Article
Computer Science, Information Systems
Jing Jiang, Fei Han, Jie Wang, Qinghua Ling, Henry Han, Zizhu Fan
Summary: This paper proposes a novel decomposition-based MOEA that considers the ideal point as the global reference point and the nadir point as conditionally the local reference point to improve search diversity. The study shows that the nadir point may aid the ideal point in some cases and be redundant in others.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
A. C. Ramesh, G. Srivatsun
Summary: Overlap community detection in complex networks, such as social, biological, economic, and other real-world networks, has become an important research area in the past two decades. The community detection problem can be modeled as a multiobjective optimization problem and has been successfully solved using Evolutionary Algorithms (EA). A clique-based representation scheme is suitable for representing overlapping communities, but there are issues with heavy overlap and increased representation length. This paper proposed a merged-maximal-clique based representation scheme which reduces chromosome length and improves the efficiency of the EA for overlapping community detection.
APPLIED SOFT COMPUTING
(2021)
Article
Geochemistry & Geophysics
Xiaohua Xu, Zhanghai Ju, Jia Luo
Summary: In this simulation study, operational GNSS satellites are used for global navigation satellite system reflectometry (GNSS-R) measurement. Different constellations of satellites are designed and optimized using multiobjective evolutionary algorithms. The optimal constellations show similar performance in terms of coverage and revisited coverage with specific inclinations and orbital altitudes.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Artificial Intelligence
Qiuyue Liu, Juan Zou, Shengxiang Yang, Jinhua Zheng
Summary: This paper proposes a new decision variable classification method for multiobjective evolutionary algorithms by analyzing the monotonicities of objectives. Based on this method, a new directional crossover method is designed for generating promising solutions. The paper also introduces an interval mapping strategy for obtaining solutions with good diversity. Experimental results demonstrate that the proposed algorithm has high competitiveness in dealing with many-objective optimization problems.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Hardware & Architecture
Wei Li, Junqing Yuan, Lei Wang
Summary: This paper proposes an enhanced multiobjective evolutionary algorithm, MOEA/D-ANED, with adaptive neighborhood operator and extended distance-based environmental selection to solve many-objective optimization problems. Experimental results show that the proposed algorithm is competitive compared to eight state-of-the-art multiobjective optimization algorithms.
JOURNAL OF SUPERCOMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Yatong Chang, Wenjian Luo, Xin Lin, Zhen Song, Carlos A. Coello Coello
Summary: This paper proposes the definition of the biparty multiobjective optimal power flow (BPMOOPF) problem and introduces a novel evolutionary biparty multiobjective optimization algorithm (BPMOOPF-EA) to solve the problem. Experimental results show that BPMOOPF-EA outperforms other algorithms in solving the MOOPF problem.
APPLIED SOFT COMPUTING
(2023)
Article
Mathematics, Interdisciplinary Applications
Wenbo Qiu, Jianghan Zhu, Huangchao Yu, Mingfeng Fan, Lisu Huo
Summary: This paper aims to improve a decomposition-based algorithm by designing an adaptive reference vector adjustment strategy. An improved angle-penalized distance (APD) method is developed to better distinguish solutions with sound convergence performance in each subspace.
Article
Computer Science, Artificial Intelligence
Xujian Wang, Fenggan Zhang, Minli Yao
Summary: To handle the inconsistency between reference vectors (RVs) distribution and Pareto front shape in decomposition based multi-objective evolutionary algorithms, researchers have proposed various methods to adjust RVs during the evolutionary process. However, most existing algorithms adjust RVs either in each generation or at a fixed frequency without considering the evolving information of the population. To tackle this issue, the proposed MBRA algorithm adjusts RVs periodically and conditionally based on the improvement rate of convergence degree of subproblems computed through d(1) distance. Extensive experiments validate the effectiveness and competitiveness of MBRA on many-objective optimization problems, especially those with irregular Pareto fronts.
COMPLEX & INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Guangyuan Liu, Yangyang Li, Licheng Jiao, Yanqiao Chen, Ronghua Shang
Summary: This study introduces a new approach using a multiobjective evolutionary algorithm assisted stacked autoencoder for PolSAR image classification, which can adaptively optimize parameters and hyperparameters to achieve competitive results.
SWARM AND EVOLUTIONARY COMPUTATION
(2021)
Article
Computer Science, Artificial Intelligence
Meriem Hemici, Djaafar Zouache
Summary: This paper proposes a new multi-objective evolutionary algorithm called MP-MOEA, which is based on multi-population, to solve the multi-objective constrained portfolio optimization problem in finance. By using a multi-population strategy and two types of archives, the algorithm improves solution quality, accelerates convergence, and demonstrates superior performance in experiments.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Computer Science, Artificial Intelligence
Tingyang Wei, Jinghui Zhong
Summary: Researchers have proposed a Generalized Resource Allocation (GRA) framework to dynamically allocate computational resources, enhancing the performance of multi-objective EMTO algorithms. By designing a normalized attainment function, multi-step nonlinear regression, and flexible adjustment of resource allocation intensity, the framework has shown success in various domains.
IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE
(2021)
Article
Computer Science, Artificial Intelligence
Meriem Hemici, Djaafar Zouache, Boualem Brahmi, Adel Got, Habiba Drias
Summary: The outbreak of the COVID-19 epidemic has caused an increase in emergency calls, posing significant issues for emergency medical services centers worldwide. This paper presents an enhanced MOEA/D algorithm, utilizing simulated annealing to address real-time ambulance dispatching and relocation problems, showcasing superior performance compared to other state-of-the-art algorithms.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Information Systems
Yuan Liu, Yikun Hu, Ningbo Zhu, Kenli Li, Juan Zou, Miqing Li
Summary: Recently, decomposition-based multiobjective evolutionary algorithms (DMEAs) have become more prevalent than other patterns for solving multiobjective optimization problems. A DMEA with weights updated adaptively (DMEA-WUA) has been developed for problems regarding various Pareto fronts to improve efficiency. The algorithm is suitable for solving problems with various Pareto fronts, including those with regular and irregular shapes.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Bai Yan, Qi Zhao, Jin Zhang, J. Andrew Zhang, Xin Yao
Summary: This paper proposes a novel idea of simultaneous source number identification and DOA estimation, utilizing a multiobjective off-grid DOA estimation model. The method accurately exploits the source number using the l(0) norm of impinging signals, and a multiobjective bilevel evolutionary algorithm is designed to solve the model efficiently with a forward search strategy.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Alvaro Rubio-Largo, Nuria Lozano-Garcia, Jose M. Granado-Criado, Miguel A. Vega-Rodriguez
Summary: This paper introduces eM2dRNAs, an enhanced version of the m2dRNAs approach, to improve the RNA inverse folding problem. The comparative study against several published methods using the Eterna100 benchmark shows that eM2dRNAs outperforms other methods and achieves the objective of improving the ability to solve the RNA inverse folding problem.
APPLIED SOFT COMPUTING
(2023)
Article
Biochemical Research Methods
Xinyu Yu, Likun Jiang, Shuting Jin, Xiangxiang Zeng, Xiangrong Liu
Summary: The interaction between microRNA and long non-coding RNA plays a crucial role in biological processes. A new deep learning model, preMLI, based on rna2vec pre-training and deep feature mining mechanism, is proposed to predict the interaction. The model outperforms existing methods on benchmark datasets and demonstrates cross-species prediction capabilities.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Yajie Meng, Changcheng Lu, Min Jin, Junlin Xu, Xiangxiang Zeng, Jialiang Yang
Summary: In this study, a novel neural collaborative filtering approach is proposed for drug repositioning, which utilizes deep-learning approaches based on a heterogeneous network. The approach takes advantage of localized information in different networks and models the complex drug-disease associations effectively. The effectiveness of the approach is verified through benchmarking comparisons and validated against clinical trials and authoritative databases.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Bosheng Song, Xiaoyan Luo, Xiaoli Luo, Yuansheng Liu, Zhangming Niu, Xiangxiang Zeng
Summary: The spatial structures of proteins are important for their functions, but the limited quantity of known protein structures restricts their application in prediction methods. Utilizing predicted protein structure information can improve sequence-based prediction methods. TAGPPI is a novel framework that uses only protein sequences to predict protein-protein interactions and extracts spatial structure information from contact maps to improve prediction performance.
BRIEFINGS IN BIOINFORMATICS
(2022)
Review
Biochemical Research Methods
Yue Liu, Junfeng Zhang, Shulin Wang, Xiangxiang Zeng, Wei Zhang
Summary: The progress of single-cell sequencing technology has allowed researchers to study cell development and differentiation processes at a single-cell level. This paper focuses on the inference of dropout events in single-cell ATAC-seq data, which is currently lacking specific methods. The authors selected several state-of-the-art scRNA-seq imputation methods and systematically evaluated their performance through various downstream analyses. The results indicated that MAGIC performed consistently better than the other methods across different assessments.
BRIEFINGS IN BIOINFORMATICS
(2022)
Review
Biochemical Research Methods
Jingxin Dong, Mingyi Zhao, Yuansheng Liu, Yansen Su, Xiangxiang Zeng
Summary: This review comprehensively summarizes the development process of retrosynthesis in the context of deep learning, covering aspects such as datasets, models, and tools. Representative models from academia and available platforms in the industry are discussed. The review also addresses the limitations of existing models and provides potential future trends for beginners to understand and participate in retrosynthesis planning.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemistry & Molecular Biology
Xiangxiang Zeng, Xinqi Tu, Yuansheng Liu, Xiangzheng Fu, Yansen Su
Summary: In this review, knowledge graph-based works for drug repurposing and adverse drug reaction prediction in drug discovery are summarized. The graph provides both structured and unstructured relations, while knowledge representation learning is a common approach to explore knowledge graphs.
CURRENT OPINION IN STRUCTURAL BIOLOGY
(2022)
Editorial Material
Genetics & Heredity
Pan Zheng, Shudong Wang, Xun Wang, Xiangxiang Zeng
FRONTIERS IN GENETICS
(2022)
Article
Biochemical Research Methods
Yun Zuo, Yue Hong, Xiangxiang Zeng, Qiang Zhang, Xiangrong Liu
Summary: A multi-label computational model, MLysPRED, has been proposed to identify multiple lysine sites in proteins, showing promising prediction performance on independent datasets.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Computer Science, Information Systems
Chunyan Li, Wei Wei, Jin Li, Junfeng Yao, Xiangxiang Zeng, Zhihan Lv
Summary: Studying deep learning-based molecular representation is significant for predicting molecular property, drug screening, and drug discovery. Most methods ignore the 3D topological structure of molecules, while our 3DMol-Net provides better molecular representation for predicting molecular properties and biochemical activities.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2022)
Article
Chemistry, Multidisciplinary
Fang Wu, Shuting Jin, Yinghui Jiang, Xurui Jin, Bowen Tang, Zhangming Niu, Xiangrong Liu, Qiang Zhang, Xiangxiang Zeng, Stan Z. Li
Summary: The study introduces a spatial-temporal pre-training method based on modified equivariant graph matching networks to capture flexibility information inside molecular dynamics trajectories, leading to significant improvements in solving binding affinity and ligand efficacy problems.
Article
Biochemical Research Methods
Yanyan Li, Bosheng Song, Xiangxiang Zeng
Summary: The article introduces neural-like P systems with plasmids (NP P systems) which are inspired by bacteria's DNA processing. It also presents NPMC P systems, which use multiple channels for communication between bacteria and explores their computation power.
IEEE TRANSACTIONS ON NANOBIOSCIENCE
(2023)
Article
Biochemical Research Methods
Xixi Yang, Zhangming Niu, Yuansheng Liu, Bosheng Song, Weiqiang Lu, Li Zeng, Xiangxiang Zeng
Summary: Prediction of drug-target affinity is crucial in drug discovery. Existing deep learning methods focus on single modality inputs, while our proposed Modality-DTA leverages the multimodality of drugs and targets for better prediction performance. Experimental results demonstrate the superiority of Modality-DTA over existing methods in all metrics.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2023)
Article
Biochemical Research Methods
Xuan Lin, Zhe Quan, Zhi-Jie Wang, Yan Guo, Xiangxiang Zeng, Philip S. S. Yu
Summary: Effectively identifying compound-protein interactions (CPIs) is crucial for new drug design. We propose a deep learning framework named GraphCPI, which captures the structural information of compounds and leverages the chemical context of protein sequences. Our method shows competitiveness and feasibility in extensive experiments based on widely-used CPI datasets.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2023)
Article
Automation & Control Systems
Ying Xu, Chong Xu, Huan Zhang, Lei Huang, Yiping Liu, Yusuke Nojima, Xiangxiang Zeng
Summary: This article proposes a new metric to calculate the contribution of each decision variable to the optimization objectives, and based on this, a multiobjective evolutionary algorithm called DVCOEA is introduced. The experimental results show that DVCOEA is a competitive approach for solving large-scale multi/many-objective problems.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Biochemical Research Methods
Hao Jiang, Fei Zhan, Congtao Wang, Jianfeng Qiu, Yansen Su, Chunhou Zheng, Xingyi Zhang, Xiangxiang Zeng
Summary: This paper proposes a novel link-driven label propagation algorithm (LLPA) to identify functional modules in protein-protein interaction (PPI) networks. LLPA outperforms other state-of-the-art detection algorithms in terms of accuracy and robustness.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2022)