Data Classification Using Carbon-Nanotubes and Evolutionary Algorithms

Abstract

The nal publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-45823-660Additional information: Use policyThe full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-pro t purposes provided that:• a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders.Please consult the full DRO policy for further details. Abstract. The potential of Evolution in Materio (EiM) for machine learning problems is explored here. This technique makes use of evolutionary algorithms (EAs) to influence the processing abilities of an unconfigured physically rich medium, via exploitation of its physical properties. The EiM results reported are obtained using particle swarm optimisation (PSO) and differential evolution (DE) to exploit the complex voltage/current relationship of a mixture of single walled carbon nanotubes (SWCNTs) and liquid crystals (LCs). The computational problem considered is simple binary data classification. Results presented are consistent and reproducible. The evolutionary process based on EAs has the capacity to evolve the material to a state where data classification can be performed. Finally, it appears that through the use of smooth signal inputs, PSO produces classifiers out of the SWCNT/LC substrate which generalise better than those evolved with DE.

Computing Based on Material Training: Application to Binary Classification Problems

“…These two contributions continue the work reported in [12], [20], [21] and [22]. The hardware platform and material are discussed in section II.…”

“…The nanotubes are 1/3 metallic, 2/3 semiconducting whilst the E7 nematic liquid crystal molecule presents no comparative conductivity. It was reported in [21] [22] that using the experimental set-up described, it was not possible to train a stand-alone LC solution in liquid state to perform a computation.…”

“…Previous papers reported results for simple, proof-ofconcept datasets [12,21,22]. The first part of our investigations focus on the training of un-configured SWCNT/LC mixture for medical datasets selected from the UCI repository.…”

“…It has been observed in our previous work [21,22] that an un-configured SWCNT/LC mixture can be trained to solve these binary classification problems. Current investigations focus on whether the SWCNT structures formed in the material during training are stable, a non-negligible contribution to the solution and finally if they can be retained, to some extent, when the material has been retrained for a new problem.…”

“…In [9], [11], and [17] a dry mix of Single-Walled Carbon Nanotubes (SWCNT) with a polymer were used as the computational material and its electrical conductance was used as the manipulated property for solving the problem of calculating Boolean functions using a threshold interpretation scheme; the same material is used in [14] and [15] for solving optimisation problems. In [12], [22], [21] and [20] the material used is a solution of SWCNT with LC in liquid rather than in dry solid state. The physical property used for evolving the material is its electrical conductivity and the ability of the SWCNT to form percolation paths within the LC.…”