In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) has been redirecting to new domain since Jan. 1st, 2025.
See More
App. Res. of Comp. Accepted Paper
Vol. 42, 2025 No. 7

Combined non-linearity convolution kernel: strong robust CNN design method based on IoT

Chai Zhi1
Ding Chuntao2
Guo Hui1
Zhang Junna1
1. College of Computer & Information Engineering, Henan Normal University, Xinxiang Henan 453007, China
2. College of Artificial Intelligence, Beijing Normal University, Beijing 100875, China
DOI: 10.19734/j.issn.1001-3695.2024.12.0500

Abstract

The use of cloud-assisted training for Convolutional Neural Networks (CNNs) with few parameters can enable their deployment on resource-constrained IoT devices. However, existing models with few parameters suffer from insufficient ability to extract complex data features and poor robustness. This article proposes a CNN design method that is adaptable to complex data and has strong robustness, called the Combined Non-linearity Convolution Kernel Generation (CN2Conv) . Firstly, randomly select some convolution kernels from the convolutional layers of the CNN model as seed convolution kernels, and use multiple generation functions to perform nonlinear transformations on the seed convolution kernels to obtain diverse generation convolution kernels. Secondly, the different generation functions use different hyperparameters to control the regularization effect of the model and improve its robustness. Finally, using the feature maps generated by the convolutional kernels to perform channel shuffling and convolutional dimensionality reduction operations, while using group normalization techniques to improve the distribution consistency of features and enhance the ability to capture complex data features. In order to verify the effectiveness of CN2Conv, carried out several experiments on CIFAR-10, CIFAR-100, CIFAR-10-C and Icons-50 datasets. On the CIFAR-10-C dataset, the accuracy of ResNet34 using CN2Conv is 8.22% higher than the standard ResNet34, and 11.86% higher than MonoCNN. The results show that the accuracy of the CNN model based on CN2Conv is better than the comparison method on multiple datasets, and the robustness is significantly improved.

Foundation Support

国家自然科学基金资助项目(62472147,62202039)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2024.12.0500
Publish at: Application Research of Computers Accepted Paper, Vol. 42, 2025 No. 7

Publish History

[2025-03-14] Accepted Paper

Cite This Article

柴智, 丁春涛, 郭慧, 等. CN2Conv：面向物联网设备的强鲁棒CNN设计方法 [J]. 计算机应用研究, 2025, 42 (7). (2025-03-14). https://doi.org/10.19734/j.issn.1001-3695.2024.12.0500. (Chai Zhi, Ding Chuntao, Guo Hui, et al. Combined non-linearity convolution kernel: strong robust CNN design method based on IoT [J]. Application Research of Computers, 2025, 42 (7). (2025-03-14). https://doi.org/10.19734/j.issn.1001-3695.2024.12.0500. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)