International Journal of Modern Science and Technology


ISSN 2456-0235

International Journal of Modern Science and Technology,1(7), 2016, Pages 230-235. 

An Artificial Neural Network based Cryptosystem

R. Preethi, A. R. Rishivarman
Department of Mathematics, Theivanai Ammal College for women (Autonomous), Villupuram 605 401. Tamilnadu, India.

The cost of production in Kenya has been high when compared to other regional producers and world market prices, which for political and economic reasons are lower than the production costs in most factories in Kenya. For these reasons, production cost drivers analysis for sugar processing in Kenya is in inevitable so that good production mix can be put in place by the various companies. The objective was to analyse cost variables using optimization models with goal programming. Use of questionnaire, observation and interview schedules were used to collect data. The findings from goal programming application on cost analysis on resource allocation reveals that, with current level of operation strategies it is still a challenge for the Kenyan sugar manufacturer to produce sugar at 300 USD or less. The result gives an under achievement of 86 USD. Meaning with the current state of our factories and built in strategies, the operating resources projected at optimal level (current constraint still in place), for example Sony sugar company producing at a cost of 841 USD can only minimise production cost to 755 USD and Mumias with relatively improved technology, which does its production at a cost 465 USD can manage 379 USD with optimal production mix. It is also important to recognise that with sugar cost which is sighted as optimal ( X1 = 0), the cost of 35 USD is still revealed as relatively high and needed to be reduced further, this can be done by introducing high sugar variety that can yield so much from an hector to compensate for primary farm inputs.

​​Keywords: Artificial neural network; Cryptography; Decryption; Encryption; Key generation. 


  1. Stallings W. Cryptography and Network Security: Principles and Practice (5th Edition). Prentice Hall, 2010.
  2. Volna E, Kotyrba M, Kocian V, Janosek M. Cryptograpy based on neural network.Journal of Engineering Science and Technology 2 (2014) 37-48.
  3. Jacek M, Zurada. Introduction to artificial neural systems. West Publishing Company, St. Paul, 1992.
  4. Ghosh A, Nath A. Cryptography algorithms using artificial neural network. International Journal of Advance Research in Computer science and Management studies 2 (2014) 375-381.
  5. Kinzel W, Kanter I. Neural Cryptography. International Journal of Soft Computing 4 (2003) 147-153.
  6. Laskari EC, Meletiou GC, Tasoulis DK, Vrahatis MN. Performance of ANN related to cryptography, Elsevier, 2005
  7. Komal T, Ashutosh R, Roshan R. Encryption and decryption using artificial neural network. International Advanced Research Journal in Science, Engineering and Technology 2 (2015)45-64.
  8. Fausett LV. Fundamentals of artificial Neural Networks. Prentice-Hall, Inc, Englewood Cliffs, New Jersey, 1994.
  9. Chakraborty RC. Fundamentals of Neural Networks. Lecture Notes, 2010.
  10. Klein E, Mislovaty R, Kanter I, Ruttor A, Kinzel W. Synchronization of neural networks by mutual learning and its application to cryptography.International Journal of Network Security7 (2004) 56-72.
  11. Adel A. Zoghabi, Amr H. Yassin, Hany H. Hussien. Cryptography based on neural networks. International Journal of Emerging Technology and Advanced Engineering 3 (2013) 47-69.
  12. Pointcheval D. Neural networks and their cryptographic applications, in Proc. of the IEEE Symposium on Foundations of Computer Science, 1993. pp. 586-597.
  13. Jha GK. Artificial neural networks and its applications. I.A.R.I, New Delhi, 1993.
  14. Wasnik TP, Patil V, Patinge S. Cryptography as an instrument to network security. International Journal of Application or Innovation in Engineering and Management 2 (2013) 72-80.
  15. Godhavari T, Alainelu NR, Soundararajan R. Cryptography using neural network, IEEE 2005. pp. 258-261.