Advances in Algorithm Optimization and Computational Intelligence

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: 15 September 2024 | Viewed by 646

Special Issue Editors

School of Engineering and Computing, University of Central Lancashire (UCLan), Preston PR1 2HE, UK
Interests: artificial intelligence; computer vision; digital healthcare; image processing; computational thinking; assisted living

E-Mail Website
Guest Editor
Department of Computer Science, Solent University, Southampton SO14 0YN, UK
Interests: affective computing; investigating multimodal data; hybrid DNNs; applications of AI; data science; computer vision; time-series and financial market analysis

E-Mail Website
Guest Editor
Graduate Institute of Intelligent Robotics, Hwa Hsia University of Technology, New Taipei City 235, Taiwan
Interests: artificial intelligence; machine learning; image processing; biometrics; pattern recognition
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The Special Issue of Electronics, “Advances in Algorithm Optimization and Computational Intelligence,” is a pivotal scholarly contribution to the dynamic domain of computer science. Our aim is to provide a conduit for academics and industry professionals in terms of disseminating their research outcomes and methodologies in the realms of algorithmic optimization and computational intelligence.

This Special Issue’s objective is to spotlight avant-garde research and methodologies that augment the efficacy, robustness, and versatility of algorithms. This aligns seamlessly with the journal’s overarching mission of fostering state-of-the-art research in computer science and its intersecting disciplines. The focus of this Issue is the exploration and development of novel algorithmic strategies, the application of machine learning techniques for optimization, and the advancement of artificial intelligence paradigms for complex problem solving.

Potential article themes for this Special Issue include, but are not limited to, machine learning algorithms, evolutionary computation, swarm intelligence, artificial neural networks, fuzzy systems, and decision support systems. These themes reflect the current trends and future directions in the realm of computational intelligence and algorithm optimization. This Issue encourages submissions that offer novel insights, propose new methodologies, or apply existing techniques in innovative ways to solve complex problems. This is an excellent opportunity for scholars to contribute to and shape discourse in this crucial research area.

In this Special Issue, original research articles and reviews are welcome. Research areas may include (but not limited to) the following:

  1. Machine learning algorithms
  2. Evolutionary computation
  3. Swarm intelligence
  4. Artificial neural networks
  5. Fuzzy systems
  6. Decision support systems
  7. Optimization algorithms
  8. Deep learning
  9. Natural language processing
  10. Computer vision

Dr. Amin Amini
Dr. Bacha Rehman
Prof. Dr. Chih-Lung Lin
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • artificial intelligence
  • image processing
  • computer vision
  • algorithm optimization
  • computational intelligence

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

15 pages, 1985 KiB  
Article
An Improvement of Adam Based on a Cyclic Exponential Decay Learning Rate and Gradient Norm Constraints
by Yichuan Shao, Jiapeng Yang, Wen Zhou, Haijing Sun, Lei Xing, Qian Zhao and Le Zhang
Electronics 2024, 13(9), 1778; https://doi.org/10.3390/electronics13091778 - 4 May 2024
Viewed by 353
Abstract
Aiming at a series of limitations of the Adam algorithm, such as hyperparameter sensitivity and unstable convergence, in this paper, an improved optimization algorithm, the Cycle-Norm-Adam (CN-Adam) algorithm, is proposed. The algorithm integrates the ideas of a cyclic exponential decay learning rate (CEDLR) [...] Read more.
Aiming at a series of limitations of the Adam algorithm, such as hyperparameter sensitivity and unstable convergence, in this paper, an improved optimization algorithm, the Cycle-Norm-Adam (CN-Adam) algorithm, is proposed. The algorithm integrates the ideas of a cyclic exponential decay learning rate (CEDLR) and gradient paradigm constraintsand accelerates the convergence speed of the Adam model and improves its generalization performance by dynamically adjusting the learning rate. In order to verify the effectiveness of the CN-Adam algorithm, we conducted extensive experimental studies. The CN-Adam algorithm achieved significant performance improvementsin both standard datasets. The experimental results show that the CN-Adam algorithm achieved 98.54% accuracy in the MNIST dataset and 72.10% in the CIFAR10 dataset. Due to the complexity and specificity of medical images, the algorithm was tested in a medical dataset and achieved an accuracy of 78.80%, which was better than the other algorithms. The experimental results show that the CN-Adam optimization algorithm provides an effective optimization strategy for improving model performance and promoting medical research. Full article
(This article belongs to the Special Issue Advances in Algorithm Optimization and Computational Intelligence)
Show Figures

Figure 1

Back to TopTop