descrbed n Secton, a query s regarded as a vector. hen, all queres of a user sesson can be clustered based on ther semantcs from vectors. A concept models queres related to one of user ntentons, and a concept can overlap other concepts snce a query s usually ambguous. One of the popular fuzzy clusterng s the Fuzzy C Means (FCM) algorthm whch allows each query to belong to more than one cluster. hs method was developed by Dunn n 1973 [11] and mproved by Bezdek n 1981 [12], and t s frequently used n pattern recognton. he FCM algorthm s based on mnmzng the followng obectve functon: (1) p(c C ) k 1 p(wk C )nk n Fg. 3. Example of the target categores. N c J m um x c 2, 1 m (2) 1 1 where m s any real number greater than 1, N s the number of measured data, u s the degree of membershp of x n the cluster, x s the th d-dmensonal measured data, c s the d-dmenson center of the cluster, and * s the norm expressng the smlarty between the measured data and center. Fuzzy parttonng s carred out through an teratve optmzaton of the obectve functon shown above, wth the update of membershp u and the cluster center c by: Ck C qk C Fg. 4. llustraton of the taxonomy-brdgng. u D. Concept dentfcaton A web query log contans anonymous user Ds, queres ssued by users, clcked URLs, and other related nformaton. n general, sesson detecton s done by consderng the tme length of a user sesson, and a user sesson has more than one query to be fulflled [1]. Here, we propose a novel method where the queres of a user sesson are clustered based on the vectors of the probabltes n dfferent target categores, and we call these clusters concepts;.e., a concept s a sesson wth coherent nformaton, whch s constructed dynamcally and not pre-defned. For example, the concept baseball can be 1 x c k 1 k c x c N c u 1 N (3) 2 m 1 x (4) u 1 m he teraton wll stop when max u( k 1) u( k ), where ε s a termnaton crteron between 0 and 1, and k s the 309
4 nternatonal Journal of Machne Learnng and Computng, Vol. 4, No. 4, August 2014 teraton step. Fnally, ths procedure converges to a local mnmum or a saddle pont of Jm. n summary, the algorthm s composed of the followng steps: 1. ntalze U=[u] matrx;.e., U(0). 2. At kth-step: calculate the center vectors C(k)=[c] usng (k) U. 3. Update U(k) nto U(k+1). 4. f U(k+1) - U(k) <ε then SOP; otherwse return to step 2. Snce the FCM algorthm s very senstve to ntal cluster centers, we use the ant based algorthm [13] to obtan ntal cluster centers. keywords) to match the navgaton patterns prevously dscovered n the HS algorthm. For matchng patterns, we use the same query-based smlarty functon mentoned n Secton to udge ther relatonshp. f they are close enough (or the smlarty value s more than γ), the hgh-scorng (or top-ranked) URLs n matched concepts would be recommended to the current user. Here, the number of recommended URLs (or top-k) from each matched concept can be expressed as follows: k round w N 2) Concept Mergng After clusterng the queres, each concept s represented by a set of queres;.e., concept = {query1, query2,, queryn}. Snce the concepts may be smlar to each other, we use query-based smlarty to udge whether a par of concepts are close enough. f a concept has strong smlarty wth another concept, then two concepts wll be merged. he query-based smlarty functon s defned as follows: Smlarryquery (c1, c2 ) C (c1, c2 ) Max(l (c1 ), l (c2 )) where w s the normalzed smlarty rato of concept and N (also specfed by the current user) s the total number of recommended URLs. n other words, the matched concepts wth more smlarty values would contrbute more recommended URLs. V. EXPERMENS hs secton descrbes how to evaluate the web recommendaton system usng dscovered user concepts. Fve evaluators are nvted to udge the lst of pages recommended by our system;.e., assgnng a numerc score to each lst. he web recommendaton system s mplemented n Java, and the experments are conducted on an ntel Core GHz CPU wth 4G man memory n Wndow XP professonal. (5) l (c) s the number of queres n the concept c, C (c1, c2 ) s the number of common queres n two concepts, where and γ s a threshold to udge whether a par of concepts are close enough. A. Dataset n ths paper, we use the dataset from AOL (.e., Amercan Onlne), whch s avalable on the Web and ncludes more than 30 mllon (non-unque) web queres collected from more than 650,000 users over three months. hs dataset was sorted by user Ds and sequentally ordered. For each request, there s also nformaton about when the query was ssued, when a lnk was clcked, the ranks of lnks, and the URLs of lnks. E. HS Algorthm For a concept, each query s nvolved wth at least one URL so that we can measure these URLs by lnk analyss. n ths secton, we use the HS algorthm to measure these URLs [14] where each URL has both a hub score and an authorty score. A good hub page s one that ponts to many good authortes; a good authorty page s one that s ponted to by many good hub pages. More precsely, let h and a denote the vectors of all hub and all authorty scores, respectvely. Gven a concept wth a set of URLs, frst, the HS algorthm produces an n-by-n adacency matrx A whose element A s 1 f URL references to URL and 0 otherwse. hen, the HS algorthm terates the followng equatons: h Aa (6) a A h (7) (8) B. Performance Measures Here, we nvte fve evaluators maorng n computer scences to rate the web pages recommended by our web recommendaton system. he personal knowledge bases (n 10 specfc domans) of each evaluator have been bult from the web pages whch he/she selects through Google and Yahoo search engnes. hese domans are dverse, ncludng baseball, musc, computer networkng, mltary, dancng, gamblng, car, comc & anmaton, nvestng, and relgon & sprtualty. n order to observe the effectveness of our recommendaton system, we use the acceptable percentage measure defned by Zhang et al. [15] for ratng each page as a 1-to-5 scale (1: not related, 2: poorly related, 3: farly related, 4: well related, and 5: strongly related). Besdes, we also use a qualty value measure to evaluate the qualty of the pages recommended by our system as follows. he acceptable percentage measure: where A denotes the transpose of the matrx A. Snce the teratve updates capture the ntuton of good hubs and good authortes, the hgh-scorng URLs would be good hubs and authortes for the concept. Fnally, we can regard the concept wth the vectors of all hub and all authorty scores as navgaton patterns. F. Recommendaton Engne n the on-lne phase, we extract top-weghted key-phrases concernng a specfc category from the personal knowledge base of a current user [9] where the number of top-weghted key-phrases and the target category are specfed by the current user through GU. hen, we use these key-phrases (or m1 310 n3 n4 n5 5 n 1 (9)
5 nternatonal Journal of Machne Learnng and Computng, Vol. 4, No. 4, August 2014 he qualty value measure: n n 5 m2 1 5 (10) 1 where n1, n2, n3, n4, and n5 are the number of recommended web pages wth a score of 1, 2, 3, 4, and 5, respectvely. C. Expermental Results and Dscussons n the experments, these fve testers evaluate the system by usng top-weghted key-phrases under dfferent op-n recommendatons (.e., op-5, op-10, and op-15). Besdes, the threshold γ s emprcally set to 0.7 so that the system can udge whether a par of concepts are close enough. Here, only the results of usng 10 top-weghted key-phrases under dfferent op-15 recommendatons are shown n Fg. 5 and Fg. 6. We found that the acceptable percentages of most domans are more than 80% and the qualty values of most domans are more than 3.5. hs means that our system works well on varous domans. 7 and Fg. 8, we found that the average acceptable percentage s more than 83% and the average qualty value s more than 3.4. All fve evaluators are very satsfed wth ther own lsts of the recommended web pages. Besdes, we also compare our method wth the method only usng personal knowledge bases. he results ndcate that our method always performs better than the method only usng personal knowledge bases. hs verfes that the navgaton patterns extracted from the dscovered concepts defntely facltate recommendng web pages. Fg. 7. Average acceptable percentage for each evaluator. Fg. 5. Acceptable percentages of all domans for op-15. Fg. 8. Average qualty value for each evaluator. V. CONCLUSONS n ths paper, we propose a web recommendaton system where user navgatonal patterns can be dscovered from web logs. hese navgatonal patterns are then used to generate recommendaton web pages by matchng the navgaton behavor of a user personal knowledge base. he pages n a recommendaton lst are ranked accordng to ther hub scores whch are computed based on page connectvty nformaton. he expermental results show that the web pages recommended by our system are of better qualty and acceptable for humans from varous domans, based on human evaluators rankng as well as qualty-value-based performance measures. Fg. 6. Qualty values of all domans for op-15. For each evaluator evaluatng our method as shown n Fg. 311
6 nternatonal Journal of Machne Learnng and Computng, Vol. 4, No. 4, August 2014 REFERENCES [1] D. He and A. Goker, Detectng sesson boundares from web user logs, n Proc. the 22nd BCS-RSG Annual Colloquum on nformaton Retreval Research, 2000, pp [2] S. M. Betzel, E. C. Jensen, D. D. Lews, A. Chowdhury, and O. Freder, Automatc classfcaton of web queres usng very large unlabeled query logs, ACM ransactons on nformaton Systems, vol. 25, no. 2, artcle 9, [3] D. Shen, J.. Sun, Q. Yang, and Z. Chen, Buldng brdges for web query classfcaton, n Proc. the 29th Annual nternatonal ACM SGR Conference on Research and Development n nformaton Retreval, 2006, pp [4] J. R. Wen, J. Y. Ne, and H. J. Zhang, Query clusterng usng user logs, ACM ransactons on nformaton Systems, vol. 20, pp , [5] H. J. Zmmermann, Fuzzy Set heory and ts Applcatons, Kluwer Academc Publshers, [6] A. Baneree, S. Merugu,. S. Dhllon, and J. Ghosh, Clusterng wth Bregman dvergences, Journal of Machne Learnng Research, vol. 6, pp , [7] C. Dng, X. He, P. Husbands, H. Zha, and H. D. Smon, PageRank, HS and a unfed framework for lnk analyss, n Proc. the 25th Annual nternatonal ACM SGR Conference on Research and Development n nformaton Retreval, 2002, pp [8] S. Daves, Stll buldng the memex, Communcatons of the ACM, vol. 54, pp , [9] Y. F. Huang and C. S. Cou, Constructng personal knowledge base: automatc key-phrase extracton from multple-doman web pages, Lecture Notes n Computer Scence, vol. 7104, 2012, pp [10] he Open Drectory Proect. [Onlne]. Avalable: [11] J. C. Dunn, A fuzzy relatve of the SODAA process and ts use n detectng compact well-separated clusters, Journal of Cybernetcs, vol. 3, pp , [12] J. C. Bezdek, Pattern Recognton wth Fuzzy Obectve Functon Algorthms, Kluwer Academc Publshers Norwell, [13] P. M. Kanade and L. O. Hall, Fuzzy ants as a clusterng concept, n Proc. the 22th nternatonal Conference of North Amercan Fuzzy nformaton Processng Socety, 2003, pp [14] J. M. Klenberg, Authortatve sources n a hyperlnked envronment, Journal of ACM, vol. 46, pp , [15] Y. Zhang, E. Mlos, and N. Zncr-Heywood, Narratve text classfcaton for automatc key phrase extracton n web document corpora, n Proc. 7th Annual ACM nternatonal Workshop on Web nformaton and Data Management, 2005, pp Yn-Fu Huang receved the B.S. degree n computer scence from Natonal Chao-ung Unversty n 1979, and the M.S. and Ph.D. degrees n computer scence from Natonal sng-hua Unversty n 1984 and 1988, respectvely. He s currently a professor n the Department of Computer Scence and nformaton Engneerng, Natonal Yunln Unversty of Scence and echnology. Between July 1988 and July 1992, he was wth Chung Shan nsttute of Scence and echnology as an assstant researcher. Hs research nterests nclude database systems, multmeda systems, data mnng, moble computng, and bonformatcs. Ja-ang Jhang receved hs B.S. degree n computer scences from Natonal Unted Unversty and M.S. degree n computer scences from Natonal Yunln Unversty of Scence and echnology n 2010 and 2012, respectvely. He s currently servng n ornado echnologes Co., Ltd. Hs maor areas of nterests are database systems and data mnng. 312
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 informationFINDING IMPORTANT NODES IN SOCIAL NETWORKS BASED ON MODIFIED PAGERANK
FINDING IMPORTANT NODES IN SOCIAL NETWORKS BASED ON MODIFIED PAGERANK L-qng Qu, Yong-quan Lang 2, Jng-Chen 3, 2 College of Informaton Scence and Technology, Shandong Unversty of Scence and Technology,
More informationA 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 informationTsinghua 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 informationCluster 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 informationClassifier Selection Based on Data Complexity Measures *
Classfer Selecton Based on Data Complexty Measures * Edth Hernández-Reyes, J.A. Carrasco-Ochoa, and J.Fco. Martínez-Trndad Natonal Insttute for Astrophyscs, Optcs and Electroncs, Lus Enrque Erro No.1 Sta.
More informationA 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 informationMachine Learning: Algorithms and Applications
14/05/1 Machne Learnng: Algorthms and Applcatons Florano Zn Free Unversty of Bozen-Bolzano Faculty of Computer Scence Academc Year 011-01 Lecture 10: 14 May 01 Unsupervsed Learnng cont Sldes courtesy of
More informationA 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 informationLinkSelector: A Web Mining Approach to. Hyperlink Selection for Web Portals
nkselector: A Web Mnng Approach to Hyperlnk Selecton for Web Portals Xao Fang and Olva R. u Sheng Department of Management Informaton Systems Unversty of Arzona, AZ 8572 {xfang,sheng}@bpa.arzona.edu Submtted
More informationThe Research of Support Vector Machine in Agricultural Data Classification
The Research of Support Vector Machne n Agrcultural Data Classfcaton Le Sh, Qguo Duan, Xnmng Ma, Me Weng College of Informaton and Management Scence, HeNan Agrcultural Unversty, Zhengzhou 45000 Chna Zhengzhou
More informationTerm 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 informationAn 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 informationAvailable 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 informationPerformance 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 informationContent 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 informationDescription of NTU Approach to NTCIR3 Multilingual Information Retrieval
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
More informationNUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS
ARPN Journal of Engneerng and Appled Scences 006-017 Asan Research Publshng Network (ARPN). All rghts reserved. NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS Igor Grgoryev, Svetlana
More informationDetermining 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 informationDecision Strategies for Rating Objects in Knowledge-Shared Research Networks
Decson Strateges for Ratng Objects n Knowledge-Shared Research etwors ALEXADRA GRACHAROVA *, HAS-JOACHM ER **, HASSA OUR ELD ** OM SUUROE ***, HARR ARAKSE *** * nsttute of Control and System Research,
More informationEnhancement of Infrequent Purchased Product Recommendation Using Data Mining Techniques
Enhancement of Infrequent Purchased Product Recommendaton Usng Data Mnng Technques Noraswalza Abdullah, Yue Xu, Shlomo Geva, and Mark Loo Dscplne of Computer Scence Faculty of Scence and Technology Queensland
More informationEffective Page Recommendation Algorithms Based on. Distributed Learning Automata and Weighted Association. Rules
Effectve Page Recommendaton Algorthms Based on Dstrbuted Learnng Automata and Weghted Assocaton Rules R. Forsat 1*, M. R. Meybod 2 1 Department of Computer Engneerng, Islamc Azad Unversty, Karaj Branch,
More informationHierarchical 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 informationUnsupervised Learning
Pattern Recognton Lecture 8 Outlne Introducton Unsupervsed Learnng Parametrc VS Non-Parametrc Approach Mxture of Denstes Maxmum-Lkelhood Estmates Clusterng Prof. Danel Yeung School of Computer Scence and
More informationSubspace clustering. Clustering. Fundamental to all clustering techniques is the choice of distance measure between data points;
Subspace clusterng Clusterng Fundamental to all clusterng technques s the choce of dstance measure between data ponts; D q ( ) ( ) 2 x x = x x, j k = 1 k jk Squared Eucldean dstance Assumpton: All features
More informationOutline. Type of Machine Learning. Examples of Application. Unsupervised Learning
Outlne Artfcal Intellgence and ts applcatons Lecture 8 Unsupervsed Learnng Professor Danel Yeung danyeung@eee.org Dr. Patrck Chan patrckchan@eee.org South Chna Unversty of Technology, Chna Introducton
More informationA Webpage Similarity Measure for Web Sessions Clustering Using Sequence Alignment
A Webpage Smlarty Measure for Web Sessons Clusterng Usng Sequence Algnment Mozhgan Azmpour-Kv School of Engneerng and Scence Sharf Unversty of Technology, Internatonal Campus Ksh Island, Iran mogan_az@ksh.sharf.edu
More informationAnalysis of Continuous Beams in General
Analyss of Contnuous Beams n General Contnuous beams consdered here are prsmatc, rgdly connected to each beam segment and supported at varous ponts along the beam. onts are selected at ponts of support,
More informationLearning 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 informationUser Authentication Based On Behavioral Mouse Dynamics Biometrics
User Authentcaton Based On Behavoral Mouse Dynamcs Bometrcs Chee-Hyung Yoon Danel Donghyun Km Department of Computer Scence Department of Computer Scence Stanford Unversty Stanford Unversty Stanford, CA
More informationPersonalized Concept-Based Clustering of Search Engine Queries
IEEE TRANSACTIONS ON JOURNAL NAME, MANUSCRIPT ID 1 Personalzed Concept-Based Clusterng of Search Engne Queres Kenneth Wa-Tng Leung, Wlfred Ng, and Dk Lun Lee Abstract The exponental growth of nformaton
More informationParallelism 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 informationRelevance Feedback for Image Retrieval
Vashal D Dhale et al, / (IJCSIT Internatonal Journal of Computer Scence and Informaton Technologes, Vol 4 (2, 203, 39-323 Relevance Feedback for Image Retreval Vashal D Dhale, Dr A R Mahaan, Prof Uma Thakur
More informationOptimizing 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 informationUB 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 informationDomain Thesaurus Construction from Wikipedia *
Internatonal Conference on Computer, Networks and Communcaton Engneerng (ICCNCE 2013) Doman Thesaurus Constructon from Wkpeda * WenKe Yn 1, Mng Zhu 2, TanHao Chen 2 1 Department of Electronc Engneerng
More informationImpact of Contextual Information for Hypertext Documents Retrieval
Impact of Contextual Informaton for Hypertext ocuments Retreval Idr Chbane and Bch-Lên oan SUPELEC Computer Scence dpt. Plateau de Moulon 3 rue Jolot Cure 9 92 Gf/Yvette France {Idr.Chbane Bch-Len.oan}@supelec.fr
More informationKeyword-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 informationA 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 informationRelated-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 informationAlignment Results of SOBOM for OAEI 2010
Algnment Results of SOBOM for OAEI 2010 Pegang Xu, Yadong Wang, Lang Cheng, Tany Zang School of Computer Scence and Technology Harbn Insttute of Technology, Harbn, Chna pegang.xu@gmal.com, ydwang@ht.edu.cn,
More informationModule 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 informationFederated 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 informationFEATURE EXTRACTION. Dr. K.Vijayarekha. Associate Dean School of Electrical and Electronics Engineering SASTRA University, Thanjavur
FEATURE EXTRACTION Dr. K.Vjayarekha Assocate Dean School of Electrcal and Electroncs Engneerng SASTRA Unversty, Thanjavur613 41 Jont Intatve of IITs and IISc Funded by MHRD Page 1 of 8 Table of Contents
More informationScheduling 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 informationUsing 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 informationAn Application of the Dulmage-Mendelsohn Decomposition to Sparse Null Space Bases of Full Row Rank Matrices
Internatonal Mathematcal Forum, Vol 7, 2012, no 52, 2549-2554 An Applcaton of the Dulmage-Mendelsohn Decomposton to Sparse Null Space Bases of Full Row Rank Matrces Mostafa Khorramzadeh Department of Mathematcal
More informationMULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION
MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION Paulo Quntlano 1 & Antono Santa-Rosa 1 Federal Polce Department, Brasla, Brazl. E-mals: quntlano.pqs@dpf.gov.br and
More informationA Novel Video Retrieval Method Based on Web Community Extraction Using Features of Video Materials
IEICE TRANS. FUNDAMENTALS, VOL.E92 A, NO.8 AUGUST 2009 1961 PAPER Specal Secton on Sgnal Processng A Novel Vdeo Retreval Method Based on Web Communty Extracton Usng Features of Vdeo Materals Yasutaka HATAKEYAMA
More informationA New Approach For the Ranking of Fuzzy Sets With Different Heights
New pproach For the ankng of Fuzzy Sets Wth Dfferent Heghts Pushpnder Sngh School of Mathematcs Computer pplcatons Thapar Unversty, Patala-7 00 Inda pushpndersnl@gmalcom STCT ankng of fuzzy sets plays
More informationThe 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 informationVirtual 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 informationA Knowledge Management System for Organizing MEDLINE Database
A Knowledge Management System for Organzng MEDLINE Database Hyunk Km, Su-Shng Chen Computer and Informaton Scence Engneerng Department, Unversty of Florda, Ganesvlle, Florda 32611, USA Wth the exploson
More informationAn Improved Neural Network Algorithm for Classifying the Transmission Line Faults
1 An Improved Neural Network Algorthm for Classfyng the Transmsson Lne Faults S. Vaslc, Student Member, IEEE, M. Kezunovc, Fellow, IEEE Abstract--Ths study ntroduces a new concept of artfcal ntellgence
More informationImproving Web Image Search using Meta Re-rankers
VOLUME-1, ISSUE-V (Aug-Sep 2013) IS NOW AVAILABLE AT: www.dcst.com Improvng Web Image Search usng Meta Re-rankers B.Kavtha 1, N. Suata 2 1 Department of Computer Scence and Engneerng, Chtanya Bharath Insttute
More informationKIDS 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 informationStudy of Data Stream Clustering Based on Bio-inspired Model
, pp.412-418 http://dx.do.org/10.14257/astl.2014.53.86 Study of Data Stream lusterng Based on Bo-nspred Model Yngme L, Mn L, Jngbo Shao, Gaoyang Wang ollege of omputer Scence and Informaton Engneerng,
More informationMaximum Variance Combined with Adaptive Genetic Algorithm for Infrared Image Segmentation
Internatonal Conference on Logstcs Engneerng, Management and Computer Scence (LEMCS 5) Maxmum Varance Combned wth Adaptve Genetc Algorthm for Infrared Image Segmentaton Huxuan Fu College of Automaton Harbn
More informationCS434a/541a: Pattern Recognition Prof. Olga Veksler. Lecture 15
CS434a/541a: Pattern Recognton Prof. Olga Veksler Lecture 15 Today New Topc: Unsupervsed Learnng Supervsed vs. unsupervsed learnng Unsupervsed learnng Net Tme: parametrc unsupervsed learnng Today: nonparametrc
More informationImprovement 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 informationTECHNIQUE 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 information2x x l. Module 3: Element Properties Lecture 4: Lagrange and Serendipity Elements
Module 3: Element Propertes Lecture : Lagrange and Serendpty Elements 5 In last lecture note, the nterpolaton functons are derved on the bass of assumed polynomal from Pascal s trangle for the fled varable.
More informationGraph-based Clustering
Graphbased Clusterng Transform the data nto a graph representaton ertces are the data ponts to be clustered Edges are eghted based on smlarty beteen data ponts Graph parttonng Þ Each connected component
More informationProblem 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 informationBioTechnology. 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 informationChapter 6 Programmng the fnte element method Inow turn to the man subject of ths book: The mplementaton of the fnte element algorthm n computer programs. In order to make my dscusson as straghtforward
More informationSimulation Based Analysis of FAST TCP using OMNET++
Smulaton Based Analyss of FAST TCP usng OMNET++ Umar ul Hassan 04030038@lums.edu.pk Md Term Report CS678 Topcs n Internet Research Sprng, 2006 Introducton Internet traffc s doublng roughly every 3 months
More informationProfessional competences training path for an e-commerce major, based on the ISM method
World Transactons on Engneerng and Technology Educaton Vol.14, No.4, 2016 2016 WIETE Professonal competences tranng path for an e-commerce maor, based on the ISM method Ru Wang, Pn Peng, L-gang Lu & Lng
More informationAn 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 informationSteps 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 informationFuzzy C-Means Initialized by Fixed Threshold Clustering for Improving Image Retrieval
Fuzzy -Means Intalzed by Fxed Threshold lusterng for Improvng Image Retreval NAWARA HANSIRI, SIRIPORN SUPRATID,HOM KIMPAN 3 Faculty of Informaton Technology Rangst Unversty Muang-Ake, Paholyotn Road, Patumtan,
More informationThe Codesign Challenge
ECE 4530 Codesgn Challenge Fall 2007 Hardware/Software Codesgn The Codesgn Challenge Objectves In the codesgn challenge, your task s to accelerate a gven software reference mplementaton as fast as possble.
More informationQuery classification using topic models and support vector machine
Query classfcaton usng topc models and support vector machne Deu-Thu Le Unversty of Trento, Italy deuthu.le@ds.untn.t Raffaella Bernard Unversty of Trento, Italy bernard@ds.untn.t Abstract Ths paper descrbes
More informationRanking Search Results by Web Quality Dimensions
Rankng Search Results by Web Qualty Dmensons Joshua C. C. Pun Department of Computer Scence HKUST Clear Water Bay, Kowloon Hong Kong punjcc@cs.ust.hk Frederck H. Lochovsky Department of Computer Scence
More informationObject-Based Techniques for Image Retrieval
54 Zhang, Gao, & Luo Chapter VII Object-Based Technques for Image Retreval Y. J. Zhang, Tsnghua Unversty, Chna Y. Y. Gao, Tsnghua Unversty, Chna Y. Luo, Tsnghua Unversty, Chna ABSTRACT To overcome the
More informationSome material adapted from Mohamed Younis, UMBC CMSC 611 Spr 2003 course slides Some material adapted from Hennessy & Patterson / 2003 Elsevier
Some materal adapted from Mohamed Youns, UMBC CMSC 611 Spr 2003 course sldes Some materal adapted from Hennessy & Patterson / 2003 Elsever Scence Performance = 1 Executon tme Speedup = Performance (B)
More informationProper Choice of Data Used for the Estimation of Datum Transformation Parameters
Proper Choce of Data Used for the Estmaton of Datum Transformaton Parameters Hakan S. KUTOGLU, Turkey Key words: Coordnate systems; transformaton; estmaton, relablty. SUMMARY Advances n technologes and
More informationModule 6: FEM for Plates and Shells Lecture 6: Finite Element Analysis of Shell
Module 6: FEM for Plates and Shells Lecture 6: Fnte Element Analyss of Shell 3 6.6. Introducton A shell s a curved surface, whch by vrtue of ther shape can wthstand both membrane and bendng forces. A shell
More informationBRDPHHC: A Balance RDF Data Partitioning Algorithm based on Hybrid Hierarchical Clustering
015 IEEE 17th Internatonal Conference on Hgh Performance Computng and Communcatons (HPCC), 015 IEEE 7th Internatonal Symposum on Cyberspace Safety and Securty (CSS), and 015 IEEE 1th Internatonal Conf
More informationRobust Classification of ph Levels on a Camera Phone
Robust Classfcaton of ph Levels on a Camera Phone B.Y. Loh, N.K. Vuong, S. Chan and C.. Lau AbstractIn ths paper, we present a new algorthm that automatcally classfes the ph level on a test strp usng color
More informationA Novel Optimization Technique for Translation Retrieval in Networks Search Engines
A Novel Optmzaton Technque for Translaton Retreval n Networks Search Engnes Yanyan Zhang Zhengzhou Unversty of Industral Technology, Henan, Chna Abstract - Ths paper studes models of Translaton Retreval.e.
More informationBiostatistics 615/815
The E-M Algorthm Bostatstcs 615/815 Lecture 17 Last Lecture: The Smplex Method General method for optmzaton Makes few assumptons about functon Crawls towards mnmum Some recommendatons Multple startng ponts
More informationX- 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 informationPRÉSENTATIONS DE PROJETS
PRÉSENTATIONS DE PROJETS Rex Onlne (V. Atanasu) What s Rex? Rex s an onlne browser for collectons of wrtten documents [1]. Asde ths core functon t has however many other applcatons that make t nterestng
More informationA Clustering Algorithm for Key Frame Extraction Based on Density Peak
Journal of Computer and Communcatons, 2018, 6, 118-128 http://www.scrp.org/ournal/cc ISSN Onlne: 2327-5227 ISSN Prnt: 2327-5219 A Clusterng Algorthm for Key Frame Extracton Based on Densty Peak Hong Zhao
More informationAn Optimal Algorithm for Prufer Codes *
J. Software Engneerng & Applcatons, 2009, 2: 111-115 do:10.4236/jsea.2009.22016 Publshed Onlne July 2009 (www.scrp.org/journal/jsea) An Optmal Algorthm for Prufer Codes * Xaodong Wang 1, 2, Le Wang 3,
More informationDocument 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 informationHybridization of Expectation-Maximization and K-Means Algorithms for Better Clustering Performance
BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 16, No 2 Sofa 2016 Prnt ISSN: 1311-9702; Onlne ISSN: 1314-4081 DOI: 10.1515/cat-2016-0017 Hybrdzaton of Expectaton-Maxmzaton
More informationHelsinki 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 informationCollaboratively Regularized Nearest Points for Set Based Recognition
Academc Center for Computng and Meda Studes, Kyoto Unversty Collaboratvely Regularzed Nearest Ponts for Set Based Recognton Yang Wu, Mchhko Mnoh, Masayuk Mukunok Kyoto Unversty 9/1/013 BMVC 013 @ Brstol,
More informationDesign of Structure Optimization with APDL
Desgn of Structure Optmzaton wth APDL Yanyun School of Cvl Engneerng and Archtecture, East Chna Jaotong Unversty Nanchang 330013 Chna Abstract In ths paper, the desgn process of structure optmzaton wth
More informationImproving Web Search Results Using Affinity Graph
Improvng Web Search Results Usng Affnty Graph Benyu Zhang, Hua L 2, Y Lu 3, Le J 4, Wens X 5, Weguo Fan 5, Zheng Chen, We-Yng Ma Mcrosoft Research Asa, 49 Zhchun Road, Bejng, 00080, P. R. Chna {byzhang,
More informationSupport Vector Machines
/9/207 MIST.6060 Busness Intellgence and Data Mnng What are Support Vector Machnes? Support Vector Machnes Support Vector Machnes (SVMs) are supervsed learnng technques that analyze data and recognze patterns.
More informationMachine Learning. Topic 6: Clustering
Machne Learnng Topc 6: lusterng lusterng Groupng data nto (hopefully useful) sets. Thngs on the left Thngs on the rght Applcatons of lusterng Hypothess Generaton lusters mght suggest natural groups. Hypothess
More informationAn 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 informationLocal Quaternary Patterns and Feature Local Quaternary Patterns
Local Quaternary Patterns and Feature Local Quaternary Patterns Jayu Gu and Chengjun Lu The Department of Computer Scence, New Jersey Insttute of Technology, Newark, NJ 0102, USA Abstract - Ths paper presents
More informationEfficient Segmentation and Classification of Remote Sensing Image Using Local Self Similarity
ISSN(Onlne): 2320-9801 ISSN (Prnt): 2320-9798 Internatonal Journal of Innovatve Research n Computer and Communcaton Engneerng (An ISO 3297: 2007 Certfed Organzaton) Vol.2, Specal Issue 1, March 2014 Proceedngs
More informationBIN XIA et al: AN IMPROVED K-MEANS ALGORITHM BASED ON CLOUD PLATFORM FOR DATA MINING
An Improved K-means Algorthm based on Cloud Platform for Data Mnng Bn Xa *, Yan Lu 2. School of nformaton and management scence, Henan Agrcultural Unversty, Zhengzhou, Henan 450002, P.R. Chna 2. College
More informationRecommended 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 informationWeb 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