Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
8.3
3.6
Journals
Future Internet
Special Issues
Innovations in Artificial Intelligence and Neural Networks
share announcement

Innovations in Artificial Intelligence and Neural Networks

A special issue of Future Internet (ISSN 1999-5903). This special issue belongs to the section "Smart System Infrastructure and Applications".

Deadline for manuscript submissions: 20 July 2026 | Viewed by 915

Special Issue Editors

Prof. Dr. Wenli Zhang

E-Mail Website
Guest Editor
Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China
Interests: computer vision and pattern recognition; 3D reconstruction; intelligent bionics and control
Special Issues, Collections and Topics in MDPI journals
Dr. Zhuwei Wang

E-Mail Website
Guest Editor
School of Information Science and Technology, Beijing University of Technology, Beijing 100124, China
Interests: networked intelligent control
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Artificial Intelligence (AI) and Neural Networks (NNs) are emerging with unprecedented momentum as the core engine driving the transformation of the Future Internet, comprehensively reshaping network architectures, innovating service models, and transforming interaction logic. This special issue, "Innovation in Artificial Intelligence and Neural Networks", focuses on cutting-edge research in the field of Future Internet, exploring in depth new pathways for the intelligent development of the next-generation Internet.

We sincerely invite original research and review articles, with a focus on the following frontier directions:

Evolution of Intelligent Network Architectures

Explore how AI and neural networks empower Software-Defined Networking (SDN), Network Function Virtualization (NFV), etc., with intelligent dynamic reconfiguration capabilities to build a new future network architecture featuring self-adaptive and self-organizing characteristics, enabling efficient and flexible allocation of network resources.

6G and Next-Generation Communication Intelligence

Investigate how AI deeply empowers 6G networks to achieve breakthroughs in intelligent resource scheduling, precise beamforming, and efficient interference suppression; explore the design of adaptive transmission protocols for neural networks in space-air-ground integrated communications to enhance communication reliability and coverage; promote innovative integration of Reconfigurable Intelligent Surfaces (RIS) with AI to significantly improve communication energy efficiency, leading 6G and next-generation communications into a new era of intelligence.

Edge Intelligence and Communication Integration

Focus on AI-driven collaborative training mechanisms between edge computing and terminal devices to facilitate the in-depth implementation of federated learning in scenarios such as the Internet of Things (IoT) and Industrial Internet, enabling localized data processing and privacy preservation while enhancing the intelligent decision-making capabilities of the overall system.

Construction of Secure and Trustworthy Systems

Focus on innovative integration of blockchain and AI to build a distributed trusted computing framework, ensuring secure storage and trusted sharing of data; leverage deep learning to strengthen network attack defense and traceability capabilities, constructing a proactive defense security system; develop intelligent security protection systems for emerging fields such as Metaverse and Web3.0 to safeguard user information security and privacy.

Immersive Interaction and Service Innovation

Highlight the key role of AI in Metaverse real-time rendering and intelligent interaction of virtual humans to enhance the realism and interactivity of virtual scenes; promote precise delivery of personalized intelligent services in the Web3.0 ecosystem, enabling service customization and intelligence based on user behavior data; optimize large-scale user behavior data analysis through federated learning to improve the quality and efficiency of service experiences.

In addition, research on challenges faced by the Future Internet, such as heterogeneous device collaboration and ultra-large-scale data processing, as well as topics like cross-layer protocol optimization and algorithm ethics, is also within the scope of manuscript solicitation.

This special issue establishes a global exchange platform, bringing together researchers, engineers, and policymakers to explore new possibilities for AI and neural networks to lead the cutting-edge development of the Future Internet. We look forward to your submission of groundbreaking achievements to jointly promote the in-depth integration and innovative leapfrogging of intelligent technologies and the Future Internet.

Prof. Dr. Wenli Zhang
Dr. Zhuwei Wang
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 250 words) can be sent to the Editorial Office for assessment.

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. Future Internet is an international peer-reviewed open access monthly 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 1800 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 (AI)
  • neural networks
  • future internet
  • 6G
  • edge intelligence
  • federated learning
  • blockchain
  • metaverse
  • Web3.0

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (1 paper)

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

Research

38 pages, 1145 KB  
Article
Transfer Learning Strategies for Comic Character Recognition in Low-Data Regimes: A Comparative Study
by Marco Parrillo, Luigi Laura and Alessandro Manna
Future Internet 2026, 18(4), 192; https://doi.org/10.3390/fi18040192 - 2 Apr 2026
Viewed by 579
Abstract
Image classification in low-data regimes remains a challenging problem, particularly in stylized visual domains where intra-class similarity and inter-class feature overlap limit discriminative capacity. This study presents a systematic evaluation of regularization and transfer learning strategies for multi-class comic character recognition under constrained [...] Read more.
Image classification in low-data regimes remains a challenging problem, particularly in stylized visual domains where intra-class similarity and inter-class feature overlap limit discriminative capacity. This study presents a systematic evaluation of regularization and transfer learning strategies for multi-class comic character recognition under constrained data conditions. Four convolutional architectures are compared: (i) a baseline CNN trained from scratch, (ii) a regularized CNN incorporating data augmentation, dropout, and early stopping, (iii) a pretrained ResNet-50 used as a fixed feature extractor, and (iv) a partially fine-tuned ResNet-50 with selective layer unfreezing. Experiments are conducted on a custom four-class dataset exhibiting moderate class imbalance, evaluated using both a fixed 70/20/10 split and 5-fold cross-validation to assess generalization stability. Results indicate that shallow CNN architectures suffer from substantial overfitting, even when regularization is applied, whereas transfer learning significantly improves macro-averaged F1-score and out-of-distribution detection performance. Cross-validated results, the primary basis for inference given the dataset scale, show that both ResNet-50 strategies achieve equivalent mean accuracy of 95.0% (SD: ±0.4% for feature extraction, ±0.8% for fine-tuning; paired t = 0.00, p = 1.000), while shallow CNN architectures reach only 81–87%. Under a single fixed 70/20/10 partition (n = 69 test samples, 95% CI: ±9–12%), fine-tuning nominally reaches 98.5%; crucially, cross-validation deflates this figure to parity with feature extraction, confirming it reflects favorable partitioning rather than genuine architectural superiority. The primary finding is therefore that frozen ResNet-50 feature extraction is the recommended strategy: it matches fine-tuning in cross-validated generalization while requiring 15× fewer trainable parameters and exhibiting lower fold-to-fold variance. The findings demonstrate that pretrained deep residual representations transfer effectively to stylized comic imagery and that evaluation protocol selection critically impacts perceived performance in small datasets. These results provide practical guidelines for robust model selection in domain-specific, limited-data image classification tasks. Full article
(This article belongs to the Special Issue Innovations in Artificial Intelligence and Neural Networks)
►▼ Show Figures

Graphical abstract

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