Development of machine learning for forecasting optimization implemented in morphology plant growth
Saved in:
| Title: | Development of machine learning for forecasting optimization implemented in morphology plant growth |
|---|---|
| Authors: | Ertina Sabarita Barus, Muhammad Zarlis, Zulkifli Nasution, Sutarman Sutarman |
| Source: | Eastern-European Journal of Enterprise Technologies; Vol. 3 No. 2 (135) (2025): Information technology. Industry control systems; 42-53 Eastern-European Journal of Enterprise Technologies; Том 3 № 2 (135) (2025): Інформаційні технології. Системи управління в промисловості; 42-53 |
| Publisher Information: | Private Company Technology Center, 2025. |
| Publication Year: | 2025 |
| Subject Terms: | оптимізація прогнозування, plant morphology, machine learning, морфологія рослин, multilinear regression neural network, нейронна мережа багатолінійної регресії, машинне навчання, forecasting optimization |
| Description: | The object of the study is the forecasting and optimizing the plant growth rather. The data distribution at each iteration in the continuous optimization process tends to produce premature convergence because the optimum points are found at the beginning of the iteration, so that the actual optimum condition cannot be achieved. For this reason, a method is needed to see the optimum points at each iteration in the continuous optimization process. A multi-linear regression approach is used to predict the variables generated at each iteration, and then optimized using a neural network method approach for each optimum point found. This research is implemented and observed on the growth morphology of chili plants with a total sample of 100 stems, for 100 days of growth. The testing process consists of 5 different experimental scenarios based on the activation function, and the iteration process is carried out at 250, 500, and 1000 epochs. Furthermore, with a percentage of 70% training data and 30% testing data, the results obtained using the ReLU activation function have an ideal value compared to the Tanh, Softplus, Elu, and Sigmoid activation functions. Compared to the time series method with an MSE value of 4.62, this value is much better than the value of 8.6 for the time series. The RMSE and MAPE values of 16.36 and 36.53 are also excellent. Comparison of the level of forecasting accuracy of the results of continuous optimization carried out with the activation function ReLU and tanh compared to the time series method, the value with the activation function ReLU and tanh has a percentage value 46.36% and 46.86% and this value is a good value compared to using the time series method, which is exactly 67.39% |
| Document Type: | Article |
| File Description: | application/pdf |
| ISSN: | 1729-4061 1729-3774 |
| DOI: | 10.15587/1729-4061.2025.331745 |
| Access URL: | https://journals.uran.ua/eejet/article/view/331745 |
| Rights: | CC BY |
| Accession Number: | edsair.doi.dedup.....b85a33df91a795cdc274e8542752e59b |
| Database: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstract: | The object of the study is the forecasting and optimizing the plant growth rather. The data distribution at each iteration in the continuous optimization process tends to produce premature convergence because the optimum points are found at the beginning of the iteration, so that the actual optimum condition cannot be achieved. For this reason, a method is needed to see the optimum points at each iteration in the continuous optimization process. A multi-linear regression approach is used to predict the variables generated at each iteration, and then optimized using a neural network method approach for each optimum point found. This research is implemented and observed on the growth morphology of chili plants with a total sample of 100 stems, for 100 days of growth. The testing process consists of 5 different experimental scenarios based on the activation function, and the iteration process is carried out at 250, 500, and 1000 epochs. Furthermore, with a percentage of 70% training data and 30% testing data, the results obtained using the ReLU activation function have an ideal value compared to the Tanh, Softplus, Elu, and Sigmoid activation functions. Compared to the time series method with an MSE value of 4.62, this value is much better than the value of 8.6 for the time series. The RMSE and MAPE values of 16.36 and 36.53 are also excellent. Comparison of the level of forecasting accuracy of the results of continuous optimization carried out with the activation function ReLU and tanh compared to the time series method, the value with the activation function ReLU and tanh has a percentage value 46.36% and 46.86% and this value is a good value compared to using the time series method, which is exactly 67.39% |
|---|---|
| ISSN: | 17294061 17293774 |
| DOI: | 10.15587/1729-4061.2025.331745 |