| Issue |
E3S Web of Conf.
Volume 469, 2023
The International Conference on Energy and Green Computing (ICEGC’2023)
|
|
|---|---|---|
| Article Number | 00019 | |
| Number of page(s) | 13 | |
| DOI | https://doi.org/10.1051/e3sconf/202346900019 | |
| Published online | 20 December 2023 | |
Optimal Artificial Neural Network using Particle Swarm Optimization
1 NIT Warangal, Warangal, India
2 LETI-ENIS, University of Sfax, Sfax, Tunisia
3 NOVA, University of Lisbon, Portugal
4 FSDM, University SMBA, Fez, Morocco
5 LETI-ENIS, University of Sfax, Sfax, Tunisia
Artificial neuron networks (ANNs) are widely used for data analyticS in broad areas of engineering applications and commercial services. The ANN has one to two hidden layers. In advanced ANN, multiple-layer ANN is used where the network extracts different features until it can recognize what it is looking for through deep learning approaches. Usually, a backpropagation algorithm is used to train the network and fix weights and biases associated with each network neuron. This paper proposes a particle swarm optimization (PSO) based algorithm for training ANN for better performance and accuracy. Two types of ANN models and their training using PSO have been developed. The performance of the developed models has been analyzed on a standard dataset. Also, the effectiveness and suitability of the developed approach have been demonstrated through statistics of the obtained results.
Key words: Activation function / hidden layer / input layer / output layer / transfer function / artificial neural networks / particle swarm optimization
© The Authors, published by EDP Sciences, 2023
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.