Performance Analysis of Combine Harvester using Hybrid Model of Artificial Neural Networks Particle Swarm Optimization

EasyChair Preprint 2781

Abstract

The performance analysis of a common combine harvester is presented using a novel hybrid machine learning model based on artificial neural networks tuned with particle swarm optimization (ANN-PSO). Increasing the performance of harvesters is of utmost important in agriculture as it can minimize the wastes during harvesting and is also beneficial to the machine maintenance. Hybridization of machine learning methods with soft computing techniques has recently shown promising results to improve the performance of the combine harvesters. This research aims at improving the results further by providing more stable models with higher accuracy.

Keyphrases: ANN model, ANN-PSO, Artificial Neural Network, Artificial Neural Networks (ANN), Fan speed, Particle Swarm Optimization, Particle Swarm Optimization (PSO), ann pso model, combine harvester, comparative analysis, electrical engineering obuda university, hidden layer, hybrid machine learning, int agric eng, machine learning, machine learning method, model number, neural network, performance analysis, swarm size, target value

@booklet{EasyChair:2781,
  author    = {László Nádai and Imre Felde and Sina Ardabili and Tarahom Mesri Gundoshmian and Gergő Pintér and Amir Mosavi},
  title     = {Performance Analysis of Combine Harvester using Hybrid Model of Artificial Neural Networks Particle Swarm Optimization},
  howpublished = {EasyChair Preprint 2781},
  year      = {EasyChair, 2020}}