Xuyao Zhang
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
Xuyao Zhang has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Dayu Xu
College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, China
7 shared publications - Beining Huang
College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, China
1 shared publication - Chunping Lu
College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, China
1 shared publication - Fang Xia
College of Economics and Management, Zhejiang A&F University, Hangzhou, China
1 shared publication Hailin Feng
School of Information Engineering Zhejiang A & F University Zhejiang Hangzhou China
1 shared publicationJiahao Chen
Fuqua School of Business, Duke University, Durham, NC, USA
1 shared publication
Latest Publications
- Open Access
A Configurational Analysis of Green Development in Forestry Enterprises Based on the Technology–Organization–Environment (TOE) Framework
The construction of ecological civilization is intrinsically connected to green development. The green development of forestry enterprises serves as a key approach to achieving this goal. The research purpose of this paper is to explore the realization path of green development of forestry enterprises. First, an improved CRITIC (Criteria Importance Through Intercriteria Correlation)–entropy weight method was used to construct a reasonable input-output indicator system. Next, a three-stage data envelopment analysis (DEA) model was employed to evaluate the comprehensive technical efficiency of green development across 33 forestry enterprises in China, using panel data from 2017 to 2022. Finally, the study explored various configurational pathways for achieving green development by integrating the Technology–Organization–Environment (TOE) framework with dynamic qualitative comparative analysis (QCA). The findings reveal that green development in forestry enterprises is shaped by the interplay of multiple factors. Four distinct configurations were identified as instrumental in driving high green development. These configurations could be classified into two categories: the environment–organization synergistic development model and the technology–organization dual-driven model. This study provides empirical insights into the complex configurational relationships underlying green development in forestry enterprises, offering valuable guidance for optimizing development strategies.
Open AccessA Configurational Analysis of Green Development in Forestry Enterprises Based on the Technology–Organization–Environment (TOE) Framework
The construction of ecological civilization is intrinsically connected to green development. The green development of forestry enterprises serves as a key approach to achieving this goal. The research purpose of this paper is to explore the realization path of green development of forestry enterprises. First, an improved CRITIC (Criteria Importance Through Intercriteria Correlation)–entropy weight method was used to construct a reasonable input-output indicator system. Next, a three-stage data envelopment analysis (DEA) model was employed to evaluate the comprehensive technical efficiency of green development across 33 forestry enterprises in China, using panel data from 2017 to 2022. Finally, the study explored various configurational pathways for achieving green development by integrating the Technology–Organization–Environment (TOE) framework with dynamic qualitative comparative analysis (QCA). The findings reveal that green development in forestry enterprises is shaped by the interplay of multiple factors. Four distinct configurations were identified as instrumental in driving high green development. These configurations could be classified into two categories: the environment–organization synergistic development model and the technology–organization dual-driven model. This study provides empirical insights into the complex configurational relationships underlying green development in forestry enterprises, offering valuable guidance for optimizing development strategies.
- Open Access
- 1 April 2025
- Published by MDPI AG in Agriengineering
- Vol. 7 (4) , 94
Combining the Pre-Trained Model Roberta with a Two-Layer Bidirectional Long- and Short-Term Memory Network and a Multi-Head Attention Mechanism for a Rice Phenomics Entity Classification Study
At a time when global food security is challenged, the importance of phenomics research on rice, as a major food crop, has become more and more prominent. In-depth analysis of rice phenotypic characteristics is of key importance to promote the genetic improvement of rice and sustainable agricultural development. However, it is a challenging task to accurately identify and classify entities from the huge amount of rice phenotypic data. In this study, a deep learning model based on Roberta-two-layer BiLSTM-MHA was innovatively constructed for rice phenomics entity classification. Firstly, with the powerful language comprehension capability of the pre-trained Roberta model, deep feature extraction was performed on the rice phenotype text data to capture the underlying semantic information in the text. Next, the contextual information is comprehensively modelled using a two-layer bidirectional long- and short-term memory network (BiLSTM) to fully explore the long-term dependencies in the text sequences. Finally, a multi-head attention mechanism is introduced to enable the model to adaptively focus on key features at different levels, which significantly improves the classification accuracy of complex phenotypic information. The experimental results show that the model performs excellently in several evaluation metrics, with accuracy, recall, and F1-scores of 89.56%, 86.40%, and 87.90%, respectively. This research result not only provides an efficient and precise entity classification tool for rice phenomics research but also provides a comparable method for other crop phenomics analyses, which is expected to promote the technological innovation in the field of crop genetic breeding and agricultural production.
- 1 April 2025
- Published by MDPI AG in Agriengineering
- Vol. 7 (4) , 94
Open AccessCombining the Pre-Trained Model Roberta with a Two-Layer Bidirectional Long- and Short-Term Memory Network and a Multi-Head Attention Mechanism for a Rice Phenomics Entity Classification Study
At a time when global food security is challenged, the importance of phenomics research on rice, as a major food crop, has become more and more prominent. In-depth analysis of rice phenotypic characteristics is of key importance to promote the genetic improvement of rice and sustainable agricultural development. However, it is a challenging task to accurately identify and classify entities from the huge amount of rice phenotypic data. In this study, a deep learning model based on Roberta-two-layer BiLSTM-MHA was innovatively constructed for rice phenomics entity classification. Firstly, with the powerful language comprehension capability of the pre-trained Roberta model, deep feature extraction was performed on the rice phenotype text data to capture the underlying semantic information in the text. Next, the contextual information is comprehensively modelled using a two-layer bidirectional long- and short-term memory network (BiLSTM) to fully explore the long-term dependencies in the text sequences. Finally, a multi-head attention mechanism is introduced to enable the model to adaptively focus on key features at different levels, which significantly improves the classification accuracy of complex phenotypic information. The experimental results show that the model performs excellently in several evaluation metrics, with accuracy, recall, and F1-scores of 89.56%, 86.40%, and 87.90%, respectively. This research result not only provides an efficient and precise entity classification tool for rice phenomics research but also provides a comparable method for other crop phenomics analyses, which is expected to promote the technological innovation in the field of crop genetic breeding and agricultural production.
- Open Access
- 1 January 2023
- Published by Wiley in Journal of Sensors
- Vol. 2023 (1)
Predicting Multidimensional Environmental Factor Trends in Greenhouse Microclimates Using a Hybrid Ensemble Approach
Trend prediction of greenhouse microclimate is crucial, as greenhouse crops are vulnerable to potential losses resulting from dramatic changes in greenhouse microclimate. Consequently, a precise greenhouse microclimate predictive model is required that can predict trends in greenhouse microclimates several weeks in advance to avoid financial losses. In the present study, we proposed a hybrid ensemble approach to predict greenhouse microclimate based on an Informer model that is optimized using improved empirical mode decomposition (IEMD). The dataset was decomposed using IEMD, and then all the decomposed datasets were predicted using the Informer model. Afterward, the predictions were combined. In the present study, five different environmental factor datasets of CO2 concentration, atmospheric pressure, light intensity, temperature, and humidity were predicted. The performance of the IEMD‐Informer model was compared with other modeling approaches. The results demonstrate that the proposed method has outstanding performance and can predict the greenhouse microclimate environmental factors more accurately.
- 1 January 2023
- Published by Wiley in Journal of Sensors
- Vol. 2023 (1)
Open AccessPredicting Multidimensional Environmental Factor Trends in Greenhouse Microclimates Using a Hybrid Ensemble Approach
Trend prediction of greenhouse microclimate is crucial, as greenhouse crops are vulnerable to potential losses resulting from dramatic changes in greenhouse microclimate. Consequently, a precise greenhouse microclimate predictive model is required that can predict trends in greenhouse microclimates several weeks in advance to avoid financial losses. In the present study, we proposed a hybrid ensemble approach to predict greenhouse microclimate based on an Informer model that is optimized using improved empirical mode decomposition (IEMD). The dataset was decomposed using IEMD, and then all the decomposed datasets were predicted using the Informer model. Afterward, the predictions were combined. In the present study, five different environmental factor datasets of CO2 concentration, atmospheric pressure, light intensity, temperature, and humidity were predicted. The performance of the IEMD‐Informer model was compared with other modeling approaches. The results demonstrate that the proposed method has outstanding performance and can predict the greenhouse microclimate environmental factors more accurately.
- Open Access
An Ecological Development Level Evaluation of the Forestry Industry in China Based on a Hybrid Ensemble Approach
The straits of ecological development in the forestry industry and the problems existing in the industrial forestry system are currently the main focus of policy-making research in China, to alleviate the contradiction between forestry economic development and the ecological environment, as well as evaluate the level and trend of the ecological development in China’s forestry industry. This paper analyzed the status of ecological development in China’s forestry industry via public data, constructed a novel evaluation index system for forestry industrial ecological development, and proposed a hybrid ensemble approach combined with principal component analysis, entropy weights, and fuzzy-DEMATEL to synthetically evaluate the ecological development level and system coordination of the forestry industry in each province of China. The experimental results show that technological innovation ability is the most significant restriction for the ecological development of China’s forestry industry. Obvious regional differences in the promotion degree of ecological development and the coordination of various elements throughout the country has also been confirmed. Findings of our research could be used for promoting the green transformation and upgrading of the forestry industry, and providing targeted practical countermeasures according to local conditions for governments at all levels.
Open AccessAn Ecological Development Level Evaluation of the Forestry Industry in China Based on a Hybrid Ensemble Approach
The straits of ecological development in the forestry industry and the problems existing in the industrial forestry system are currently the main focus of policy-making research in China, to alleviate the contradiction between forestry economic development and the ecological environment, as well as evaluate the level and trend of the ecological development in China’s forestry industry. This paper analyzed the status of ecological development in China’s forestry industry via public data, constructed a novel evaluation index system for forestry industrial ecological development, and proposed a hybrid ensemble approach combined with principal component analysis, entropy weights, and fuzzy-DEMATEL to synthetically evaluate the ecological development level and system coordination of the forestry industry in each province of China. The experimental results show that technological innovation ability is the most significant restriction for the ecological development of China’s forestry industry. Obvious regional differences in the promotion degree of ecological development and the coordination of various elements throughout the country has also been confirmed. Findings of our research could be used for promoting the green transformation and upgrading of the forestry industry, and providing targeted practical countermeasures according to local conditions for governments at all levels.
- Open Access
- 30 June 2020
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2020, 1-12
A Novel Ensemble Credit Scoring Model Based on Extreme Learning Machine and Generalized Fuzzy Soft Sets
This paper mainly discusses the hybrid application of ensemble learning, classification, and feature selection (FS) algorithms simultaneously based on training data balancing for helping the proposed credit scoring model perform more effectively, which comprises three major stages. Firstly, it conducts preprocessing for collected credit data. Then, an efficient feature selection algorithm based on adaptive elastic net is employed to reduce the weakly related or uncorrelated variables to get high-quality training data. Thirdly, a novel ensemble strategy is proposed to make the imbalanced training data set balanced for each extreme learning machine (ELM) classifier. Finally, a new weighting method for single ELM classifiers in the ensemble model is established with respect to their classification accuracy based on generalized fuzzy soft sets (GFSS) theory. A novel cosine-based distance measurement algorithm of GFSS is also proposed to calculate the weights of each ELM classifier. To confirm the efficiency of the proposed ensemble credit scoring model, we implemented experiments with real-world credit data sets for comparison. The process of analysis, outcomes, and mathematical tests proved that the proposed model is capable of improving the effectiveness of classification in average accuracy, area under the curve (AUC), H-measure, and Brier’s score compared to all other single classifiers and ensemble approaches.
- 30 June 2020
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2020, 1-12
Open AccessA Novel Ensemble Credit Scoring Model Based on Extreme Learning Machine and Generalized Fuzzy Soft Sets
This paper mainly discusses the hybrid application of ensemble learning, classification, and feature selection (FS) algorithms simultaneously based on training data balancing for helping the proposed credit scoring model perform more effectively, which comprises three major stages. Firstly, it conducts preprocessing for collected credit data. Then, an efficient feature selection algorithm based on adaptive elastic net is employed to reduce the weakly related or uncorrelated variables to get high-quality training data. Thirdly, a novel ensemble strategy is proposed to make the imbalanced training data set balanced for each extreme learning machine (ELM) classifier. Finally, a new weighting method for single ELM classifiers in the ensemble model is established with respect to their classification accuracy based on generalized fuzzy soft sets (GFSS) theory. A novel cosine-based distance measurement algorithm of GFSS is also proposed to calculate the weights of each ELM classifier. To confirm the efficiency of the proposed ensemble credit scoring model, we implemented experiments with real-world credit data sets for comparison. The process of analysis, outcomes, and mathematical tests proved that the proposed model is capable of improving the effectiveness of classification in average accuracy, area under the curve (AUC), H-measure, and Brier’s score compared to all other single classifiers and ensemble approaches.
- Open Access
- 19 May 2020
- Published by MDPI AG in Sustainability
- Vol. 12 (10) , 4147
Life Cycle Assessment of Complex Forestry Enterprise: A Case Study of a Forest–Fiberboard Integrated Enterprise
The complex forestry enterprises incorporate the production activities of different links in the value chain of forest products and should be the mainstay for the sustainable forestry production of China in the foreseeable future. This case study was carried out and main data were collected in a forest–board integrated enterprise of South China. A life cycle model using the impact 2002+ method was applied to identify the resource consumption and environmental impacts of different production stages along the industrial chain. This study incorporates the calculation of carbon sequestration per unit output into the standard LCA to evaluate the effect of the forest cultivation stage. The objective of this study is two-fold. The first objective is to gain a better understanding of the environmental impacts of the complex forestry enterprises. The second objective is to put forward environmental management suggestions for the identified hotspots along the forest value chain. Factors affecting the environment include carbon sequestration and seedlings, electric power, and the use of wood fuel. Improvement suggestions are put forward from three perspectives: Changing the type and application method of fertilizer, reducing electric power consumption, and reducing wood fuel consumption.
- 19 May 2020
- Published by MDPI AG in Sustainability
- Vol. 12 (10) , 4147
Open AccessLife Cycle Assessment of Complex Forestry Enterprise: A Case Study of a Forest–Fiberboard Integrated Enterprise
The complex forestry enterprises incorporate the production activities of different links in the value chain of forest products and should be the mainstay for the sustainable forestry production of China in the foreseeable future. This case study was carried out and main data were collected in a forest–board integrated enterprise of South China. A life cycle model using the impact 2002+ method was applied to identify the resource consumption and environmental impacts of different production stages along the industrial chain. This study incorporates the calculation of carbon sequestration per unit output into the standard LCA to evaluate the effect of the forest cultivation stage. The objective of this study is two-fold. The first objective is to gain a better understanding of the environmental impacts of the complex forestry enterprises. The second objective is to put forward environmental management suggestions for the identified hotspots along the forest value chain. Factors affecting the environment include carbon sequestration and seedlings, electric power, and the use of wood fuel. Improvement suggestions are put forward from three perspectives: Changing the type and application method of fertilizer, reducing electric power consumption, and reducing wood fuel consumption.
- 23 October 2018
- Published by Wiley in International Journal of Finance & Economics
- Vol. 24 (2) , 903-921
Generalized fuzzy soft sets theory‐based novel hybrid ensemble credit scoring model
In banking and peer‐to‐peer loan applicant firms, customer credit scores have numerous applications in risk control and precision marketing. Numerous credit scoring techniques act as classification methods. In this paper, the main issue is simultaneous and hybrid utilization of the feature selection (FS) algorithm and ensemble learning classification algorithms with respect to their parameter settings to achieve higher performance in the proposed credit scoring model. As a result, this paper reports a hybrid data mining model of generalized fuzzy soft sets (GFSS) theory‐based ensemble learning classification algorithms based on three stages. The first stage addresses data gathering and preprocessing. The second stage uses the adaptive elastic net‐based FS algorithm to eliminate irrelevant or weakly correlated variables. After the appropriate variables are chosen, they are applied to the proposed ensemble model. In the third stage, GFSS theory is exploited to construct a novel weight assignment mechanism for each individual credit scoring model in the ensemble model according to performance. Several comparisons are conducted to validate the proposed model using real world credit datasets. The experimental results, analysis, and statistical tests prove the ability of the proposed approach to improve classification performance against all of the base classifier, hybrid, and combination methods in terms of average accuracy, area under the curve, H‐measure, and Brier score.
- 23 October 2018
- Published by Wiley in International Journal of Finance & Economics
- Vol. 24 (2) , 903-921
Generalized fuzzy soft sets theory‐based novel hybrid ensemble credit scoring model
In banking and peer‐to‐peer loan applicant firms, customer credit scores have numerous applications in risk control and precision marketing. Numerous credit scoring techniques act as classification methods. In this paper, the main issue is simultaneous and hybrid utilization of the feature selection (FS) algorithm and ensemble learning classification algorithms with respect to their parameter settings to achieve higher performance in the proposed credit scoring model. As a result, this paper reports a hybrid data mining model of generalized fuzzy soft sets (GFSS) theory‐based ensemble learning classification algorithms based on three stages. The first stage addresses data gathering and preprocessing. The second stage uses the adaptive elastic net‐based FS algorithm to eliminate irrelevant or weakly correlated variables. After the appropriate variables are chosen, they are applied to the proposed ensemble model. In the third stage, GFSS theory is exploited to construct a novel weight assignment mechanism for each individual credit scoring model in the ensemble model according to performance. Several comparisons are conducted to validate the proposed model using real world credit datasets. The experimental results, analysis, and statistical tests prove the ability of the proposed approach to improve classification performance against all of the base classifier, hybrid, and combination methods in terms of average accuracy, area under the curve, H‐measure, and Brier score.