Neural Networks for Forecasting: An Introduction

Kohzadi, Nowrouz; Boyd, Milton S.; Kaastra, Iebeling; Kermanshahi, B.; Scuse, David

doi:10.1111/j.1744-7976.1995.tb00135.x

Cited by 34 publications

(24 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…General descriptions of ANN modelling can be found in Lawrence (1993), Smith (1993) and Kohzadi et al (1995). We constructed feed-forward ANN models using NeuralWorks Predict® v3.21 software (NeuralWare®, Carnegie, PA) on a desktop PC (2.4 GHz).…”

Section: Ann Modellingmentioning

confidence: 99%

An Artificial Neural Network Model to Predict Wheat Stem Sawfly Cutting in Solid-Stemmed Wheat Cultivars

et al. 2017

View full text Add to dashboard Cite

The wheat stem sawfly, Cephus cinctus Norton (Hymenoptera: Cephidae), is a major pest of wheat (Triticum aestivum L.) in the northern Great Plains of North America. The use of solid-stemmed cultivars helps mitigate crop losses and can also affect the survivorship of C. cinctus. The efficacy of a plant's resistance is based on its ability to develop pith in the culm of the stem, which is influenced greatly by interactions between the genotype and environment. Precipitation-related weather interacts with photoperiod to reduce pith expression in solid-stemmed wheat. A model that predicts pith expression could serve as a management tool to prevent losses by alerting producers if in-season precipitation patterns have caused less than ideal pith expression in a cultivar. Artificial Neural Network (ANN) models are used to make predictions for complex, non-linear systems with many co-related variables. Our objective was to improve upon past models that used regression analyses by deploying an ANN model to predict in-season stem cutting of wheat by wheat stem sawfly. Results indicate that stem cutting is influenced by the precipitation within a 5 wk period from 1 June to 5 July. These results were successfully deployed in a model that should assist with predictions of potential late season stem cutting. Deployment of this ANN model as a transferable executable file may facilitate predictions of stem cutting by wheat stem sawfly in any given year, which will empower producers to implement the appropriate harvest management strategies to reduce losses.Key words: Triticum aestivum L., host plant, bread wheat, solid-stemmed, sawfly, Cephus cinctus.Résumé : Dans le nord des grandes plaines nord-américaines, le cèphe du blé, Cephus cinctus Norton (Hymenoptera: Cephidae), est un important ravageur du blé (Triticum aestivum L.). L'usage de cultivars à tige pleine concourt à atténuer les pertes et peut affecter la capacité de survie de l'insecte. La plante résiste dans la mesure où elle réussit à produire de la moelle dans la tige, propriété qui subit considérablement l'influence des interactions entre le génotype et l'environnement. Un temps pluvieux modifiera la photopériode, ce qui réduira la synthèse de moelle chez les variétés à tige pleine. Un modèle qui prévoirait la production de moelle aurait son utilité en agronomie, car on pourrait alors éviter des pertes en signalant aux cultivateurs si les précipitations saisonnières engendrent une production insuffisante de moelle chez tel ou tel cultivar. On se sert des modèles à réseau neuronal artificiel (RNA) pour formuler des prévisions sur les systèmes complexes, non linéaires, comportant de nombreuses variables apparentées. Les auteurs voulaient améliorer les anciens modèles de prévision reposant sur l'analyse par régression en recourant à un modèle RNA pour établir l'importance des dommages causés par le cèphe au blé durant la période végétative. Les résultats obtenus indiquent que ces dommages sont influencés For personal use only.par l'intensité des précipitati...

show abstract

Section: Ann Modellingmentioning

confidence: 99%

An Artificial Neural Network Model to Predict Wheat Stem Sawfly Cutting in Solid-Stemmed Wheat Cultivars

et al. 2017

View full text Add to dashboard Cite

show abstract

“…General descriptions of NN modelling can be found in Lawrence (1993), Smith (1993), Elizondo et al (1994) and Kohzadi et al (1995). We constructed feed-forward NN models using NeuralWorks Predict ® v3.11 software (NeuralWare ® , Carnegie, PA) on a desktop PC (2.26 GHz).…”

Section: Nn Modellingmentioning

confidence: 99%

Neural network modelling of fruit colour and crop variables to predict harvest dates of greenhouse-grown sweet peppers

Lin¹,

Hill²

2007

Can. J. Plant Sci.

View full text Add to dashboard Cite

Lin, W. C. and Hill, B. D. 2007. Neural network modelling of fruit colour and crop variables to predict harvest dates of greenhouse-grown sweet peppers. Can. J. Plant Sci. 87: 137-143. Sweet peppers (Capsicum annuum L.) grown in the greenhouse have irregular yields. Modelling colouration of individual fruit could help growers predict the number of fully coloured peppers that will be ready to harvest within a routine harvest period. We monitored the red, green and blue colour intensities of developing pepper fruit via digital image processing. These colour measurements together with crop phenology and environmental variables were used as inputs into neural network (NN) models to predict days-to-harvest (D-to-H) for individual fruit. When 18 inputs were evaluated, a typical "best" NN model needed only five of the inputs to predict D-to-H (range 0 to 28 d) for red peppers with a R 2 of 0.79, a root mean square error (RMSE) of 3.4 d, and an average absolute error (AAE) of 2.5 d. D-to-H were more difficult to predict for yellow peppers, with the "best" model using eight inputs to achieve a R 2 of 0.69, a RMSE of 4.4 d, and an AAE of 3.4 d. Light and temperature made little contribution to predictions of D-to-H. NN models with only three inputs (Julian day, nodal position of the target fruit and ratio of red:green intensities) could still make useful predictions of harvest maturity. For both red and yellow peppers, the R 2 values of NN models were higher than the corresponding R 2 a (R 2 adjusted) values derived from multiple linear regression models. It is concluded that NN have potential to assist greenhouse operators to predict D-to-H of sweet peppers. Modéliser la coloration des fruits individuels aiderait les producteurs à prévoir le nombre de fruits entièrement colorés qu'ils pourront cueillir au cours d'une période donnée. Les auteurs ont établi l'intensité des couleurs rouge, verte et bleue des fruits en développement par numérisation des images. La quantification des couleurs, les stades phénologiques de la culture et des variables environnementales ont servi à créer un modèle de type « réseau neuronal » (RN) permettant de prévoir le nombre de jours avant la récolte (JAR) de chaque fruit. Sur 18 paramètres évalués, le meilleur modèle RN n'en a besoin que de cinq pour prévoir le JAR (fourchette de 0 à 28 jours) des poivrons rouges, avec une valeur R 2 de 0,79, une erreur-type de 3,4 jours et une erreur absolue moyenne de 2,5 jours. Le JAR est plus difficile à établir pour les poivrons jaunes, le « meilleur » modèle recourant à huit paramètres pour donner une R 2 de 0,69, une erreur-type de 4,4 jours et une erreur absolue moyenne de 3,4 jours. La luminosité et la température concourent peu à la prévision du JAR. Les modèles RN n'intégrant que trois paramètres (jour julien, emplacement du fruit par rapport au noeud et rapport entre l'intensité du rouge et du vert) pourraient tout de même donner une prévision utile de la maturité à la cueillette. Pour les poivrons rouges et jaunes, les modèles RN donnent une val...

show abstract

“…Fonte: KOHZADI et al (1995) A camada de entrada ( x) fornece os insumos (dados ou informações) sem nenhum procedimento computacional. A camada oculta (h) recebe as informações da camada de insumos, ou de outra camada oculta, e fornece informações para outra camada oculta ou para a camada de saída.…”

Section: Figura 2 -Rna Do Tipo Feedforwardunclassified

“…Contudo, a escolha da estrutura ideal da RNA é uma tarefa difícil, envolvendo desde a definição do número de observações a ser utilizado até a determinação dos componentes da camada oculta. Segundo KOHZADI et al (1995), o número inicial de neurônios na camada de entrada pode ser estabelecido pela natureza do problema estudado e pelo seu referencial teórico.…”

Section: Figura 3 -Esquema De Uma Rna Para Previsão De Preçosunclassified

Tomada de decisão em futuros agropecuários com modelos de previsão de séries temporais

Bressan¹

2004

RAE electron.

View full text Add to dashboard Cite

Este artigo trata da aplicabilidade de modelos de previsão de séries temporais como ferramenta de decisão de compra e venda de contratos futuros de boi gordo, café e soja na BM&F, em datas próximas ao vencimento. Os modelos estudados são: ARIMA, Redes Neurais Artificiais, e Modelos Lineares Dinâmicos. Os dados correspondem às cotações semanais, nos mercados físico e futuro, entre 1996 e 1999. O objetivo consiste em calcular os retornos médios dos modelos em operações no mercado futuro de boi gordo, café e soja, de modo a indicar o potencial ou limitação dos modelos, utilizando o índice Sharpe como parâmetro de comparação. Os resultados apresentam retornos financeiros positivos na maioria dos contratos analisados, indicando o potencial de utilização desses modelos como ferramenta de decisão em negociações de contratos para datas próximas ao vencimento, com destaque para operações fundamentadas nas previsões nos MLD e ARIMA havendo, contudo, diferenças de desempenho preditivo.

show abstract

Neural Networks for Forecasting: An Introduction

Cited by 34 publications

References 7 publications

An Artificial Neural Network Model to Predict Wheat Stem Sawfly Cutting in Solid-Stemmed Wheat Cultivars

An Artificial Neural Network Model to Predict Wheat Stem Sawfly Cutting in Solid-Stemmed Wheat Cultivars

Neural network modelling of fruit colour and crop variables to predict harvest dates of greenhouse-grown sweet peppers

Tomada de decisão em futuros agropecuários com modelos de previsão de séries temporais

Contact Info

Product

Resources

About