Artificial immune systems for artificial olfaction data analysis: Comparison between AIRS and ANN models

S. De Vito, E. Martinelli, R. Di Fuccio, F. Tortorella, G. Di Francia, A. D'Amico, C. Di Natale

Research output: Contribution to conferencePaper

3 Citations (Scopus)

Abstract

Artificial Olfaction (AO) data analysts have gained long term experience on nervous system based machine learning metaphors such as Artificial Neural Networks. In this work we propose and evaluate the use of a novel tool based on an emerging, however, powerful metaphor: the Artificial Immune Systems (AIS). AIS models were developed in the '90s; ever since they have reached significant maturity, and were to show good performance in both explorative data analysis and classification tasks. After selecting different artificial olfaction databases, we compare the utility of classic Back-Propagation Neural Network (BPNN) models with Artificial Immune Recognition Systems (AIRS) algorithms for classification problems, discussing its architectural strengths and weaknesses. Although BPNN retained a slight performance advantage on the investigated datasets, we were able to show that the AIS metaphor can express interesting characteristics for artificial olfaction data analysis. As an example, in a preliminary setup, the AIRS classifier showed superior performance when the sensor signals are affected by drift. © 2010 IEEE.

Conference

Conference2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010
CountrySpain
Period1/1/10 → …

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

De Vito, S., Martinelli, E., Di Fuccio, R., Tortorella, F., Di Francia, G., D'Amico, A., & Di Natale, C. (2010). Artificial immune systems for artificial olfaction data analysis: Comparison between AIRS and ANN models. Paper presented at 2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010, Spain. https://doi.org/10.1109/IJCNN.2010.5596599