Thesis Open Access

# A NEURAL NETWORK PREDICTION MODEL TO CONTROL THE INTERIOR OF GREENHOUSES

SAMUEL AYELE AYTENFSU

### DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<creators>
<creator>
<creatorName>SAMUEL AYELE AYTENFSU</creatorName>
<affiliation>ADDIS ABABA SCIENCE AND TECHNOLOGY UNIVERSITY</affiliation>
</creator>
</creators>
<titles>
<title>A NEURAL NETWORK PREDICTION MODEL TO CONTROL THE INTERIOR OF GREENHOUSES</title>
</titles>
<publisher>National Academic Digital Repository of Ethiopia</publisher>
<publicationYear>2019</publicationYear>
<subjects>
<subject>Greenhouse Interior Control, Elman Neural Network, Prediction Model, Convergence Theorem,</subject>
</subjects>
<contributors>
<contributor contributorType="Supervisor">
<contributorName>Asrat Mulatu (PhD)</contributorName>
<affiliation>ADDIS ABABA SCIENCE AND TECHNOLOGY UNIVERSITY</affiliation>
</contributor>
<contributor contributorType="Supervisor">
<contributorName>Mr. Tameru H/Sellasie</contributorName>
<affiliation>ADDIS ABABA SCIENCE AND TECHNOLOGY UNIVERSITY</affiliation>
</contributor>
</contributors>
<dates>
<date dateType="Issued">2019-10-25</date>
</dates>
<language>en</language>
<resourceType resourceTypeGeneral="Text">Thesis</resourceType>
<alternateIdentifiers>
</alternateIdentifiers>
<relatedIdentifiers>
</relatedIdentifiers>
<rightsList>
<rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
</rightsList>
<descriptions>
<description descriptionType="Abstract">&lt;p&gt;The main function of a greenhouse is climate adaptation by the side of the interior of the&lt;br&gt;
closed structure; it aims to produce a perfect condition for the development and growth of&lt;br&gt;
specific crops. It also ensures isolation and protection against harsh weather conditions&lt;br&gt;
and possible animal intrusions.&lt;br&gt;
This research proposed an Elman recurrent neural network prediction model to control&lt;br&gt;
the interior of greenhouses by considering four input parameters that influence the&lt;br&gt;
greenhouse. The input parameter considered is wind velocity,  concentration, outside&lt;br&gt;
temperature and humidity. This paper also considered the data acquisition technique for&lt;br&gt;
acquiring the parameter. The data used for developing the model also part of the research&lt;br&gt;
paper and acquired in the place of Addis Ababa by setting experiments in property of&lt;br&gt;
Ethiopian environmental and forest research institute.&lt;br&gt;
The data acquisition technique is very economical and done using the Arduino platform.&lt;br&gt;
The data after collected is filtered and normalized using the Min-Max normalization&lt;br&gt;
technique. Then scaled all the data to {0 1} and finally, the model is developed using&lt;br&gt;
Elman neural network. Several selection criteria for fixing the proper number of a hidden&lt;br&gt;
neuron are analyzed; 53 different criteria is tested based on evaluating the performance&lt;br&gt;
using different statistical error measurement. The design of a neural network is&lt;br&gt;
implemented based on these selection criteria using a convergence theorem. After&lt;br&gt;
implementation, to verify the effectiveness the proposed model simulation was conducted&lt;br&gt;
in real-time inside temperature and inside relative humidity greenhouse data. The result&lt;br&gt;
obtained a minimal MSE of 0.0218, MAE of 0.1016, and RMSE of 0.1477.&lt;br&gt;
The proposed model is simple, economical especially for developing countries, efficient&lt;br&gt;
for predicting with minimal error. These papers also include the comparison of other&lt;br&gt;
models with the proposed and summarized in the table&lt;br&gt;
&amp;nbsp;&lt;/p&gt;</description>
</descriptions>
</resource>

13
2
views