Iris Classification using ANN on 8-bit Microcontroller
Keywords:
Artificial Neural Network (ANN), Competitive Majority Network Trained by error correction (C-Mantec), Constructive Neural Network, 8-bit Microcontroller.Abstract
Conventional approach to develop embedded applications are commonly being used today. However recent study has revealed that techniques involving Artificial Neural Network can be used as an alternative to develop embedded applications. A lot of applications have benefited using them, most common example is Google search engine, Stock market prediction etc. ANNs are a kind of machine learning models, inspired on the functioning of the brain can be incorporated in low cost microcontrollers. ANN could be implemented in number of applications related to embedded system, process control wireless sensor networks. Few common applications are dynamic reprogramming of sensor nodes, intelligent sensors, auto calibration of process instruments, weather prediction, free-fall detection etc. In this project work, we have selected C-Mantec which is a constructive neural network algorithm as it generates compact architecture suitable for microcontroller implementation. For the implementation, on embedded side we have selected 8 bit microcontroller and to compare on faster processors python programming language is used.
References
[1] FranciscoOrtega-Zamoranoa,*,JoséM.Jereza, JoséL.Subirats a, IgnacioMolinab, LeonardoFranco a, ,”Smart sensor/actuator node reprogramming in changing environments using a neural network model”Journal on Engineering Applications of Artificial Intelligence Elsevier ,Volume 30 April 2014, Pages 179–188
[2] Sanket Nartam and Prof. Mr Anant More, “Neural Network based alternate approach for embedded applications”, e-PG Project Exhibition 2016 for M.E. E&Tc Students under Savitribai Phule University of Pune, June2016.
[3] José L. Subirats, Leonardo Franco ∗, José M. Jerez,” C-Mantec: A novel constructive neural network algorithm incorporating competition between neurons” Journal on Neural Networks, Elsevier 26 (2012) 130–140.
[4] Francisco Ortega-Zamorano, José M. Jerez, and Leonardo Franco, Senior Member, IEEE. FPGA Implementation of the C-Mantec Neural Network Constructive Algorithm”. IEEE Transactions on Industrial Informatics, vol. 10, no. 2, May 2014.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Under this license, authors retain ownership of the copyright for their articles. By submitting to the International Journal of Advanced Research in Science, Management, and Technology (IJARSMT), authors grant the journal the right of first publication. Users are free to share, copy, and redistribute the material in any medium or format, and to adapt, remix, transform, and build upon the material for any purpose, including commercially, provided that appropriate credit is given to the original author(s) and the journal, a link to the license is provided, and any changes made are indicated.
