Performance evolution of a newly developed general-use hybrid AIS-ANN system: AaA-response

In this study, we have developed a nonlinear recognition system in the artificial immune systems (AIS) field named `AaA-response (artificial neural network (ANN)-aided AIS-response)', which is different from previous AIS methods in that it uses a different modeling strategy in the formation of the memory response. Because it also uses ANNs in the determination of the correct output, it can be seen as a hybrid system that involves AIS and ANN approaches. Unlike the other AIS methods, AaA-response uses multiple system units (or antibodies) to form an output for a presented input. This property gives the proposed system the ability of producing the desired output values, other than just being a classification algorithm. That is, AaA-response can also be used as a regression method, like ANNs, by producing any output value for the given inputs. The parameter analyses of the system were conducted on an artificially generated dataset, the Chainlink dataset, and the important points in the parameter selection were emphasized. To investigate the performance of the system for real-world problems, the Iris dataset and Statlog Heart Disease dataset, taken from the University of California - Irvine machine learning repository, were used. The system, which obtained 99.33% classification accuracy on the Iris dataset, has shown an important performance superiority with regard to the classification accuracy to other methods in the literature by reaching 90.37% classification accuracy for the Statlog Heart Disease dataset.

Performance evolution of a newly developed general-use hybrid AIS-ANN system: AaA-response

In this study, we have developed a nonlinear recognition system in the artificial immune systems (AIS) field named `AaA-response (artificial neural network (ANN)-aided AIS-response)', which is different from previous AIS methods in that it uses a different modeling strategy in the formation of the memory response. Because it also uses ANNs in the determination of the correct output, it can be seen as a hybrid system that involves AIS and ANN approaches. Unlike the other AIS methods, AaA-response uses multiple system units (or antibodies) to form an output for a presented input. This property gives the proposed system the ability of producing the desired output values, other than just being a classification algorithm. That is, AaA-response can also be used as a regression method, like ANNs, by producing any output value for the given inputs. The parameter analyses of the system were conducted on an artificially generated dataset, the Chainlink dataset, and the important points in the parameter selection were emphasized. To investigate the performance of the system for real-world problems, the Iris dataset and Statlog Heart Disease dataset, taken from the University of California - Irvine machine learning repository, were used. The system, which obtained 99.33% classification accuracy on the Iris dataset, has shown an important performance superiority with regard to the classification accuracy to other methods in the literature by reaching 90.37% classification accuracy for the Statlog Heart Disease dataset.

___

  • L.N. de Castro, F.J. Von Zuben, “An evolutionary immune network for data clustering”, Proceedings of the IEEE Brazilian Symposium on Artificial Neural Networks, pp. 84–89, 2000.
  • J. Timmis, M. Neal, “A resource limited artificial immune system”, Knowledge Based Systems, Vol. 14, pp. 121–130, 200 J.D. Farmer, N.H. Packard, A.S. Perelson, “The immune system, adaptation, and machine learning”, Physica, Vol. 22, pp. 187–204, 1986.
  • J.E. Hunt, D.E. Cooke, “An adaptive and distributed learning system based on the immune system”, Proceedings of the IEEE International Conference on Systems Man and Cybernetics, pp. 2494–2499, 1995.
  • A. Watkins, AIRS: A Resource Limited Artificial Immune Classifier, MSc, Mississippi State University, Mississippi, USA, 2002.
  • S.M. Garrett, “A paratope is not an epitope: implications for immune network models and clonal selection”, Lecture Notes in Computer Science, Vol. 2787, pp. 217–228, 2003.
  • S. Sahan, H. Kodaz, S. G¨ une¸s, K. Polat, “A new classifier based on attribute weighted artificial immune system (AWAIS)”, Lecture Notes in Computer Science, Vol. 3280, pp. 11–20, 2004.
  • V. Cutello, G. Narzisi, G. Nicosia, M. Pavone, “Clonal selection algorithms: a comparative case study using effective mutation potentials”, Lecture Notes in Computer Science, Vol. 3627, pp. 13–28, 2005.
  • S. ¨ Oz¸sen, S. Kara, F. Latifo˘ glu, S. G¨ une¸s, “A new supervised classification algorithm in artificial immune systems with its application to carotid artery Doppler signals to diagnose atherosclerosis”, Computer Methods and Programs in Biomedicine, Vol. 88, pp. 246–255, 2007.
  • I. Aydin, M. Karakose, E. Engin, “Artificial immune classifier with swarm learning”, Engineering Applications of Artificial Intelligence, Vol. 23, pp. 1291–1302, 2010.
  • A.J. Graaff, A.P. Engelbrecht, “Clustering data in an uncertain environment using an artificial immune system”, Pattern Recognition Letters, Vol. 32, pp. 342–351, 2011.
  • G.C. Luh, C.Y. Lin, “PCA based immune networks for human face recognition”, Applied Soft Computing, Vol. 11, pp. 1743–1752, 2011.
  • X. Ji, Y. Liu, X. Yu, J. Wu, “Alternative combination of quantum immune algorithm and backpropagation neural network”, Proceedings of the 7th International Conference on Natural Computation, pp. 66–70, 2011.
  • University of California - Irvine, UCI Machine Learning Repository, available at http://archive.ics.uci.edu/ml/ (last accessed 22 May 2012).
  • A.K. Abbas, A.H. Lichtman, Cellular and Molecular Immunology, 4th ed., Philadelphia, Saunders Publishing, 1994. L.N. de Castro, J. Timmis, Artificial Immune Systems: A New Computational Intelligence Approach, Heidelberg, Springer-Verlag, 2002.
  • A.S. Perelson, G.F. Oster, “Theoretical studies of clonal selection: minimal antibody repertoire size and reliability of self–non-self discrimination”, Journal of Theoretical Biology, Vol. 81, pp. 645–670, 1979.
  • E. Micheli-Tzanakou, Supervised and Unsupervised Pattern Recognition, Boca Raton, Florida, USA, CRC Press, 19
Turkish Journal of Electrical Engineering and Computer Science-Cover
  • ISSN: 1300-0632
  • Yayın Aralığı: Yılda 6 Sayı
  • Yayıncı: TÜBİTAK
Sayıdaki Diğer Makaleler

Direct adaptive fuzzy sliding mode decoupling control for a class of underactuated mechanical systems

Fares NAFA, Salim LABIOD, Hachemi CHEKIREB

Bidding strategy of generation companies in a competitive electricity market using the shuffled frog leaping algorithm

Vijaya Kumar JONNALAGADDA, Vinod Kumar DULLA MALLESHAM

Four-dimensional model for describing the status of peers in peer-to-peer distributed systems

Seyedeh Leili MIRTAHERI, Ehsan Mousavi KHANEGHAH, Mohsen SHARIFI, Behrouz MINAEI-BIDGOLI, Bijan RAAHEMI, Mohammad Norouzi ARAB, Abbas Saleh ARDESTANI

Classification of power quality disturbances using S-transform and TT-transform based on the artificial neural network

Sajad JASHFAR, Saeid ESMAEILI, Mehdi ZAREIAN-JAHROMI

A new extension of activity networks for modeling and verification of timed systems

Hassan MOTALLEBI, Mohammad Abdollahi AZGOMI, Mohammad Saber MIRZAEI

Robust sensorless predictive control of induction motors with sliding mode voltage model observer

Seyed Alireza DAVARI, Davood Arab KHABURI, Fengxiang WANG, Ralph KENNEL

Encoderless position estimation and error correction techniques for miniature mobile robots

Farshad ARVIN, Masoud BEKRAVI

Opposition-based discrete action reinforcement learning automata algorithm case study: optimal design of a PID controller

Fatemeh MOHSENI POUR, Ali Akbar GHARAVEISI

Economic power dispatch of power systems with pollution control using artificial bee colony optimization

Linda SLIMANI, Tarek BOUKTIR

CADA: channel and delay aware scheduler for real-time applications in WiMAX networks

Melek OKTAY, Hacı Ali MANTAR