Search

A method of establishing a prediction model of the greenhouse temperature based on time-series analysis and the boosting tree model is proposed, aiming at the problem that the temperature of a greenhouse cannot be accurately predicted owing to nonlinear changes in the temperature of the closed ecosystem of a greenhouse featuring modern agricultural technology and various influencing factors. This model comprehensively considers environmental parameters, including humidity inside and outside the greenhouse, air pressure inside and outside the greenhouse, and temperature outside the greenhouse, as well as time-series changes, to make a more accurate prediction of the temperature in the greenhouse. Experiments show that the R2 determination coefficients of different prediction models are improved and the mean square error and mean absolute error are reduced after adding time-series features. Among the models tested, LightGBM performs best, with the mean square error of the prediction results of the model decreasing by 18.61% after adding time-series features. Comparing with the support vector machine, radial basis function neural network, back-propagation neural network, and multiple linear regression model after adding time-series features, the mean square error is 11.70% to 29.12% lower. Furthermore, the fitting degree of LightGBM is the best among the models. The prediction results of LightGBM therefore have important application value in greenhouse temperature control. [ABSTRACT FROM AUTHOR]

A method of establishing a prediction model of the greenhouse temperature based on time-series analysis and the boosting tree model is proposed, aiming at the problem that the temperature of a greenhouse cannot be accurately predicted owing to nonlinear changes in the temperature of the closed ecosystem of a greenhouse featuring modern agricultural technology and various influencing factors. This model comprehensively considers environmental parameters, including humidity inside and outside the greenhouse, air pressure inside and outside the greenhouse, and temperature outside the greenhouse, as well as time-series changes, to make a more accurate prediction of the temperature in the greenhouse. Experiments show that the R2 determination coefficients of different prediction models are improved and the mean square error and mean absolute error are reduced after adding time-series features. Among the models tested, LightGBM performs best, with the mean square error of the prediction results of the model decreasing by 18.61% after adding time-series features. Comparing with the support vector machine, radial basis function neural network, back-propagation neural network, and multiple linear regression model after adding time-series features, the mean square error is 11.70% to 29.12% lower. Furthermore, the fitting degree of LightGBM is the best among the models. The prediction results of LightGBM therefore have important application value in greenhouse temperature control.

Data mining and machine learning are both useful tools in the field of data analysis. Classification algorithm is one of the most important techniques in data mining, therefore, it is of great significance to select suitable classification models with high efficiency to show superiority when solving classification problems with the use of Iris data. With this goal, a decision tree induction algorithm, namely graftedTree, is proposed to build randomized decision trees. Randomization is explicitly introduced into this algorithm, such that applying the algorithm several times on the same training data results in diversified models. An ensemble classification model is constructed using multiple randomized decision trees via majority voting. In order to show the performance of different models in classification, we propose the usage of precision, recall, F-Measure, the area under the ROC curve (AUC) and Gini coefficient as evaluation indexes of the classifying performance on the Iris dataset. The experimental results show that classification with Random Forests model has generally better performance than that with the Boosting Tree model and other three popular algorithms: KNN, SMO and Simple Cart. However, the Gini coefficient of the Random Forests model shows that it gets less pure training set than other models. The new GraftedTrees model inherits the advantages of Random Forest and further employs random mixture of two interchangeable node splitting rule inductions with the aim to obtain higher computational efficiency and better performance in terms of accuracy. With its superiority, it is expected that the new GraftedTrees model can prove to be the most powerful model with better performance in classification in the near future. [ABSTRACT FROM AUTHOR]