Skip to main content
SpringerLink
Log in

Artificial neural networks to identify naturally existing disease severity status

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Classification is a central endeavour in Biology. Heterogeneity of biological systems makes classification more challenging, but this is crucial for effective disease control and management. This study is a computational modelling attempt to classify a plant disease using visual symptoms to ease crop management programmes. Weligama coconut leaf wilt disease (WCLWD), a phytoplasma-borne coconut disease characterised by three foliar symptoms (flaccidity (bending of leaflets), yellowing and marginal necrosis) found in Sri Lanka, was used to demonstrate its applicability. Self-organising map (SOM) was optimised to discover naturally existing categories of WCLWD using foliar symptoms. Ward clustering of SOM identified three distinct disease categories. Results agreed with the nature of disease progression and are supported by K-means clustering. Conversion of SOM clusters to a parsimonious multi-layer perceptron (MLP) supported by a novel efficient network pruning algorithm regenerated identical results proving that precise models can be developed for WCLWD classification using these approaches. The MLP (100 %) outperformed counter propagation (CP) neural network (91 %) in generalisation ability indicating the validity of the MLP model. The study identified flaccidity as the most influential symptom followed by yellowing and necrosis. Comparison of our results with expert decision on disease severity classification revealed 73.45 % correspondence. In-depth investigation into the results from the two approaches using statistical methods revealed that when multiple symptoms are blended, expert decisions rely more on the intensely visible symptom and mainly on a single dimension, whereas the SOM/MLP classifier more accurately captures the average, variation and multi-dimensionality in data indicating that the model is more realistic and capable than the naked eye in detecting the disease.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Jeger MJ (2004) Analysis of disease progress as a basis for evaluating disease management practices. Annu Rev Phytopathol 42:61–82

    Article  Google Scholar 

  2. Perera SCN, Herath HMNB, Wijesekara HTR, Subhathma WGR, Weerakkody WATL, Wijesooriya WATD (2011) Sri Lanka green dwarf coconuts are resistant to weligama coconut leaf wilt disease. Coconut technology update 2011. Coconut Research Institute, Sri Lanka

    Google Scholar 

  3. Silverberg MS, Satsangi J, Ahmad T, Arnott ID, Bernstein CN, Brant SR, Caprilli R, Colombel JF, Gasche C, Geboes K (2005) Toward an integrated clinical, molecular and serological classification of inflammatory bowel disease: report of a working party of the 2005 montreal world congress of gastroenterology. Can J Gastroenterol 19(Suppl A):5–36

    Google Scholar 

  4. Lee E, Chuang HY, Kim JW, Ideker T, Lee D (2008) Inferring pathway activity toward precise disease classification. PLoS comput biol 4(11):p.e1000217

    Article  Google Scholar 

  5. Contreras-Medina LM, Osornio-Rios RA, Torres-Pacheco I, RdJ Romero-Troncoso, Guevara-González RG, Millan-Almaraz JR (2012) Smart sensor for real-time quantification of common symptoms present in unhealthy plants. Sensors (Basel, Switzerland) 12:784–805

    Article  Google Scholar 

  6. Sankaran S, Mishra A, Ehsani R, Davis C (2010) A review of advanced techniques for detecting plant diseases. Comput Electron Agric 72:1–13

    Article  Google Scholar 

  7. Delalieux S, Auwerkerken A, Verstraeten WW, Somers B, Valcke R, Lhermitte S, Keulemans J, Coppin P (2009) Hyperspectral reflectance and fluorescence imaging to detect scab induced stress in apple leaves. Remote Sens 1:858–874

    Article  Google Scholar 

  8. Chaerle L, Hagenbeek D, De Bruyne E, Valcke R, Van Der Straeten D (2004) Thermal and chlorophyll-fluorescence imaging distinguish plant-pathogen interactions at an early stage. Plant Cell Physiol 45:887–896

    Article  Google Scholar 

  9. Sannakki SS, Rajpurohit VS, Nargund VB, Kumar A, Yallur PS (2011) Leaf disease grading by machine vision and fuzzy logic. Int J Comp Tech Appl 2(5):1709–1716

    Google Scholar 

  10. Zhang GP (2000) Neural networks for classification: a survey. IEEE Trans Syst Man Cybern Part C Appl Rev 30(4):451–462

    Article  Google Scholar 

  11. Samarasinghe S (2007) Neural networks for applied sciences and engineering: from fundamentals to complex pattern recognition. Auerbach Publications, Florida

    Google Scholar 

  12. Zhang G, Hu L, Jin W (2004) Resemblance coefficient and a quantum genetic algorithm for feature selection. In: Suzuki E, Arikawa S (eds) Discovery Science, vol 3245., Lecture notes in computer scienceSpringer, Berlin, pp 155–168

    Chapter  Google Scholar 

  13. Hsieh CH, Lu RH, Lee NH, Chiu WT, Hsu MH, Li YCJ (2011) Novel solutions for an old disease: diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks. Surgery 149:87–93

    Article  Google Scholar 

  14. Keyvanfard F, Shoorehdeli M, Teshnehlab M, Nie K, Su M-Y (2012) Specificity enhancement in classification of breast MRI lesion based on multi-classifier. Neural Comput Appl 22(1):35–45. doi:10.1007/s00521-012-0937-y

    Google Scholar 

  15. Jalali-Heravi M, Mani-Varnosfaderani A, Jahromi PE, Mahmoodi MM, Taherinia D (2011) Classification of anti-HIV compounds using counterpropagation artificial neural networks and decision trees. SAR QSAR Environ Res 22(7–8):639–660. doi:10.1080/1062936x.2011.623318

    Article  Google Scholar 

  16. Dhondalay GK, Lemetre C, Ball GR (2012) Modeling estrogen receptor pathways in breast cancer using an Artificial Neural Networks based inference approach. In: Proceedings of 2012 IEEE-EMBS international conference on biomedical and health informatics, pp 948–951

  17. Malone J, McGarry K, Wermter S, Bowerman C (2006) Data mining using rule extraction from Kohonen self-organising maps. Neural Comput Appl 15(1):9–17

    Article  Google Scholar 

  18. López-Benavides MG, Samarasinghe S, Hickford JGH (2003) The use of artificial neural networks to diagnose mastitis in dairy cattle. In: Proceedings of the international joint conference on neural networks, pp 582–555. doi:10.1109/IJCNN.2003.1223420

  19. Lan J, Hu MY, Patuwo E, Zhang GP (2010) An investigation of neural network classifiers with unequal misclassification costs and group sizes. Decis Support Syst 48(4):582–591

    Article  Google Scholar 

  20. Gil D, Johnsson M (2010) Supervised SOM based architecture versus multilayer perceptron and RBF networks. In: Proceedings of the Linköping Electronic Conference, pp 15–24

  21. Wijesekara HTR, Nainanayaka A, Waidyaratne KP, Subhathma WGR, Weerakkody T, Hettiarachchi D (2010) Epidemiological and pathological studies on weligama coconut leaf wilt disease. In: Proceedings of international conference on coconut biodiversity for prosperity

  22. Nainanayaka AD, Weerakkody WATL, Wijesekara HTR, Waidyaratne KP, Subhathma WGR (2010) Impact of Weligama coconut leaf wilt disease (WCLWD) on morphological, physiological and yield aspects of coconut palms. In: Proceedings of the third symposium on plantation crop research: stakeholder empowerment through technological advances, pp 258–275

  23. Manimekalai R, Nair S, Soumya VP, Roshna OM, Thomas GV (2011) Real-time PCR technique-based detection of coconut root (wilt) phytoplasma. Curr Sci 101(9):1209–1213

    MATH  Google Scholar 

  24. Rajan P (2011) Transmission of coconut root (wilt) disease through plant hopper, Proutista moesta Westwood (Homoptera: Derbidae). Pest Manag Hortic Ecosyst 17(1):1–5

    MathSciNet  Google Scholar 

  25. Perera L, Meegahakumbura MK, Wijesekara HRT, Fernando WBS, Dickinson MJ (2012) A phytoplasma is associated with the Weligama coconut leaf wilt disease in Sri Lanka. J Plant Pathol 94(1):205–209

    Google Scholar 

  26. Nejat N, Vadamalai G (2011) Phytoplasma detection in coconut palm and other tropical crops. Plant Pathol J 9:112–121

    Google Scholar 

  27. Hoat TX, Bon NG, Van Quan M, Hien VD, Thanh ND, Dickinson M (2012) Detection and molecular characterization of sugarcane grassy shoot phytoplasma in Vietnam. Phytoparasitica 40(4):351–359

    Article  Google Scholar 

  28. Yankey EN, Swarbrick P, Dickinson M, Tomlinson J, Boonham N, Nipah JO, Robert NQ (2011) Improving molecular diagnostics for the detection of lethal disease phytoplasma of coconut in Ghana. B Insectol 64:S47–S48

    Google Scholar 

  29. Patil JK, Kumar R (2011) Advances in image processing for detection of plant diseases. J Adv Bioinform Appl Res 2(2):135–141

    Google Scholar 

  30. Revathi P, Revathi R, Hemalatha M (2011) Knowledge discovery in diagnose of crop diseases using machine learning techniques. Int J Eng Sci 3(9):7187–7190

    Google Scholar 

  31. Rumpf T, Mahlein AK, Steiner U, Oerke EC, Dehne HW, Plümer L (2010) Early detection and classification of plant diseases with support vector machines based on hyperspectral reflectance. Comput Electron Agric 74:91–99

    Article  Google Scholar 

  32. Tello M-L, Redondo C, Gaforio L, Pastor S, Mateo-Sagasta E (2005) Development of a disease severity rating scale for plane tree anthracnose. Urban For Urban Green 3(2):93–101. doi:10.1016/j.ufug.2004.09.003

    Article  Google Scholar 

  33. George MV, Radha K (1973) Computation of disease index of root (wilt) disease of coconut. Indian J Agr Sci 43:366–370

    Google Scholar 

  34. Nambiar PTN, Pillai NG (1985) A simplified method of indexing root (wilt) affected coconut palms. J Plant Crops 13(1):35–37

    Google Scholar 

  35. Minitab 16 Statistical Software (2010) State College, PA: Minitab, Inc. (www.minitab.com)

  36. MATLAB version R2011a (2011) Natick, Massachusetts. The MathWorks Inc (www.mathworks.com)

  37. Potočnik P, Berlec T, Starbek M, Govekar E (2012) Self-organizing neural network-based clustering and organization of production cells. Neural Comput Appl 22(Suppl 1):S113–S124

    Google Scholar 

  38. Dreiseitl S, Ohno-Machado L (2002) Logistic regression and artificial neural network classification models: a methodology review. J Biomed Inform 35(5–6):352–359

    Article  Google Scholar 

  39. Samarasinghe S (2007) Optimum Structures of Feed Forward Neural Networks by SOM Clustering of Neuron Activations. In: Oxley L, Kulasiri D (eds) MODSIM 2007 international congress on modelling and simulation, pp 2278–2284

  40. Al-yousef A, Samarasinghe S (2011) Ultrasound based computer aided diagnosis of breast cancer: evaluation of a new feature of mass central regularity Degree. In: Chan F, Marinova D, Anderssen R (eds) MODSIM2011, 19th international congress on modelling and simulation, pp 1063–1069

  41. Norman D (1983) Some observations on mental models. In: Gentner D, Stevens AL (eds) Mental models. Lawrence Erlbaum Associates Inc, New Jersey, pp 7–14

    Google Scholar 

  42. Lupaşcu C, Tegolo D (2011) Automatic unsupervised segmentation of retinal vessels using self-organizing maps and k-means clustering. In: Proceedings of 7th international conference on computational intelligence methods for bioinformatics and biostatistics, pp 263–274

  43. Sun Z (2008) Application of artificial neural networks in early detection of Mastitis from improved data collected on-line by robotic milking stations. Dissertation, Lincoln University, New Zealand

  44. Ballabio D, Consonni V, Todeschini R (2009) The Kohonen and CP-ANN toolbox: a collection of MATLAB modules for self organizing maps and counterpropagation artificial neural networks. Chemom Intell Lab Syst 98:115–122

    Article  Google Scholar 

  45. Ballabio D, Vasighi M (2012) A MATLAB toolbox for self organizing maps and supervised neural network learning strategies. Chemom Intell Lab Syst 118:24–32. doi:10.1016/j.chemolab.2012.07.005

    Article  Google Scholar 

  46. Milne L (1995) Feature selection using neural networks with contribution measures. In: Proceedings of eighth Australian joint conference on artificial intelligence AI’95, World Scientific Publishing, pp 571–571

  47. Alavi AH, Gandomi AH (2011) Prediction of principal ground-motion parameters using a hybrid method coupling artificial neural networks and simulated annealing. Comput Struct 89:2176–2194

    Article  Google Scholar 

  48. Wong TC, Law KMY, Yau HK, Ngan SC (2011) Analyzing supply chain operation models with the PC-algorithm and the neural network. Expert Syst Appl 38:7526–7534

    Article  Google Scholar 

  49. Al-Bulushi N, King P, Blunt M, Kraaijveld M (2012) Artificial neural networks workflow and its application in the petroleum industry. Neural Comput Appl 21:409–421

    Article  Google Scholar 

  50. Al Hiary H, Bani Ahmad S, Reyalat M, Braik M, Alrahamneh Z (2011) Fast and accurate detection and classification of plant diseases. Int J Comput Appl 17(1):31–38

    Google Scholar 

Download references

Acknowledgments

Authors are grateful to the Research, Technical and Field staff at Coconut Research Institute (CRI) of Sri Lanka, who contributed expert knowledge, implementation field study and data collection in this research. We acknowledge the CRI approval to use this data in our study.

Author information

Authors and Affiliations

  1. Integrated Systems Modelling Group, Lincoln University, Christchurch, New Zealand

    K. P. Waidyarathne & S. Samarasinghe

Authors
  1. K. P. Waidyarathne
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. S. Samarasinghe
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to S. Samarasinghe.

Electronic supplementary material

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Waidyarathne, K.P., Samarasinghe, S. Artificial neural networks to identify naturally existing disease severity status. Neural Comput & Applic 25, 1031–1041 (2014). https://doi.org/10.1007/s00521-014-1572-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-014-1572-6

Keywords

Search

Navigation