Fuping Hu

Dr. Fuping Hu

orcid

Research Focus & Metrics

Representative Publications

View All Publications
18 October 2023 in IEEE Transactions on Fuzzy Systems
Verified
Journal Article
Closed access
FHFuping Hu
Fuping Hu
ZDZhaohong Deng
Zhaohong Deng
GWGuanjin Wang
Guanjin Wang
ZXZhenping Xie
Zhenping Xie
KCKup-Sze Choi
Kup-Sze Choi
SWShitong Wang
Shitong Wang
Fuzzy Systems (FSs) have been widely utilized in diverse domains such as pattern recognition, intelligent control, data mining and bioinformatics due to their strong interpretation and learning abilities. Traditionally, FSs have mainly been applied to model Euclidean data. However, with the emergence of scenarios involving graph data such as social networks and traffic route maps, which inherently possess non-Euclidean structures, there is a need to develop FS modeling methods suitable for graph data while retaining the advantages of traditional FSs. This paper presents a novel FS called Graph Fuzzy System (GFS) specifically designed for modelling whole graph data. The concepts, modeling framework, and construction algorithms are systematically developed. Firstly, the paper defines GFS-related concepts, including the graph fuzzy rule base, graph fuzzy sets, and Graph Consequent Processing Unit (GCPU). Secondly, the learning framework for GFS is proposed. It includes a novel K-Means with Graph Similarity Measure clustering approach (KM-GSM) for generating antecedents in GFS and a new consequent parameters learning algorithm based on Graph Neural Network (GNNs). Moreover, three different versions of the GFS implementation algorithm are developed and thoroughly evaluated through experiments on various graph prediction datasets. The results demonstrate that the proposed GFS inherits the advantages of mainstream GNNs methods and conventional FSs methods while achieving superior performance in whole graph prediction compared to existing approaches.

20 September 2024 in IEEE Transactions on Fuzzy Systems
Verified
Journal Article
Closed access
FHFuping Hu
Fuping Hu
ZDZhaohong Deng
Zhaohong Deng
ZXZhenping Xie
Zhenping Xie
TZTe Zhang
Te Zhang
KCKup-Sze Choi
Kup-Sze Choi
SWShitong Wang
Shitong Wang
Graph data modeling is non-trivial due to the challenges to ensure model interpretability and handle data uncertainty. While methods derived from deep learning models, such as graph neural networks (GNNs), are able to handle graph data, the interpretability is limited. Graph fuzzy systems (GFSs) based on the fuzzy rules and fuzzy inference have been proposed to improve interpretability, but the existing methods are developed for whole graph prediction only and cannot deal with node prediction which is a more common task in graph data modeling. To tackle the challenges, a novel GFS for node prediction (GFS-node) is investigated in this study. For this purpose, the concepts, framework, and algorithms of GFS-node are systematically developed. First, several related concepts are defined, including the node fuzzy rule base, node fuzzy set, and node consequent processing module (NCPM). A general framework for GFS-node is then presented, where the construction of antecedents and consequents of fuzzy rules are analyzed. Furthermore, a concrete implementation method of GFS-node is designed. Specially, the kernel K virtual central nodes clustering (KVCN) algorithm is proposed to develop the algorithm for antecedent generation, and the linear message passing network (LMPN) is adopted to develop the algorithm for consequent generation and learning. Experiments are carried out on multiple benchmark datasets, and the results show that GFS-node combine the advantages of both traditional FSs and classical GNNs for node prediction

28 November 2023 in IEEE/ACM Transactions on Computational Biology and Bioinformatics
Verified
Journal Article
Closed access
ZDZhaohong Deng
Zhaohong Deng
ZDZhaohong Deng
Zhaohong Deng
HZHanwen Zhou
Hanwen Zhou
WZWei Zhang
Wei Zhang
FHFuping Hu
Fuping Hu
SWShitong Wang
Shitong Wang
As a class of extremely significant of biocatalysts, enzymes play an important role in the process of biological reproduction and metabolism. Therefore, the prediction of enzyme function is of great significance in biomedicine fields. Recently, computational methods for predicting enzyme function have been proposed, and they effectively reduce the cost of enzyme function prediction. However, there are still deficiencies for effectively mining the discriminant information for enzyme function recognition in existing methods. In this study, we present MVDINET, a novel method for multi-level enzyme function prediction. First, the initial multi-view feature data is extracted by the enzyme sequence. Then, the above initial views are fed into various deep specific network modules to learn the depth-specificity information. Further, a deep view interaction network is designed to extract the interaction information. Finally, the specificity information and interaction information are fed into a multi-view adaptively weighted classification. We compressively evaluate MVDINET on benchmark datasets and demonstrate that MVDINET is superior to existing methods. The source code can be found at https://github.com/insight-miss/MVDINET.

1 October 2009
Verified
Conference Paper
Closed access
FHFuping Hu
Fuping Hu
SWShu Wang
Shu Wang
ZCZhuo Cheng
Zhuo Cheng
A key enabling functionality in implementing Cognitive Radio is to reliably detect the licensed users. In recent literature, cooperation among spectrum sensing terminals is suggested to offer reliable sensing performance. We consider the problem that the presence of malfunctioning or malicious sensing terminals will severely degrade the performance of cooperative spectrum sensing. In this paper, we extend the Weighted Sequential Probability Ratio Test (WSPRT) by replacing the binary local report with N-bits local report to achieve a better detection performance. Additionally, three types of reputation rating evaluation schemes are introduced: neutral, punitive and heavy punitive. Simulation results show that the extended WSPRT technique improves detection performance. Moreover, the extended WSPRT with heavy punitive scheme is shown to be the most robust against the malfunctioning or malicious sensing terminals.

31 July 2025 in IEEE Transactions on Computational Biology and Bioinformatics
Verified
Journal Article
Closed access
LHLiangwen He
Liangwen He
ZDZhaohong Deng
Zhaohong Deng
FHFuping Hu
Fuping Hu
ZWZhongyu Wang
Zhongyu Wang
YZYun Zuo
Yun Zuo
JWJing Wu
Jing Wu
Intelligent prediction of protein function is more efficient and less resource-consuming and has achieved significant progress in recent years. However, most of the current methods are performed solely based on the sequence information of proteins. These methods overlook information of other modalities that the proteins themselves possess, which makes it difficult to achieve the desired predicted results. Furthermore, a few existing methods based on multiple modal information fuse them in a simple splicing manner and fail to fully exploit the complementary relation between different modalities. To address the abovementioned challenges, we propose Multi-modal Multi-attention fusion Features (DMMAFS), a method based on deep learning, to predict protein function. On the one hand, DMMAFS gains the semantic information embedded in the sequence itself through the self-attention learning of the sequence. On the other hand, DMMAFS employs the 3D structural information of proteins to compensate for the sequence information. Particularly, a S-C cross-modal cross-attention fusion network module is proposed that not only optimizes the weights of the semantic information but also efficiently fuses the sequence features with the structural information, thus avoiding the simple splicing of different modal features. Our experimental results demonstrate that the proposed DMMAFS outperforms the state-of-the-art methods in protein function prediction.

30 March 2026 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
CZChao Zhang
Chao Zhang
YMYunfeng Ma
Yunfeng Ma
FHFuping Hu
Fuping Hu
QWQi Wang
Qi Wang
The integration of graph-based fuzzy systems into power system state estimation (SE) remains underexplored, yet it offers strong potential for interpretable and resilient grid monitoring under cyber threats. As modern power grids become increasingly complex, ensuring accurate SE while defending against false data injection (FDI) attacks poses a critical challenge. Traditional SE techniques and bad-data detection methods, relying on linearized models and single-estimator residual checks, often fail to capture nonlinear topology-coupled dependencies and noise in practice, thereby limiting their ability to detect stealthy and coordinated attacks. To bridge this gap, we propose a Graph Fuzzy Competitive Equilibrium State Estimation (GF-CESE) framework that combines graph fuzzy reasoning with power grid topology to enhance interpretability and anomaly detection. By constructing fuzzy rules via virtual center nodes (VCNs) and embedding network connectivity into rule consequents through message propagation, GF-CESE models nonlinear state evolution in a topology-consistent manner. By further introducing a multi-estimator competitive-equilibrium mechanism and cross-estimator residual fusion with a sliding-window test, GF-CESE improves estimation stability and robustness against stealthy FDI attacks. Extensive experiments on IEEE 14-, 118-, and 300-bus systems validate the effectiveness, scalability, and robustness of the proposed approach under high measurement noise and large-scale coordinated multi-node attacks.