检索结果-内蒙古大学图书馆

AutoFace: How to Obtain Mobile Neural Network-Based Facial Feature Extractor in Less Than 10 Minutes?

IEEE ACCESS 2024年 12卷 25106-25118页

作者： Savchenko, Andrey V. Sber AI Lab Moscow 117312 Russia HSE Univ Lab Algorithms & Technol Network Anal Nizhnii Novgorod 603155 Russia

Various mobile and edge devices have significantly different processing capabilities, making it challenging to develop a single universal architecture of a neural network to extract facial embeddings. In this paper, we study the automated machine learning techniques to design a neural network with the best performance on a concrete device. The novel procedure is proposed to choose the better subnetwork of the Supernet based on a genetic algorithm with a surrogate binary classifier to compare the expected accuracy of two subnetworks. The latter uses only encoding of a candidate subnetwork and does not require directly estimating its accuracy on a validation set. As a result, the most computationally efficient and accurate model in TensorFlow Lite format is obtained in less than 10 minutes for a specific device and latency constraint. An Android demo application has been developed to demonstrate the potential of designed neural networks. It is experimentally shown that the proposed approach is universal: it can extract deep embeddings for tasks such as face verification and facial expression recognition and for various types of devices, including smartphones and Raspberry Pi single-board mini-computers. Our models process one facial image in real-time and achieve much higher accuracy when compared to the best-known lightweight networks.

关键词： Face recognition Task analysis Training Computer architecture Feature extraction Artificial neural networks Performance evaluation Mobile communication Genetic algorithms Search methods evolutionary computation Emotion recognition Mobile applications edge devices genetic algorithms evolutionary search face verification facial expression recognition

来源：评论

学校读者我要写书评

暂无评论

A Bi-Objective evolutionary Algorithm for Multimodal Multiobjective Optimization

引用

IEEE TRANSACTIONS ON evolutionary computation 2024年第1期28卷 168-177页

作者： Wei, Zhifang Gao, Weifeng Gong, Maoguo Yen, Gary G. Xidian Univ Sch Math & Stat Xian 710126 Peoples R China Xidian Univ Int Res Ctr Intelligent Percept & Computat Key Lab Intelligent Percept & Image Understanding Minist Educ Xian 710071 Peoples R China Oklahoma State Univ Sch Elect & Comp Engn Stillwater OK 74078 USA

Multimodal multiobjective optimization problems (MMOPs) possess multiple Pareto optimal sets (PSs) corresponding to the identical Pareto optimal front (PF). To handle MMOPs, we propose a bi-objective evolutionary algorithm (BOEA), which transforms an MMOP into a bi-objective optimization problem. This problem is constructed by the penalty boundary intersection technique and a diversity indicator to obtain multiple PSs. The first objective reflects the population convergence and factors in the population diversity in the objective space, while the other objective concentrates more on the population diversity in the decision space. Furthermore, an environmental selection strategy is designed to choose the offspring solutions, which consists of nondominated sorting based on the transformed optimization problem and hierarchical clustering for selecting promising solutions. Experiments on 34 MMOPs demonstrate that BOEA performs better than selected state-of-the-art representatives, including 22 MMOPs from CEC2019 and 12 imbalanced MMOPs. In addition, the effectiveness of BOEA is further validated by six feature selection problems in real-world applications.

关键词： Optimization Convergence Pareto optimization Statistics Sociology Sorting evolutionary computation Multimodal multiobjective optimization multiobjective optimization Pareto optimal front (PF) Pareto optimal set (PS)

来源：评论

学校读者我要写书评

暂无评论

Can evolutionary Clustering Have Theoretical Guarantees?

引用

IEEE TRANSACTIONS ON evolutionary computation 2024年第5期28卷 1220-1234页

作者： Qian, Chao Nanjing Univ State Key Lab Novel Software Technol Nanjing 210023 Peoples R China

Clustering is a fundamental problem in many areas, which aims to partition a given data set into groups based on some distance measure, such that the data points in the same group are similar while that in different groups are dissimilar. Due to its importance and NP-hardness, a lot of methods have been proposed, among which evolutionary algorithms (EAs) are a class of popular ones. evolutionary clustering has found many successful applications, but all the results are empirical, lacking theoretical support. This article fills this gap by proving that the approximation performance of the global simple evolutionary multiobjective optimizer (GSEMO) (a simple multiobjective EA) for solving four formulations of clustering, i.e., k-tMM, k-center, discrete k-median, and k-means, can be theoretically guaranteed. Furthermore, we consider clustering under fairness, which tries to avoid algorithmic bias, and has recently been an important research topic in machine learning. We prove that for discrete k-median clustering under individual fairness, the approximation performance of the GSEMO can be theoretically guaranteed with respect to both the objective function and the fairness constraint.

关键词： Clustering algorithms Linear programming Partitioning algorithms evolutionary computation Data analysis Heuristic algorithms Euclidean distance Clustering discrete k-median evolutionary algorithms (EAs) fairness k-tMM k-center k-means theoretical analysis

来源：评论

学校读者我要写书评

暂无评论

Efficient Surrogate Modeling Method for evolutionary Algorithm to Solve Bilevel Optimization Problems

引用

IEEE TRANSACTIONS ON CYBERNETICS 2024年第7期54卷 4335-4347页

作者： Jiang, Hao Chou, Kang Tian, Ye Zhang, Xingyi Jin, Yaochu Anhui Univ Sch Artificial Intelligence Key Lab Intelligent Comp & Signal Proc Minist Educ Hefei 230601 Peoples R China Anhui Univ Inst Phys Sci & Informat Technol Key Lab Intelligent Comp & Signal Proc Minist Educ Hefei 230601 Peoples R China Bielefeld Univ Fac Technol Chair Nat Inspired Comp & Engn D-33619 Bielefeld Germany

The purpose of this study was to develop an evolutionary algorithm (EA) with bilevel surrogate modeling, called BL-SAEA, for tackling bilevel optimization problems (BLOPs), in which an upper level problem is to be solved subject to the optimality of a corresponding lower level problem. The motivation of this article is that the extensive lower level optimization required by each upper level solution consumes too many function evaluations, leading to poor optimization performance of EAs. To this end, during the upper level optimization, the BL-SAEA builds an upper level surrogate model to select several promising upper level solutions for the lower level optimization. Because only a small number of upper level solutions require the lower level optimization, the number of function evaluations can be considerably reduced. During the lower level optimization, the BL-SAEA constructs multiple lower level surrogate models to initialize the population of the lower level optimization, thus further decreasing the number of function evaluations. Experimental results on two widely used benchmarks and two real-world BLOPs demonstrate the superiority of our proposed algorithm over six state-of-the-art algorithms in terms of effectiveness and efficiency.

关键词： Optimization Statistics Sociology Linear programming Search problems evolutionary computation Signal processing algorithms Bilevel optimization problem (BLOP) evolutionary algorithm (EA) Kriging model surrogate model

来源：评论

学校读者我要写书评

暂无评论

Tour Multi-Route Planning With Matrix-Based Differential Evolution

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第9期25卷 11753-11767页

作者： Sun, Pei-Fa Li, Jian-Yu Li, Ming-Yu Gao, Zhan-Yang Jin, Hu Jeon, Sang-Woon Zhang, Jun Hanyang Univ Dept Elect & Elect Engn ERICA Campus Ansan 15588 South Korea Zhejiang Normal Univ Sch Comp Sci & Technol Jinhua 321017 Peoples R China Nankai Univ Tianjin 300071 Peoples R China Victoria Univ Inst Sustainable Ind & Liveable Cities ISILC Melbourne Vic 8001 Australia

Tourism is an important industry sector that requires tour companies to plan multiple routes for different tour groups, which is called tour multi-route planning. This paper focuses on tour multi-route planning, which can improve the economic benefit and allocation efficiency of tour resources. The main contributions of this paper are threefold. First, we propose a novel multiple routes planning model that captures the real-world tourism scenario and practical constraints. We also define four typical constraints for tourism planning and classify them into soft and hard constraints. Second, we develop a matrix-based differential evolution algorithm to jointly optimize multiple routes that can efficiently handle the high-dimensional optimization under various constraints. Third, we collect real-world data to construct problem instances and compare the performance of our algorithm with the conventional differential evolution algorithms in terms of runtimes. The experimental results show that our algorithm can effectively solve tour multi-route planning problems and achieve excellent runtimes performance, suitable for large-scale transportation network optimization.

关键词： Tour multiple routes planning evolutionary computation differential evolution matrix-based evolutionary computation matrix-based differential evolution

来源：评论

学校读者我要写书评

暂无评论

Adapting the population size in CMA-ES using nearest-better clustering method for multimodal optimization

引用

APPLIED SOFT COMPUTING 2024年 167卷

作者： Nguyen, Duc Manh Hanoi Natl Univ Educ 136 Xuan Thuy Hanoi Vietnam

The covariance matrix adaptation evolution strategy (CMA-ES) is one of the advanced algorithms for solving continuous single-objective optimization. In this algorithm, the population size is an important parameter which represents the number of candidate points generated in each iteration. A larger population size allows for better exploration of the search space and is typically required for handling multimodal functions, while a smaller population size facilitates quicker convergence. Adapting the population size in this algorithm raises a question about how to increase/decrease/keep it in an efficient way to solve specific problems. In this paper, we propose a novel approach for this purpose based on the information of niches observed during the evolution process. Firstly, the nearest-better clustering (NBC) technique is employed to detect the number of niches in each iteration, then the information will be used to adapt the population size accordingly. Additionally, a quasi-Newton method, which serves as a local search, can be incorporated into the algorithm in order to speed it up. We evaluate the effectiveness of our method through numerical simulations on multimodal test functions, the black-box optimization benchmarking (BBOB) noiseless testbed, and the CEC 2014 and CEC 2017 benchmark testing suites.

关键词： evolutionary computation CMA-ES Black-box optimization Nearest-better clustering Population size adaptation Multimodal functions

来源：评论

学校读者我要写书评

暂无评论

Face recognition for human identification through integration of complex domain unsupervised and supervised frameworks

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第5期83卷 14085-14109页

作者： Srivastava, Swati Sharma, Himanshu GLA Univ Dept Comp Engn & Applicat Mathura India

Human identification can be performed through various available biometric traits such as the face, iris, fingerprint, ECG, gait, and ear. Among them, face is one of the most popular and widely used biometrics. In the security domain, early warnings and the trace of suspects can be accomplished using face recognition. The contemplated augmentation projected an intelligent computational model for human recognition which is an ingenious melding of unsupervised outline and complex domain neurocomputing. The unsupervised framework of our proposal constitutes evolutionary fuzzy computations in complex domain. The supervised schema capitalizes on a complex domain neural network with higher-order neurons and resilient propagation algorithm. Trainable multiple stages are populated in this proposal for the estimation of recognition and classification. This proposal offers an intelligent performance on recognition and classification tasks. Comprehensive experimental analysis on the datasets of AR face, PubFig83, and Indian face evidenced the enhanced precision of the proposed model. Our model achieves an impressive accuracy range of 97% to 99% across all datasets. These results clearly demonstrate the superior performance of our approach, showcasing the dominance of the combined unsupervised and supervised frameworks over other state-of-the-art methods.

关键词： Supervised Unsupervised Face recognition Human identification Complex domain Neural network Fuzzy clustering evolutionary computation

来源：评论

学校读者我要写书评

暂无评论

Reputation-Based Interaction Promotes Cooperation With Reinforcement Learning

引用

IEEE TRANSACTIONS ON evolutionary computation 2024年第4期28卷 1177-1188页

作者： Ren, Tianyu Zeng, Xiao-Jun Univ Manchester Dept Comp Sci Manchester M13 9PL England

Dynamical interaction represents a fundamental coevolutionary rule that addresses the intricacies of cooperation in social dilemmas. It provides a normative account for the changes in ties within interaction networks in response to the behavior of social partners. While considerable efforts have explored the role of partner selection in fostering cooperation, there remains a limited understanding of how agents learn to establish effective interaction patterns and adapt their connections accordingly. To bridge this knowledge gap, we leverage recent advancements in reinforcement learning (RL) and propose an adaptive interaction mechanism to investigate self-organization behavior in the iterated prisoner's dilemma game. Within this framework, artificial agents are trained using a self-regarding Roth-Erev algorithm, utilizing reputation as a dynamic signal to update their willingness to engage with neighbors. Additionally, these agents are endowed with the capability to sever inactive connections. Simulation results demonstrate the effectiveness of utilizing RL and local information from reputation to capture the dynamics of interactions. Notably, we discover that the entangled coevolution of strategy and interaction network can facilitate the emergence and maintenance of cooperation, despite the optimal tolerance threshold for ineffective neighbors varying depending on the strength of the social dilemma. Furthermore, the emerging network topology presented in this work accurately captures the assortative mixing pattern observed in previous experiments and realistic evidence. Finally, we validate the simulation results through theoretical analysis and confirm the robustness of the proposed mechanism across populations of varying sizes and initial structures.

关键词： Games Statistics Sociology Heuristic algorithms Simulation Task analysis Intelligent agents Computer simulation evolutionary computation intelligent agents multiagent systems nonlinear network analysis

来源：评论

学校读者我要写书评

暂无评论

Solving multi-objective robust optimization problems via Stakelberg-based game model

引用

SWARM AND evolutionary computation 2024年 91卷

作者： Salih, Adham Matalon, Erella Eisenstadt Braude Coll Engn Dept Mech Engn Karmiel Israel

Real-world multi-objective engineering problems frequently involve uncertainties stemming from environmental factors, production inaccuracies, and other sources. A critical aspect of addressing these problems, termed Multi-Objective Robust Optimization (MORO) problems, is the development of solutions that are both optimal and resilient to uncertainties. This paper proposes addressing these uncertainties through the application of Stackelberg game models, a novel approach involving the interaction of two players. The Leader searches for optimal and robust solutions and the Follower generates uncertainties based on the Leader's chosen solutions. The Follower seeks to tackle the most challenging uncertainties associated with the Leader's candidate solutions. Additionally, this paper introduces a novel metric to assess the robustness of a given set of solutions concerning specified uncertainties. Based on the proposed approach, a co-evolutionary algorithm is developed. A numerical study is then conducted to evaluate the algorithm by comparing its performance with those obtained by four benchmark algorithms on nine benchmark MORO problems. The numerical study also aims to assess its sensitivity to run parameter variations. The experimental results demonstrate the proposed approach's effectiveness in identifying a non-dominated robust set of solutions.

关键词： Robust multi-objective optimization Multi-objective games Stacklberg game model Pareto-optimality evolutionary computation Co-evolutionary algorithms Uncertainty

来源：评论

学校读者我要写书评

暂无评论

Double-Closed-Loop Robust Optimal Control for Uncertain Nonlinear Systems

引用

IEEE TRANSACTIONS ON CYBERNETICS 2024年第4期54卷 2332-2344页

作者： Han, Honggui Zhang, Jiacheng Hou, Ying Qiao, Junfei Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China Beijing Univ Technol Beijing Key Lab Computat Intelligence & Intelligen Beijing 100124 Peoples R China

Optimal control methods have gained significant attention due to their promising performance in nonlinear systems. In general, an optimal control method is regarded as an optimization process for solving the optimal control laws. However, for uncertain nonlinear systems with complex optimization objectives, the solving of optimal reference trajectories is difficult and significant that might be ignored to obtain robust performance. For this problem, a double-closed-loop robust optimal control (DCL-ROC) is proposed to maintain the optimal control reliability of uncertain nonlinear systems. First, a double-closed-loop scheme is established to divide the optimal control process into a closed-loop optimization process that solves optimal reference trajectories and a closed-loop control process that solves optimal control laws. Then, the ability of the optimal control method can be improved to solve complex uncertain optimization problems. Second, a closed-loop robust optimization (CL-RO) algorithm is developed to express uncertain optimization objectives as data-driven forms and adjust optimal reference trajectories in a close loop. Then, the optimality of reference trajectories can be improved under uncertainties. Third, the optimal reference trajectories are tracked by an adaptive controller to derive the optimal control laws without certain system dynamics. Then, the adaptivity and reliability of optimal control laws can be improved. The experimental results demonstrate that the proposed method can achieve better performance than other optimal control methods.

关键词： Optimization Optimal control Trajectory Process control Nonlinear systems Uncertainty Robustness Adaptive control evolutionary computation optimal control robust optimization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：