Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.7
2.9
Journals
Electronics
Special Issues
Advances in Swarm Intelligence, Data Science and Their Applications, 2nd...
share announcement

Advances in Swarm Intelligence, Data Science and Their Applications, 2nd Edition

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: 25 May 2024 | Viewed by 4966

Special Issue Editor

Prof. Dr. Ying Tan

E-Mail Website
Guest Editor
School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China
Interests: swarm intelligence; swarm intelligence optimization algorithm; fireworks algorithm; swarm robotics; machine learning and data mining
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

This Special Issue will cover the most recent discovery and development centered around two major topics: swarm intelligence and data science.

Swarm intelligence systems typically study the complex collective behavior that arises from decentralized simple agents with local and/or global interaction. The inspiration for swarm intelligence algorithms usually comes from natural behavior or phenomena, such as ant colonies, bird flocks, fireworks, etc. Typical subdomains of swarm intelligence are swarm-based optimization techniques and multi-agent cooperative systems. It has been proven that swarm intelligence is an effective way to tackle complex problems that arise in various domains such as power systems, robotics, information systems, image processing, computation chemistry, and so on. The importance of swarm intelligence in today’s society is gradually being brought to a whole new level.

On the other hand, data science has gained more and more momentum in the era of big data and artificial intelligence. It utilizes theories and techniques from machine learning, statistics, and information theory to help us extract valuable knowledge, patterns, and insights from data that are usually very large and complex. Some typical applications of data science are fraud detection, recommender systems, bioinformatics, stock market prediction, and so on. Our Special Issue is mainly concerned with advances in the field of data mining, machine learning, pattern recognition, automatic control, and their respective applications.

Prof. Dr. Ying Tan
Guest Editor

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

  • swarm intelligence
  • big data
  • natural computing
  • fireworks algorithms
  • multi-agent theories
  • optimization theories
  • data mining
  • machine learning
  • pattern recognition
  • automatic control

Related Special Issue

Published Papers (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

20 pages, 4938 KiB  
Article
AdvMix: Adversarial Mixing Strategy for Unsupervised Domain Adaptive Object Detection
by Ruimin Chen, Dailin Lv, Li Dai, Liming Jin and Zhiyu Xiang
Electronics 2024, 13(4), 685; https://doi.org/10.3390/electronics13040685 - 07 Feb 2024
Cited by 1 | Viewed by 672
Abstract
Recent object detection networks suffer from performance degradation when training data and test data are distinct in image styles and content distributions. In this paper, we propose a domain adaptive method, Adversarial Mixing (AdvMix), where the label-rich source domain and unlabeled target domain [...] Read more.
Recent object detection networks suffer from performance degradation when training data and test data are distinct in image styles and content distributions. In this paper, we propose a domain adaptive method, Adversarial Mixing (AdvMix), where the label-rich source domain and unlabeled target domain are jointly trained by the adversarial feature alignment and a self-training strategy. To diminish the style gap, we design the Adversarial Gradient Reversal Layer (AdvGRL), containing a global-level domain discriminator to align the domain features by gradient reversal, and an adversarial weight mapping function to enhance the stability of domain-invariant features by hard example mining. To eliminate the content gap, we introduce a region mixing self-supervised training strategy where a region of the target image with the highest confidence is selected to merge with the source image, and the synthesis image is self-supervised by the consistency loss. To improve the reliability of self-training, we propose a strict confidence metric combining both object and bounding box uncertainty. Extensive experiments conducted on three benchmarks demonstrate that AdvMix achieves prominent performance in terms of detection accuracy, surpassing existing domain adaptive methods by nearly 5% mAP. Full article
(This article belongs to the Special Issue Advances in Swarm Intelligence, Data Science and Their Applications, 2nd Edition)
►▼ Show Figures

Figure 1

16 pages, 3104 KiB  
Article
LMFRNet: A Lightweight Convolutional Neural Network Model for Image Analysis
by Guangquan Wan and Lan Yao
Electronics 2024, 13(1), 129; https://doi.org/10.3390/electronics13010129 - 28 Dec 2023
Viewed by 1147
Abstract
Convolutional neural networks (CNNs) have transformed the landscape of image analysis and are widely applied across various fields. With their widespread adoption in fields like medical diagnosis and autonomous driving, CNNs have demonstrated powerful capabilities. Despite their success, existing models face challenges in [...] Read more.
Convolutional neural networks (CNNs) have transformed the landscape of image analysis and are widely applied across various fields. With their widespread adoption in fields like medical diagnosis and autonomous driving, CNNs have demonstrated powerful capabilities. Despite their success, existing models face challenges in deploying and operating in resource-constrained environments, limiting their practicality in real-world scenarios. We introduce LMFRNet, a lightweight CNN model. Its innovation resides in a multi-feature block design, effectively reducing both model complexity and computational load. Achieving an exceptional accuracy of 94.6% on the CIFAR-10 dataset, this model showcases remarkable performance while demonstrating parsimonious resource utilization. We further validate the performance of the model on the CIFAR-100, MNIST, and Fashion-MNIST datasets, demonstrating its robustness and generalizability across diverse datasets. Furthermore, we conducted extensive experiments to investigate the influence of critical hyperparameters. These experiments provided valuable insights for effective model training. Full article
(This article belongs to the Special Issue Advances in Swarm Intelligence, Data Science and Their Applications, 2nd Edition)
►▼ Show Figures

Figure 1

22 pages, 4718 KiB  
Article
Improving Dual-Population Differential Evolution Based on Hierarchical Mutation and Selection Strategy
by Yawei Huang, Xuezhong Qian and Wei Song
Electronics 2024, 13(1), 62; https://doi.org/10.3390/electronics13010062 - 22 Dec 2023
Viewed by 608
Abstract
The dual-population differential evolution (DDE) algorithm is an optimization technique that simultaneously maintains two populations to balance global and local search. It has been demonstrated to outperform single-population differential evolution algorithms. However, existing improvements to dual-population differential evolution algorithms often overlook the importance [...] Read more.
The dual-population differential evolution (DDE) algorithm is an optimization technique that simultaneously maintains two populations to balance global and local search. It has been demonstrated to outperform single-population differential evolution algorithms. However, existing improvements to dual-population differential evolution algorithms often overlook the importance of selecting appropriate mutation and selection operators to enhance algorithm performance. In this paper, we propose a dual-population differential evolution (DPDE) algorithm based on a hierarchical mutation and selection strategy. We divided the population into elite and normal subpopulations based on fitness values. Information exchange between the two subpopulations was facilitated through a hierarchical mutation strategy, promoting a balanced exploration–exploitation trade-off in the algorithm. Additionally, this paper presents a new hierarchical selection strategy aimed at improving the population’s capacity to avoid local optima. It achieves this by accepting discarded trial vectors differently compared to previous methods. We expect that the newly introduced hierarchical selection and mutation strategies will work in synergy, effectively harnessing their potential to enhance the algorithm’s performance. Extensive experiments were conducted on the CEC 2017 and CEC 2011 test sets. The results showed that the DPDE algorithm offers competitive performance, comparable to six state-of-the-art differential evolution algorithms. Full article
(This article belongs to the Special Issue Advances in Swarm Intelligence, Data Science and Their Applications, 2nd Edition)
►▼ Show Figures

Figure 1

19 pages, 5053 KiB  
Article
Head and Voice-Controlled Human-Machine Interface System for Transhumeral Prosthesis
by Ludwin Molina Arias, Marek Iwaniec, Paulina Pirowska, Magdalena Smoleń and Piotr Augustyniak
Electronics 2023, 12(23), 4770; https://doi.org/10.3390/electronics12234770 - 24 Nov 2023
Viewed by 800
Abstract
The design of artificial limbs is a research topic that has, over time, attracted considerable interest from researchers in various fields of study, such as mechanics, electronics, robotics, and neuroscience. Continuous efforts are being made to build electromechanical systems functionally equivalent to the [...] Read more.
The design of artificial limbs is a research topic that has, over time, attracted considerable interest from researchers in various fields of study, such as mechanics, electronics, robotics, and neuroscience. Continuous efforts are being made to build electromechanical systems functionally equivalent to the original limbs and to develop strategies to control them appropriately according to the intentions of the user. The development of Human–Machine Interfaces (HMIs) is a key point in the development of upper limb prostheses, since the actions carried out with the upper limbs lack fixed patterns, in contrast to the more predictable nature of lower limb movements. This paper presents the development of an HMI system for the control of a transhumeral prosthesis. The HMI is based on a hybrid control strategy that uses voice commands to trigger prosthesis movements and regulates the applied grip strength when the user turns his head. A prototype prosthesis was built using 3D technology and trials were conducted to test the proposed control strategy under laboratory conditions. Numerical simulations were also performed to estimate the grip strength generated. The results obtained show that the proposed prosthesis with the dedicated HMI is a promising low-cost alternative to the current solutions. The proposed hybrid control system is capable of recognizing the user’s voice with an accuracy of up to 90%, controlling the prosthesis joints and adjusting the grip strength according to the user’s wishes. Full article
(This article belongs to the Special Issue Advances in Swarm Intelligence, Data Science and Their Applications, 2nd Edition)
►▼ Show Figures

Figure 1

14 pages, 1299 KiB  
Article
Exploring Zero-Shot Semantic Segmentation with No Supervision Leakage
by Yiqi Wang and Yingjie Tian
Electronics 2023, 12(16), 3452; https://doi.org/10.3390/electronics12163452 - 15 Aug 2023
Cited by 1 | Viewed by 1161
Abstract
Zero-shot semantic segmentation (ZS3), the process of classifying unseen classes without explicit training samples, poses a significant challenge. Despite notable progress made by pre-trained vision-language models, they have a problem of “supervision leakage” in the unseen classes due to their large-scale pre-trained data. [...] Read more.
Zero-shot semantic segmentation (ZS3), the process of classifying unseen classes without explicit training samples, poses a significant challenge. Despite notable progress made by pre-trained vision-language models, they have a problem of “supervision leakage” in the unseen classes due to their large-scale pre-trained data. For example, CLIP is trained on 400M image–text pairs that contain large label space categories. So, it is not convincing for real “zero-shot” learning in machine learning. This paper introduces SwinZS3, an innovative framework that explores the “no-supervision-leakage” zero-shot semantic segmentation with an image encoder that is not pre-trained on the seen classes. SwinZS3 integrates the strengths of both visual and semantic embeddings within a unified joint embedding space. This approach unifies a transformer-based image encoder with a language encoder. A distinguishing feature of SwinZS3 is the implementation of four specialized loss functions in the training progress: cross-entropy loss, semantic-consistency loss, regression loss, and pixel-text score loss. These functions guide the optimization process based on dense semantic prototypes derived from the language encoder, making the encoder adept at recognizing unseen classes during inference without retraining. We evaluated SwinZS3 with standard ZS3 benchmarks, including PASCAL VOC and PASCAL Context. The outcomes affirm the effectiveness of our method, marking a new milestone in “no-supervison-leakage” ZS3 task performance. Full article
(This article belongs to the Special Issue Advances in Swarm Intelligence, Data Science and Their Applications, 2nd Edition)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop