An Optimized Analogy-Based Project Effort Estimation

Size: px
Start display at page:

Download "An Optimized Analogy-Based Project Effort Estimation"

Transcription

1 (IJACSA) Internatonal Journal of Advanced Computer Scence and Applcatons, An Optmzed Analogy-Based Project Effort Estmaton Mohammad Azzeh Faculty of Informaton Technology Appled Scence UnverstyAmman, Jordan POBOX 166 Yousef Elshekh Faculty of Informaton Technology Appled Scence Unversty Amman, Jordan Marwan Alsed Faculty of Informaton Technology Appled Scence Unversty Amman, Jordan Abstract Despte the predctve performance of Analogy- Based Estmaton (ABE) n generatng better effort estmates, there s no consensus on: (1) how to predetermne the approprate number of analoges, (2) whch adjustment technque produces better estmates. Yet, there s no pror works attempted to optmze both number of analoges and feature dstance weghts for each test project. Perhaps rather than usng fxed number, t s better to optmze ths value for each project ndvdually and then adjust the retreved analoges by optmzng and approxmatng complex relatonshps between features and reflects that approxmaton on the fnal estmate. The Artfcal Bees Algorthm s utlzed to fnd, for each test project, the approprate number of closest projects and features dstance weghts that are used to adjust those analoges efforts. The proposed technque has been appled and valdated to 8 publcally datasets from PROMISE repostory. Results obtaned show that: (1) the predctve performance of ABE has notceably been mproved; (2) the number of analoges was remarkably varable for each test project. Whle there are many technques to adjust ABE, Usng optmzaton algorthm provdes two solutons n one technque and appeared useful for datasets wth complex structure. Keywords Cost Estmaton; Effort Estmaton by Analogy; Bees Optmzaton Algorthm I. INTRODUCTION Analogy-Based Estmaton (ABE) has preserved popularty wthn software engneerng research communty because of ts outstandng performance n predcton when dfferent data types are used [1, 15]. The dea behnd ths method s rather smple such that the new project s effort can be estmated by reusng efforts about smlar, already documented projects n a dataset, where n a frst step one has to dentfy smlar projects whch contan the useful predctons [15]. The predctve performance of ABE reles sgnfcantly on the choce of two nterrelated parameters: number of nearest analoges and adjustment strategy [8]. The goal of usng adjustment n ABE s twofold: (1) mnmzng the dfference between a new project and ts nearest analoges, and (2) producng more successful estmates n comparson to orgnal ABE [2]. If the researchers read the lterature on ABE, they wll encounter large number of ABE models that use varety of adjustment strateges. Those strateges suffer from common problems such as they are not able to produces stable results when appled n dfferent contexts as well as they use fxed number of analoges for the whole dataset [1]. Usng fxed number of analoges has been proven to be unsuccessful n many stuatons because t depends heavly on expert opnon and requres extensve expermentaton to dentfy the best k value, whch mght not be predctve for ndvdual projects [2]. The am of ths work s therefore to propose a new method based on Artfcal Bees Algorthm (BA) [14] to adjust ABE by optmzng the feature smlarty coeffcents that mnmzes dfference between new project and ts nearest projects, and predctng the best k number of nearest analoges. The paper s structured as follows: Secton 2 ntroduces an overvew to ABE and adjustment methods. Secton 3 presents the proposed adjustment method. Secton 4 presents research methodology. Secton 5 shows obtaned results. Fnally the paper ends wth our conclusons. II. RELATED WORKS ABE method generates new predcton based on assumpton that smlar projects wth respect to features descrpton have smlar efforts [8, 15]. Adjustment s a part of ABE that attempts to mnmze the dfference between new observaton ( ê ) and each nearest smlar observaton ( e ), then reflects that dfference on the derved soluton n order to obtan better soluton ( e t ). Consequentally, all adjusted solutons are aggregated usng smple statstcal methods such 1 k as mean ( et k eˆ 1 ). In prevous study [17] we nvestgated the performance of BA, on adjustng ABE and fndng best k value for the whole dataset. Ths model showed some mprovements on the accuracy, but on the other sde t dd not solve the problem of predctng the best k value for each ndvdual project. In addton the soluton space of BA was a challenge because there was only one common weght for all nearest analoges. The used optmzaton crteron (.e. MMRE) was problematc because t was proven to be based towards underestmaton. For all these reason and snce we need to compare our proposed model wth valdated and replcated models, we excluded ths model from comparson later n ths paper. Ths paper thereby attempts to solve abovementoned lmtatons. In lterature there s a sgnfcant number of adjustment methods that have been documented and replcated n prevous studes. Therefore we selected and summarzed only the most wdely used strateges. Walkerden and Jeffery proposed Lnear Sze Adjustment () [16] based on the sze extrapolaton. Mendes et al. [12] proposed Multple Lnear Feature Extrapolaton () to nclude all related sze features. 6 P a g e

2 (IJACSA) Internatonal Journal of Advanced Computer Scence and Applcatons, Jorgenson et al. [6] proposed Regresson Towards the Mean () to adjust projects based on ther productvty values. Chu and Huang [4] proposed another adjustment based on Genetc Algorthm () to optmze the coeffcent αj for each feature dstance based on mnmzng performance measure. Recently, L et al. [10] proposed the use of Neural Network () to learn the dfference between projects and reflects the dfference on the fnal estmate. Further detals about these methods and ther functons can be found n [1]. Indeed, the most mportant questons to consder when to use such methods s how to predct the best number of nearest analoges (k). In recent years varous approaches have been proposed to specfy ths number such as: 1) fxed number selecton (.e. k=1, 2, 3 etc) as n studes of [7, 11, 12, 16], 2) Dynamc selecton based on clusterng as n study of [2, 17]. 3) Smlarty threshold based selecton as n studes of [5, 9]. Generally, these studes except [2] use the same k value for all projects n the dataset whch does not necessarly produce best performance for each ndvdual project. On the other hand, the certan problem wth [2] s that t does not nclude adjustment method but t predcts the best k value based on the structure of dataset. III. THE PROPOSED METHOD () The proposed adjustment method starts wth Bees Algorthm n order to fnd out, for each project: (1) the feature weghts (w), and (2) the best k number of nearest analoges that mnmze mean absolute error. The search space of BA can be seen as a set of n weght matrxes where the sze of each matrx (.e. soluton) s k m. That means each possble soluton contans weght matrx wth dmenson equvalent to the number of analoges (k) and number of features (m) as shown n Fgure 1. The number of rows (.e. k) and weght values are ntally generated by random. Each row represents m weghts for one selected analogy and accordngly w j 1 j 1. In each run the algorthm selects the top k nearest analoges based on the number of k weghts n the search space. Then each selected analogy s adjusted wth correspondng weghts taken from the matrx w as shown Eq.1. The algorthm contnues searchng untl the value of Mean Error (.e. MR 1 k k j 1 j ) between new project and ts k analoges s mnmzed. The optmzed k value and weght matrx are then appled to Eqs. 1, 2 and 3 to generate new estmate. The new ntegraton between ABE wth BA wll be called Optmzed Analogy Based Estmaton (hereafter ). Fg. 1. w11 w21 w wk1 w12 w22 wk 2 w1 m w2m wkm Weght Matrx for one soluton n the search space 1 m j w f - f j j ( tj j) m 1 (1) eˆ e j (2) k k r eˆ e 1 1 t k (3) 1 The settng parameters for AB have been found after performng senstvty analyss on the employed datasets to see the approprate values. Table I shows BA parameters, ther abbrevatons and ntal values used n ths study. Below we brefly descrbe the process of BA n fndng best k values and the correspondng weghts for each new project. The algorthm starts wth an ntal set of weght matrxes generated after randomly ntalzng k for each matrx. The solutons are assessed and sorted n ascendng order after they are beng evaluated based on MR. The best from 1 to b solutons are beng selected for neghborhood search for better solutons, and form new patch. Smlarly, a number of bees (nsp) are also recruted for each soluton ranked from b+1 to u, to search n the neghborhood. The best soluton n each patch wll replace the old best soluton n that patch and the remanng bees wll be replaced randomly wth other solutons. The algorthm contnues searchng n the neghborhood of the selected stes, recrutng more bees to search near to the best stes whch may have promsng solutons. These steps are repeated untl the crteron of stop (mnmum MR) s met or the number of teraton has fnshed. TABLE I. BA PARAMETERS Parameter Descrpton Value q dmenson of soluton (number of features +1) n represents sze of ntal solutons 100 u b number of stes selected out of n vsted stes number of best stes out of s selected stes nep number of bees recruted for best b stes 30 nsp Number of bees recruted for the other selected stes ngh ntal sze of patches (ngh) 0.05 IV. METHODOLOGY A. Datasets The proposed model has been valdated over 8 software effort estmaton datasets come from companes of dfferent ndustral sectors [3]. The datasets characterstcs are provded n Table II whch shows that the datasets are strongly postvely skewed ndcatng many small projects and a lmted number of outlers. It s mportant to note that all contnuous features have been scaled and all observaton wth mssng values are excluded P a g e

3 (IJACSA) Internatonal Journal of Advanced Computer Scence and Applcatons, TABLE II. DESCRIPTIVE STATISTICS OF THE DATASETS Dataset Feature Sze Effort Data Mn Max Mean Skew Albrecht Kemerer Nasa Desharnas COCOMO Chna Maxwell Telecom B. Performance measures A key queston to any estmaton model s whether the predcatons are accurate, the dfference between the actual effort ( e ) and the predcted effort ( ê ) should be as small as possble because large devaton wll have opposte effect on the development progress of the new software project [13]. Ths secton descrbes several performance measures used n ths research as shown n Table III. Although some measures such as MMRE, MMER have been crtczed as based to under and over estmatons, we nsst to use them because they are wdely used n commentng on the success of predctons [13]. TABLE III. ERROR MEASURES Error Measure Name Equaton e eˆ Magntude Relatve Error MRE e Mean Magntude MMRE N 1 Relatve Error MRE Medan Magntude MdMRE medan ( MRE) Relatve Error Mean Magntude of Error e Relatve to the estmate eˆ MMER N 1 eˆ Mean Balanced Error 1 e eˆ MBER N (MBRE) mn, ˆ e e 100 N Predcton Performance 1 f MRE 0.25 pred l N 1 0 otherwse Interpretng these error measures wthout any statstcal test can lead to concluson nstablty, therefore we used wnte-loss algorthm [8] to compare the performance of to other estmaton methods. We frst check f two methods method ; method j are statstcally dfferent accordng to the Wlcoxon test. If so, we update wn ; wn j and loss ; loss j after checkng whch one s better accordng to the performance measure at hand; otherwse we ncrease te and te j. The performance measures used here are MRE, MMRE, MdMRE, MMER, MBER and Pred 25. Algorthm 1 llustrates the wn-teloss algorthm [8]. Also, the Bonferron-Dunn test s used to perform multple comparsons for dfferent models based on the absolute error to check whether there are dfferences n populaton rank means among more than populatons. Algorthm 1. Pseudocode of wn-te-loss algorthm betweenmethod and method jbased on performance measure E [8] 1: Wn =0,te =0,loss =0 2: Wn j=0,te j=0;loss j=0 3: f Wlcoxon (MRE(method ), MRE(method j), 95) says they are the same then 4: te = te + 1; 5: te j = te j + 1; 6:else 7: f better(e(method ), E(method j)) then 8: wn = wn + 1 9: loss j = loss j : else 11: wn j = wn j : loss = loss :end f 14: end f V. RESULTS Ths secton presents performance fgures of aganst varous adjustment technques used n constructng ABE models. Snce the selecton of the best k settng n s dynamc, there was no need to pre-set the best k value. In contrast, for other varants of adjustment technques there was necessarly fndng the best k value that almost fts each model, therefore we appled dfferent k settngs from 1 to 5 on each model as suggested by L et al. [9] and the settng that produces best overall performance has been selected for comparson wth other dfferent models. Tables IV, V, VI, VII and VIII summarze the resultng performance fgures for all nvestgated ABE models. The most successful method should have lower MMRE, MdMRE, MMER, MBER and hgher Pred 25. The obtaned results suggest that the produced accurate predctons than other methods wth qute good performance fgures over most datasets. TABLE IV. MMRE RESULTS Dataset Albrecht Kemerer Desharnas COCOMO Maxwell Chna Telecom Nasa TABLE V. PRED 25 RESULTS Dataset Albrecht Kemerer Desharnas COCOMO Maxwell Chna Telecom Nasa TABLE VI. MDMRE RESULTS Dataset Albrecht Kemerer Desharnas COCOMO Maxwell Chna Telecom Nasa P a g e

4 (IJACSA) Internatonal Journal of Advanced Computer Scence and Applcatons, However, these fndngs are ndcatve of the superorty of BA n optmzng k analoges and adjustng the retreved project efforts, and consequentally mprove overall predctve performance of ABE. Also from the obtaned results we can observe that there s evdence that usng adjustment technques can work better for datasets wth dscontnutes (e.g. Maxwell, Kemerer and COCOMO). Note that the result s exactly the searchng for the best k settng result as mght be predcted by the researchers mentoned n the related work. We speculate that pror Software Engneerng researchers who faled to fnd best k settng, dd not attempt to optmze ths k value wth adjustment technque tself for each ndvdual project before buldng the model. TABLE VII. MMER RESULTS Dataset Albrecht Kemerer Desharnas COCOMO Maxwell Chna Telecom Nasa TABLE VIII. MBRE RESULTS Dataset Albrecht Kemerer Desharnas COCOMO Maxwell Chna Telecom Nasa Furthermore, two results worth some attenton whle we are carryng ths experment: Frstly, the general trend of predctve accuracy mprovements across all error measures, overall datasets s not clear ths certanly depends on the structure of the dataset. Secondly, there s no consstent results regardng the sutablty of for small datasets wth categorcal features (as n Maxwell and Kemerer datasets) but we can nsst that s stll comparable to n terms of MMRE and Pred 25 and have potental to produce better estmates. In contrast, showed better performance than for the other two small datasets (NASA and Telecom) that do not have categorcal features. To summarze the results we run the wn-te-loss algorthm to show the overall performance. Fgure 3 shows the sum of wn, te and loss values for all models, over all datasets. Every model n Fgure 2 s compared to other fve models, over sx error measures and eght datasets. Notce n Fgure 2 that except the low performng model on, the te values are n band. Therefore, they would not be so nformatve as to dfferentate the methods, so we consult wn and loss statstcs to tell us whch model performs better over all datasets usng dfferent error measures. Apparently, there s sgnfcant dfference between the best and worst models n terms of wn and loss values (n the extreme case t s close to 119). The wn-te-loss results offer yet more evdence for the superorty of over other adjustment technques. Also the obtaned wn-te-loss results confrmed that the predctons based on model presented statstcally sgnfcant but necessarly accurate estmatons than other technques. Two aspects of these results are worth commentng: 1) The was the bg loser wth bad performance for adjustment. 2) technque performs better than whch shows that usng sze measure only s more predctve than usng all sze related features. We use the Bonferron-Dunn test to compare the method aganst other methods as shown n Fgure 3. The plots have been obtaned after applyng ANOVA test followed by Bonferron test. The ANOVA test results n p-value close to zero whch mples that the dfferences between two methods are statstcally sgnfcant based on AR measure. The horzontal axs n these fgures corresponds to the average rank of methods based on AR. The dotted vertcal lnes n the fgures ndcate the crtcal dfference at the 95% confdence level. Obvously, the methods generated lower AR than other methods over most datasets except for small datasets. For such datasets, all models except generated relatvely smlar estmates but wth preference to that has smaller error. Ths ndcates that adjustment method s far less prone to ncorrect estmates. Fg. 2. Wn-Te-Loss Results for all Models VI. CONCLUSIONS AND FUTURE WORK Ths paper presents a new adjustment technque to tune ABE usng Bees optmzaton algorthm. The BA was used to automatcally fnd the approprate k value and ts feature weghts n order to adjust the retreved k closest analoges. The results obtaned over 8 datasets showed sgnfcant mprovements on predcton accuracy of ABE. We can notce that all models rankng can change by some amount but has relatvely stable rankng accordng to all error measure as shown n Fgure 2. Future work s planned to study the mpact of usng ensemble adjustment technques. VII. ACKNOWLEDGEMENT The authors are grateful to the Appled Scence Prvate Unversty, Amman, Jordan, for the fnancal support granted to ths research project. 9 P a g e

5 (IJACSA) Internatonal Journal of Advanced Computer Scence and Applcatons, groups have mean ranks sgnfcantly dfferent from (a) Albrecht dataset groups have mean ranks sgnfcantly dfferent from (b) Kemere dataset groups have mean ranks sgnfcantly dfferent from (c) Desharnas dataset groups have mean ranks sgnfcantly dfferent from (d) COCOMO dataset groups have mean ranks sgnfcantly dfferent from (e) Maxwell dataset groups have mean ranks sgnfcantly dfferent from (f) Chna dataset The mean ranks of groups and are sgnfcantly dfferent (g) Telecom dataset Fg. 3. Bonferron-Dunn test multple comparson test over all datasets REFERENCES [1] M. Azzeh, A replcated assessment and comparson of adaptaton technques for analogy-based effort estmaton, Journal of Emprcal Software Engneerng vol. 17, pp , [2] M. Azzeh, Y. Elshekh, Learnng Best K analoges from Data Dstrbuton for Case-Based Software Effort Estmaton, The Seventh Internatonal Conference on Software Engneerng Advances (ICSEA 2012), pp , [3] G. Boettcher, T. Menzes, T. Ostrand, PROMISE Repostory of emprcal software engneerng data repostory, West Vrgna Unversty, Department of Computer Scence The mean ranks of groups and are sgnfcantly dfferent (h) NASA dataset [4] N. H. Chu, S. J. Huang, The adjusted analogy-based software effort estmaton based on smlarty dstances, Journal of System and Software, Vol. 80, pp , [5] A. Idr, A. Abran, T. Khoshgoftaar, Fuzzy Analogy: a New Approach for Software Effort Estmaton, 11th Internatonal Workshop n Software Measurements, pp , [6] M. Jorgensen, U. Indahl, D. Sjoberg, Software effort estmaton by analogy and regresson toward the mean, Journal of System and Software, vol. 68, pp , [7] C. Krsopp, E. Mendes, R. Premraj, M. Shepperd, An emprcal analyss of lnear adaptaton technques for case-based predcton, Internaton 10 P a g e

6 (IJACSA) Internatonal Journal of Advanced Computer Scence and Applcatons, conference on Case-Based Reasonng Research and Development, pp , 2003 [8] E. Kocagunel, T. Menzes, A. Bener, J. Keung, Explotng the Essental Assumptons of Analogy-based Effort Estmaton, Journal of IEEE transacton on Software Engneerng, vol. 38, pp , [9] J. Z. L, G. Ruhe, A. Al-Emran, M. Rchter, A flexble method for software effort estmaton by analogy, Journal of Emprcal Software Engneerng, vol. 12, pp , [10] Y. F. L, M. Xe, T. N. Goh, A study of A study of the non-lnear adjustment for analogy based software cost estmaton, Journal of Emprcal Software Engneerng, vol. 14, pp , [11] U. Lpowezky, Selecton of the optmal prototype subset for 1-nn classfcaton, Pattern Recog. Letters, vol. 19, pp , [12] E. Mendes, N. Mosley, S. Counsell, A replcated assessment of the use of adaptaton rules to mprove Web cost estmaton, Internatonal Symposum on Emprcal Software Engneerng, pp , [13] I. Myrtvet, E. Stensrud, M. Shepperd, Relablty and valdty n comparatve studes of software predcton models, Journal of IEEE Transacton on Software Engneerng, vol. 3, pp , [14] D. T. Pham, A. Ghanbarzadeh, E. Koç, S. Otr, S. Rahm, M. Zad, The Bees Algorthm A novel tool for complex optmsaton problems, Proceedngs of the 2nd Vrtual Internatonal Conference on Intellgent Producton Machnes and Systems, pp , [15] M. Shepperd, C. Schofeld, Estmatng software project effort usng analoges, Journal of IEEE Transacton on Software Engneerng, vol. 23, pp , [16] F. Walkerden, D. R. Jeffery, An emprcal study of analogy-based software effort Estmaton, Journal of Emprcal Software Engneerng, vol. 4, pp , [17] M. Azzeh, "Adjusted case-based software effort estmaton usng bees optmzaton algorthm. Internatonal conference on Knowlege-Based and Intellgent Informaton and Engneerng Systems. Sprnger BerlnHedelberg, pp , P a g e

An Optimized Analogy-Based Project Effort Estimation

An Optimized Analogy-Based Project Effort Estimation An Optimized Analogy-Based Project Effort Estimation Mohammad Azzeh Faculty of Information Technology Applied Science University Amman, Jordan POBOX 166 m.y.azzeh@asu.edu.jo Abstract. Yousef Elsheikh Faculty

More information

CS 534: Computer Vision Model Fitting

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

More information

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

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

y and the total sum of

y and the total sum of Lnear regresson Testng for non-lnearty In analytcal chemstry, lnear regresson s commonly used n the constructon of calbraton functons requred for analytcal technques such as gas chromatography, atomc absorpton

More information

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

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

More information

Classifier Selection Based on Data Complexity Measures *

Classifier 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 information

Meta-heuristics for Multidimensional Knapsack Problems

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

More information

Support Vector Machines

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

More information

S1 Note. Basis functions.

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

More information

Should Duration and Team Size be Used for Effort Estimation?

Should Duration and Team Size be Used for Effort Estimation? Should Duraton and Team Sze be Used for Effort Estmaton? Takesh Kakmoto 1, Masateru Tsunoda 2, and Akto Monden 3 Abstract Project management actvtes such as schedulng and project progress management are

More information

This is a repository copy of Fuzzy grey relational analysis for software effort estimation.

This is a repository copy of Fuzzy grey relational analysis for software effort estimation. Ths s a repostory copy of Fuzzy grey relatonal analyss for software effort estmaton. Whte Rose Research Onlne URL for ths paper: http://eprnts.whterose.ac.u/75052/ Verson: Submtted Verson Artcle: Azzeh,

More information

APPLICATION OF MULTIVARIATE LOSS FUNCTION FOR ASSESSMENT OF THE QUALITY OF TECHNOLOGICAL PROCESS MANAGEMENT

APPLICATION OF MULTIVARIATE LOSS FUNCTION FOR ASSESSMENT OF THE QUALITY OF TECHNOLOGICAL PROCESS MANAGEMENT 3. - 5. 5., Brno, Czech Republc, EU APPLICATION OF MULTIVARIATE LOSS FUNCTION FOR ASSESSMENT OF THE QUALITY OF TECHNOLOGICAL PROCESS MANAGEMENT Abstract Josef TOŠENOVSKÝ ) Lenka MONSPORTOVÁ ) Flp TOŠENOVSKÝ

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

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

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

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

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

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

More information

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

A Robust Method for Estimating the Fundamental Matrix

A Robust Method for Estimating the Fundamental Matrix Proc. VIIth Dgtal Image Computng: Technques and Applcatons, Sun C., Talbot H., Ourseln S. and Adraansen T. (Eds.), 0- Dec. 003, Sydney A Robust Method for Estmatng the Fundamental Matrx C.L. Feng and Y.S.

More information

The Man-hour Estimation Models & Its Comparison of Interim Products Assembly for Shipbuilding

The Man-hour Estimation Models & Its Comparison of Interim Products Assembly for Shipbuilding Internatonal Journal of Operatons Research Internatonal Journal of Operatons Research Vol., No., 9 4 (005) The Man-hour Estmaton Models & Its Comparson of Interm Products Assembly for Shpbuldng Bn Lu and

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

BOOSTING CLASSIFICATION ACCURACY WITH SAMPLES CHOSEN FROM A VALIDATION SET

BOOSTING CLASSIFICATION ACCURACY WITH SAMPLES CHOSEN FROM A VALIDATION SET 1 BOOSTING CLASSIFICATION ACCURACY WITH SAMPLES CHOSEN FROM A VALIDATION SET TZU-CHENG CHUANG School of Electrcal and Computer Engneerng, Purdue Unversty, West Lafayette, Indana 47907 SAUL B. GELFAND School

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

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

Feature Reduction and Selection

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

More information

An Optimal Algorithm for Prufer Codes *

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

More information

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

Empirical Distributions of Parameter Estimates. in Binary Logistic Regression Using Bootstrap

Empirical Distributions of Parameter Estimates. in Binary Logistic Regression Using Bootstrap Int. Journal of Math. Analyss, Vol. 8, 4, no. 5, 7-7 HIKARI Ltd, www.m-hkar.com http://dx.do.org/.988/jma.4.494 Emprcal Dstrbutons of Parameter Estmates n Bnary Logstc Regresson Usng Bootstrap Anwar Ftranto*

More information

A Simple and Efficient Goal Programming Model for Computing of Fuzzy Linear Regression Parameters with Considering Outliers

A Simple and Efficient Goal Programming Model for Computing of Fuzzy Linear Regression Parameters with Considering Outliers 62626262621 Journal of Uncertan Systems Vol.5, No.1, pp.62-71, 211 Onlne at: www.us.org.u A Smple and Effcent Goal Programmng Model for Computng of Fuzzy Lnear Regresson Parameters wth Consderng Outlers

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

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

CS246: Mining Massive Datasets Jure Leskovec, Stanford University

CS246: Mining Massive Datasets Jure Leskovec, Stanford University CS46: Mnng Massve Datasets Jure Leskovec, Stanford Unversty http://cs46.stanford.edu /19/013 Jure Leskovec, Stanford CS46: Mnng Massve Datasets, http://cs46.stanford.edu Perceptron: y = sgn( x Ho to fnd

More information

A Semi-parametric Regression Model to Estimate Variability of NO 2

A Semi-parametric Regression Model to Estimate Variability of NO 2 Envronment and Polluton; Vol. 2, No. 1; 2013 ISSN 1927-0909 E-ISSN 1927-0917 Publshed by Canadan Center of Scence and Educaton A Sem-parametrc Regresson Model to Estmate Varablty of NO 2 Meczysław Szyszkowcz

More information

Cluster Analysis of Electrical Behavior

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

More information

Problem 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

FEATURE EXTRACTION. Dr. K.Vijayarekha. Associate Dean School of Electrical and Electronics Engineering SASTRA University, Thanjavur

FEATURE 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 information

The Research of Support Vector Machine in Agricultural Data Classification

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

More information

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

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

Three supervised learning methods on pen digits character recognition dataset

Three supervised learning methods on pen digits character recognition dataset Three supervsed learnng methods on pen dgts character recognton dataset Chrs Flezach Department of Computer Scence and Engneerng Unversty of Calforna, San Dego San Dego, CA 92093 cflezac@cs.ucsd.edu Satoru

More information

Machine Learning. Topic 6: Clustering

Machine 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 information

ʋ-svr Polynomial Kernel for Predicting the Defect Density in New Software Projects

ʋ-svr Polynomial Kernel for Predicting the Defect Density in New Software Projects ʋ-svr Polynomal Kernel for Predctng the Defect Densty n New Software Projects Cuauhtémoc López-Martín Department of Informaton Systems Unversdad de Guadalajara Méxco cuauhtemoc@cucea.udg.mx Mohammad Azzeh

More information

Validating and Understanding Software Cost Estimation Models based on Neural Networks

Validating and Understanding Software Cost Estimation Models based on Neural Networks Valdatng and Understandng Software Cost Estmaton Models based on eural etworks Al Idr Department of Software Engneerng ESIAS, Mohamed V Unversty Rabat, Morocco E-mal : dr@ensas.ma Alan Abran École de Technologe

More information

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

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

More information

User Authentication Based On Behavioral Mouse Dynamics Biometrics

User 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 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

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

Mathematics 256 a course in differential equations for engineering students

Mathematics 256 a course in differential equations for engineering students Mathematcs 56 a course n dfferental equatons for engneerng students Chapter 5. More effcent methods of numercal soluton Euler s method s qute neffcent. Because the error s essentally proportonal to the

More information

A New Feature of Uniformity of Image Texture Directions Coinciding with the Human Eyes Perception 1

A New Feature of Uniformity of Image Texture Directions Coinciding with the Human Eyes Perception 1 A New Feature of Unformty of Image Texture Drectons Concdng wth the Human Eyes Percepton Xng-Jan He, De-Shuang Huang, Yue Zhang, Tat-Mng Lo 2, and Mchael R. Lyu 3 Intellgent Computng Lab, Insttute of Intellgent

More information

FINDING IMPORTANT NODES IN SOCIAL NETWORKS BASED ON MODIFIED PAGERANK

FINDING 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 information

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

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

More information

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

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

More information

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

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

A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS

A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS Proceedngs of the Wnter Smulaton Conference M E Kuhl, N M Steger, F B Armstrong, and J A Jones, eds A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS Mark W Brantley Chun-Hung

More information

2x x l. Module 3: Element Properties Lecture 4: Lagrange and Serendipity Elements

2x 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 information

NAG Fortran Library Chapter Introduction. G10 Smoothing in Statistics

NAG Fortran Library Chapter Introduction. G10 Smoothing in Statistics Introducton G10 NAG Fortran Lbrary Chapter Introducton G10 Smoothng n Statstcs Contents 1 Scope of the Chapter... 2 2 Background to the Problems... 2 2.1 Smoothng Methods... 2 2.2 Smoothng Splnes and Regresson

More information

Intelligent Information Acquisition for Improved Clustering

Intelligent Information Acquisition for Improved Clustering Intellgent Informaton Acquston for Improved Clusterng Duy Vu Unversty of Texas at Austn duyvu@cs.utexas.edu Mkhal Blenko Mcrosoft Research mblenko@mcrosoft.com Prem Melvlle IBM T.J. Watson Research Center

More information

NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS

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

More information

R s s f. m y s. SPH3UW Unit 7.3 Spherical Concave Mirrors Page 1 of 12. Notes

R s s f. m y s. SPH3UW Unit 7.3 Spherical Concave Mirrors Page 1 of 12. Notes SPH3UW Unt 7.3 Sphercal Concave Mrrors Page 1 of 1 Notes Physcs Tool box Concave Mrror If the reflectng surface takes place on the nner surface of the sphercal shape so that the centre of the mrror bulges

More information

Biostatistics 615/815

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

More information

A Statistical Model Selection Strategy Applied to Neural Networks

A Statistical Model Selection Strategy Applied to Neural Networks A Statstcal Model Selecton Strategy Appled to Neural Networks Joaquín Pzarro Elsa Guerrero Pedro L. Galndo joaqun.pzarro@uca.es elsa.guerrero@uca.es pedro.galndo@uca.es Dpto Lenguajes y Sstemas Informátcos

More information

Why visualisation? IRDS: Visualization. Univariate data. Visualisations that we won t be interested in. Graphics provide little additional information

Why visualisation? IRDS: Visualization. Univariate data. Visualisations that we won t be interested in. Graphics provide little additional information Why vsualsaton? IRDS: Vsualzaton Charles Sutton Unversty of Ednburgh Goal : Have a data set that I want to understand. Ths s called exploratory data analyss. Today s lecture. Goal II: Want to dsplay data

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

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

Solutions to Programming Assignment Five Interpolation and Numerical Differentiation

Solutions to Programming Assignment Five Interpolation and Numerical Differentiation College of Engneerng and Coputer Scence Mechancal Engneerng Departent Mechancal Engneerng 309 Nuercal Analyss of Engneerng Systes Sprng 04 Nuber: 537 Instructor: Larry Caretto Solutons to Prograng Assgnent

More information

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

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

More information

Repeater Insertion for Two-Terminal Nets in Three-Dimensional Integrated Circuits

Repeater Insertion for Two-Terminal Nets in Three-Dimensional Integrated Circuits Repeater Inserton for Two-Termnal Nets n Three-Dmensonal Integrated Crcuts Hu Xu, Vasls F. Pavlds, and Govann De Mchel LSI - EPFL, CH-5, Swtzerland, {hu.xu,vasleos.pavlds,govann.demchel}@epfl.ch Abstract.

More information

Analysis of Continuous Beams in General

Analysis 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 information

Outline. Self-Organizing Maps (SOM) US Hebbian Learning, Cntd. The learning rule is Hebbian like:

Outline. Self-Organizing Maps (SOM) US Hebbian Learning, Cntd. The learning rule is Hebbian like: Self-Organzng Maps (SOM) Turgay İBRİKÇİ, PhD. Outlne Introducton Structures of SOM SOM Archtecture Neghborhoods SOM Algorthm Examples Summary 1 2 Unsupervsed Hebban Learnng US Hebban Learnng, Cntd 3 A

More information

Parameter estimation for incomplete bivariate longitudinal data in clinical trials

Parameter estimation for incomplete bivariate longitudinal data in clinical trials Parameter estmaton for ncomplete bvarate longtudnal data n clncal trals Naum M. Khutoryansky Novo Nordsk Pharmaceutcals, Inc., Prnceton, NJ ABSTRACT Bvarate models are useful when analyzng longtudnal data

More information

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

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

More information

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

Unsupervised Learning

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

More information

Face Recognition University at Buffalo CSE666 Lecture Slides Resources:

Face Recognition University at Buffalo CSE666 Lecture Slides Resources: Face Recognton Unversty at Buffalo CSE666 Lecture Sldes Resources: http://www.face-rec.org/algorthms/ Overvew of face recognton algorthms Correlaton - Pxel based correspondence between two face mages Structural

More information

Network Intrusion Detection Based on PSO-SVM

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

More information

SHAPE RECOGNITION METHOD BASED ON THE k-nearest NEIGHBOR RULE

SHAPE RECOGNITION METHOD BASED ON THE k-nearest NEIGHBOR RULE SHAPE RECOGNITION METHOD BASED ON THE k-nearest NEIGHBOR RULE Dorna Purcaru Faculty of Automaton, Computers and Electroncs Unersty of Craoa 13 Al. I. Cuza Street, Craoa RO-1100 ROMANIA E-mal: dpurcaru@electroncs.uc.ro

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

Complex System Reliability Evaluation using Support Vector Machine for Incomplete Data-set

Complex System Reliability Evaluation using Support Vector Machine for Incomplete Data-set Internatonal Journal of Performablty Engneerng, Vol. 7, No. 1, January 2010, pp.32-42. RAMS Consultants Prnted n Inda Complex System Relablty Evaluaton usng Support Vector Machne for Incomplete Data-set

More information

SVM-based Learning for Multiple Model Estimation

SVM-based Learning for Multiple Model Estimation SVM-based Learnng for Multple Model Estmaton Vladmr Cherkassky and Yunqan Ma Department of Electrcal and Computer Engneerng Unversty of Mnnesota Mnneapols, MN 55455 {cherkass,myq}@ece.umn.edu Abstract:

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

Dynamic Integration of Regression Models

Dynamic Integration of Regression Models Dynamc Integraton of Regresson Models Nall Rooney 1, Davd Patterson 1, Sarab Anand 1, Alexey Tsymbal 2 1 NIKEL, Faculty of Engneerng,16J27 Unversty Of Ulster at Jordanstown Newtonabbey, BT37 OQB, Unted

More information

Machine Learning 9. week

Machine Learning 9. week Machne Learnng 9. week Mappng Concept Radal Bass Functons (RBF) RBF Networks 1 Mappng It s probably the best scenaro for the classfcaton of two dataset s to separate them lnearly. As you see n the below

More information

An Efficient Genetic Algorithm with Fuzzy c-means Clustering for Traveling Salesman Problem

An Efficient Genetic Algorithm with Fuzzy c-means Clustering for Traveling Salesman Problem An Effcent Genetc Algorthm wth Fuzzy c-means Clusterng for Travelng Salesman Problem Jong-Won Yoon and Sung-Bae Cho Dept. of Computer Scence Yonse Unversty Seoul, Korea jwyoon@sclab.yonse.ac.r, sbcho@cs.yonse.ac.r

More information

A Two-Stage Algorithm for Data Clustering

A Two-Stage Algorithm for Data Clustering A Two-Stage Algorthm for Data Clusterng Abdolreza Hatamlou 1 and Salwan Abdullah 2 1 Islamc Azad Unversty, Khoy Branch, Iran 2 Data Mnng and Optmsaton Research Group, Center for Artfcal Intellgence Technology,

More information

Support Vector Machines

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

More information

Maximum Variance Combined with Adaptive Genetic Algorithm for Infrared Image Segmentation

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

More information

Active Contours/Snakes

Active Contours/Snakes Actve Contours/Snakes Erkut Erdem Acknowledgement: The sldes are adapted from the sldes prepared by K. Grauman of Unversty of Texas at Austn Fttng: Edges vs. boundares Edges useful sgnal to ndcate occludng

More information

Adjustment methods for differential measurement errors in multimode surveys

Adjustment methods for differential measurement errors in multimode surveys Adjustment methods for dfferental measurement errors n multmode surveys Salah Merad UK Offce for Natonal Statstcs ESSnet MM DCSS, Fnal Meetng Wesbaden, Germany, 4-5 September 2014 Outlne Introducton Stablsng

More information

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

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

More information

LECTURE : MANIFOLD LEARNING

LECTURE : MANIFOLD LEARNING LECTURE : MANIFOLD LEARNING Rta Osadchy Some sldes are due to L.Saul, V. C. Raykar, N. Verma Topcs PCA MDS IsoMap LLE EgenMaps Done! Dmensonalty Reducton Data representaton Inputs are real-valued vectors

More information

The Codesign Challenge

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

More information

EXTENDED BIC CRITERION FOR MODEL SELECTION

EXTENDED BIC CRITERION FOR MODEL SELECTION IDIAP RESEARCH REPORT EXTEDED BIC CRITERIO FOR ODEL SELECTIO Itshak Lapdot Andrew orrs IDIAP-RR-0-4 Dalle olle Insttute for Perceptual Artfcal Intellgence P.O.Box 59 artgny Valas Swtzerland phone +4 7

More information

Improving Classifier Fusion Using Particle Swarm Optimization

Improving Classifier Fusion Using Particle Swarm Optimization Proceedngs of the 7 IEEE Symposum on Computatonal Intellgence n Multcrtera Decson Makng (MCDM 7) Improvng Classfer Fuson Usng Partcle Swarm Optmzaton Kalyan Veeramachanen Dept. of EECS Syracuse Unversty

More information

Generating Fuzzy Term Sets for Software Project Attributes using and Real Coded Genetic Algorithms

Generating Fuzzy Term Sets for Software Project Attributes using and Real Coded Genetic Algorithms Generatng Fuzzy Ter Sets for Software Proect Attrbutes usng Fuzzy C-Means C and Real Coded Genetc Algorths Al Idr, Ph.D., ENSIAS, Rabat Alan Abran, Ph.D., ETS, Montreal Azeddne Zah, FST, Fes Internatonal

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 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

Improved Methods for Lithography Model Calibration

Improved Methods for Lithography Model Calibration Improved Methods for Lthography Model Calbraton Chrs Mack www.lthoguru.com, Austn, Texas Abstract Lthography models, ncludng rgorous frst prncple models and fast approxmate models used for OPC, requre

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