检索结果-南通市图书馆

Optimization methods for regularization-based ill-posed problems： a survey and a multi-objective framework

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2017年第3期11卷 362-391页

作者： maoguo gong Xiangming JIANG Hao LI Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Xi'an 710071 China

Ill-posed problems are widely existed in signat processing. In this paper, we review popular regularization models such as truncated singular value decomposi- tion regularization, iterative regularization, variational regularizafion. Meanwhile, we also retrospect popular optimiza- tion approaches and regularization parameter choice meth- ods. In fact, the regularization problem is inherently a multi- objective problem. The traditional methods usually combine the fidelity term and the regularization term into a single- objective with regularization parameters, which are difficult to tune. Therefore, we propose a multi-objective framework for ill-posed problems, which can handle complex features of problem such as non-convexity, discontinuity. In this framework, the fidelity term and regularization term are optimized simultaneously to gain more insights into the ill-posed prob- lems. A case study on signal recovery shows the effectiveness of the multi-objective framework for ill-posed problems.

关键词： ill-posed problem regularization multi- objective optimization evolutionary algorithm signal processing

Two-phase clustering algorithm with density exploring distance measure

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2018年第1期3卷 59-64页

作者： Jingjing Ma Xiangming Jiang maoguo gong Key Lab of Intelligent Perception and Image Understanding of Ministry of Education of China Xidian University PO Box 224 Xi'an 710071People's Republic of China

Here, the authors propose a novel two-phase clustering algorithm with a density exploring distance （DED） measure. In the first phase, the fast global K-means clustering algorithm is used to obtain the cluster number and the prototypes. Then, the prototypes of all these clusters and representatives of points belonging to these clusters are regarded as the input data set of the second phase. Afterwards, all the prototypes are clustered according to a DED measure which makes data points locating in the same structure to possess high similarity with each other. In experimental studies, the authors test the proposed algorithm on seven artificial as well as seven UCI data sets. The results demonstrate that the proposed algorithm is flexible to different data distributions and has a stronger ability in clustering data sets with complex non-convex distribution when compared with the comparison algorithms.

关键词：密度探索距离聚类算法计算方法人工智能

BA-GNN: Behavior-aware graph neural network for session-based recommendation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2023年第6期17卷 135-144页

作者： Yongquan LIANG Qiuyu SONG Zhongying ZHAO Hui ZHOU maoguo gong School of Computer Science and Engineering Shandong University of Science and TechnologyQingdao 266590China School of Electronic Engineering Xidian UniversityXi’an 710071China

Session-based recommendation is a popular research topic that aims to predict users’next possible interactive item by exploiting anonymous *** existing studies mainly focus on making predictions by considering users’single interactive *** recent efforts have been made to exploit multiple interactive behaviors,but they generally ignore the influences of different interactive behaviors and the noise in interactive *** address these problems,we propose a behavior-aware graph neural network for session-based ***,different interactive sequences are modeled as directed ***,the item representations are learned via graph neural ***,a sparse self-attention module is designed to remove the noise in behavior ***,the representations of different behavior sequences are aggregated with the gating mechanism to obtain the session *** results on two public datasets show that our proposed method outperforms all competitive *** source code is available at the website of GitHub.

关键词： session-based recommendation multiple interactive behaviors graph neural networks

Optimal approximation of linear systems by artificial immune response

在线全文

学校读者我要写书评

暂无评论

Science in China(Series F) 2006年第1期49卷 63-79页

作者： gong maoguo DU Haifeng JIAO Licheng Institute of Intelligent Information Processing and Key Laboratory of Radar Signal Processing Xidian University Xi'an 710071 China School of Mechanical Engineering Xi'an Jiaotong University Xi'an 710049 China

This paper puts forward a novel artificial immune response algorithm for optimal approximation of linear systems. A quaternion model of artificial immune response is proposed for engineering computing. The model abstracts four elements, namely, antigen, antibody, reaction rules among antibodies, and driving algorithm describing how the rules are applied to antibodies, to simulate the process of immune response. Some reaction rules including clonal selection rules, immunological memory rules and immune regulation rules are introduced. Using the theorem of Markov chain, it is proofed that the new model is convergent. The experimental study on the optimal approximation of a stable linear system and an unstable one show that the approximate models searched by the new model have better performance indices than those obtained by some existing algorithms including the differential evolution algorithm and the multi-agent genetic algorithm.

关键词： approximation of linear systems artificial immune systems immune response clonal selection,immunological memory

A memetic algorithm based on hyper-heuristics for examination timetabling problems

在线全文

学校读者我要写书评

暂无评论

International Journal of Intelligent Computing and Cybernetics 2015年第2期8卷 139-151页

作者： Yu Lei maoguo gong Licheng Jiao Yi Zuo Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education International Research Center for Intelligent Perception and ComputationXidian UniversityXi’anChina

Purpose–The examination timetabling problem is an NP-hard problem.A large number of approaches for this problem are developed to find more appropriate search ***-heuristic is a kind of representative *** hyper-heuristic,the high-level search is executed to construct heuristic lists by traditional methods(such as Tabu search,variable neighborhoods and so on).The purpose of this paper is to apply the evolutionary strategy instead of traditional methods for high-level search to improve the capability of global ***/methodology/approach–This paper combines hyper-heuristic with evolutionary strategy to solve examination timetabling ***,four graph coloring heuristics are employed to construct heuristic *** the evolutionary algorithm framework,the iterative initialization is utilized to improve the number of feasible solutions in the population;meanwhile,the crossover and mutation operators are applied to find potential heuristic lists in the heuristic space(high-level search).At last,two local search methods are combined to optimize the feasible solutions in the solution space(low-level search).Findings–Experimental results demonstrate that the proposed approach obtains competitive results and outperforms the compared approaches on some benchmark ***/value–The contribution of this paper is the development of a framework which combines evolutionary algorithm and hyper-heuristic for examination timetabling problems.

关键词： Evolutionary computation Examination timetabling problem Hyper-heuristic Memetic algorithm

Federated Collaborative Graph Neural Networks for Few-shot Graph Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第6期21卷 1077-1091页

作者： Yu Xie Yanfeng Liang Chao Wen A.K.Qin maoguo gong School of Computer and Information Technology Shanxi UniversityTaiyuan030000China Key Laboratory of Collaborative Intelligence Systems of Ministry of Education Xidian UniversityXi’an710071China Department of Computer Science and Software Engineering Swinburne University of TechnologyMelbourne3000Australia

Graph neural networks(GNNs)have achieved state-of-the-art performance on graph classification tasks,which aim to pre-dict the class labels of entire graphs and have widespread ***,existing GNN based methods for graph classification are data-hungry and ignore the fact that labeling graph examples is extremely expensive due to the intrinsic *** import-antly,real-world graph data are often scattered in different *** by these observations,this article presents federated collaborative graph neural networks for few-shot graph classification,termed *** its owned graph examples,each client first trains two branches to collaboratively characterize each graph from different views and obtains a high-quality local few-shot graph learn-ing model that can generalize to novel categories not seen while *** each branch,initial graph embeddings are extracted by any GNN and the relation information among graph examples is incorporated to produce refined graph representations via relation aggrega-tion layers for few-shot graph classification,which can reduce over-fitting while learning with scarce labeled graph ***,multiple clients owning graph data unitedly train the few-shot graph classification models with better generalization ability and effect-ively tackle the graph data island *** experimental results on few-shot graph classification benchmarks demonstrate the ef-fectiveness and superiority of our proposed framework.

关键词： Graph neural networks federated learning collaborative learning few-shot learning graph classification

Adaptive chaos clonal evolutionary programming algorithm

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science in China(Series F) 2005年第5期48卷 579-595页

作者： DU Haifeng gong maoguo LIU Ruochen JIAO Licheng Institute of Intelligent Information Processing and Key Laboratory of Radar Signal Processing XidianUniversity Xi'an 710071 China School of Mechanical Engineering Xi'an Jiaotong University Xi'an 710049 China

Based on the chaos movement and the clonal selection theory, a novel artificial immune system algorithm, Adaptive Chaos Clonal Evolutionary Programming Algorithm （ACCEP）, is proposed in this paper. The new algorithm uses the Logistic Sequence to control the mutation scale and uses the Chaos Mutation Operator to control the clonal selection. Compared with SGA and Clonal Selection Algorithm, ACCEP can enhance the precision and stability, avoid prematurity to some extent, and have the high convergence speed. The results of the experiment indicate that ACCEP has the capability to solve complex machine learning tasks, like Multimodal Function Optimization.

关键词： chaos clonal selection evolutionary algorithms

Multiobjective optimization using an immunodominance and clonal selection inspired algorithm

在线全文

学校读者我要写书评

暂无评论

Science in China(Series F) 2008年第8期51卷 1064-1082页

作者： gong maoguo JIAO LiCheng MA WenPing DU HaiFeng Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi'an 710071 China School of Public and Administration Xi'an Jiaotong University Xi'an 710049 China

Based on the mechanisms of immunodominance and clonal selection theory, we propose a new multiobjective optimization algorithm, immune dominance clonal multiobjective algorithm （IDCMA）. IDCMA is unique in that its fitness values of current dominated individuals are assigned as the values of a custom distance measure, termed as Ab-Ab affinity, between the dominated individuals and one of the nondominated individuals found so far. According to the values of Ab-Ab affinity, all dominated individuals （antibodies） are divided into two kinds, subdominant antibodies and cryptic antibodies. Moreover, local search only applies to the subdominant antibodies, while the cryptic antibodies are redundant and have no function during local search, but they can become subdominant （active） antibodies during the subsequent evolution. Furthermore, a new immune operation, clonal proliferation is provided to enhance local search. Using the clonal proliferation operation, IDCMA reproduces individuals and selects their improved maturated progenies after local search, so single individuals can exploit their surrounding space effectively and the newcomers yield a broader exploration of the search space. The performance comparison of IDCMA with MISA, NSGA-Ⅱ, SPEA, PAES, NSGA, VEGA, NPGA, and HLGA in solving six well-known multiobjective function optimization problems and nine multiobjective 0/1 knapsack problems shows that IDCMA has a good performance in converging to approximate Pareto-optimal fronts with a good distribution.

关键词： multiobjective optimization immunodominance clonal selection artificial immune systems evolutionaryalgorithms

Guest Editorial:Advances in Bio-inspired Heuristics for Computing

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2019年第3期4卷 127-128页

作者： XINCHAO ZHAO maoguo gong XINGQUAN ZUO LINQIANG PAN School of Science Beijing University of Posts and TelecommunicationsBeijing 100876PR China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian UniversityXi’an 710071PR China School of Computer Science Beijing University of Posts and TelecommunicationsBeijing 100876PR China Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of AutomationHuazhong University of Science and TechnologyWuhan 430074PR China

Bio-inspired computing (BIC), short for biologically inspired computing, is a field of study that loosely knits together subfields related to the topics of connectionism, social behaviour and emergence. The field of bio-inspired computing brings together researchers from many disciplines, including biology, computer science, mathematics, physics and genetics.

关键词： Guest Editorial Advances Bio-inspired Heuristics Computing