File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Using a novel clustered 3D-CNN model for improving crop future price prediction

TitleUsing a novel clustered 3D-CNN model for improving crop future price prediction
Authors
KeywordsArtificial intelligence
Clustered 3D-CNN model
Food insecurity
Prediction model
Issue Date25-Jan-2023
PublisherElsevier
Citation
Knowledge-Based Systems, 2023, v. 260 How to Cite?
Abstract

Many research studies used statistics to predict food production, distribution and price trends. Researchers used statistical inference for discovering the relationships of data to build predictive model. However, crop production and its price trend do not only depend on ecosystems, molecular biology, precision agriculture, veterinary science, animal genes, and technology, but also depend on the environmental change and economic factors. Most importantly, the crop price trend is in non-stationary pattern and is influenced by multiple dimensional factors that the traditional techniques of time series forecasting, such as ARIMA, cannot perform well in prediction. Since CNN model can cope with non-stationary data and learn non-linearity by adjusting the model parameters, it can overcome the limitations of the traditional statistical methods in prediction. Therefore, the aims of this research are to conduct a review to identify a more complete factors that may influence crop production and price changes, and to propose a novel Clustered 3D-CNN model for predicting crop future price. The experiments to compare the performance of our proposed model and ARIMA model were done. The average results found that our proposed Clustered 3D-CNN model (MAPE = 0.083, RMSE = 40.39, MAE = 32.31) outperforms the ARIMA model (MAPE = 0.108, RMSE = 59.95, MAE = 46.35). The 3D-CNN model helps decision makers to better predict crop price trend, and to develop a strategic plan for selecting trading partners to reduce the cost and for solving food insecurity problem.


Persistent Identifierhttp://hdl.handle.net/10722/335556
ISSN
2023 Impact Factor: 7.2
2023 SCImago Journal Rankings: 2.219
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorCheung, Liege-
dc.contributor.authorWang, Yun-
dc.contributor.authorLau, Adela SM-
dc.contributor.authorChan, Rogers MC -
dc.date.accessioned2023-11-28T09:43:34Z-
dc.date.available2023-11-28T09:43:34Z-
dc.date.issued2023-01-25-
dc.identifier.citationKnowledge-Based Systems, 2023, v. 260-
dc.identifier.issn0950-7051-
dc.identifier.urihttp://hdl.handle.net/10722/335556-
dc.description.abstract<p>Many research studies used <a href="https://www.sciencedirect.com/topics/mathematics/statistics" title="Learn more about statistics from ScienceDirect's AI-generated Topic Pages">statistics</a> to predict food production, distribution and price trends. Researchers used <a href="https://www.sciencedirect.com/topics/mathematics/inferential-statistics" title="Learn more about statistical inference from ScienceDirect's AI-generated Topic Pages">statistical inference</a> for discovering the relationships of data to build <a href="https://www.sciencedirect.com/topics/mathematics/predictive-model" title="Learn more about predictive model from ScienceDirect's AI-generated Topic Pages">predictive model</a>. However, crop production and its price trend do not only depend on ecosystems, molecular biology, precision agriculture, veterinary science, animal genes, and technology, but also depend on the environmental change and economic factors. Most importantly, the crop price trend is in non-stationary pattern and is influenced by multiple dimensional factors that the traditional techniques of time series forecasting, such as ARIMA, cannot perform well in prediction. Since <a href="https://www.sciencedirect.com/topics/engineering/convolutional-neural-network" title="Learn more about CNN from ScienceDirect's AI-generated Topic Pages">CNN</a> model can cope with non-stationary data and learn non-linearity by adjusting the model parameters, it can overcome the limitations of the traditional statistical methods in prediction. Therefore, the aims of this research are to conduct a review to identify a more complete factors that may influence crop production and price changes, and to propose a novel Clustered 3D-CNN model for predicting <a href="https://www.sciencedirect.com/topics/engineering/future-crop" title="Learn more about crop future from ScienceDirect's AI-generated Topic Pages">crop future</a> price. The experiments to compare the performance of our proposed model and <a href="https://www.sciencedirect.com/topics/mathematics/moving-average-model" title="Learn more about ARIMA model from ScienceDirect's AI-generated Topic Pages">ARIMA model</a> were done. The average results found that our proposed Clustered 3D-CNN model (MAPE = 0.083, <a href="https://www.sciencedirect.com/topics/engineering/root-mean-square-error" title="Learn more about RMSE from ScienceDirect's AI-generated Topic Pages">RMSE</a> = 40.39, <a href="https://www.sciencedirect.com/topics/engineering/mean-absolute-error" title="Learn more about MAE from ScienceDirect's AI-generated Topic Pages">MAE</a> = 32.31) outperforms the ARIMA model (MAPE = 0.108, RMSE = 59.95, MAE = 46.35). The 3D-CNN model helps <a href="https://www.sciencedirect.com/topics/engineering/decision-maker" title="Learn more about decision makers from ScienceDirect's AI-generated Topic Pages">decision makers</a> to better predict crop price trend, and to develop a strategic plan for selecting trading partners to reduce the cost and for solving food insecurity problem.<br></p>-
dc.languageeng-
dc.publisherElsevier-
dc.relation.ispartofKnowledge-Based Systems-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjectArtificial intelligence-
dc.subjectClustered 3D-CNN model-
dc.subjectFood insecurity-
dc.subjectPrediction model-
dc.titleUsing a novel clustered 3D-CNN model for improving crop future price prediction-
dc.typeArticle-
dc.identifier.doi10.1016/j.knosys.2022.110133-
dc.identifier.scopuseid_2-s2.0-85144091273-
dc.identifier.volume260-
dc.identifier.eissn1872-7409-
dc.identifier.isiWOS:000990787500001-
dc.identifier.issnl0950-7051-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats