Discriminative histogram taxonomy features for snake species identification

详细信息    查看全文

• 作者：Alex Pappachen James (1) (2)
  Bincy Mathews (2)
  Sherin Sugathan (2)
  Dileep Kumar Raveendran (3)
  
• 关键词：Snake classification ; Snake database ; Taxonomy ; Classifiers ; Feature analysis
• 刊名：Human-centric Computing and Information Sciences
• 出版年：2014
• 出版时间：December 2014
• 年：2014
• 卷：4
• 期：1
• 全文大小：867 KB
• 参考文献：1. Smith MA (1981) Reptilia and Amphibia, vol 3, Serpentes. Today & Tomorrow’s Printers & Publishers, India
  2. Whitaker R, Captain A, Ahmed F (2004) Snakes of India: the field guide. Draco Books, Chengalpattu
  3. Mattison C (1999) Snake. Dorling Kindersley, New York,USA
  4. Firth SMJWJR (2002) Snake. Scholastic, India
  5. Weidensaul S (1996) Snakes of the World. Grange Books Ltd, Chartwell House, London
  6. Mertens T (1995) Deadly & Dangerous Snakes. Magic Bean. Era Publications, Flinders Park, South Australia
  7. Backshall S (2007) Venomous Animals of the World. Johns Hopkins University Press, Maryland, USA
  8. Stevens D (2011) The Big Four Snakes: The Indian Cobra, the Common Krait, the Russell’s Viper, and the Saw-Scaled Viper. Webster’s Digital Services, USA
  9. Premawardhena A, De Silva C, Fonseka M, Gunatilake S, De Silva H (1999) Low dose subcutaneous adrenaline to prevent acute adverse reactions to antivenom serum in people bitten by snakes: randomised, placebo controlled trial. BMJ: Brit Med J 318(7190):1041 CrossRef
  10. Warrell DA (1999) The clinical management of snake bites in the Southeast Asian region. Southeast Asian J Trop Med Public Health 1(Suppl 1):1-9
  11. Calvete JJ, Ju’arez P, Sanz L (2007) Snake venomics. Strategy and applications. J Mass Spectrom 42(11):1405-414 CrossRef
  12. Sorower MS, Yeasin M (2007) Robust Classification of Dialog Acts from the Transcription of Utterances. In ICSC 2007. IEEE International Conference on Semantic Computing, 3-10
  13. Chanda P, Cho YR, Zhang A, Ramanathan M (2009) Mining of attribute interactions using information theoretic metrics. In: Data mining workshops, ICDMW-9. IEEE International Conference on Data Mining, Florida, USA, pp 350-55
  14. Devi MI, Rajaram R, Selvakuberan K (2008) Generating best features for web page classification. Webology 5., http://www.webology.org/2008/v5n1/a52.html
  15. Marquez-Vera C, Romero C (2011) Ventura S: Predicting school failure using data mining. In Proceedings of the 4th International Conference on Educational Data Mining 271-76
  16. John GH, Kohavi R, Pfleger K (1994) Irrelevant features and the subset selection problem. In Proceedings of the eleventh international conference on machine learning, Volume 129, San Francisco 121-29
  17. Jensen R, Shen Q (2007) Fuzzy-rough sets assisted attribute selection. Fuzzy Systems, IEEE Transactions on 15:73-9 CrossRef
  18. Meng YX (2011) The practice on using machine learning for network anomaly intrusion detection. In IEEE International Conference on Machine Learning and Cybernetics (ICMLC), 2011, Vol. 2, 576-581
  19. Indra Devi M, Rajaram R, Selvakuberan K (2007) Automatic web page classification by combining feature selection techniques and lazy learners. In conference on computational intelligence and multimedia applications, 2007. Int Conference on 2:33-7
  20. Koonsanit K, Jaruskulchai C (2011) Band selection for hyperspectral image using principal components anal-ysis and maxima-minima functional. In: Knowledge, Information, and Creativity Support Systems. Thailand, Springer, pp 103-12 CrossRef
  21. Frank E, Hall M, Holmes G, Kirkby R, Pfahringer B, Witten IH, Trigg L (2005) Weka. In: Data Mining and Knowledge Discovery Handbook. Springer, USA, pp 1305-314 CrossRef
  22. Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH (2009) The WEKA data mining software: an update. ACM SIGKDD Explorations Newsletter 11:10-8 CrossRef
  23. James AP, Dimitrijev S (2012) Ranked selection of nearest discriminating features. Hum-centric Comput Inform Sci 2:12 CrossRef
  24. Milacic M, James AP, Dimitrijev S (2013) Biologically inspired features used for robust phoneme recognition. International Journal of Machine Intelligence and Sensory Signal Processing 1(1):46-4 CrossRef
  25. James AP, Maan AK (2011) Improving feature selection algorithms using normalised feature histograms. Electron Lett 47(8):490-91 CrossRef
  26. Longstaff ID, Cross JF (1987) A pattern recognition approach to understanding the multi-layer perception. Pattern Recogn Lett 5(5):315-19 CrossRef
  27. Kim SB, Han KS, Rim HC, Myaeng SH (2006) Some effective techniques for naive bayes text classification. Knowledge and Data Engineering, IEEE Transactions on 18(11):1457-466 CrossRef
  28. Freund Y, Schapire RE (1995) A desicion-theoretic generalization of on-line learning and an application to boosting. In Computational learning theory, Springer 23-7
  29. Benbouzid D, Busa-Fekete R, Casagrande N, Collin FD, Kégl B (2012) MultiBoost: a multi-purpose boosting package. J Mach Learn Res 13:549-53
  30. Buhmann MD (2003) Radial basis functions: theory and implementations, Volume 12. Cambridge university press CrossRef
  31. Aha DW, Kibler D, Albert MK (1991) Instance-based learning algorithms. Machine learning, Boston,USA, pp 37-6, 6
  32. Atkeson CG, Moore AW, Schaal S (1997) Locally weighted learning for control. Artif Intell Rev 11(1-):75-13 CrossRef
  33. Kohavi R (2001) Bayes rule based and decision tree hybrid classifier. [US Patent 6,182,058]
  34. Kotsiantis SB, Zaharakis ID, Pintelas PE (2006) Machine learning: a review of classification and combining techniques. Artif Intell Rev 26(3):159-90 CrossRef
  35. Ho TK (1998) The random subspace method for constructing decision forests. Pattern Anal Mach Intel, IEEE Transactions on 20(8):832-44
  36. Breiman L (1996) Bagging predictors. Mach Learn 24(2):123-40
  37. Singhal A, Brown C (1997) Dynamic Bayes net approach to multimodal sensor fusion. In Proceedings of the SPIE-The International Society for Optical Engineering, Volume 3209, 2-0
  
• 作者单位：Alex Pappachen James (1) (2)
  Bincy Mathews (2)
  Sherin Sugathan (2)
  Dileep Kumar Raveendran (3)
  
  1. School of Engineering, Nazarbayev University, Astana, Kazakhstan
  2. Enview R&D Labs, Thiruvananthapuram, India
  3. Department of Computational Biology and Bioinformatics, University of Kerala, Trivandrum, India
  
• ISSN：2192-1962

文摘

Background Incorrect snake identification from the observable visual traits is a major reason for death resulting from snake bites in tropics. So far no automatic classification method has been proposed to distinguish snakes by deciphering the taxonomy features of snake for the two major species of snakes i.e. Elapidae and Viperidae. We identify 38 different taxonomically relevant features to develop the Snake database from 490 sample images of Naja Naja (Spectacled cobra), 193 sample images of Ophiophagus Hannah (King cobra), 88 images of Bungarus caeruleus (Common krait), 304 sample images of Daboia russelii (Russell’s viper), 116 images of Echis carinatus (Saw scaled viper) and 108 images of Hypnale hypnale (Hump Nosed Pit Viper). Results Snake identification performances with 13 different types of classifiers and 12 attribute elevator demonstrate that 15 out of 38 taxonomically relevant features are enough for snake identification. Interestingly, these features were almost equally distributed from the logical grouping of top, side and body views of snake images, and the features from the bottom view of snakes had the least role in the snake identification. Conclusion We find that only few of the taxonomically relevant snake features are useful in the process of snake identification. These discriminant features are essential to improve the accuracy of snake identification and classification. The presented study indicate that automated snake identification is useful for practical applications such as in medical diagnosis, conservation studies and surveys by interdisciplinary practitioners with little expertise in snake taxonomy.