Browsing by Author "Mzelikahle, Kernan"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Optimisation of Self Organising Maps Using the Bat Algorithm
    (2017) Mzelikahle, Kernan; Mapuma, Dunstan Junior; Hlatywayo, Dumisani J.; Trimble, John; Hlatywayo, Dumisani J.
    Self Organising Maps are among the most widely used unsupervised neural network approaches to clustering. They have been shown to be efficient in handling large and high dimensional data. The Bat Algorithm is a swarm intelligence based, meta- heuristic optimisation algorithm. It is based on the echolocation behaviour of micro-bats with varying emission pulse rates and loudness. This paper gives a novel hybrid optimisation method which is here called the Bat Optimised Self-Organising Map. It combines the basic Self Organising Map learning algorithm with the Bat Algorithm. In this optimisation technique, the Bat Algorithm is used to initialise the weight vectors for a Self Organising Map to a near global optimum prior to the competition.
  • Thumbnail Image
    Item
    Using Fuzzy ARTMAP for Symmetric Key Generation
    (American Institute of Science., 2015) Mulopa, John; Ndlovu, Siqabukile; Mzelikahle, Kernan; Nyathi, Thambo
    Neural cryptography deals with the problem of key exchange between two communicating neural networks using the mutual learning concept. It is the first algorithm for key generation over public channels which are not based on the number theory. The two networks exchange their outputs and the key between the two communicating parties is eventually presented in the final learned weights, when the two networks are synchronised. The security of neural synchronisation is put at risk if an attacker is capable of synchronising with any of the two parties during the training processes. However, the security of a cryptosystem is robust if the algorithm is strong and the keys are long, unpredictable, and random This research proposes use of two distant remote Adaptive Resonance Theory MAP (ARTMAP) architectures that are trained to learn from a unique data set and finally synchronise to same weights.