Two forecasting model selection methods based on time series image feature augmentation

Abstract Forecasting and early warning of agricultural product prices is a crucial task in stream data event analysis and agricultural data mining. Existing methods for forecasting agricultural product prices suffer from inefficient feature engineering and challenges in handling imbalanced sample da...

Full description

Saved in:
Bibliographic Details
Main Authors: Wentao Jiang, Quan Wang, Hongbo Li
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-10072-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849388239474917376
author Wentao Jiang
Quan Wang
Hongbo Li
author_facet Wentao Jiang
Quan Wang
Hongbo Li
author_sort Wentao Jiang
collection DOAJ
description Abstract Forecasting and early warning of agricultural product prices is a crucial task in stream data event analysis and agricultural data mining. Existing methods for forecasting agricultural product prices suffer from inefficient feature engineering and challenges in handling imbalanced sample data. To address these issues, we propose a novel predictive model selection approach based on time series image encoding. Specifically, we utilize Gramian Angular Fields (GAF), Markov Transition Fields (MTF), and Recurrence Plots (RP) to transform time series data into image representations. We then introduce an Information Fusion Feature Augmentation (IFFA) method to effectively combine these time series images, ensuring that all relevant event information is preserved. The combined time series images (TSCI) are subsequently fed into a Convolutional Neural Network (CNN) classifier for model selection. Furthermore, to accommodate the unique characteristics of the data, we incorporate Transfer Learning (TL) and S-Folder Cross Validation (S-FCV) to optimize the model selection process, thereby mitigating overfitting due to limited or imbalanced data. Experimental results demonstrate that the proposed IFFA-TSCI-CNN-SFCV method outperforms existing approaches in terms of both efficiency and accuracy.
format Article
id doaj-art-a7ec19e183e24d5399b4d5ea290f0c77
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-a7ec19e183e24d5399b4d5ea290f0c772025-08-20T03:42:22ZengNature PortfolioScientific Reports2045-23222025-07-0115111510.1038/s41598-025-10072-4Two forecasting model selection methods based on time series image feature augmentationWentao Jiang0Quan Wang1Hongbo Li2School of Internet of Things Engineering, Wuxi UniversitySchool of Internet of Things Engineering, Wuxi UniversityCollege of Mathematics and Information Science, South China Agricultural UniversityAbstract Forecasting and early warning of agricultural product prices is a crucial task in stream data event analysis and agricultural data mining. Existing methods for forecasting agricultural product prices suffer from inefficient feature engineering and challenges in handling imbalanced sample data. To address these issues, we propose a novel predictive model selection approach based on time series image encoding. Specifically, we utilize Gramian Angular Fields (GAF), Markov Transition Fields (MTF), and Recurrence Plots (RP) to transform time series data into image representations. We then introduce an Information Fusion Feature Augmentation (IFFA) method to effectively combine these time series images, ensuring that all relevant event information is preserved. The combined time series images (TSCI) are subsequently fed into a Convolutional Neural Network (CNN) classifier for model selection. Furthermore, to accommodate the unique characteristics of the data, we incorporate Transfer Learning (TL) and S-Folder Cross Validation (S-FCV) to optimize the model selection process, thereby mitigating overfitting due to limited or imbalanced data. Experimental results demonstrate that the proposed IFFA-TSCI-CNN-SFCV method outperforms existing approaches in terms of both efficiency and accuracy.https://doi.org/10.1038/s41598-025-10072-4Time series encodingForecasting model selectionFeature augmentation
spellingShingle Wentao Jiang
Quan Wang
Hongbo Li
Two forecasting model selection methods based on time series image feature augmentation
Scientific Reports
Time series encoding
Forecasting model selection
Feature augmentation
title Two forecasting model selection methods based on time series image feature augmentation
title_full Two forecasting model selection methods based on time series image feature augmentation
title_fullStr Two forecasting model selection methods based on time series image feature augmentation
title_full_unstemmed Two forecasting model selection methods based on time series image feature augmentation
title_short Two forecasting model selection methods based on time series image feature augmentation
title_sort two forecasting model selection methods based on time series image feature augmentation
topic Time series encoding
Forecasting model selection
Feature augmentation
url https://doi.org/10.1038/s41598-025-10072-4
work_keys_str_mv AT wentaojiang twoforecastingmodelselectionmethodsbasedontimeseriesimagefeatureaugmentation
AT quanwang twoforecastingmodelselectionmethodsbasedontimeseriesimagefeatureaugmentation
AT hongboli twoforecastingmodelselectionmethodsbasedontimeseriesimagefeatureaugmentation