Thesis Open Access

A NEURAL NETWORK PREDICTION MODEL TO CONTROL THE INTERIOR OF GREENHOUSES

SAMUEL AYELE AYTENFSU


Citation Style Language JSON Export

{
  "DOI": "10.20372/nadre/4195", 
  "abstract": "<p>The main function of a greenhouse is climate adaptation by the side of the interior of the<br>\nclosed structure; it aims to produce a perfect condition for the development and growth of<br>\nspecific crops. It also ensures isolation and protection against harsh weather conditions<br>\nand possible animal intrusions.<br>\nThis research proposed an Elman recurrent neural network prediction model to control<br>\nthe interior of greenhouses by considering four input parameters that influence the<br>\ngreenhouse. The input parameter considered is wind velocity,  concentration, outside<br>\ntemperature and humidity. This paper also considered the data acquisition technique for<br>\nacquiring the parameter. The data used for developing the model also part of the research<br>\npaper and acquired in the place of Addis Ababa by setting experiments in property of<br>\nEthiopian environmental and forest research institute.<br>\nThe data acquisition technique is very economical and done using the Arduino platform.<br>\nThe data after collected is filtered and normalized using the Min-Max normalization<br>\ntechnique. Then scaled all the data to {0 1} and finally, the model is developed using<br>\nElman neural network. Several selection criteria for fixing the proper number of a hidden<br>\nneuron are analyzed; 53 different criteria is tested based on evaluating the performance<br>\nusing different statistical error measurement. The design of a neural network is<br>\nimplemented based on these selection criteria using a convergence theorem. After<br>\nimplementation, to verify the effectiveness the proposed model simulation was conducted<br>\nin real-time inside temperature and inside relative humidity greenhouse data. The result<br>\nobtained a minimal MSE of 0.0218, MAE of 0.1016, and RMSE of 0.1477.<br>\nThe proposed model is simple, economical especially for developing countries, efficient<br>\nfor predicting with minimal error. These papers also include the comparison of other<br>\nmodels with the proposed and summarized in the table<br>\n&nbsp;</p>", 
  "author": [
    {
      "family": "SAMUEL AYELE AYTENFSU"
    }
  ], 
  "id": "4195", 
  "issued": {
    "date-parts": [
      [
        2019, 
        10, 
        25
      ]
    ]
  }, 
  "language": "eng", 
  "title": "A NEURAL NETWORK PREDICTION MODEL TO CONTROL THE INTERIOR OF GREENHOUSES", 
  "type": "thesis"
}
13
2
views
downloads
All versions This version
Views 1313
Downloads 22
Data volume 4.1 MB4.1 MB
Unique views 77
Unique downloads 22

Share

Cite as