Wei Zhong
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
Research Subjects
Wei Zhong has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Jieyue He
School of Computer Science and Engineering Key Lab of Computer Network and Information Integration MOE Southeast University 210018 Nanjing Jiangsu China
5 shared publications - Feng Gu
Department of Computer Science, College of Staten Island, Staten Island, New York, USA
2 shared publications - Gulsah Altun
DDepartment of Nephrology, Department of Internal Medicine, Duzce University Faculty of Medicine, Duzce, Turkey
2 shared publications - Phang-Cheng Tai
Department of Biology, Center for Biotechnology and Drug Design, Georgia State University, Atlanta, GA 30303, USA
2 shared publications - Robert W. Harrison
Georgia State University
2 shared publications - Xudong Zhang
University of South Carolina Upstate, USA
2 shared publications
Latest Publications
- Open Access
- 8 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 319-325
A Hybrid Resampling Technique with Adaptive Intervals Used in the Parallel/Distributed Particle Filters
Parallel/Distributed particle filters estimate the states of dynamic systems by using Bayesian interference and stochastic sampling techniques with multiple processing units (PUs). The sampling procedure and the resampling procedure alternatively execute to estimate the states in particle filters. There are two basic types of resampling techniques used in parallel/distributed particle filters. They are centralized resampling and decentralized resampling. The high communication between PUs in centralized resampling lowers the speedup factor in parallel computing but improves the estimation accuracy. The decentralized resampling can avoid the communication and improve the performance. Some types of hybrid resampling techniques mainly execute the decentralized resampling and only invoke the centralized resampling with constant intervals to achieve ideal performance without losing the estimation accuracy. However, the constant intervals cannot guarantee that the centralized resamplings are invoked timely. In this study, we proposed a hybrid resampling technique with adaptive intervals between centralized resamplings to overcome that issue. The experimental results indicate that the proposed hybrid resampling technique is able to improve the performance and the estimation accuracy.
- 8 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 319-325
Open AccessA Hybrid Resampling Technique with Adaptive Intervals Used in the Parallel/Distributed Particle Filters
Parallel/Distributed particle filters estimate the states of dynamic systems by using Bayesian interference and stochastic sampling techniques with multiple processing units (PUs). The sampling procedure and the resampling procedure alternatively execute to estimate the states in particle filters. There are two basic types of resampling techniques used in parallel/distributed particle filters. They are centralized resampling and decentralized resampling. The high communication between PUs in centralized resampling lowers the speedup factor in parallel computing but improves the estimation accuracy. The decentralized resampling can avoid the communication and improve the performance. Some types of hybrid resampling techniques mainly execute the decentralized resampling and only invoke the centralized resampling with constant intervals to achieve ideal performance without losing the estimation accuracy. However, the constant intervals cannot guarantee that the centralized resamplings are invoked timely. In this study, we proposed a hybrid resampling technique with adaptive intervals between centralized resamplings to overcome that issue. The experimental results indicate that the proposed hybrid resampling technique is able to improve the performance and the estimation accuracy.
- Open Access
- 30 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 4711-4725
Performance Analysis of Resampling Algorithms of Parallel/Distributed Particle Filters
Particle filters have been widely used in various fields due to their advantages in dealing with non-linear and/or non-Gaussian systems. A large number of particles are needed to guarantee the convergence of particle filters for the state estimation, especially for large-scale complex systems. Therefore, parallel/distributed particle filters were adopted to improve the performance, in which different paradigms of resampling were proposed, including the centralized resampling, the decentralized resampling, and the hybrid resampling. To ease their adoptions, we analyze time consumptions and speedup factors of parallel/distributed particle filters with various resampling algorithms, state sizes, system complexities, numbers of processing units, and model dimensions in this study. The experimental results indicate that the decentralized resampling achieves the highest speedup factors due to the local transfer of particles, the centralized resampling always has the lowest speedup factors because of the global transfer of particles, and the hybrid resampling attains the speedup factors between. Moreover, we define the complexity-state ratio, as the ratio between the system complexity and the system state size to study how it impacts the speedup factor. The experiments show that the higher complexity-state ratio results in the increase of the speedup factors. This is one of the earliest attempts to analyze and compare the performance of parallel/distributed particle filters with different resampling algorithms. The analysis can provide potential solutions for further performance improvements and guide the appropriate selection of the resampling algorithm for parallel/distributed particle filters.
- 30 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 4711-4725
Open AccessPerformance Analysis of Resampling Algorithms of Parallel/Distributed Particle Filters
Particle filters have been widely used in various fields due to their advantages in dealing with non-linear and/or non-Gaussian systems. A large number of particles are needed to guarantee the convergence of particle filters for the state estimation, especially for large-scale complex systems. Therefore, parallel/distributed particle filters were adopted to improve the performance, in which different paradigms of resampling were proposed, including the centralized resampling, the decentralized resampling, and the hybrid resampling. To ease their adoptions, we analyze time consumptions and speedup factors of parallel/distributed particle filters with various resampling algorithms, state sizes, system complexities, numbers of processing units, and model dimensions in this study. The experimental results indicate that the decentralized resampling achieves the highest speedup factors due to the local transfer of particles, the centralized resampling always has the lowest speedup factors because of the global transfer of particles, and the hybrid resampling attains the speedup factors between. Moreover, we define the complexity-state ratio, as the ratio between the system complexity and the system state size to study how it impacts the speedup factor. The experiments show that the higher complexity-state ratio results in the increase of the speedup factors. This is one of the earliest attempts to analyze and compare the performance of parallel/distributed particle filters with different resampling algorithms. The analysis can provide potential solutions for further performance improvements and guide the appropriate selection of the resampling algorithm for parallel/distributed particle filters.
- 30 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 19 (1) , 593-604
Predicting Local Protein 3D Structures Using Clustering Deep Recurrent Neural Network
Since protein 3D structure prediction is very important for biochemical study and drug design, researchers have developed many machine learning algorithms to predict protein 3D structures using the sequence information only. Understanding the sequence-to-structure relationship is key for the successful structure prediction. Previous approaches including the single shallow learning model, the single deep learning model and clustering algorithms all have disadvantages to understand precise sequence-to-structure relationship. In order to further improve the performance of the local protein structure prediction, a novel deep learning model called Clustering Recurrent Neural Network (CRNN) is proposed. In this model, the whole protein dataset is divided into multiple cluster subtrees. A RNN is trained for each cluster in the subtrees so that each RNN can be used to learn the computationally simpler local sequence-to-structure relationship instead of attempting to capture the global sequence-to-structure relationship. After learning the local sequence-to-structure relationship using RNN, CRNN is designed to predict distance matrices, torsion angles and secondary structures for backbone -carbon atoms of protein sequence segments. Our experimental analysis indicates that 3D structure prediction accuracy is comparable or better than other state-of-art approaches.
- 30 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 19 (1) , 593-604
Predicting Local Protein 3D Structures Using Clustering Deep Recurrent Neural Network
Since protein 3D structure prediction is very important for biochemical study and drug design, researchers have developed many machine learning algorithms to predict protein 3D structures using the sequence information only. Understanding the sequence-to-structure relationship is key for the successful structure prediction. Previous approaches including the single shallow learning model, the single deep learning model and clustering algorithms all have disadvantages to understand precise sequence-to-structure relationship. In order to further improve the performance of the local protein structure prediction, a novel deep learning model called Clustering Recurrent Neural Network (CRNN) is proposed. In this model, the whole protein dataset is divided into multiple cluster subtrees. A RNN is trained for each cluster in the subtrees so that each RNN can be used to learn the computationally simpler local sequence-to-structure relationship instead of attempting to capture the global sequence-to-structure relationship. After learning the local sequence-to-structure relationship using RNN, CRNN is designed to predict distance matrices, torsion angles and secondary structures for backbone -carbon atoms of protein sequence segments. Our experimental analysis indicates that 3D structure prediction accuracy is comparable or better than other state-of-art approaches.
- Open Access
- 20 November 2014
- Published by Tsinghua University Press in Tsinghua Science and Technology
- Vol. 19 (6) , 658-667
PBNA: An improved probabilistic biological network alignment method
Biological network alignment is an important research topic in the field of bioinformatics. Nowadays almost every existing alignment method is designed to solve the deterministic biological network alignment problem. However, it is worth noting that interactions in biological networks, like many other processes in the biological realm, are probabilistic events. Therefore, more accurate and better results can be obtained if biological networks are characterized by probabilistic graphs. This probabilistic information, however, increases difficulties in analyzing networks and only few methods can handle the probabilistic information. Therefore, in this paper, an improved Probabilistic Biological Network Alignment (PBNA) is proposed. Based on IsoRank, PBNA is able to use the probabilistic information. Furthermore, PBNA takes advantages of Contributor and Probability Generating Function (PGF) to improve the accuracy of node similarity value and reduce the computational complexity of random variables in similarity matrix. Experimental results on dataset of the Protein-Protein Interaction (PPI) networks provided by Todor demonstrate that PBNA can produce some alignment results that ignored by the deterministic methods, and produce more biologically meaningful alignment results than IsoRank does in most of the cases based on the Gene Ontology Consistency (GOC) measure. Compared with Prob method, which is designed exactly to solve the probabilistic alignment problem, PBNA can obtain more biologically meaningful mappings in less time.
- 20 November 2014
- Published by Tsinghua University Press in Tsinghua Science and Technology
- Vol. 19 (6) , 658-667
Open AccessPBNA: An improved probabilistic biological network alignment method
Biological network alignment is an important research topic in the field of bioinformatics. Nowadays almost every existing alignment method is designed to solve the deterministic biological network alignment problem. However, it is worth noting that interactions in biological networks, like many other processes in the biological realm, are probabilistic events. Therefore, more accurate and better results can be obtained if biological networks are characterized by probabilistic graphs. This probabilistic information, however, increases difficulties in analyzing networks and only few methods can handle the probabilistic information. Therefore, in this paper, an improved Probabilistic Biological Network Alignment (PBNA) is proposed. Based on IsoRank, PBNA is able to use the probabilistic information. Furthermore, PBNA takes advantages of Contributor and Probability Generating Function (PGF) to improve the accuracy of node similarity value and reduce the computational complexity of random variables in similarity matrix. Experimental results on dataset of the Protein-Protein Interaction (PPI) networks provided by Todor demonstrate that PBNA can produce some alignment results that ignored by the deterministic methods, and produce more biologically meaningful alignment results than IsoRank does in most of the cases based on the Gene Ontology Consistency (GOC) measure. Compared with Prob method, which is designed exactly to solve the probabilistic alignment problem, PBNA can obtain more biologically meaningful mappings in less time.
- Open Access
- 1 January 2014
- Published by Springer Nature in BMC Systems Biology
- Vol. 8 (Suppl 3) , S6
An novel frequent probability pattern mining algorithm based on circuit simulation method in uncertain biological networks
Motif mining has always been a hot research topic in bioinformatics. Most of current research on biological networks focuses on exact motif mining. However, due to the inevitable experimental error and noisy data, biological network data represented as the probability model could better reflect the authenticity and biological significance, therefore, it is more biological meaningful to discover probability motif in uncertain biological networks. One of the key steps in probability motif mining is frequent pattern discovery which is usually based on the possible world model having a relatively high computational complexity. In this paper, we present a novel method for detecting frequent probability patterns based on circuit simulation in the uncertain biological networks. First, the partition based efficient search is applied to the non-tree like subgraph mining where the probability of occurrence in random networks is small. Then, an algorithm of probability isomorphic based on circuit simulation is proposed. The probability isomorphic combines the analysis of circuit topology structure with related physical properties of voltage in order to evaluate the probability isomorphism between probability subgraphs. The circuit simulation based probability isomorphic can avoid using traditional possible world model. Finally, based on the algorithm of probability subgraph isomorphism, two-step hierarchical clustering method is used to cluster subgraphs, and discover frequent probability patterns from the clusters. The experiment results on data sets of the Protein-Protein Interaction (PPI) networks and the transcriptional regulatory networks of E. coli and S. cerevisiae show that the proposed method can efficiently discover the frequent probability subgraphs. The discovered subgraphs in our study contain all probability motifs reported in the experiments published in other related papers. The algorithm of probability graph isomorphism evaluation based on circuit simulation method excludes most of subgraphs which are not probability isomorphism and reduces the search space of the probability isomorphism subgraphs using the mismatch values in the node voltage set. It is an innovative way to find the frequent probability patterns, which can be efficiently applied to probability motif discovery problems in the further studies.
- 1 January 2014
- Published by Springer Nature in BMC Systems Biology
- Vol. 8 (Suppl 3) , S6
Open AccessAn novel frequent probability pattern mining algorithm based on circuit simulation method in uncertain biological networks
Motif mining has always been a hot research topic in bioinformatics. Most of current research on biological networks focuses on exact motif mining. However, due to the inevitable experimental error and noisy data, biological network data represented as the probability model could better reflect the authenticity and biological significance, therefore, it is more biological meaningful to discover probability motif in uncertain biological networks. One of the key steps in probability motif mining is frequent pattern discovery which is usually based on the possible world model having a relatively high computational complexity. In this paper, we present a novel method for detecting frequent probability patterns based on circuit simulation in the uncertain biological networks. First, the partition based efficient search is applied to the non-tree like subgraph mining where the probability of occurrence in random networks is small. Then, an algorithm of probability isomorphic based on circuit simulation is proposed. The probability isomorphic combines the analysis of circuit topology structure with related physical properties of voltage in order to evaluate the probability isomorphism between probability subgraphs. The circuit simulation based probability isomorphic can avoid using traditional possible world model. Finally, based on the algorithm of probability subgraph isomorphism, two-step hierarchical clustering method is used to cluster subgraphs, and discover frequent probability patterns from the clusters. The experiment results on data sets of the Protein-Protein Interaction (PPI) networks and the transcriptional regulatory networks of E. coli and S. cerevisiae show that the proposed method can efficiently discover the frequent probability subgraphs. The discovered subgraphs in our study contain all probability motifs reported in the experiments published in other related papers. The algorithm of probability graph isomorphism evaluation based on circuit simulation method excludes most of subgraphs which are not probability isomorphism and reduces the search space of the probability isomorphism subgraphs using the mismatch values in the node voltage set. It is an innovative way to find the frequent probability patterns, which can be efficiently applied to probability motif discovery problems in the further studies.
- Open Access
- 25 June 2012
- Published by Springer Nature in BMC Bioinformatics
- Vol. 13 (S10) , S19
Efficient and accurate greedy search methods for mining functional modules in protein interaction networks
Most computational algorithms mainly focus on detecting highly connected subgraphs in PPI networks as protein complexes but ignore their inherent organization. Furthermore, many of these algorithms are computationally expensive. However, recent analysis indicates that experimentally detected protein complexes generally contain Core/attachment structures.
- 25 June 2012
- Published by Springer Nature in BMC Bioinformatics
- Vol. 13 (S10) , S19
Open AccessEfficient and accurate greedy search methods for mining functional modules in protein interaction networks
Most computational algorithms mainly focus on detecting highly connected subgraphs in PPI networks as protein complexes but ignore their inherent organization. Furthermore, many of these algorithms are computationally expensive. However, recent analysis indicates that experimentally detected protein complexes generally contain Core/attachment structures.
- 31 January 2012
- Published by Elsevier in Expert Systems with Applications
- Vol. 39 (1) , 1474-1483
Clinical charge profiles prediction for patients diagnosed with chronic diseases using Multi-level Support Vector Machine
- 31 January 2012
- Published by Elsevier in Expert Systems with Applications
- Vol. 39 (1) , 1474-1483
Clinical charge profiles prediction for patients diagnosed with chronic diseases using Multi-level Support Vector Machine
- 1 October 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 21-26
Multiclass Fuzzy Clustering Support Vector Machines for Protein Local Structure Prediction
Local protein structure prediction is a central task in bioinformatics research. Local protein structure prediction can be transformed into the multiclass problem for huge datasets. In previous study, multiclass clustering support vector machines (CSVMs) was proposed for local protein structure prediction. The greedy algorithm is utilized to select the next closest class if CSVM modeled for the assigned class predicts the sequence segment as negative. However, the greedy algorithm may not be optimal. If all CSVM predict the sequence segment as negative, this sequence segment cannot be classified. In order to further improve performance of the multiclass problem, we propose fuzzy clustering support vector machines (FCSVMs) in this study. The FCSVMs model calculates the class membership value of the given sequence segment for each class and assigns the representative structure of the finally selected class to the sequence segment. Values of the fuzzy membership function are based on testing accuracy of decision function outputs from FCSVMs. Under this mechanism, values of different fuzzy membership functions can be compared. FCSVMs are built specifically for each class partitioned intelligently by the clustering algorithm. This feature makes learning tasks for each FCSVM more specific and simpler. Furthermore, FCSVM modeled for each class can be easily parallelized to handle the complex multiclass problems for huge datasets. Using fuzzy membership functions, all sequence segments can be classified. Compared with the conventional clustering algorithm and CSVMs, testing accuracy for local structure prediction has been improved noticeably when the FCSVMs model is applied.
- 1 October 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 21-26
Multiclass Fuzzy Clustering Support Vector Machines for Protein Local Structure Prediction
Local protein structure prediction is a central task in bioinformatics research. Local protein structure prediction can be transformed into the multiclass problem for huge datasets. In previous study, multiclass clustering support vector machines (CSVMs) was proposed for local protein structure prediction. The greedy algorithm is utilized to select the next closest class if CSVM modeled for the assigned class predicts the sequence segment as negative. However, the greedy algorithm may not be optimal. If all CSVM predict the sequence segment as negative, this sequence segment cannot be classified. In order to further improve performance of the multiclass problem, we propose fuzzy clustering support vector machines (FCSVMs) in this study. The FCSVMs model calculates the class membership value of the given sequence segment for each class and assigns the representative structure of the finally selected class to the sequence segment. Values of the fuzzy membership function are based on testing accuracy of decision function outputs from FCSVMs. Under this mechanism, values of different fuzzy membership functions can be compared. FCSVMs are built specifically for each class partitioned intelligently by the clustering algorithm. This feature makes learning tasks for each FCSVM more specific and simpler. Furthermore, FCSVM modeled for each class can be easily parallelized to handle the complex multiclass problems for huge datasets. Using fuzzy membership functions, all sequence segments can be classified. Compared with the conventional clustering algorithm and CSVMs, testing accuracy for local structure prediction has been improved noticeably when the FCSVMs model is applied.
- 1 October 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1051-1055
Mutual Information based Minimum Spanning Trees Model for Selecting Discriminative Genes
Recent studies have shown that gene selection is a crucial technology in microarray data analysis as a result of its large number of genes and relatively small number of samples. Filter methods are fast convergent algorithms with low time complexity. However, filter methods neglect correlation among genes. Other methods for gene selection also have disadvantages. For example, the measurement used to calculate the correlation in other methods can not effectively reflect function similarity among genes, the time complexity will be high based on the whole gene set. Therefore, we propose a novel selection model called mutual information based minimum spanning trees (MIMST) which considers both gene interaction and complementary genes. In this new model, we first use filter methods to remove non-relevant genes, and then compute the interdependence of top-ranked genes. Finally, we construct MST to remove the redundant genes. The experiment results show that MIMST can find the smallest siMIMSTgnificant genes subset with higher classification accuracy compared with other methods.
- 1 October 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1051-1055
Mutual Information based Minimum Spanning Trees Model for Selecting Discriminative Genes
Recent studies have shown that gene selection is a crucial technology in microarray data analysis as a result of its large number of genes and relatively small number of samples. Filter methods are fast convergent algorithms with low time complexity. However, filter methods neglect correlation among genes. Other methods for gene selection also have disadvantages. For example, the measurement used to calculate the correlation in other methods can not effectively reflect function similarity among genes, the time complexity will be high based on the whole gene set. Therefore, we propose a novel selection model called mutual information based minimum spanning trees (MIMST) which considers both gene interaction and complementary genes. In this new model, we first use filter methods to remove non-relevant genes, and then compute the interdependence of top-ranked genes. Finally, we construct MST to remove the redundant genes. The experiment results show that MIMST can find the smallest siMIMSTgnificant genes subset with higher classification accuracy compared with other methods.
- 24 February 2007
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 41 (1) , 1-16
Parallel protein secondary structure prediction schemes using Pthread and OpenMP over hyper-threading technology
- 24 February 2007
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 41 (1) , 1-16
Parallel protein secondary structure prediction schemes using Pthread and OpenMP over hyper-threading technology