A Multisensor Fusion System for the Detection of Plant Viruses by Combining Artificial Neural Networks

  • Dimitrios Frossyniotis
  • Yannis Anthopoulos
  • Spiros Kintzios
  • Antonis Perdikaris
  • Constantine P. Yialouris
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4132)


Several researchers have shown that substantial improvements can be achieved in difficult pattern recognition problems by combining the outputs of multiple neural networks. In this work, we present and test a multi-net system for the detection of plant viruses, using biosensors. The system is based on the Bioelectric Recognition Assay (BERA) method for the detection of viruses, developed by our team. BERA sensors detect the electric response of culture cells suspended in a gel matrix, as a result to their interaction with virus’s cells, rendering thus feasible his identification. Currently this is achieved empirically by examining the biosensor’s response data curve. In this paper, we use a combination of specialized Artificial Neural Networks that are trained to recognize plant viruses according to biosensors’ responses. Experiments indicate that the multi-net classification system exhibits promising performance compared with the case of single network training, both in terms of error rates and in terms of training speed (especially if the training of the classifiers is done in parallel).


Artificial Neural Network Plant Virus Smoothing Technique Multiple Classifier System Neural Classifier 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Alpaydin, E.: Techniques for combining multiple learners. In: Proceedings of Engineering of Intelligent Systems, vol. 2, pp. 6–12. ICSC Press (1998)Google Scholar
  2. 2.
    Kuncheva, L.: Combining Classifiers by Clustering, Selection and Decision Templates. Technical report, University of Wales, UK (2000)Google Scholar
  3. 3.
    Maclin, R., Opitz, D.: An empirical evaluation of bagging and boosting. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence, pp. 546–551. AAAI Press/MIT Press (1997)Google Scholar
  4. 4.
    Freund, Y., Schapire, R.E.: Experiments with a new boosting algorithm. In: Proceedings of the Thirteenth International Conference on Machine Learning, pp. 148–156. Morgan Kaufmann, San Francisco (1996)Google Scholar
  5. 5.
    Kuncheva, L.: Clustering-and-selection model for classifier combination. In: Proceedings of the 4th International Conference on Knowledge-based Intelligent Engineering Systems (KES 2000), Brighton, UK (2000)Google Scholar
  6. 6.
    Vericas, A., Lipnickas, A., Malmqvist, K., Bacauskiene, M., Gelzinis, A.: Soft combination of neural classifiers: A comparative study. Pattern Recognition Letters 20, 429–444 (1999)CrossRefGoogle Scholar
  7. 7.
    Tumer, K., Ghosh, J.: Classifier combining through trimmed means and order statistics. In: Proceedings of the International Joint Conference on Neural Networks, Anchorage, Alaska (1998)Google Scholar
  8. 8.
    Tumer, K., Ghosh, J.: Order statistics combiners for neural classifiers. In: Proceedings of the World Congress on Neural Networks, pp. I31–I34. INNS Press, Washington D.C (1995)Google Scholar
  9. 9.
    Sharkey, A.J.C.: Combining Artificial Neural Nets: Ensemble and Modular Multi-Net Systems. Springer, Heidelberg (1999)MATHGoogle Scholar
  10. 10.
    Tumer, K., Ghosh, J.: Limits to performance gains in combined neural classifiers. In: Proceedings of the Artificial Neural Networks in Engineering 1995, pp. 419–424. St. Louis (1995)Google Scholar
  11. 11.
    Tumer, K., Ghosh, J.: Error correlation and error reduction in ensemble classifiers. Connection Science, Special Issue on Combining Artificial Neural Networks: Ensemble Approaches 8(3-5), 385–404 (1996)Google Scholar
  12. 12.
    Alpaydin, E.: Voting over multiple condensed nearest neighbour subsets. Artificial Intelligence Review 11, 115–132 (1997)CrossRefGoogle Scholar
  13. 13.
    Breiman, L.: Bagging predictors. Technical report, no. 421, Department of Statistics. University of California, Berkeley (1994)Google Scholar
  14. 14.
    Chan, P.K., Stolfo, S.J.: A comparative evaluation of voting and meta-learning on partitioned data. In: Proceedings of the Twelfth International Machine Learning Conference, pp. 90–98. Morgan Kaufmann, San Mateo (1995)Google Scholar
  15. 15.
    Kintzios, S., Pistola, E., Panagiotopoulos, P., Bomsel, M., Alexandropoulos, N., Bem, F., Biselis, I., Levin, R.: Bioelectric recognition assay (BERA). Biosensors and Bioelectronics 16, 325–336 (2001)CrossRefGoogle Scholar
  16. 16.
    Kintzios, S., Pistola, E., Konstas, J., Bem, F., Matakiadis, T., Alexandropoulos, N., Biselis, I., Levin, R.: Application of the Bioelectric recognition assay (BERA) for the detection of human and plant viruses: definition of operational parameters. Biosensors and Bioelectronics 16, 467–480 (2001)CrossRefGoogle Scholar
  17. 17.
    Kintzios, S., Bem, F., Mangana, O., Nomikou, K., Markoulatos, P., Alexandropoulos, N., Fasseas, C., Arakelyan, V., Petrou, A.-L., Soukouli, K., Moschopoulou, G., Yialouris, C., Simonian, A.: Study on the mechanism of Bioelectric Recognition Assay: evidence for immobilized cell membrane interactions with viral fragments. Biosensors & Bioelectronics 20, 907–916 (2004)CrossRefGoogle Scholar
  18. 18.
    Kintzios, S., Makrygianni, E.f., Pistola, E., Panagiotopoulos, P., Economou, G.: Effect of amino acids and amino acid analogues on the in vitro expreesion of glyphosate tolerance in johnsongrass (Sorghum halepense L. pers.). J. Food, Agriculture and Environment 3, 180–184 (2003)Google Scholar
  19. 19.
    Kintzios, S., Goldstein, J., Perdikaris, A., Moschopoulou, G., Marinopoulou, I., Mangana, O., Nomikou, K., Papanastasiou, I., Petrou, A.-L., Arakelyan, V., Economou, A., Simonian, A.: The BERA Diagnostic System: An all-purpose cell biosensor for the 21th Century. In: 5th Biodetection Conference, Baltimore, MD, USA, June 9-10 (2005)Google Scholar
  20. 20.
    Moschopoulou, G., Kintzios, S.: Membrane engineered Bioelectric Recognition Cell sensors for the detection of subnanomolar concentrations of superoxide: A novel biosensor principle. In: International Conference on Instrumental Methods of Analysis (IMA) 2005, Crete, Greece, October 1-5 (2005)Google Scholar
  21. 21.
    Kintzios, S., Marinopoulou, I., Moschopoulou, G., Mangana, O., Nomikou, K., Endo, K., Papanastasiou, I., Simonian, A.: Construction of a novel, multi-analyte biosensor system for assaying cell division. Biosensors and Bioelectronics (in press)Google Scholar
  22. 22.
    Tzafestas, G.S., Anthopoulos, Y.: Neural Networks Based Sensorial Signal Fusion: An Application to Material Identification. In: DSP 1997, Santorini, Greece, July 2-4 (1997)Google Scholar
  23. 23.
    Dennis, J.E., Schnabel, R.B.: Numerical methods for unconstrained optimization and nonlinear equations. Prentice-Hall, Englewood Cliffs (1983)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Dimitrios Frossyniotis
    • 1
  • Yannis Anthopoulos
    • 1
  • Spiros Kintzios
    • 2
  • Antonis Perdikaris
    • 2
  • Constantine P. Yialouris
    • 1
  1. 1.Department of ScienceAgricultural University Of Athens, Informatics LaboratoryAthensGreece
  2. 2.Laboratory of Plant Physiology and Morphology, Department of Agricultural BiotechnologyAgricultural University Of AthensAthensGreece

Personalised recommendations