Estimation of automatic detection of erythemato-squamous diseases through AdaBoost and its hybrid classifiers

详细信息    查看全文

• 作者：N. Badrinath ; G. Gopinath ; K. S. Ravichandran…
• 关键词：Erythemato ; squamous diseases ; AdaBoost (real ; gentle and modest) ; Support vector machine (SVM) ; Feature selection ; Apriori algorithm
• 刊名：Artificial Intelligence Review
• 出版年：2016
• 出版时间：April 2016
• 年：2016
• 卷：45
• 期：4
• 页码：471-488
• 全文大小：1,625 KB
• 参考文献：Agrawal R, Shafer JC (1996) Parallel mining of association rules. IEEE Trans Knowl Data Eng 8(6):962–969CrossRef
  Agrawal R, Srikant R (1994) Fast algorithms for mining association rules in large data bases. In: Proceedings of the 20th international conference on very large data bases, September 12–15, pp 487–499
  Aruna S, Nandakishore LV, Rajagopalan SP (2012) A hybrid feature selection method based on IGSBFS and naïve bayes for the diagnosis of erythemato-squamous diseases. Int J Comput Appl 41(7):13–18
  Balas VE, Fodor J, Várkonyi-Kóczy AR, Dombi J, Lakhmi CJ (2013) Soft computing applications. In: Proceedings of the 5th international workshop soft computing applications (SOFA) 195:01–04
  Bauer E, Kohavi R (1999) An empirical comparison of voting classification algorithms: bagging, boosting, and variants. Mach Learn 36:105–139CrossRef
  Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140MathSciNet MATH
  Castellano G, Castiello C, Fanelli AM, Leone C (2003) Diagnosis of dermatological diseases by a neuro-fuzzy approach. In: Proceedings of international conference in fuzzy logic and technology (EUSFLAT 2003). Zittau, Germany, September 10–12. 747–750
  Chatterjee C, Roychowdhury VP, Chong EKP (1998) On relative convergence properties of principal component analysis algorithms. IEEE Trans Neural Netw 9:319–329CrossRef
  Cover T, Hart P (1967) Nearest neighbor pattern classification. Proc IEEE Trans Inf Theory 13(1):21–27CrossRef MATH
  Davar G, Salimi H, Bitaraf AA, Khademian Y (2011) Detection of erythemato-squamous diseases using AR-CatfishBPSO-KSVM. Signal Image Process Int J (SIPIJ) 2(4):57–72CrossRef
  Demuth H, Beale M (1992) Neural network toolbox, for use with MATLAB. User’s Guide 4:18–20
  Duda R, Hart P, Stork D (2001) Pattern classification, 2nd edn. John Wiley and Sons, New YorkMATH
  Efron B (1982) The jackknife, the bootstrap and other resampling plans. Society for Industrial and Applied Mathematics (SIAM), PhiladelphiaCrossRef MATH
  Elsayad AM (2010) Diagnosis of erythemato-squamous diseases using ensemble of data mining methods. ICGST-BIME J 10(1):13–23
  Freund Y, Schapire R (1996a) Experiments with a new boosting algorithm. In: Thirteenth international conference on machine learning. Bari, Italy, pp 148–156
  Freund Y, Schapire R (1996b) Game theory on-line prediction and boosting. In: Ninth annual conference on computer learning theory. Desenzano del Garda, Italy, pp 325–332
  Friedman J, Hastie T, Tibshirani R (2000) Additive logistic regression: a statistical view of boosting. Ann Stat 28(2):337–374MathSciNet CrossRef MATH
  Gómez-Verdejo V, Ortega-Moral M, Arenas-Gárcia J, Figueiras-Vidal A (2006) Boosting of weighting critical and erroneous samples. Neurocomputing 69(7–9):679–685CrossRef
  Güvenir HA, Emeksiz N (2000) An expert system for the differential diagnosis of erythemato-squamous diseases. Exp Syst Appl 18:43–49CrossRef
  Guvenir HA, Demiroz G, Ilter N (1998) Learning differential diagnosis of erythemato-squamous diseases using voting feature intervals. Artif Intell Med 13:147–165CrossRef
  Hastie T, Tibshirani R, Friedman J (2001) The elements of statistical learning, 2nd edn. Springer, BerlinCrossRef MATH
  Hyvärinen A (1999) Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans Neural Netw 10(3):626–634CrossRef
  Hyvärinen A, Oja E (2000) Independent component analysis: algorithms and applications. IEEE Trans Neural Netw 13:411–430CrossRef
  Jang JSR (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern 23(3):665–685CrossRef
  Jang JSR (1992) Self-learning fuzzy controllers based on temporal backpropagation. IEEE Trans Neural Netw 3(5):714–723CrossRef
  Nanni Loris (2006) An ensemble of classifiers for the diagnosis of erythemato-squamous diseases. Neurocomputing 69:842–845CrossRef
  Narendra PM, Fukunaga K (1977) A branch and bound algorithm for feature subset selection. IEEE Trans Comput 26(9):917–922. doi:10.​1109/​TC.​1977.​1674939 CrossRef MATH
  Parthiban L, Subramainan R (2009) An intelligent agent for detection of erythemato-squamous diseases using co-active neuro-fuzzy inference system and genetic algorithm. In: Proceeding of the international conference on intelligent agent and multi-agent systems, 01–06
  Ravichandran KS, Alsheyuhi SS (2011) FELM based intelligent optimal switching capacitor placement, FSKD, pp 366-371
  Ravichandran KS, Badrinath N, Gopinath G, Ravalli S, Sindhura J (2014) An efficient approach to an automatic detection of erythemato-squamous diseases. Neural Comput Appl 25(1):105–114CrossRef
  Saltelli A et al (2008) Global sensitivity analysis: the premier. Wiley, LondonMATH
  Schapire R, Singer Y (1999) Improved boosting algorithms using confidence-rated predictions. Mach Learn 37(3):297–336CrossRef MATH
  Übeyli ED, Güler I (2005) Automatic detection of erythemato-squamous diseases using adaptive neuro-fuzzy inference systems. Comput Biol Med Int J 35:421–433
  Ubeyli ED, Dogdu E (2010) Automatic detection of erythemato-squamous diseases using k-means clustering. J Med Syst 34:179–184CrossRef
  Ubeyli ED (2008) Multiclass support vector machines for diagnosis of erythemato-squamous diseases. Exp Syst Appl 35:1733–1740CrossRef
  Ubeyli ED (2009) Combined neural networks for diagnosis of erythemato-squamous diseases. Exp Syst Appl 36(5107–5112):2009
  Vapnik VN (1995) The nature of statistical learning theory. Springer, New YorkCrossRef MATH
  Vezhnevets A, Vezhnevets V (2005) Modest adaboost—teaching adaboost to generalize better. Graphicon 12(5):987–997
  Wang J, Gao L, Zhang H, Xu J (2011) Adaboost with SVM-based classifier for the classification of brain motor imagery tasks. Lecture Notes in Computer Science. 6766:629–634
  Xie J, Lei J, Xie W, Gao X, Shi Y, Liu X (2012) Novel hybrid feature selection algorithms for diagnosing erythemato-squamous diseases, health information science. Lecture Notes in Computer Science 7231:173–185
  
• 作者单位：N. Badrinath (1)
  G. Gopinath (1)
  K. S. Ravichandran (2)
  R. Girish Soundhar (3)
  
  1. Department of Computer Science and Engineering, Bharathidasan University, Khajamalai Campus, Tiruchirapalli, Tamil Nadu, 620014, India
  2. School of Computing, SASTRA University, Thanjavur, Tamil Nadu, 613401, India
  3. Sri Manakula Vinayagar Medical College and Hospital, Kalitheerthalkuppam, Madagadipet, Puducherry, 605107, India
  
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Science, general
  Complexity
  
• 出版者：Springer Netherlands
• ISSN：1573-7462

文摘

This paper focuses on efficient techniques based on AdaBoost and its hybrid (AdaBoost-SVM) classifiers for an automatic detection of the erythemato-squamous diseases (ESD). The classification of ESD requires an enormous amount of computational effort, as all the features of the diseases have more than 90 % commonality. Some of the approaches reported in literature are fuzzy logic, artificial neural networks, neuro-fuzzy models and support vector machine. Recently, AdaBoost and its hybrid algorithms are widely used to enhance the accuracy of the learning algorithms. In this paper, we propose AdaBoost and its hybrid algorithms for diagnosis of erythemato-squamous diseases for the first time. User-friendly-interface is designed to assist dermatologists to estimate the ESD with the help of 34 features includes patient’s histopathological and clinical data sets. Efficient interface design is based on the following steps: (1) feature selection for all the 34 parameters involved in the erythemato-squamous disease is done using association rule based Apriori algorithm, (2) association rules are used to find \(\upalpha \%\) of transactions (diseases) to meet \(\upbeta \%\) of the features of the diseases, (3) support value of all the subset of \(\upalpha \) transaction from \(\upalpha \%\) of transactions is found and the dominant subset is found using Apriori algorithm, and (4) AdaBoost and its hybrid classifiers are used to classify the diseases. In this paper, the real, modest, gentle and hybrid AdaBoost algorithms are implemented and tested with the dataset of 366 patients. The data preprocessing reduces the dimensionality of the dataset and improves the time complexity of the estimation of the diseases. Proposed methodologies are proved as a potential solution for diagnosing ESD with significant improvement in computational time and accuracy compared to other models discussed in the recent literature.