Advertisement

An Object-Oriented Neural Network Toolbox Based on Design Patterns

  • Christian NapoliEmail author
  • Emiliano Tramontana
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 538)

Abstract

Generally, the resolution of a problem by using soft-computing support requires several attempts for setting up a proper neural network. Such attempts consist of designing and training a neural network and can be a relevant effort for the developer. This paper proposes a toolbox that automates several steps for setting up a neural network, and provides high-level abstractions allowing a developer to choose classical network topologies and configure them as desired, as well as design a neural network from a scratch. A valuable aspect of our solution is given by the modularity of the whole design that builds on object-orientation and design patterns.

Keywords

Artificial intelligence Soft-computing Modularity Software design Software evolution 

References

  1. Booch, G., Maksimchuk, R.A.: Object-Oriented Analysis and Design with Applications. Addison-Wesley, Reading (2007)Google Scholar
  2. Bonanno, F., Capizzi, G., Napoli, C.,: Some remarks on the application of RNN and PRNN for the charge-discharge simulation of advanced Lithium-ions battery energy storage. In: International Symposium on Power Electronics, Electrical Drives, Automation and Motion (SPEEDAM), pp. 941–945 (20–22 June 2012). doi: 10.1109/SPEEDAM.2012.6264500
  3. Bonanno, F., Capizzi, G., Sciuto, G.L., Napoli, C., Pappalardo, G., Tramontana, E.: A novel cloud-distributed toolbox for optimal energy dispatch management from renewables in IGSs by using WRNN predictors and GPU parallel solutions. In: International Symposium on Power Electronics, Electrical Drives, Automation and Motion (SPEEDAM), pp. 1077–1084 (18–20 June 2014) (2014a). doi: 10.1109/SPEEDAM.2014.6872127
  4. Bonanno, F., Capizzi, G., Coco, S., Napoli, C., Laudani, A., Sciuto, G.L.: Optimal thicknesses determination in a multilayer structure to improve the SPP efficiency for photovoltaic devices by an hybrid FEM - Cascade Neural Network based approach. In: International Symposium on Power Electronics, Electrical Drives, Automation and Motion (SPEEDAM), pp. 355–362 (18–20 June 2014) (2014b). doi: 10.1109/SPEEDAM.2014.6872103
  5. Bonanno, F., Capizzi, G., Sciuto, G.L., Napoli, C., Pappalardo, G., Tramontana, E.: A cascade neural network architecture investigating surface plasmon polaritons propagation for thin metals in OpenMP. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2014, Part I. LNCS, vol. 8467, pp. 22–33. Springer, Heidelberg (2014c)CrossRefGoogle Scholar
  6. Borowik, G., Wozniak, M., Fornaia, A., Giunta, R., Napoli, C., Pappalardo, G., Tramontana, E.: A software architecture assisting workflow executions on cloud resources. Int. J. Electron. Telecommun. 61(1), 17–23 (2015). doi: 10.1515/eletel-2015-0002CrossRefGoogle Scholar
  7. Fowler, M., Beck, K., Brant, J., Opdyke, W., Roberts, D.: Refactoring: Improving the Design of Existing Code. Addison-Wesley, Reading (1999)Google Scholar
  8. Gabryel, M., Woźniak, M., Damaševičius, R.: An application of differential evolution to positioning queueing systems. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) Artificial Intelligence and Soft Computing. LNCS, vol. 9120, pp. 379–390. Springer, Heidelberg (2015)CrossRefGoogle Scholar
  9. Gamma, E., Helm, R., Johnson, R., Vlissiders, J.: Design Patterns: Elements of Reusable Object-Oriented Software. Addison-Wesley, Reading (1994)Google Scholar
  10. Gupta, M., Lian, J., Noriyas, H.: Static and Dynamic Neural Networks: from Fundamentals to Advanced Theory. Wiley, New York (2004)Google Scholar
  11. Haykin, S.: Neural Networks: a Comprehensive Foundation. Pearson, London (2004)zbMATHGoogle Scholar
  12. Haykin, S.: Neural Networks and Learning Machines. Pearson, London (2009)Google Scholar
  13. Hopfield, J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. 79(8), 2554–2558 (1982)MathSciNetCrossRefGoogle Scholar
  14. Musavi, M.T.: On the training of radial basis function classifiers. Neural Netw. 5(4), 595–603 (1992)CrossRefGoogle Scholar
  15. Napoli, C., Pappalardo, G., Tramontana, E.: Using modularity metrics to assist move method refactoring of large systems. In: IEEE International Conference on Complex, Intelligent, and Software Intensive Systems (CISIS), pp. 529–534 (July 2013) (2013a). doi: 10.1109/CISIS.2013.96
  16. Napoli, C., Pappalardo, G., Tramontana, E.: Improving files availability for bittorrent using a diffusion model. In: 23rd IEEE WETICE Conference (WETICE), pp. 191–196 (23–25 June 2014) (2014a). doi: 10.1109/WETICE.2014.65
  17. Napoli, C., Pappalardo, G., Tramontana, E., Marszalek, Z., Polap, D., Wozniak, M.: Simplified firefly algorithm for 2D image key-points search. In: IEEE Symposium on Computational Intelligence for Human-like Intelligence (CIHLI), pp. 1–8 (9–12 December 2014) (2014b). doi: 10.1109/CIHLI.2014.7013395
  18. Napoli, C., Pappalardo, G., Tramontana, E.:”An agent-driven semantical identifier using radial basis neural networks and reinforcement learning. In: XV Workshop Dagli Oggetti agli Agenti (WOA 2014), Catania, Italy (25–26 Sepember 2014) (2014c). doi: 10.13140/2.1.1446.7843
  19. Napoli, C., Pappalardo, G., Tramontana, E., Zappalà, G.: A cloud-distributed GPU architecture for pattern identification in segmented detectors big-data surveys. Comput. J. bxu147 (2014) (2014d). doi: 10.1093/comjnl/bxu147CrossRefGoogle Scholar
  20. Napoli, C., Pappalardo, G., Tramontana, E., Nowicki, R.K., Starczewski, J.T., Woźniak, M.: Toward work groups classification based on probabilistic neural network approach. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) Artificial Intelligence and Soft Computing. LNCS, vol. 9119, pp. 79–89. Springer, Heidelberg (2015)CrossRefGoogle Scholar
  21. Napoli, C., Pappalardo, G., Tramontana, E.: A hybrid neuro–wavelet predictor for QoS control and stability. In: Baldoni, M., Baroglio, C., Boella, G., Micalizio, R. (eds.) AI*IA 2013. LNCS, vol. 8249, pp. 527–538. Springer, Heidelberg (2013b)CrossRefGoogle Scholar
  22. Nowak, B.A., Nowicki, R.K., Woźniak, M., Napoli, C.: Multi-class nearest neighbour classifier for incomplete data handling. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.). LNCS, vol. 9119, pp. 469–480Springer, Heidelberg (2015)CrossRefGoogle Scholar
  23. Pappalardo, G, Tramontana, E.: Suggesting extract class refactoring opportunities by measuring strength of method interactions. In: IEEE Asia Pacific Software Engineering Conference (APSEC), pp. 105–110 (December 2013)Google Scholar
  24. Ševarac, Z.: An open source software framework for neural network development. Neuroph. 11(43), 40–44 (2012)Google Scholar
  25. Tramontana, E.: Automatically characterising components with concerns and reducing tangling. In: QUORS workshop at Compsac. IEEE, pp. 499–504 (2013)Google Scholar
  26. Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural Comput. 1(2), 270–280 (1989)CrossRefGoogle Scholar
  27. Woźniak, M., Połap, D., Gabryel, M., Nowicki, R.K., Napoli, C., Tramontana, E.: Can we process 2D images using artificial bee colony? In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) Artificial Intelligence and Soft Computing. LNCS, vol. 9119, pp. 660–671. Springer, Heidelberg (2015a)CrossRefGoogle Scholar
  28. Wozniak, M., Polap, D.: Basic concept of cuckoo search algorithm for 2D images processing with some research results: an idea to apply cuckoo search algorithm in 2D images key-points search. In: International Conference on Signal Processing and Multimedia Applications SIGMAP 2014, pp. 157–164, Setubal (2014). doi: 10.5220/0005015801570164

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Department of Mathematics and InformaticsUniversity of CataniaCataniaItaly

Personalised recommendations