Enguang Zuo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Enguang Zuo has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Xiaoyi Lv
Xinjiang University
3 shared publications - Chen Chen
School of Software, Xinjiang University, Urumqi 830091, China
2 shared publications - Cheng Chen
Xinjiang University
2 shared publications - Junyu Zhu
School of Computer Science and Technology, Xinjiang University, Urumqi 830046, China
2 shared publications - Ziwei Yan
School of Software, Xinjiang University, Urumqi 830091, China
2 shared publications Cheng Chen
Xinjiang University
1 shared publication
Latest Publications
- Open Access
VCformer: Variable-Centric Multi-Scale Transformer for Multivariate Time Series Forecasting
Multivariate time series forecasting is crucial for numerous practical applications ranging from financial markets to climate monitoring. Traditional multivariate time series forecasting methods primarily adopt a time-centric modeling paradigm, applying attention mechanisms to the temporal dimension, which presents significant limitations when handling complex dependencies between variables. To better capture inter-variable interaction patterns, this paper proposes the Variable-Centric Transformer (VCformer), which shifts the attention paradigm from time-centric to variable-centric through sequence transposition. Building upon this foundation, we further design a dual-scale architecture that simultaneously models feature representations at both the original variable level and variable group level. Combined with an adaptive variable grouping mechanism, we construct a parameter-sharing dual-path encoder and finally select the optimal feature fusion strategy through comparative experiments. Experimental results on seven benchmark datasets demonstrate that VCformer achieves comprehensive improvements in prediction accuracy compared to traditional time-centric methods, while exhibiting stronger modeling capabilities on high-dimensional data. Ablation studies and interpretability analysis further validate the effectiveness of each component.
Open AccessVCformer: Variable-Centric Multi-Scale Transformer for Multivariate Time Series Forecasting
Multivariate time series forecasting is crucial for numerous practical applications ranging from financial markets to climate monitoring. Traditional multivariate time series forecasting methods primarily adopt a time-centric modeling paradigm, applying attention mechanisms to the temporal dimension, which presents significant limitations when handling complex dependencies between variables. To better capture inter-variable interaction patterns, this paper proposes the Variable-Centric Transformer (VCformer), which shifts the attention paradigm from time-centric to variable-centric through sequence transposition. Building upon this foundation, we further design a dual-scale architecture that simultaneously models feature representations at both the original variable level and variable group level. Combined with an adaptive variable grouping mechanism, we construct a parameter-sharing dual-path encoder and finally select the optimal feature fusion strategy through comparative experiments. Experimental results on seven benchmark datasets demonstrate that VCformer achieves comprehensive improvements in prediction accuracy compared to traditional time-centric methods, while exhibiting stronger modeling capabilities on high-dimensional data. Ablation studies and interpretability analysis further validate the effectiveness of each component.
- Open Access
DTCMMA: Efficient Wind-Power Forecasting Based on Dimensional Transformation Combined with Multidimensional and Multiscale Convolutional Attention Mechanism
With the growing global demand for clean energy, the accuracy of wind-power forecasting plays a vital role in ensuring the stable operation of power systems. However, wind-power generation is significantly influenced by meteorological conditions and is characterized by high uncertainty and multiscale fluctuations. Traditional recurrent neural network (RNN) and long short-term memory (LSTM) models, although capable of handling sequential data, struggle with modeling long-term temporal dependencies due to the vanishing gradient problem; thus, they are now rarely used. Recently, Transformer models have made notable progress in sequence modeling compared to RNNs and LSTM models. Nevertheless, when dealing with long wind-power sequences, their quadratic computational complexity (O(L2)) leads to low efficiency, and their global attention mechanism often fails to capture local periodic features accurately, tending to overemphasize redundant information while overlooking key temporal patterns. To address these challenges, this paper proposes a wind-power forecasting method based on dimension-transformed collaborative multidimensional multiscale attention (DTCMMA). This method first employs fast Fourier transform (FFT) to automatically identify the main periodic components in wind-power data, reconstructing the one-dimensional time series as a two-dimensional spatiotemporal representation, thereby explicitly encoding periodic features. Based on this, a collaborative multidimensional multiscale attention (CMMA) mechanism is designed, which hierarchically integrates channel, spatial, and pixel attention to adaptively capture complex spatiotemporal dependencies. Considering the geometric characteristics of the reconstructed data, asymmetric convolution kernels are adopted to enhance feature extraction efficiency. Experiments on multiple wind-farm datasets and energy-related datasets demonstrate that DTCMMA outperforms mainstream methods such as Transformer, iTransformer, and TimeMixer in long-sequence forecasting tasks, achieving improvements in MSE performance by 34.22%, 2.57%, and 0.51%, respectively. The model’s training speed also surpasses that of the fastest baseline by 300%, significantly improving both prediction accuracy and computational efficiency. This provides an efficient and accurate solution for wind-power forecasting and contributes to the further development and application of wind energy in the global energy mix.
Open AccessDTCMMA: Efficient Wind-Power Forecasting Based on Dimensional Transformation Combined with Multidimensional and Multiscale Convolutional Attention Mechanism
With the growing global demand for clean energy, the accuracy of wind-power forecasting plays a vital role in ensuring the stable operation of power systems. However, wind-power generation is significantly influenced by meteorological conditions and is characterized by high uncertainty and multiscale fluctuations. Traditional recurrent neural network (RNN) and long short-term memory (LSTM) models, although capable of handling sequential data, struggle with modeling long-term temporal dependencies due to the vanishing gradient problem; thus, they are now rarely used. Recently, Transformer models have made notable progress in sequence modeling compared to RNNs and LSTM models. Nevertheless, when dealing with long wind-power sequences, their quadratic computational complexity (O(L2)) leads to low efficiency, and their global attention mechanism often fails to capture local periodic features accurately, tending to overemphasize redundant information while overlooking key temporal patterns. To address these challenges, this paper proposes a wind-power forecasting method based on dimension-transformed collaborative multidimensional multiscale attention (DTCMMA). This method first employs fast Fourier transform (FFT) to automatically identify the main periodic components in wind-power data, reconstructing the one-dimensional time series as a two-dimensional spatiotemporal representation, thereby explicitly encoding periodic features. Based on this, a collaborative multidimensional multiscale attention (CMMA) mechanism is designed, which hierarchically integrates channel, spatial, and pixel attention to adaptively capture complex spatiotemporal dependencies. Considering the geometric characteristics of the reconstructed data, asymmetric convolution kernels are adopted to enhance feature extraction efficiency. Experiments on multiple wind-farm datasets and energy-related datasets demonstrate that DTCMMA outperforms mainstream methods such as Transformer, iTransformer, and TimeMixer in long-sequence forecasting tasks, achieving improvements in MSE performance by 34.22%, 2.57%, and 0.51%, respectively. The model’s training speed also surpasses that of the fastest baseline by 300%, significantly improving both prediction accuracy and computational efficiency. This provides an efficient and accurate solution for wind-power forecasting and contributes to the further development and application of wind energy in the global energy mix.
- Open Access
- 8 July 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (14) , 7626
Deep Learning in Food Image Recognition: A Comprehensive Review
Food not only fulfills basic human survival needs but also significantly impacts health and culture. Research on food-related topics holds substantial theoretical and practical significance, with food image recognition being a core task in fine-grained image recognition. This field has broad applications and promising prospects in smart dining, intelligent healthcare, and smart retail. With the rapid advancement of artificial intelligence, deep learning has emerged as a key technology that enhances recognition efficiency and accuracy, enabling more practical applications. This paper comprehensively reviews the techniques and challenges of deep learning in food image recognition. First, we outline the historical development of food image recognition technologies, categorizing the primary methods into manual feature extraction-based and deep learning-based approaches. Next, we systematically organize existing food image datasets and summarize the characteristics of several representative datasets. Additionally, we analyze typical deep learning models and their performance on different datasets. Finally, we discuss the practical applications of food image recognition in calorie estimation and food safety, identify current research challenges, and propose future research directions.
- 8 July 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (14) , 7626
Open AccessDeep Learning in Food Image Recognition: A Comprehensive Review
Food not only fulfills basic human survival needs but also significantly impacts health and culture. Research on food-related topics holds substantial theoretical and practical significance, with food image recognition being a core task in fine-grained image recognition. This field has broad applications and promising prospects in smart dining, intelligent healthcare, and smart retail. With the rapid advancement of artificial intelligence, deep learning has emerged as a key technology that enhances recognition efficiency and accuracy, enabling more practical applications. This paper comprehensively reviews the techniques and challenges of deep learning in food image recognition. First, we outline the historical development of food image recognition technologies, categorizing the primary methods into manual feature extraction-based and deep learning-based approaches. Next, we systematically organize existing food image datasets and summarize the characteristics of several representative datasets. Additionally, we analyze typical deep learning models and their performance on different datasets. Finally, we discuss the practical applications of food image recognition in calorie estimation and food safety, identify current research challenges, and propose future research directions.
- 26 April 2025
- Published by Springer Nature
- p. 394-411
MBGNet: Mamba-Based Boundary-Guided Multimodal Medical Image Segmentation Network
- 26 April 2025
- Published by Springer Nature
- p. 394-411
MBGNet: Mamba-Based Boundary-Guided Multimodal Medical Image Segmentation Network