Wentao Jiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Wentao Jiang has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Dabin Zhang
College of Mathematics and Information, South China Agricultural University, Guangzhou, China
3 shared publications - Liwen Ling
College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China
3 shared publications Dabin Zhang
South China Agricultural University
2 shared publicationsHongbo Li
College of Mathematics and Information Science, South China Agricultural University, Guangzhou, China
2 shared publicationsLiling Zeng
South China Agricultural University
2 shared publicationsLiwen Ling
South China Agricultural University
2 shared publications
Latest Publications
- Open Access
- 26 July 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-15
Two forecasting model selection methods based on time series image feature augmentation
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.
- 26 July 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-15
Open AccessTwo forecasting model selection methods based on time series image feature augmentation
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.
- Open Access
- 1 July 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-14
Time series image coding classification theory based on Lagrange multiplier method
Time series classification is a crucial area of research within data analysis. Recent advancements in convolutional neural networks (CNNs) for image recognition and classification have inspired innovative approaches in this field. Researchers have begun transforming one-dimensional time series (TS) into visual representations, harnessing the capabilities of image classification paradigms to improve TS classification accuracy. Despite extensive research on the classification of time series images (TSI), the underlying classification principles have not been fully established. To address this gap, our paper integrates time series image encoding with algebraic techniques, utilizing Gramian Angular Summation Fields (GASF) and Gramian Angle Difference Fields (GADF) as effective encoding methods. We provide a theoretical justification for the advantages of CNNs in TSI classification by employing the Lagrange multiplier method and the Karush-Kuhn-Tucker (KKT) conditions. This rigorous proof framework enhances the theoretical foundation for TSI classification based on image encoding. To validate our theoretical assertions, we conduct experiments using the benchmark UCR dataset, with empirical findings largely corroborating our theoretical proofs. In summary, our work not only advances the theoretical understanding of TSI classification but also demonstrates its practical effectiveness.
- 1 July 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-14
Open AccessTime series image coding classification theory based on Lagrange multiplier method
Time series classification is a crucial area of research within data analysis. Recent advancements in convolutional neural networks (CNNs) for image recognition and classification have inspired innovative approaches in this field. Researchers have begun transforming one-dimensional time series (TS) into visual representations, harnessing the capabilities of image classification paradigms to improve TS classification accuracy. Despite extensive research on the classification of time series images (TSI), the underlying classification principles have not been fully established. To address this gap, our paper integrates time series image encoding with algebraic techniques, utilizing Gramian Angular Summation Fields (GASF) and Gramian Angle Difference Fields (GADF) as effective encoding methods. We provide a theoretical justification for the advantages of CNNs in TSI classification by employing the Lagrange multiplier method and the Karush-Kuhn-Tucker (KKT) conditions. This rigorous proof framework enhances the theoretical foundation for TSI classification based on image encoding. To validate our theoretical assertions, we conduct experiments using the benchmark UCR dataset, with empirical findings largely corroborating our theoretical proofs. In summary, our work not only advances the theoretical understanding of TSI classification but also demonstrates its practical effectiveness.
- 24 August 2023
- Published by Springer Nature in Soft Computing
- Vol. 27 (20) , 14673-14688
Time series to imaging-based deep learning model for detecting abnormal fluctuation in agriculture product price
- 24 August 2023
- Published by Springer Nature in Soft Computing
- Vol. 27 (20) , 14673-14688
Time series to imaging-based deep learning model for detecting abnormal fluctuation in agriculture product price
- 13 February 2023
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (5) , 5783-5810
A Time Series Forecasting Model Selection Framework using CNN and Data Augmentation for Small Sample Data
- 13 February 2023
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (5) , 5783-5810
A Time Series Forecasting Model Selection Framework using CNN and Data Augmentation for Small Sample Data
- Open Access
- 29 August 2022
- Published by Springer Nature in Research Square
Time series to imaging based deep learning model for detecting abnormal fluctuation in agriculture product price
In the analysis of agricultural product price time series, the detection of abnormal fluctuation is the primary task. Accurately judging the abnormal fluctuation of agricultural product prices will give the policy support to the government and also assist farmers increase production and income. A deep convolutional neural network model based on time series image(TSI) is introduced to identify the abnormal fluctuation of agricultural prices under the improved standard deviation-Slope judgment. Markov Transfer Field(MTF) method is used to transform the pre-processed sparse one-dimensional time series of agricultural prices into two-dimensional dense images, and a deep convolutional neural network(CNN) model is used for automatic feature extraction and classification of time series images containing abnormal fluctuations. The empirical evaluation of China's corn and wheat price datasets are performed in our paper, and compared with other abnormal fluctuation judgment methods, the accuracy of the proposed algorithm is about 20% higher on average, which confirms the applicability of the standard deviation-slope time series Image-Resnet-34 (SDS-TSI-Resnet34) model in practical scenarios. Finally, some feasible suggestions for the efficient development of agricultural economy are proposed based on the abnormal fluctuation judgment method proposed in this paper.
- 29 August 2022
- Published by Springer Nature in Research Square
Open AccessTime series to imaging based deep learning model for detecting abnormal fluctuation in agriculture product price
In the analysis of agricultural product price time series, the detection of abnormal fluctuation is the primary task. Accurately judging the abnormal fluctuation of agricultural product prices will give the policy support to the government and also assist farmers increase production and income. A deep convolutional neural network model based on time series image(TSI) is introduced to identify the abnormal fluctuation of agricultural prices under the improved standard deviation-Slope judgment. Markov Transfer Field(MTF) method is used to transform the pre-processed sparse one-dimensional time series of agricultural prices into two-dimensional dense images, and a deep convolutional neural network(CNN) model is used for automatic feature extraction and classification of time series images containing abnormal fluctuations. The empirical evaluation of China's corn and wheat price datasets are performed in our paper, and compared with other abnormal fluctuation judgment methods, the accuracy of the proposed algorithm is about 20% higher on average, which confirms the applicability of the standard deviation-slope time series Image-Resnet-34 (SDS-TSI-Resnet34) model in practical scenarios. Finally, some feasible suggestions for the efficient development of agricultural economy are proposed based on the abnormal fluctuation judgment method proposed in this paper.
- 15 March 2022
- Published by Springer Nature in Neural Processing Letters
- Vol. 54 (5) , 3727-3748
Time Series Classification Based on Image Transformation Using Feature Fusion Strategy
- 15 March 2022
- Published by Springer Nature in Neural Processing Letters
- Vol. 54 (5) , 3727-3748
Time Series Classification Based on Image Transformation Using Feature Fusion Strategy
- Open Access
- 17 February 2022
- Published by Springer Nature in Research Square
A Time Series Forecasting Model Selection Framework Using CNN and Data Augmentation for Small Sample Data
The key to the accuracy of time series forecasting is to find the most appropriate forecasting method. Therefore, the forecasting model selection of time series has become a new research hotspot in the data analysis field. However, most of the existing forecasting model selection methods reduce the forecasting efficiency for relying on subjective manual selection of features. In this paper, an automatic time series feature extraction framework is proposed for forecasting model selection based on the idea of meta learning. Inspired by computer vision, we transform one -dimensional time series into two-dimensional images, and use convolution neural network (CNN) to train and classify time series images (model selection). Moreover, in order to deal with the over fitting problem caused by small sample datasets, the sliding window data augmentation method is used to improve the accuracy of small datasets model selection. A large-scale empirical study on M3 datasets shows that the proposed framework has better model selection accuracy and smaller forecasting error(MAPE) than Support vector machine(SVM) and traditional time series image algorithms. Moreover, the classification rate(model selection accuracy) of the proposed algorithm are increased by 6.5% and 4.4% compare with the traditional time series image method and Support vector machine respectively in average
- 17 February 2022
- Published by Springer Nature in Research Square
Open AccessA Time Series Forecasting Model Selection Framework Using CNN and Data Augmentation for Small Sample Data
The key to the accuracy of time series forecasting is to find the most appropriate forecasting method. Therefore, the forecasting model selection of time series has become a new research hotspot in the data analysis field. However, most of the existing forecasting model selection methods reduce the forecasting efficiency for relying on subjective manual selection of features. In this paper, an automatic time series feature extraction framework is proposed for forecasting model selection based on the idea of meta learning. Inspired by computer vision, we transform one -dimensional time series into two-dimensional images, and use convolution neural network (CNN) to train and classify time series images (model selection). Moreover, in order to deal with the over fitting problem caused by small sample datasets, the sliding window data augmentation method is used to improve the accuracy of small datasets model selection. A large-scale empirical study on M3 datasets shows that the proposed framework has better model selection accuracy and smaller forecasting error(MAPE) than Support vector machine(SVM) and traditional time series image algorithms. Moreover, the classification rate(model selection accuracy) of the proposed algorithm are increased by 6.5% and 4.4% compare with the traditional time series image method and Support vector machine respectively in average