Comparison among Feature Encoding Techniques for HIV-1 Protease Cleavage Specificity
|
|
- Toby Stewart
- 5 years ago
- Views:
Transcription
1 Internatonal Journal of Intellgent Systems and Applcatons n Engneerng Advanced Technology and Scence ISSN: Orgnal Research Paper Comparson among Feature Encodng Technques for HIV-1 Protease Cleavage Specfcty Uğur Turhal 1, Murat Gök* 2, Aykut Durgut 3 Accepted 15 th August 2014 DOI: /jsae.21005DOI: /b000000x Abstract: HIV-1 protease whch s responsble for the generaton of nfectous vral partcles by cleavng the vrus polypeptdes, play an ndspensable role n the lfe cycle of HIV-1. Knowledge of the substrate specfcty of HIV-1 protease wll pave the way of development of effcacous HIV-1 protease nhbtors. In the predcton of HIV-1 protease cleavage ste technques, many efforts have been devoted. Last decade, several works have approached the predcton of HIV-1 protease cleavage ste problem by applyng a number of methods from the feld of machne learnng. However, t s stll dffcult for researchers to choose the best method due to the lack of an effectve and up-to-date comparson. Here, we have made an extensve study on feature encodng technques for the problem of HIV-1 protease specfcty on dverse machne learnng algorthms. Also, for the frst tme, we appled OEDICHO technque, whch s a combnaton of orthonormal encodng and the bnary representaton of selected 10 best physcochemcal propertes of amno acds derved from Amno Acd ndex database, to predct HIV-1 protease cleavage stes. Keywords: HIV-1 protease specfcty, Feature extracton, Peptde classfcaton, Machne learnng algorthms, Amno acds 1. Introducton Owng to the fact that HIV-1 protease cleaves vrus polypeptdes at defned susceptble stes, t s responsble for processng polyprotens that contan the structural protens (Gag polyproten) and the enzymes (Gag/Pol polyproten) requred for vrus structure and replcaton (Zachary Q. Beck et al, 2000). The nvestgaton of substrate specfcty of HIV-1 protease s the ultmate goal as well as to dentfy optmal sequences to act as a framework for development of hghly effcent nhbtors whch target the actve ste of the protease. Therefore, the knowledge of the polyproten cleavage stes by HIV-1 protease s vtal. The cleavablty predcton task, gven a sequence of eght amno acds (an octamer), ams at knowng whch peptde sequences are cleaved or non-cleaved by the protease. So far, no perfect task s yet known that determnes where a peptde wll be cleaved or non-cleaved by the protease. A standard feed-forward multlayer perceptron (MLP) was used (You-Dong Ca and Kuo-Chen Chou, 1998, Thomas B. Thompson et al., 1995). Support vector machnes (SVM) was adopted several tmes to predct the cleavablty (Yu-Dong Ca et al., 2002, Thorstenn Rognvaldsson and Lwen You, 2004, Lors Nann, 2006). In (Thorstenn Rognvaldsson and Lwen You, 2004), authors showed that the lnear SVM works well for the problem. But these all works were conducted on an out-ofdate dataset ncludng 362 peptde substrates. More recently, a larger dataset (PR-1625), whch was composed of 1625 peptde sequences, was provded by Kontjevsks et al (Aleksejs Kontjevsks et al., 2007). They proposed a statstcally vald 1,3 Unversty of Balıkesr 10100, Turkey 2 Unversty of Yalova 77100, Turkey * Correspondng Author: Emal: murat.gok@yalova.edu.tr Note :Ths paper has been presented at the Internatonal Conference on Advanced Technology&Scences (ICAT'14) held n Antalya (Turkey), August 12-15, rule-based model for the HIV-1 protease specfcty. In (Bng Nu et al., 2009) k-nearest Neghbors (knn) algorthm was appled wth a feature representaton based on the amno acd propertes constructed by Amno Acd ndex database (AAndex) (Shuch Kawashma and Mnoru Kanehsa, 2000). For the protease specfcty, several studes have been conducted applyng orthonormal encodng (OE) method along wth dfferent machne learnng technques (You-Dong Ca and Kuo-Chen Chou, 1998, Lors Nann, 2006). Ruan et al. (Jshou Ruan et al., 2005) proposed a new encodng, termed composton moment vector (CMV), and based resdue s order n a proten sequence. Another approach s OETMAP encodng (Murat Gök and Ahmet T. Özcert, 2012) whch s n conjuncton of OE and Taylor s Venn-dagram (TVD). OEDICHO feature encodng (Murat Gök and Ahmet T. Özcert, 2012), whch was created for the T-cell eptopes recognton, has been tested for the frst tme for HIV-1 protease specfcty problem n ths study. In ths paper, fve encodng technques wth fve learnng algorthms as a standalone approach have been performed to predct HIV-1 protease cleavage stes on PR-1625 HIV-1 dataset. The computatonal results demonstrate hgher performance of OEDICHO n comparson wth the feature encodng methods on a standalone classfer approaches. 2. Methods 2.1. Feature Encodng Feature encodng, whch s a commonly used technque appled before classfcaton, defnes a mappng from the orgnal representaton space nto a new space where the classes are more easly separable. The goal of feature encodng s to dstll the pattern data nto a more concentrated and manageable form. Ths wll reduce the classfer complexty, ncreasng n most cases classfer accuracy (Alberto J. Perez-Jmenez and Juan C. Ths journal s Advanced Technology & Scence 2015 IJISAE, 2015, 3(2),
2 Perez-Cortes, 2006). The evaluated feature encodng technques are gven n bref terms as follows: 1) OE technque s a common encodng method. Accordng to OE, each amno acd symbol P n a peptde s replaced by an orthonormal vector, d (,,..., ) where j s the Kronecker delta symbol. Then, each P s represented by a 20-bt vector, 19 bts are set to zero and 1 bt s set to one based on alphabetc order of amno acds. Each d vector s orthogonal to the rest of d vectors and P can be any one of the twenty amno acds avalable n human body (Thorstenn Rognvaldsson and Lwen You, 2004). The man drawback of OE technque s that OE bnary feature vectors result n nformaton loss. 2) CMV encodng ncludes nformaton about both composton and poston of amno acds n the sequence. CMV provdes functonal relaton wth the structure content,.e. there must not be two or more prmary amno acd sequences that would have dfferent structure content but the same composton moment vector. The feature vector s obtaned concatenatng the frst, the second and the thrd moment vectors (Jshou Ruan et al., 2005). 3) OETMAP encodng conssts of a conjuncton of OE and Taylor s Venn-dagram methods whch are complementary to each other. OETMAP shows the relatonshp of the 20 naturally occurrng amno acds to a selecton of physcochemcal propertes whch are mportant n the determnaton of proten tertary structure (Murat Gök and Ahmet T. Özcert, 2012) 4) OEDICHO encodng combnes the OE and amno acd physcochemcal propertes knowledge to gve complementary recognton nformaton to OE. It therefore ncreases the effectveness of OE. 10 best physcochemcal propertes were selected wth pc-based encodng and were converted ther ndex s values nto bnary feature vectors. Then OE and ths complementary bnary feature vector were concatenated for each resdue n the peptde sequence (Murat Gök and Ahmet T. Özcert, 2012) Classfcaton A proten sequence s composed of a seres of 20 amno acds represented by characters as A, R, N, D, C, Q, E, G, H, I, L, K, M, F, P, S, T, W, Y and V. A peptde s denoted by P = P4P3P2P1 P1 P2 P3 P4 where P s an amno acd. The scssle bond s located between postons P1 and P1 (Israel Schechter and Areh Berger, 1967). The HIV-1 protease cleavage specfcty can be consdered as a bnary classfcaton problem where an octomer peptde s requred to be assgned to cleavable or non-cleavable class. We used fve types of learnng algorthms such as J48, knn, K-star, lnear SVM and MLP for classfcaton under WEKA data mnng software. The evaluated algorthms are gven n bref terms as follows: 1) J48 classfer s a smple C4.5 algorthm. C4.5 generates classfers expressed as decson trees. In decson tree learnng, the learned functon s represented by a decson tree. Each node n the tree represents a test of some attrbute of the tranng example, and each branch corresponds to one of the possble values for ts source node (attrbute) (Pang-Nng Tan et al., 2005). J48 creates a bnary tree. The confdence factor parameter whch s used for prunng has been set to 0.25.Mnmum number of nstances per leaf has been chosen as 2. 2) knn classfcaton, fnds a group of k objects n the tranng set that are closest to the test object, and bases the assgnment of a label on the predomnance of a partcular class n ths neghborhood. There are three key elements of ths approach: a set of labeled objects, a dstance or smlarty metrc to compute dstance between objects, and the value of k, the number of nearest neghbors. To classfy an unlabeled object, the dstance of ths object to the labeled objects s computed, ts k-nearest neghbors are dentfed, and the class labels of these nearest neghbors are then used to determne the class label of the object (Xndong Wu et al., 2008). 3) KStar s an nstance-based classfer. The class of a test nstance s based upon the class of those nstances n the tranng set smlar to t, as determned by some smlarty measurement. The underlyng assumpton of ths type of classfers s that smlar cases belong to the same class (Du Zhang and Jeffrey J. P. Tsa, 2007). The global blend parameter for KStar has been chosen as 20. 4) SVM s an effectve dscrmnatve classfcaton method of statstc learnng theory and n recent tmes, t s successvely appled by a number of other researchers. SVM ams to fnd the maxmum margn hyperplane to separate two classes of patterns. In lnear SVM classfer, classes of two patterns are lnearly separated by the use of a maxmum margn hyperplane, whch s unquely defned by the support vectors, gves the best separaton between the classes (Chrstopher J.C. Burges, 1998). The parameters of the stand-alone SVM (kernel { lnear }, cost of the constran volaton (C) = 10) have been appled for the dataset. 5) Multple layer perceptron (MLP) are the most common type of feed-forward networks and the neurons are organzed nto layers that have undrectonal connectons between them. Based on ths ratonale, the learnng process can be vewed as the problem of updatng connecton weghts from avalable tranng patterns so that the network can effcently perform a specfc task. Performance s mproved over tme by teratvely updatng the weghts n the network. Ths learnng process can be effcently performed wth the Back-propagaton algorthm, whch s based on gradent descend. Then, the actual output of the network s generated and the (possble) error produced by the dfference between the actual output and the desred output s used to modfy the connectons weghts n order to gradually reduce the overall error (Davd E. Rumelhart et al., 1986). The parameters of MLP were learnng rate = 0.3, momentum = Results 3.1. Expermental Setup We conducted our tests on PR-1625 (Aleksejs Kontjevsks et al., 2007) HIV-1 protease dataset, composed by sequences of eght amno acds that can be cleaved or not by the HIV-1 protease. PR-1625 contans 1625 octamer peptdes, of whch 374 are cleaved and 1251 are non-cleaved. Gven a set of peptde sequences wth known labels of cleavable and non-cleavable, we bult OEDICHO encodng feature vectors. OEDICHO was mplemented as n (Murat Gök and Ahmet T. Özcert, 2012). To create bnary feature vector for HIV-1 protease ste predcton, frstly, 10 best physcochemcal propertes were selected accordng to physcochemcal (pc) encodng technque and were converted ther ndex s values nto bnary feature vectors. Lnear support vector machnes were used as the classfer n case of beng mplementng pc-based encodng. Pc-based encodng was repeated for each 544 physcochemcal propertes ndces n AAndex (Murat Gök and Ahmet T. Özcert, 2012). Accordng Ths journal s Advanced Technology & Scence 2015 IJISAE, 2015, 3(2),
3 Table best physcochemcal propertes selected for PR-1625 Order Physcochemcal Property (PR-1625) 1 Energy transfer from out to n (95%bured) 2 Sde chan nteracton parameter 3 Average relatve fractonal occurrence n AL() 4 Average gan n surroundng hydrophobcty 5 Hydrophobcty-related ndex 6 Membrane preference for cytochrome b: MPH89 7 ALTLS ndex 8 Hydrophobcty scale from natve proten structures 9 Rato of bured and accessble molar fractons 10 Normalzed frequency of turn n alpha+beta class In the second step, for each best property s mean was calculated. If the ndex value s smaller than or equals the mean value, t s accepted as 0. If the ndex value s bgger than the mean value, t s accepted as 1. In ths way, bnary encodng table was obtaned. Consequently, dfferent pc-encodng tables obtaned for each dataset. The bult feature vectors, OE (20-bt) and bnary encodng for the best 10 physcochemcal property of each resdue (10-bt) s concatenated, respectvely. Hence, the feature vector has a dmenson of 240-bt (30-bt x 8 resdue) for each octomer peptde. The performances of the classfers were evaluated by means of accuracy (acc), kappa error (ke), F-score and the Matthews correlaton coeffcent (MCC) value metrcs. True postves (TP), true negatves (TN), false postves (FP) and false negatves (FN) values are obtaned va confuson matrx (Tom Fawcett, 2004, Jn Huang and Charles X. Lng, 2005). Acc s a wdely used measure to determne class dscrmnaton ablty, and t s calculated as: TP TN acc TP FP TN FN (1) In statstcal analyss, quantfyng the performance of classfer to accuracy performance obtaned, 10-best physcochemcal propertes, shown n Table 1, were selected for PR algorthms n terms of just usng the percentage of msses as the sngle meter for accuracy can gve msleadng results. Therefore, the cost of error must also be taken nto account. Kappa error s a good metrc to nspect classfcatons that may be due to chance. Kappa error takes values between ( 1, 1). As the Kappa value approaches to 1, then the performance of the related classfer s assumed to be more realstc rather than by chance. Kappa error s calculated as (Are Ben-Davd, 2008): p0 pc ke (2) 1 pc In Eq. 2, s the total agreement probablty and p c s the agreement probablty due to chance. MCC, whch s used as a measure of the qualty of bnary (twoclass) classfcatons, takes nto account true and false postves and negatves. MCC TP TN FP FN ( TP FP)( TP FN)( TN FP)( TN FN) F-score s a measure of a test's accuracy determnng accuracy accountng for both precson and for recall from confuson matrx. F-score accounted as shown n Eq. 4. precson recall F 2 precson recall 3.2. Performance of Feature Encodng Technques 10-fold cross valdaton (10-fold CV) testng scheme s appled to evaluate the performance of the methods n terms of accuracy, kappa, F-score and averaged over 10 experments on PR In a cross-valdaton run, the 10 folds are randomly created. In 10-fold CV, the encodng scheme methods are traned usng 90 % of the data and the remanng 10 % of the data are used for testng of the methods (Rchard O. Duda et al., 2000). Ths process s repeated 10 tmes so that each peptde n datasets s used once. The 10 folds used n the tranng are dfferent from the 10 folds used n the testng. Havng completed the procedures above, the average accuracy, kappa statstc, F-score and MCC values of the each method over these 10 turns are obtaned, as shown Table 2 and Table 3. (3) (4) Table 3. F-Score and MCC Performances of All Methods on Pr-1625 HIV-1 Dataset Lnear SVM MLP J48 IBK K-Star F-Score MCC F-Score MCC F-Score MCC F-Score MCC F-Score MCC OE 0,94 0,84 0,94 0,84 0,91 0,76 0,90 0,75 0,92 0,79 CMV 0,79 0,47 0,89 0,69 0,90 0,73 0,89 0,69 0,94 0,83 OE+CMV 0,90 0,72 0,87 0,64 0,92 0,76 0,88 0,66 0,89 0,71 OETMAP 0,95 0,85 0,95 0,86 0,91 0,75 0,90 0,74 0,91 0,76 OEDICHO 0,95 0,85 0,96 0,88 0,92 0,77 0,90 0,73 0,90 0,74 The results ponts out that OEDICHO has obtaned the best result for both F-score and MCC values wth the value of 0.96 and 0.88, respectvely. 64 IJISAE, 2015, 1(4), Ths journal s Advanced Technology & Scence 2015
4 Table 2. Accuracy Performance of Amno Acd Encodng Schemes on Pr-1625 HIV-1 Dataset Lnear SVM MLP J48 IBK K-Star Acc (%) Kappa Acc (%) Kappa Acc (%) Kappa Acc (%) Kappa Acc (%) Kappa OE CMV OE+CMV OETMAP OEDICHO The results report that OEDICHO encodng outperforms the competng encodng technques wth the value of %. Also hghest Kappa value of OEDICHO wth MLP (0.88) confrms ts robustness of measurement. Note that IBK algorthm obtaned the worst performance among learnng algorthms wth nearly all feature encodng technques. OEDICHO method yelds hgh accurate emprcal results compared to all feature encodng technques for HIV-1 protease specfcty. We notce that OEDICHO combnes the both effectveness of OE and selected 10-best physcochemcal propertes of AAndex. However, OETMAP uses TVD that s not up-to-date n comparson wth OEDICHO s 10-best physcochemcal propertes. A rule based method, the orthogonal search-based rule extracton (OSRE), s presented by Rognvaldsson et al. (Thorstenn Rögnvaldsson et al., 2009). OSRE obtaned accuracy of 93% on PR OEDICHO shows better performance wth the accuracy of %. 4. Conclusons The problem addressed n ths paper s to recognze, gven a sequence of amno acds, HIV-1 protease cleavage ste. We performed an expermental comparson of fve encodng technque wth fve learnng classfers such as lnear SVM, MLP, J48, IBK and K-Star usng up-to-date PR-1625 HIV-1 dataset. OEDICHO technque, whch jons OE technque and complementary bnary feature vector whch comprses selected 10 best physcochemcal propertes ndex values for each resdue n a peptde sequence, shows the best performance wth MLP algorthm. Besde HIV-1 protease ste predcton, OEDICHO encouraged to be used for other peptde classfcaton problems. Due to the fact that ndependent and accurate classfers can make errors on dfferent regons of the feature space, they can be ensemble to acheve better scores. Based on ths ratonale, future works mght nvolve the ensemble of classfers wth dverse encodng technques especally wth OEDICHO encodng. Acknowledgment Ths work was supported by Yalova Unversty, YL Project (Grant 2014/YL/037). References [1] Zachary Q. Beck, Laurence Hervo, Phlp E. Dawson, John H. Elder and Edwn L. Madson (2000). Identfcaton of Effcently Cleaved Substrates for HIV-1 Protease Usng a Phage Dsplay Lbrary and Use n Inhbtor Development. Vrology. Vol Pages [2] You-Dong Ca and Kuo-Chen Chou (1998). Artfcal Neural Network Model for Predctng HIV Protease Cleavage Stes n Proten. Advances n Engneerng Software. Vol. 29. Pages [3] Thomas B. Thompson, Kuo-Chen Chou and Chong Zheng (1995). Neural Network Predcton of the HIV-1 Protease Cleavage Stes. Journal of Theoretcal Bology. Vol Pages [4] Yu-Dong Ca, Xao-Jun Lu, Xue-Bao Xu and Kuo-Chen Chou (2002). Support Vector Machnes for Predctng HIV Protease Cleavage Stes n Proten. Journal of Computatonal Chemstry. Vol. 23. Pages [5] Thorstenn Rognvaldsson and Lwen You (2004). Why Neural Networks Should Not Be Used For HIV-1 Protease Cleavage Ste Predcton. Bonformatcs. Vol. 20. Pages [6] Lors Nann (2006). Comparson among Feature Extracton Methods for HIV-1 Protease Cleavage Ste Predcton. Pattern Recognton. Vol. 39. Pages [7] Aleksejs Kontjevsks, Jarl E. S. Wkberg and Jan Komorowsk (2007). Computatonal Proteomcs Analyss of HIV-1 Protease Interactome. Protens: Structure, Functon and Bonformatcs. Vol. 68. Pages [8] Bng Nu, Ln Lu, Lang Lu, Tan H. Gu, Ka-Yan Feng, Wen-Cong Lu and Yu-Dong Ca (2009). HIV-1 Protease Cleavage Ste Predcton Based on Amno Acd Property. Journal of Computatonal Chemstry. Vol. 30. Pages [9] Shuch Kawashma and Mnoru Kanehsa (2000). AAndex: Amno Acd Index Database. Nuclec Acds Research. Vol. 28. Page Avalable onlne: [10] Jshou Ruan, Ku Wang, Je Yang, Lukasz A. Kurgan and Krzysztof Cos (2005). Hghly Accurate and Consstent Method for Predcton of Elx and Strand Content from Prmary Proten Sequences. Artfcal Intellgence n Medcne. Vol. 35. Pages [11] Murat Gök and Ahmet T. Özcert (2012). OETMAP: A New Feature Encodng Scheme for MHC Class I Bndng Predcton. Molecular and Cellular Bochemstry. Vol Pages [12] Murat Gök and Ahmet T. Özcert (2012). Predcton of MHC Class I Bndng Peptdes wth a New Feature Encodng Technque. Cellular Immunology. Vol Pages [13] Alberto J. Perez-Jmenez and Juan C. Perez-Cortes (2006). Genetc Algorthms for Lnear Feature Extracton. Pattern Recognton Letters. Vol. 27. Pages [14] Israel Schechter and Areh Berger (1967). On the Sze of the Actve Ste n Proteases. I. Papan. Bochemcal and Bophyscal Research Communcatons. Vol. 27. Pages [15] Pang-Nng Tan, Mchael Stenbach and Vpn Kumar (2005). Introducton to Data Mnng. Addson-Wesley Longman Publshng Co., Inc. Boston, ISBN: [16] Xndong Wu, Vpn Kumar, J. Ross Qunlan, Joydeep Ths journal s Advanced Technology & Scence 2015 IJISAE, 2015, 3(2),
5 Ghosh, Qang Yang, Hrosh Motoda, Geoffrey J. McLachlan, Angus Ng, Bng Lu, Phlp S. Yu, Zh-Hua Zhou, Mchael Stenbach, Davd J. Hand and Dan Stenberg (2008). Top 10 Algorthms n Data Mnng. Knowledge and Informaton Systems. Vol. 14. Pages [17] Du Zhang and Jeffrey J. P. Tsa (2007). Advances n Machne Learnng Applcatons n Software Engneerng. Idea Group Publshng. Page [18] Chrstopher J.C. Burges (1998). A Tutoral on Support Vector Machnes for Pattern Recognton. Data Mnng and Knowledge Dscovery. Vol. 2. Pages [19] Davd E. Rumelhart, Geoffrey E. Hnton and Ronald J. Wllams (1986). Learnng Internal Representatons by Error Propagaton. Parallel Dstrbuted Processng: Exploratons n the Mcrostructure of Cognton. Vol. 1. Pages [20] Tom Fawcett (2004). ROC Graphs: Notes and Practcal Consderatons for Researchers. Techncal Report, HP Laboratores. MS Page Mll Road. Palo Alto CA USA, [21] Jn Huang and Charles X. Lng (2005). Usng AUC and Accuracy n Evaluatng Learnng Algorthms. IEEE Transactons on Knowledge and Data Engneerng. Vol. 17. Pages [22] Are Ben-Davd (2008). Comparson of Classfcaton Accuracy Usng Cohen s Weghted Kappa. Expert Systems wth Applcatons. Vol. 34. Pages [23] Rchard O. Duda, Peter E. Hart and Davd G. Stork (2000). Wley. New York. ISBN: [24] Thorstenn Rögnvaldsson, Terence A. Etchells, Lwen You, Danel Garwcz, Ian Jarman and Paulo J. G. Lsboa (2009). How to Fnd Smple and Accurate Rules for Vral Protease Cleavage Specfctes. BMC Bonformatcs. Vol. 10. Page IJISAE, 2015, 1(4), Ths journal s Advanced Technology & Scence 2015
Study and Comparison of Various Techniques of Image Edge Detection
Gureet Sngh et al Int. Journal of Engneerng Research Applcatons RESEARCH ARTICLE OPEN ACCESS Study Comparson of Varous Technques of Image Edge Detecton Gureet Sngh*, Er. Harnder sngh** *(Department of
More informationAN ENHANCED GAGS BASED MTSVSL LEARNING TECHNIQUE FOR CANCER MOLECULAR PATTERN PREDICTION OF CANCER CLASSIFICATION
www.arpapress.com/volumes/vol8issue2/ijrras_8_2_02.pdf AN ENHANCED GAGS BASED MTSVSL LEARNING TECHNIQUE FOR CANCER MOLECULAR PATTERN PREDICTION OF CANCER CLASSIFICATION I. Jule 1 & E. Krubakaran 2 1 Department
More informationBiomarker Selection from Gene Expression Data for Tumour Categorization Using Bat Algorithm
Receved: March 20, 2017 401 Bomarker Selecton from Gene Expresson Data for Tumour Categorzaton Usng Bat Algorthm Gunavath Chellamuthu 1 *, Premalatha Kandasamy 2, Svasubramanan Kanagaraj 3 1 School of
More informationParameter Estimates of a Random Regression Test Day Model for First Three Lactation Somatic Cell Scores
Parameter Estmates of a Random Regresson Test Day Model for Frst Three actaton Somatc Cell Scores Z. u, F. Renhardt and R. Reents Unted Datasystems for Anmal Producton (VIT), Hedeweg 1, D-27280 Verden,
More informationGene Selection Based on Mutual Information for the Classification of Multi-class Cancer
Gene Selecton Based on Mutual Informaton for the Classfcaton of Mult-class Cancer Sheng-Bo Guo,, Mchael R. Lyu 3, and Tat-Mng Lok 4 Department of Automaton, Unversty of Scence and Technology of Chna, Hefe,
More informationInternational Journal of Emerging Technologies in Computational and Applied Sciences (IJETCAS)
Internatonal Assocaton of Scentfc Innovaton and Research (IASIR (An Assocaton Unfyng the Scences, Engneerng, and Appled Research Internatonal Journal of Emergng Technologes n Computatonal and Appled Scences
More information310 Int'l Conf. Par. and Dist. Proc. Tech. and Appl. PDPTA'16
310 Int'l Conf. Par. and Dst. Proc. Tech. and Appl. PDPTA'16 Akra Sasatan and Hrosh Ish Graduate School of Informaton and Telecommuncaton Engneerng, Toka Unversty, Mnato, Tokyo, Japan Abstract The end-to-end
More informationPhysical Model for the Evolution of the Genetic Code
Physcal Model for the Evoluton of the Genetc Code Tatsuro Yamashta Osamu Narkyo Department of Physcs, Kyushu Unversty, Fukuoka 8-856, Japan Abstract We propose a physcal model to descrbe the mechansms
More informationCLUSTERING is always popular in modern technology
Max-Entropy Feed-Forward Clusterng Neural Network Han Xao, Xaoyan Zhu arxv:1506.03623v1 [cs.lg] 11 Jun 2015 Abstract The outputs of non-lnear feed-forward neural network are postve, whch could be treated
More informationeconstor Make Your Publications Visible.
econstor Make Your Publcatons Vsble. A Servce of Wrtschaft Centre zbwlebnz-informatonszentrum Economcs Chang, Huan-Cheng; Chang, Pn-Hsang; Tseng, Sung-Chn; Chang, Ch- Chang; Lu, Yen-Chao Artcle A comparatve
More informationLymphoma Cancer Classification Using Genetic Programming with SNR Features
Lymphoma Cancer Classfcaton Usng Genetc Programmng wth SNR Features Jn-Hyuk Hong and Sung-Bae Cho Dept. of Computer Scence, Yonse Unversty, 134 Shnchon-dong, Sudaemoon-ku, Seoul 120-749, Korea hjnh@candy.yonse.ac.kr,
More informationUsing Past Queries for Resource Selection in Distributed Information Retrieval
Purdue Unversty Purdue e-pubs Department of Computer Scence Techncal Reports Department of Computer Scence 2011 Usng Past Queres for Resource Selecton n Dstrbuted Informaton Retreval Sulleyman Cetntas
More informationInvestigation of zinc oxide thin film by spectroscopic ellipsometry
VNU Journal of Scence, Mathematcs - Physcs 24 (2008) 16-23 Investgaton of znc oxde thn flm by spectroscopc ellpsometry Nguyen Nang Dnh 1, Tran Quang Trung 2, Le Khac Bnh 2, Nguyen Dang Khoa 2, Vo Th Ma
More informationA MIXTURE OF EXPERTS FOR CATARACT DIAGNOSIS IN HOSPITAL SCREENING DATA
Journal of Theoretcal and Appled Informaton Technology 2005 ongong JATIT & LLS ISSN: 1992-8645 www.jatt.org E-ISSN: 1817-3195 A MIXTURE OF EXPERTS FOR CATARACT DIAGNOSIS IN HOSPITAL SCREENING DATA 1 SUNGMIN
More informationA New Machine Learning Algorithm for Breast and Pectoral Muscle Segmentation
Avalable onlne www.ejaet.com European Journal of Advances n Engneerng and Technology, 2015, 2(1): 21-29 Research Artcle ISSN: 2394-658X A New Machne Learnng Algorthm for Breast and Pectoral Muscle Segmentaton
More informationA Classification Model for Imbalanced Medical Data based on PCA and Farther Distance based Synthetic Minority Oversampling Technique
A Classfcaton Model for Imbalanced Medcal Data based on PCA and Farther Dstance based Synthetc Mnorty Oversamplng Technque NADIR MUSTAFA School of Computer Scence and Engneerng Unversty of Electronc Scence
More informationAUTOMATED DETECTION OF HARD EXUDATES IN FUNDUS IMAGES USING IMPROVED OTSU THRESHOLDING AND SVM
AUTOMATED DETECTION OF HARD EXUDATES IN FUNDUS IMAGES USING IMPROVED OTSU THRESHOLDING AND SVM Wewe Gao 1 and Jng Zuo 2 1 College of Mechancal Engneerng, Shangha Unversty of Engneerng Scence, Shangha,
More informationINTEGRATIVE NETWORK ANALYSIS TO IDENTIFY ABERRANT PATHWAY NETWORKS IN OVARIAN CANCER
INTEGRATIVE NETWORK ANALYSIS TO IDENTIFY ABERRANT PATHWAY NETWORKS IN OVARIAN CANCER LI CHEN 1,2, JIANHUA XUAN 1,*, JINGHUA GU 1, YUE WANG 1, ZHEN ZHANG 2, TIAN LI WANG 2, IE MING SHIH 2 1The Bradley Department
More informationCopy Number Variation Methods and Data
Copy Number Varaton Methods and Data Copy number varaton (CNV) Reference Sequence ACCTGCAATGAT TAAGCCCGGG TTGCAACGTTAGGCA Populaton ACCTGCAATGAT TAAGCCCGGG TTGCAACGTTAGGCA ACCTGCAATGAT TTGCAACGTTAGGCA
More informationStatistically Weighted Voting Analysis of Microarrays for Molecular Pattern Selection and Discovery Cancer Genotypes
IJCSNS Internatonal Journal of Computer Scence and Network Securty, VOL.6 No.2, December 26 73 Statstcally Weghted Votng Analyss of Mcroarrays for Molecular Pattern Selecton and Dscovery Cancer Genotypes
More information*VALLIAPPAN Raman 1, PUTRA Sumari 2 and MANDAVA Rajeswari 3. George town, Penang 11800, Malaysia. George town, Penang 11800, Malaysia
38 A Theoretcal Methodology and Prototype Implementaton for Detecton Segmentaton Classfcaton of Dgtal Mammogram Tumor by Machne Learnng and Problem Solvng *VALLIAPPA Raman, PUTRA Sumar 2 and MADAVA Rajeswar
More informationAvailable online at ScienceDirect. Procedia Computer Science 46 (2015 )
Avalable onlne at www.scencedrect.com ScenceDrect Proceda Computer Scence 46 (215 ) 1762 1769 Internatonal Conference on Informaton and Communcaton Technologes (ICICT 214) Automatc Characterzaton of Bengn
More informationPrediction of Total Pressure Drop in Stenotic Coronary Arteries with Their Geometric Parameters
Tenth Internatonal Conference on Computatonal Flud Dynamcs (ICCFD10), Barcelona, Span, July 9-13, 2018 ICCFD10-227 Predcton of Total Pressure Drop n Stenotc Coronary Arteres wth Ther Geometrc Parameters
More informationA Geometric Approach To Fully Automatic Chromosome Segmentation
A Geometrc Approach To Fully Automatc Chromosome Segmentaton Shervn Mnaee ECE Department New York Unversty Brooklyn, New York, USA shervn.mnaee@nyu.edu Mehran Fotouh Computer Engneerng Department Sharf
More informationFast Algorithm for Vectorcardiogram and Interbeat Intervals Analysis: Application for Premature Ventricular Contractions Classification
Fast Algorthm for Vectorcardogram and Interbeat Intervals Analyss: Applcaton for Premature Ventrcular Contractons Classfcaton Irena Jekova, Vessela Krasteva Centre of Bomedcal Engneerng Prof. Ivan Daskalov
More informationSurvival Rate of Patients of Ovarian Cancer: Rough Set Approach
Internatonal OEN ACCESS Journal Of Modern Engneerng esearch (IJME) Survval ate of atents of Ovaran Cancer: ough Set Approach Kamn Agrawal 1, ragat Jan 1 Department of Appled Mathematcs, IET, Indore, Inda
More informationJournal of Engineering Science and Technology Review 11 (2) (2018) Research Article
Jestr Journal of Engneerng Scence and Technology Revew () (08) 5 - Research Artcle Prognoss Evaluaton of Ovaran Granulosa Cell Tumor Based on Co-forest ntellgence Model Xn Lao Xn Zheng Juan Zou Mn Feng
More informationPrice linkages in value chains: methodology
Prce lnkages n value chans: methodology Prof. Trond Bjorndal, CEMARE. Unversty of Portsmouth, UK. and Prof. José Fernández-Polanco Unversty of Cantabra, Span. FAO INFOSAMAK Tangers, Morocco 14 March 2012
More informationAn Approach to Discover Dependencies between Service Operations*
36 JOURNAL OF SOFTWARE VOL. 3 NO. 9 DECEMBER 2008 An Approach to Dscover Dependences between Servce Operatons* Shuyng Yan Research Center for Grd and Servce Computng Insttute of Computng Technology Chnese
More informationSparse Representation of HCP Grayordinate Data Reveals. Novel Functional Architecture of Cerebral Cortex
1 Sparse Representaton of HCP Grayordnate Data Reveals Novel Functonal Archtecture of Cerebral Cortex X Jang 1, Xang L 1, Jngle Lv 2,1, Tuo Zhang 2,1, Shu Zhang 1, Le Guo 2, Tanmng Lu 1* 1 Cortcal Archtecture
More informationClassification of Breast Tumor in Mammogram Images Using Unsupervised Feature Learning
Amercan Journal of Appled Scences Orgnal Research Paper Classfcaton of Breast Tumor n Mammogram Images Usng Unsupervsed Feature Learnng 1 Adarus M. Ibrahm, 1 Baharum Baharudn, 1 Abas Md Sad and 2 P.N.
More informationModeling the Survival of Retrospective Clinical Data from Prostate Cancer Patients in Komfo Anokye Teaching Hospital, Ghana
Internatonal Journal of Appled Scence and Technology Vol. 5, No. 6; December 2015 Modelng the Survval of Retrospectve Clncal Data from Prostate Cancer Patents n Komfo Anokye Teachng Hosptal, Ghana Asedu-Addo,
More informationCancer Classification Based on Support Vector Machine Optimized by Particle Swarm Optimization and Artificial Bee Colony
molecules Artcle Cancer Classfcaton Based on Support Vector Machne Optmzed by Partcle Swarm Optmzaton and Artfcal Bee Colony Lngyun Gao 1 ID, Mngquan Ye 1, * and Changrong Wu 2 1 School of Medcal Informaton,
More informationModeling Multi Layer Feed-forward Neural. Network Model on the Influence of Hypertension. and Diabetes Mellitus on Family History of
Appled Mathematcal Scences, Vol. 7, 2013, no. 41, 2047-2053 HIKARI Ltd, www.m-hkar.com Modelng Mult Layer Feed-forward Neural Network Model on the Influence of Hypertenson and Dabetes Melltus on Famly
More informationReconstruction of gene regulatory network of colon cancer using information theoretic approach
Reconstructon of gene regulatory network of colon cancer usng nformaton theoretc approach Khald Raza #1, Rafat Parveen * # Department of Computer Scence Jama Mlla Islama (Central Unverst, New Delh-11005,
More informationTowards Prediction of Radiation Pneumonitis Arising from Lung Cancer Patients Using Machine Learning Approaches
Towards Predcton of Radaton Pneumonts Arsng from Lung Cancer Patents Usng Machne Learnng Approaches Jung Hun Oh, Adtya Apte, Rawan Al-Loz, Jeffrey Bradley, Issam El Naqa * Dvson of Bonformatcs and Outcomes
More informationIMPROVING THE EFFICIENCY OF BIOMARKER IDENTIFICATION USING BIOLOGICAL KNOWLEDGE
IMPROVING THE EFFICIENCY OF BIOMARKER IDENTIFICATION USING BIOLOGICAL KNOWLEDGE JOHN H. PHAN The Wallace H. Coulter Department of Bomedcal Engneerng, Georga Insttute of Technology, 313 Ferst Drve Atlanta,
More informationAn Introduction to Modern Measurement Theory
An Introducton to Modern Measurement Theory Ths tutoral was wrtten as an ntroducton to the bascs of tem response theory (IRT) modelng and ts applcatons to health outcomes measurement for the Natonal Cancer
More informationOptimal Planning of Charging Station for Phased Electric Vehicle *
Energy and Power Engneerng, 2013, 5, 1393-1397 do:10.4236/epe.2013.54b264 Publshed Onlne July 2013 (http://www.scrp.org/ournal/epe) Optmal Plannng of Chargng Staton for Phased Electrc Vehcle * Yang Gao,
More informationBalanced Query Methods for Improving OCR-Based Retrieval
Balanced Query Methods for Improvng OCR-Based Retreval Kareem Darwsh Electrcal and Computer Engneerng Dept. Unversty of Maryland, College Park College Park, MD 20742 kareem@glue.umd.edu Douglas W. Oard
More informationPrognosis and Diagnosis of Breast Cancer Using Interactive Dashboard Through Big Data Analytics
Prognoss and Dagnoss of Breast Cancer Usng Interactve Dashboard Through Bg Data Analytcs Gomath N, and Sandhya P 2 * Department of Computer Scence and Engneerng, Veltech Dr. RR & Dr. SR Unversty, Avad,
More informationA Linear Regression Model to Detect User Emotion for Touch Input Interactive Systems
2015 Internatonal Conference on Affectve Computng and Intellgent Interacton (ACII) A Lnear Regresson Model to Detect User Emoton for Touch Input Interactve Systems Samt Bhattacharya Dept of Computer Scence
More informationA Support Vector Machine Classifier based on Recursive Feature Elimination for Microarray Data in Breast Cancer Characterization. Abstract.
A Support Vector Machne Classfer based on Recursve Feature Elmnaton for Mcroarray Data n Breast Cancer Characterzaton. R.Campann, D. Dongovann, E. Iamper, N. Lanconell, G. Palermo, M. Roffll, A. Rccard
More informationIntroduction ORIGINAL RESEARCH
ORIGINAL RESEARCH Assessng the Statstcal Sgnfcance of the Acheved Classfcaton Error of Classfers Constructed usng Serum Peptde Profles, and a Prescrpton for Random Samplng Repeated Studes for Massve Hgh-Throughput
More informationA Computer-aided System for Discriminating Normal from Cancerous Regions in IHC Liver Cancer Tissue Images Using K-means Clustering*
A Computer-aded System for Dscrmnatng Normal from Cancerous Regons n IHC Lver Cancer Tssue Images Usng K-means Clusterng* R. M. CHEN 1, Y. J. WU, S. R. JHUANG, M. H. HSIEH, C. L. KUO, Y. L. MA Department
More informationJournal of Engineering Science and Technology Review 11 (2) (2018) Research Article
Jestr Journal of Engneerng Scence and Technology Revew 11 (2) (2018) 8-12 Research Artcle Detecton Lung Cancer Usng Gray Level Co-Occurrence Matrx (GLCM) and Back Propagaton Neural Network Classfcaton
More informationNon-linear Multiple-Cue Judgment Tasks
Non-lnear Multple-Cue Tasks Anna-Carn Olsson (anna-carn.olsson@psy.umu.se) Department of Psychology, Umeå Unversty SE-09 87, Umeå, Sweden Tommy Enqvst (tommy.enqvst@psyk.uu.se) Department of Psychology,
More informationEvaluation of Literature-based Discovery Systems
Evaluaton of Lterature-based Dscovery Systems Melha Yetsgen-Yldz 1 and Wanda Pratt 1,2 1 The Informaton School, Unversty of Washngton, Seattle, USA. 2 Bomedcal and Health Informatcs, School of Medcne,
More informationAn expressive three-mode principal components model for gender recognition
Journal of Vson (4) 4, 36-377 http://journalofvson.org/4/5// 36 An expressve three-mode prncpal components model for gender recognton James W. Davs Hu Gao Department of Computer and Informaton Scence,
More informationEvaluation of the generalized gamma as a tool for treatment planning optimization
Internatonal Journal of Cancer Therapy and Oncology www.jcto.org Evaluaton of the generalzed gamma as a tool for treatment plannng optmzaton Emmanoul I Petrou 1,, Ganesh Narayanasamy 3, Eleftheros Lavdas
More informationPerformance Evaluation of Public Non-Profit Hospitals Using a BP Artificial Neural Network: The Case of Hubei Province in China
Int. J. Envron. Res. Publc Health 2013, 10, 3619-3633; do:10.3390/jerph10083619 OPEN ACCESS Artcle Internatonal Journal of Envronmental Research and Publc Health ISSN 1660-4601 www.mdp.com/journal/jerph
More informationA New Diagnosis Loseless Compression Method for Digital Mammography Based on Multiple Arbitrary Shape ROIs Coding Framework
I.J.Modern Educaton and Computer Scence, 2011, 5, 33-39 Publshed Onlne August 2011 n MECS (http://www.mecs-press.org/) A New Dagnoss Loseless Compresson Method for Dgtal Mammography Based on Multple Arbtrary
More informationSubject-Adaptive Real-Time Sleep Stage Classification Based on Conditional Random Field
Subject-Adaptve Real-Tme Sleep Stage Classfcaton Based on Condtonal Random Feld Gang Luo, PhD, Wanl Mn, PhD IBM TJ Watson Research Center, Hawthorne, NY {luog, wanlmn}@usbmcom Abstract Sleep stagng s the
More informationIncorrect Beliefs. Overconfidence. Types of Overconfidence. Outline. Overprecision 4/22/2015. Econ 1820: Behavioral Economics Mark Dean Spring 2015
Incorrect Belefs Overconfdence Econ 1820: Behavoral Economcs Mark Dean Sprng 2015 In objectve EU we assumed that everyone agreed on what the probabltes of dfferent events were In subjectve expected utlty
More informationEXAMINATION OF THE DENSITY OF SEMEN AND ANALYSIS OF SPERM CELL MOVEMENT. 1. INTRODUCTION
JOURNAL OF MEDICAL INFORMATICS & TECHNOLOGIES Vol.3/00, ISSN 64-6037 Łukasz WITKOWSKI * mage enhancement, mage analyss, semen, sperm cell, cell moblty EXAMINATION OF THE DENSITY OF SEMEN AND ANALYSIS OF
More informationA Support Vector Machine Classifier based on Recursive Feature Elimination for Microarray Data in Breast Cancer Characterization. Abstract.
A Support Vector Machne Classfer based on Recursve Feature Elmnaton for Mcroarray Data n Breast Cancer Characterzaton. R.Campann, D. Dongovann, N. Lanconell, G. Palermo, A. Rccard, M. Roffll Dpartmento
More informationINTRAUTERINE GROWTH RESTRICTION (IUGR) RISK DECISION BASED ON SUPPORT VECTOR MACHINES
Mathematcal and Computatonal Applcatons, Vol. 15, No. 3, pp. 472-480, 2010. Assocaton for Scentfc Research INTRAUTERINE GROWTH RESTRICTION (IUGR) RISK DECISION BASED ON SUPPORT VECTOR MACHINES Zeynep Zengn
More informationFeature Selection for Predicting Tumor Metastases in Microarray Experiments using Paired Design
Feature Selecton for Predctng Tumor Metastases n Mcroarray Experments usng Pared Desgn Qhua Tan 1,2, Mads Thomassen 1 and Torben A. Kruse 1 ORIGINAL RESEARCH 1 Department of Bochemstry, Pharmacology and
More informationHierarchical kernel mixture models for the prediction of AIDS disease progression using HIV structural gp120 profiles
PROCEEDINGS Open Access Herarchcal kernel mxture models for the predcton of AIDS dsease progresson usng HIV structural gp20 profles Paul D Yoo,2*, Yung Shwen Ho 3, Jason Ng 4, Mchael Charleston 5, Ntn
More informationEVALUATION OF BULK MODULUS AND RING DIAMETER OF SOME TELLURITE GLASS SYSTEMS
Chalcogende Letters Vol. 12, No. 2, February 2015, p. 67-74 EVALUATION OF BULK MODULUS AND RING DIAMETER OF SOME TELLURITE GLASS SYSTEMS R. EL-MALLAWANY a*, M.S. GAAFAR b, N. VEERAIAH c a Physcs Dept.,
More informationENRICHING PROCESS OF ICE-CREAM RECOMMENDATION USING COMBINATORIAL RANKING OF AHP AND MONTE CARLO AHP
ENRICHING PROCESS OF ICE-CREAM RECOMMENDATION USING COMBINATORIAL RANKING OF AHP AND MONTE CARLO AHP 1 AKASH RAMESHWAR LADDHA, 2 RAHUL RAGHVENDRA JOSHI, 3 Dr.PEETI MULAY 1 M.Tech, Department of Computer
More informationProceedings of the 6th WSEAS Int. Conf. on EVOLUTIONARY COMPUTING, Lisbon, Portugal, June 16-18, 2005 (pp )
Proceedngs of the 6th WSEAS Int. Conf. on EVOLUTIONARY COMPUTING, Lsbon, Portugal, June 6-8, 2005 (pp285-20) Novel Intellgent Edge Detector for Sonographcal Images Al Rafee *, Mohammad Hasan Morad **,
More informationNonstandard Machine Learning Algorithms for Microarray Data Mining. Byoung-Tak Zhang
Nonstandard Machne Learnng Algorthms for Mcroarray Data Mnng Byoung-Tak Zhang Center for Bonformaton Technology (CBIT) & Bontellgence Laboratory School of Computer Scence and Engneerng Seoul Natonal Unversty
More informationUsing the Perpendicular Distance to the Nearest Fracture as a Proxy for Conventional Fracture Spacing Measures
Usng the Perpendcular Dstance to the Nearest Fracture as a Proxy for Conventonal Fracture Spacng Measures Erc B. Nven and Clayton V. Deutsch Dscrete fracture network smulaton ams to reproduce dstrbutons
More informationEncoding processes, in memory scanning tasks
vlemory & Cognton 1976,4 (5), 501 506 Encodng processes, n memory scannng tasks JEFFREY O. MILLER and ROBERT G. PACHELLA Unversty of Mchgan, Ann Arbor, Mchgan 48101, Three experments are presented that
More informationDetection of Lung Cancer at Early Stage using Neural Network Techniques for Preventing Health Care
IJSRD - Internatonal Journal for Scentfc Research & Development Vol. 3, Issue 4, 15 ISSN (onlne): 31-613 Detecton of Lung Cancer at Early Stage usng Neural Network echnques for Preventng Health Care Megha
More informationCONSTRUCTION OF STOCHASTIC MODEL FOR TIME TO DENGUE VIRUS TRANSMISSION WITH EXPONENTIAL DISTRIBUTION
Internatonal Journal of Pure and Appled Mathematcal Scences. ISSN 97-988 Volume, Number (7), pp. 3- Research Inda Publcatons http://www.rpublcaton.com ONSTRUTION OF STOHASTI MODEL FOR TIME TO DENGUE VIRUS
More informationJOINT SUB-CLASSIFIERS ONE CLASS CLASSIFICATION MODEL FOR AVIAN INFLUENZA OUTBREAK DETECTION
JOINT SUB-CLASSIFIERS ONE CLASS CLASSIFICATION MODEL FOR AVIAN INFLUENZA OUTBREAK DETECTION Je Zhang, Je Lu, Guangquan Zhang Centre for Quantum Computaton & Intellgent Systems Faculty of Engneerng and
More informationARTICLE IN PRESS. computer methods and programs in biomedicine xxx (2007) xxx xxx. journal homepage:
computer methods and programs n bomedcne xxx (2007) xxx xxx journal homepage: www.ntl.elseverhealth.com/journals/cmpb Improvng bran tumor characterzaton on MRI by probablstc neural networks and non-lnear
More informationINITIAL ANALYSIS OF AWS-OBSERVED TEMPERATURE
INITIAL ANALYSIS OF AWS-OBSERVED TEMPERATURE Wang Yng, Lu Xaonng, Ren Zhhua, Natonal Meteorologcal Informaton Center, Bejng, Chna Tel.:+86 684755, E-mal:cdcsjk@cma.gov.cn Abstract From, n Chna meteorologcal
More informationARTICLE IN PRESS Neuropsychologia xxx (2010) xxx xxx
Neuropsychologa xxx (200) xxx xxx Contents lsts avalable at ScenceDrect Neuropsychologa journal homepage: www.elsever.com/locate/neuropsychologa Storage and bndng of object features n vsual workng memory
More informationDr.S.Sumathi 1, Mrs.V.Agalya 2 Mahendra Engineering College, Mahendhirapuri, Mallasamudram
Detecton Of Myocardal Ischema In ECG Sgnals Usng Support Vector Machne Dr.S.Sumath 1, Mrs.V.Agalya Mahendra Engneerng College, Mahendhrapur, Mallasamudram Abstract--Ths paper presents an ntellectual dagnoss
More informationStudy on Psychological Crisis Evaluation Combining Factor Analysis and Neural Networks *
Psychology 2011. Vol.2, No.2, 138-142 Copyrght 2011 ScRes. DOI:10.4236/psych.2011.22022 Study on Psychologcal Crss Evaluaton Combnng Factor Analyss and Neural Networks * Hu Ln 1, Yngb Zhang 1, Hengqng
More informationThe Limits of Individual Identification from Sample Allele Frequencies: Theory and Statistical Analysis
The Lmts of Indvdual Identfcaton from Sample Allele Frequences: Theory and Statstcal Analyss Peter M. Vsscher 1 *, Wllam G. Hll 2 1 Queensland Insttute of Medcal Research, Brsbane, Australa, 2 Insttute
More informationMaize Varieties Combination Model of Multi-factor. and Implement
Maze Varetes Combnaton Model of Mult-factor and Implement LIN YANG,XIAODONG ZHANG,SHAOMING LI Department of Geographc Informaton Scence Chna Agrcultural Unversty No. 17 Tsnghua East Road, Bejng 100083
More informationIncorporating prior biological knowledge for network-based differential gene expression analysis using differentially weighted graphical LASSO
Zuo et al. BMC Bonformatcs (2017) 18:99 DOI 10.1186/s12859-017-1515-1 METHODOLOGY ARTICLE Open Access Incorporatng pror bologcal knowledge for network-based dfferental gene expresson analyss usng dfferentally
More informationPERFORMANCE EVALUATION OF DIVERSIFIED SVM KERNEL FUNCTIONS FOR BREAST TUMOR EARLY PROGNOSIS
AR Journal of Engneerng and Appled Scences 2006-2014 Asan Research ublshng etwork (AR). All rghts reserved. ERFORMACE EVALUAIO OF DIVERSIFIED SVM KEREL FUCIOS FOR BREAS UMOR EARLY ROGOSIS Khondker Jahd
More informationArrhythmia Detection based on Morphological and Time-frequency Features of T-wave in Electrocardiogram ABSTRACT
Orgnal Artcle Arrhythma Detecton based on Morphologcal and Tme-frequency Features of T-wave n Electrocardogram Elham Zeraatkar, Saeed Kerman, Alreza Mehrdehnav 1, A. Amnzadeh 2, E. Zeraatkar 3, Hamd Sane
More informationThis article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and
Ths artcle appeared n a journal publshed by Elsever. The attached copy s furnshed to the author for nternal non-commercal research and educaton use, ncludng for nstructon at the authors nsttuton and sharng
More informationWhat Determines Attitude Improvements? Does Religiosity Help?
Internatonal Journal of Busness and Socal Scence Vol. 4 No. 9; August 2013 What Determnes Atttude Improvements? Does Relgosty Help? Madhu S. Mohanty Calforna State Unversty-Los Angeles Los Angeles, 5151
More informationJoint Modelling Approaches in diabetes research. Francisco Gude Clinical Epidemiology Unit, Hospital Clínico Universitario de Santiago
Jont Modellng Approaches n dabetes research Clncal Epdemology Unt, Hosptal Clínco Unverstaro de Santago Outlne 1 Dabetes 2 Our research 3 Some applcatons Dabetes melltus Is a serous lfe-long health condton
More informationJurnal Teknologi USING ASSOCIATION RULES TO STUDY PATTERNS OF MEDICINE USE IN THAI ADULT DEPRESSED PATIENTS. Full Paper
Jurnal Teknolog USING ASSOCIATION RULES TO STUDY PATTERNS OF MEDICINE USE IN THAI ADULT DEPRESSED PATIENTS Chumpoonuch Sukontavaree, Verayuth Lertnattee * Faculty of Pharmacy, Slpakorn Unversty, Nakhon
More informationComparison of support vector machine based on genetic algorithm with logistic regression to diagnose obstructive sleep apnea
Orgnal Artcle Comparson of support vector machne based on genetc algorthm wth logstc regresson to dagnose obstructve sleep apnea Zohreh Manoochehr, Nader Salar 1, Mansour Rezae 1, Habbolah Khazae 2, Sara
More informationA GEOGRAPHICAL AND STATISTICAL ANALYSIS OF LEUKEMIA DEATHS RELATING TO NUCLEAR POWER PLANTS. Whitney Thompson, Sarah McGinnis, Darius McDaniel,
A GEOGRAPHICAL AD STATISTICAL AALYSIS OF LEUKEMIA DEATHS RELATIG TO UCLEAR POWER PLATS Whtney Thompson, Sarah McGnns, Darus McDanel, Jean Sexton, Rebecca Pettt, Sarah Anderson, Monca Jackson ABSTRACT:
More informationUsing a Wavelet Representation for Classification of Movement in Bed
Usng a Wavelet Representaton for Classfcaton of Movement n Bed Adrana Morell Adam Depto. de Matemátca e Estatístca Unversdade de Caxas do Sul Caxas do Sul RS E-mal: amorell@ucs.br André Gustavo Adam Depto.
More informationLETTERS. Effects of thymic selection of the T-cell repertoire on HLA class I-associated control of HIV infection
do:1.138/nature8997 LETTERS Effects of thymc selecton of the T-cell repertore on HLA class I-assocated control of HIV nfecton Andrej Košmrlj 1,2 *, Elzabeth L. Read 1,3,4 *, Yng Q 5, Todd M. Allen 1, Marcus
More informationOptimization of Neem Seed Oil Extraction Process Using Response Surface Methodology
ISSN 4-186 (Paper) ISSN 5-091 (Onlne) Vol., No.6, 01 Optmzaton of Neem Seed Ol Extracton Process Usng Response Surface Methodology Tunmse Latfat Adewoye 1 and Oladpupo Olaosebkan Ogunleye 1 Department
More information4.2 Scheduling to Minimize Maximum Lateness
4. Schedulng to Mnmze Maxmum Lateness Schedulng to Mnmzng Maxmum Lateness Mnmzng lateness problem. Sngle resource processes one ob at a tme. Job requres t unts of processng tme and s due at tme d. If starts
More informationComputing and Using Reputations for Internet Ratings
Computng and Usng Reputatons for Internet Ratngs Mao Chen Department of Computer Scence Prnceton Unversty Prnceton, J 8 (69)-8-797 maoch@cs.prnceton.edu Jaswnder Pal Sngh Department of Computer Scence
More informationBoosting for tumor classification with gene expression data. Seminar für Statistik, ETH Zürich, CH-8092, Switzerland
BIOINFORMATICS Vol. 19 no. 9 2003, pages 1061 1069 DOI: 10.1093/bonformatcs/btf867 Boostng for tumor classfcaton wth gene expresson data Marcel Dettlng and Peter Bühlmann Semnar für Statstk, ETH Zürch,
More informationImprovement of Automatic Hemorrhages Detection Methods using Brightness Correction on Fundus Images
Improvement of Automatc Hemorrhages Detecton Methods usng Brghtness Correcton on Fundus Images Yuj Hatanaka *a, Toshak Nakagawa *b, Yoshnor Hayash *c, Masakatsu Kakogawa *c, Akra Sawada *d, Kazuhde Kawase
More informationDETECTION AND CLASSIFICATION OF BRAIN TUMOR USING ML
DOI: http://dx.do.org/0.26483/arcs.v92.5807 Volume 9, No. 2, March-Aprl 208 Internatonal Journal of Advanced Research n Computer Scence RESEARCH PAPER Avalable Onlne at www.arcs.nfo ISSN No. 0976-5697
More informationTowards Automated Pose Invariant 3D Dental Biometrics
Towards Automated Pose Invarant 3D Dental Bometrcs Xn ZHONG 1, Depng YU 1, Kelvn W C FOONG, Terence SIM 3, Yoke San WONG 1 and Ho-lun CHENG 3 1. Mechancal Engneerng, Natonal Unversty of Sngapore, 117576,
More informationFAST DETECTION OF MASSES IN MAMMOGRAMS WITH DIFFICULT CASE EXCLUSION
computng@tanet.edu.te.ua www.tanet.edu.te.ua/computng ISSN 727-6209 Internatonal Scentfc Journal of Computng FAST DETECTION OF MASSES IN MAMMOGRAMS WITH DIFFICULT CASE EXCLUSION Gábor Takács ), Béla Patak
More information(From the Gastroenterology Division, Cornell University Medical College, New York 10021)
ROLE OF HEPATIC ANION-BINDING PROTEIN IN BROMSULPHTHALEIN CONJUGATION* BY N. KAPLOWITZ, I. W. PERC -ROBB,~ ANn N. B. JAVITT (From the Gastroenterology Dvson, Cornell Unversty Medcal College, New York 10021)
More informationAutomated and ERP-Based Diagnosis of Attention-Deficit Hyperactivity Disorder in Children
Orgnal Artcle Automated and ERP-Based Dagnoss of Attenton-Defct Hyperactvty Dsorder n Chldren Abstract Event-related potental (ERP) s one of the most nformatve and dynamc methods of montorng cogntve processes,
More informationN-back Training Task Performance: Analysis and Model
N-back Tranng Task Performance: Analyss and Model J. Isaah Harbson (jharb@umd.edu) Center for Advanced Study of Language and Department of Psychology, Unversty of Maryland 7005 52 nd Avenue, College Park,
More informationProject title: Mathematical Models of Fish Populations in Marine Reserves
Applcaton for Fundng (Malaspna Research Fund) Date: November 0, 2005 Project ttle: Mathematcal Models of Fsh Populatons n Marne Reserves Dr. Lev V. Idels Unversty College Professor Mathematcs Department
More informationA comparison of statistical methods in interrupted time series analysis to estimate an intervention effect
Peer revew stream A comparson of statstcal methods n nterrupted tme seres analyss to estmate an nterventon effect a,b, J.J.J., Walter c, S., Grzebeta a, R. & Olver b, J. a Transport and Road Safety, Unversty
More informationPrototypes in the Mist: The Early Epochs of Category Learning
Journal of Expermental Psychology: Learnng, Memory, and Cognton 1998, Vol. 24, No. 6, 1411-1436 Copyrght 1998 by the Amercan Psychologcal Assocaton, Inc. 0278-7393/98/S3.00 Prototypes n the Mst: The Early
More information