Multi-Channel Graph Convolutional Network for Evaluating Innovation Capability Toward Sustainable Seed Enterprises
文献类型： 外文期刊
作者： Tang, Shanshan 1 ; Wang, Kaiyi 1 ; Yang, Feng 2 ; Pan, Shouhui 2 ;
作者机构： 1.Heilongjiang Bayi Agr Univ, Coll Informat & Elect Engn, Daqing 163319, Peoples R China
2.Beijing Acad Agr & Forestry Sci, Informat Technol Res Ctr, Beijing 100097, Peoples R China
3.Natl Innovat Ctr Digital Seed Ind, Beijing, Peoples R China
关键词： innovation capacity evaluation; graph neural network; multi-channel; seed enterprises sustainability
期刊名称：SUSTAINABILITY （ 影响因子：3.3； 五年影响因子：3.6 ）
ISSN：
年卷期： 2025 年 17 卷 16 期
页码：
收录情况： SCI
摘要： The innovation capability of seed enterprises reflects their core competitiveness and serves as a vital foundation for sustainable agricultural development and modernization. Therefore, evaluating this capability is of great importance. However, existing evaluation methods primarily focus on internal enterprise attributes, overlooking the complex inter-enterprise relationships and lacking sufficient feature fusion capabilities to capture latent information. To address these limitations, this paper proposes a Multi-Channel Graph Convolutional Network (MGCN) model that integrates enterprise attributes with three types of relational graphs. The model adopts a multi-channel architecture for feature extraction and employs a gated attention mechanism for cross-graph feature fusion, jointly considering node features and relation information to improve prediction accuracy. Experimental results demonstrate that MGCN achieves an average accuracy of 83.59% under five-fold cross-validation, outperforming several mainstream models such as Random Forest and traditional GCN. Case studies further reveal that MGCN not only captures key features of individual enterprises but also leverages features and label distribution from neighboring enterprises, facilitating more context-aware classification decisions. In conclusion, the MGCN model provides an effective method for the intelligent evaluation of innovation capability in seed enterprises and supports the formulation of sustainable strategic plans at both the national and enterprise level.
- 相关文献
作者其他论文 更多>>
-
A Study of Maize Genotype-Environment Interaction Based on Deep K-Means Clustering Neural Network
作者：Bai, Longpeng;Bai, Longpeng;Wang, Kaiyi;Zhang, Qiusi;Zhang, Qi;Wang, Xiaofeng;Pan, Shouhui;He, Xuliang;Li, Ran;Zhang, Dongfeng;Han, Yanyun;Wang, Kaiyi;Pan, Shouhui;Zhang, Liyang;He, Xuliang;Li, Ran
关键词：small ecological region delineation; deep k-means clustering neural network; genotype by environment interaction
-
Hybrid Deep Learning Approaches for Improved Genomic Prediction in Crop Breeding
作者：Li, Ran;Zhang, Dongfeng;Han, Yanyun;Liu, Zhongqiang;Zhang, Qiusi;Zhang, Qi;Wang, Xiaofeng;Pan, Shouhui;Sun, Jiahao;Wang, Kaiyi;Li, Ran;Pan, Shouhui;Sun, Jiahao;Wang, Kaiyi
关键词：CNN; hybrid models; LSTM; phenotypic prediction; ResNet
-
VMGP: A unified variational auto-encoder based multi-task model for multi-phenotype, multi-environment, and cross-population genomic selection in plants
作者：Zhao, Xiangyu;Li, Jinlong;Zhang, Dongfeng;Zhang, Qiusi;Liu, Zhongqiang;Wang, Kaiyi;Sun, Fuzhen;Tan, Changwei;Ma, Hongxiang;Zhao, Xiangyu;Wang, Kaiyi;Zhao, Xiangyu;Zhang, Dongfeng;Liu, Zhongqiang;Wang, Kaiyi
关键词：Genomic selection; Variational auto-encoder; Multi-task; Deep learning; Genomic prediction
-
Multi-view hypergraph networks incorporating interpretability analysis for predicting lodging in corn varieties
作者：Wang, Kaiyi;Yang, Feng;Zhao, Xiangyu;Liu, Zhongqiang;Zhang, Qiusi;Li, Jinlong;Zhang, Dongfeng;Bai, Wenqin;Wang, Shun;Zhang, Yong;Wang, Kaiyi;Yang, Feng;Zhao, Xiangyu;Liu, Zhongqiang;Zhang, Qiusi;Li, Jinlong;Zhang, Dongfeng
关键词：Corn lodging classification; Multi-view hypergraph network; Graph interpretability
-
Prediction of maize cultivar yield based on machine learning algorithms for precise promotion and planting
作者：Han, Yanyun;Wang, Kaiyi;Yang, Feng;Pan, Shouhui;Liu, Zhongqiang;Zhang, Qiusi;Zhang, Qi;Han, Yanyun;Wang, Kaiyi;Yang, Feng;Pan, Shouhui;Liu, Zhongqiang;Zhang, Qiusi;Zhang, Qi
关键词：Prediction of maize cultivar yield; Machine learning; Random forest; Levenberg - Marquardt neural network; Multilayer perceptron neural network; Assessment of varieties
-
Developing a comprehensive evaluation model of variety adaptability based on machine learning method
作者：Han, Yanyun;Wang, Kaiyi;Zhang, Qi;Yang, Feng;Pan, Shouhui;Liu, Zhongqiang;Zhang, Qiusi;Han, Yanyun;Wang, Kaiyi;Zhang, Qi;Yang, Feng;Pan, Shouhui;Liu, Zhongqiang;Zhang, Qiusi
关键词：Maize variety adaptability evaluation; Variety adaptability comprehensive evaluation index; Entropy weight method; Machine learning method
-
TrG2P: A transfer-learning-based tool integrating multi-trait data for accurate prediction of crop yield
作者：Li, Jinlong;Zhang, Dongfeng;Yang, Feng;Zhang, Qiusi;Pan, Shouhui;Zhao, Xiangyu;Zhang, Qi;Han, Yanyun;Wang, Kaiyi;Zhao, Chunjiang;Li, Jinlong;Zhang, Dongfeng;Yang, Feng;Zhang, Qiusi;Pan, Shouhui;Zhao, Xiangyu;Zhang, Qi;Han, Yanyun;Wang, Kaiyi;Zhao, Chunjiang;Yang, Jinliang;Yang, Jinliang
关键词：crop; genotype to phenotype; transfer learning; yield prediction; multi-trait
