An improved LogNNet classifier for IoT application

TL;DR

This paper introduces an improved LogNNet neural network utilizing a Henon chaotic map, optimized with particle swarm, achieving higher accuracy for IoT devices with limited resources.

Contribution

The paper presents a novel LogNNet architecture with a chaotic map and optimization method, enhancing classification accuracy for resource-constrained IoT applications.

Findings

Higher accuracy compared to original LogNNet

Effective use of chaotic maps for input transformation

Demonstrated relation between entropy and classification accuracy

Abstract

In the age of neural networks and Internet of Things (IoT), the search for new neural network architectures capable of operating on devices with limited computing power and small memory size is becoming an urgent agenda. Designing suitable algorithms for IoT applications is an important task. The paper proposes a feed forward LogNNet neural network, which uses a semi-linear Henon type discrete chaotic map to classify MNIST-10 dataset. The model is composed of reservoir part and trainable classifier. The aim of the reservoir part is transforming the inputs to maximize the classification accuracy using a special matrix filing method and a time series generated by the chaotic map. The parameters of the chaotic map are optimized using particle swarm optimization with random immigrants. As a result, the proposed LogNNet/Henon classifier has higher accuracy and the same RAM usage, compared to the original version of LogNNet, and offers promising opportunities for implementation in IoT devices. In addition, a direct relation between the value of entropy and accuracy of the classification is demonstrated.