Frontiers of Information Technology & Electronic Engineering最新文献

An attack-resilient distributed extended Kalman consensus filtering algorithm with applications to multi-UAV tracking problems 抗攻击分布式扩展卡尔曼共识滤波算法，应用于多无人机跟踪问题

Frontiers of Information Technology & Electronic Engineering Pub Date : 2024-08-08 DOI: 10.1631/fitee.2300621

Yuru Hu, Wangyan Li, Lifeng Wu, Zhensheng Yu

引用次数: 0

Sora for foundation robots with parallel intelligence: three world models, three robotic systems 具有并行智能的基础机器人 Sora：三个世界模型，三个机器人系统

Frontiers of Information Technology & Electronic Engineering Pub Date : 2024-04-22 DOI: 10.1631/fitee.2400144

Lili Fan, Chao Guo, Yonglin Tian, Hui Zhang, Jun Zhang, Fei-Yue Wang

引用次数: 1

The engineering of circular causality for specialization and design of complex systems: cad2CAS and casCAD2 用于复杂系统专业化和设计的循环因果关系工程：cad2CAS 和 casCAD2

Frontiers of Information Technology & Electronic Engineering Pub Date : 2023-12-15 DOI: 10.1631/fitee.2300443

Xiaolong Liang, Rui Qin, Juanjuan Li, Fei-Yue Wang

引用次数: 0

A hybrid-model optimization algorithm based on the Gaussian process and particle swarm optimization for mixed-variable CNN hyperparameter automatic search 一种基于高斯过程和粒子群优化的混合模型优化算法用于混合变量CNN超参数自动搜索

Frontiers of Information Technology & Electronic Engineering Pub Date : 2023-09-07 DOI: 10.1631/fitee.2200515

Han Yan, Chongquan Zhong, Yuhu Wu, Liyong Zhang, Wei Lu

{"title":"A hybrid-model optimization algorithm based on the Gaussian process and particle swarm optimization for mixed-variable CNN hyperparameter automatic search","authors":"Han Yan, Chongquan Zhong, Yuhu Wu, Liyong Zhang, Wei Lu","doi":"10.1631/fitee.2200515","DOIUrl":"https://doi.org/10.1631/fitee.2200515","url":null,"abstract":": Convolutional neural networks (CNNs) have developed quickly in many real-word fields. However, a CNN’s performance heavily depends on its hyperparameters, and finding suitable hyperparameters for CNNs working in application fields is challenging for three reasons: (1) the problem of mixed-variable encoding for different types hyperparameters in CNNs; (2) expensive computational costs in evaluating candidate hyperparameters configuration; and (3) the problem of ensuring convergence rates and model performance during hyperparameters searching. To overcome these problems and challenges, a hybrid-model optimization algorithm (OA) is proposed in this paper to search suitable hyperparameters configurations automatically based on the Gaussian process (GP) and the particle swarm optimization (PSO) algorithm (GPPSO). First, a new encoding method is designed to efficiently deal with the CNN hyperparameter mixed-variable problem. Second, a hybrid-surrogate-assisted (HSA) model is proposed to reduce the high cost of evaluating candidate hyperparameters configuration. Third, a novel activate function is suggested to improve the model performance and ensure the convergence rate. Intensive experiments are performed on image-classification benchmark datasets to demonstrate the superior performance of GPPSO over the state-of-the-art (SOTA) methods. Moreover, a case study on metal fracture (MF) diagnosis is carried out to evaluate the GPPSO algorithm performance in practical applications. Experiment results demonstrate the effectiveness and efficiency of GPPSO, which achieves accuracy of 95.26% and 76.36% only through 0.04 and 1.70 GPU days on the CIFAR10 and CIFAR100 datasets, respectively.","PeriodicalId":430963,"journal":{"name":"Frontiers of Information Technology & Electronic Engineering","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115133788","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Parallel intelligent education with ChatGPT ChatGPT并行智能教育

Frontiers of Information Technology & Electronic Engineering Pub Date : 2023-06-08 DOI: 10.1631/fitee.2300166

Jiacun Wang, Ying Tang, Ryan Hare, Feiyue Wang

引用次数: 0

Erratum to: Depth estimation using an improved stereo network 勘误:使用改进的立体网络进行深度估计

Frontiers of Information Technology & Electronic Engineering Pub Date : 2023-04-04 DOI: 10.1631/fitee.20e0676

Wanpeng Xu, Ling Zou, Lingda Wu, Yue Qi, Zhaoyong Qian

引用次数: 0

ChatGPT: potential, prospects, and limitations ChatGPT:潜力、前景和局限性

Frontiers of Information Technology & Electronic Engineering Pub Date : 2023-02-28 DOI: 10.1631/fitee.2300089

Jie Zhou, Pei Ke, Xipeng Qiu, Minlie Huang, Junping Zhang