Submit

Login Login

Register Register

Home / Journals / CMC / Special Issue / Advances in Deep Learning and Neural Networks: Architectures, Applications, and Challenges
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Advances in Deep Learning and Neural Networks: Architectures, Applications, and Challenges

Submission Deadline: 31 July 2025 (closed) View: 4903 Submit to Journal

Guest Editors

Prof. Dae-Ki Kang

Email: dkkang@dongseo.ac.kr

Affiliation: Department of Computer Engineering, Dongseo University, Busan, 47011, South Korea

Homepage:

Research Interests: Adversarial Machine Learning, Generative Models, Deep Reinforcement Learning, Hyperparameter Optimization and Network Architecture Search, Multi-Agent Reinforcement Learning, Bankruptcy prediction models and financial ratio analysis, Datamining based intrusion detection

图片1.png

Summary

Deep learning and neural networks have revolutionized various fields, including computer vision, natural language processing, and healthcare. As these technologies continue to evolve, it is essential to explore their latest advancements, applications, and challenges. This special issue aims to gather innovative research contributions that highlight significant progress and practical implementations of deep learning and neural networks.

We invite original research articles and reviews that cover, but are not limited to, the following topics:

 

1. Architectural Innovations:

   - Novel neural network architectures (e.g., CNNs, RNNs, GANs, Transformers)

   - Techniques for improving model efficiency and performance

 

2. Training and Optimization:

   - Advanced training methods (e.g., transfer learning, reinforcement learning)

   - Optimization algorithms and their impact on convergence

 

3. Applications:

   - Use cases in various domains, including:

     - Healthcare: medical imaging, diagnosis, and treatment planning

     - Autonomous systems: robotics and self-driving cars

     - Finance: fraud detection and algorithmic trading

     - Environmental science: climate modeling and resource management

 

4. Ethics and Fairness:

   - Addressing bias and fairness in deep learning models

   - Ethical considerations in AI deployment

 

5. Future Directions:
   - Large Language Models

     - Emerging trends and future challenges in deep learning research

     - Interdisciplinary approaches combining deep learning with other fields

Keywords

Deep Learning, Neural Networks, Transformers, Large Language Models

Published Papers

Show export options

  • Open Access

    ARTICLE

    MRFNet: A Progressive Residual Fusion Network for Blind Multiscale Image Deblurring

    Wang Zhang, Haozhuo Cao, Qiangqiang Yao
    CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.072948
    （This article belongs to the Special Issue: Advances in Deep Learning and Neural Networks: Architectures, Applications, and Challenges)
    Abstract Recent advances in deep learning have significantly improved image deblurring; however, existing approaches still suffer from limited global context modeling, inadequate detail restoration, and poor texture or edge perception, especially under complex dynamic blur. To address these challenges, we propose the Multi-Resolution Fusion Network (MRFNet), a blind multi-scale deblurring framework that integrates progressive residual connectivity for hierarchical feature fusion. The network employs a three-stage design: (1) TransformerBlocks capture long-range dependencies and reconstruct coarse global structures; (2) Nonlinear Activation Free Blocks (NAFBlocks) enhance local detail representation and mid-level feature fusion; and (3) an optimized residual subnetwork… More >

    View

    69

    Download

    12

  • Open Access

    ARTICLE

    Efficient Video Emotion Recognition via Multi-Scale Region-Aware Convolution and Temporal Interaction Sampling

    Xiaorui Zhang, Chunlin Yuan, Wei Sun, Ting Wang
    CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.071043
    （This article belongs to the Special Issue: Advances in Deep Learning and Neural Networks: Architectures, Applications, and Challenges)
    Abstract Video emotion recognition is widely used due to its alignment with the temporal characteristics of human emotional expression, but existing models have significant shortcomings. On the one hand, Transformer multi-head self-attention modeling of global temporal dependency has problems of high computational overhead and feature similarity. On the other hand, fixed-size convolution kernels are often used, which have weak perception ability for emotional regions of different scales. Therefore, this paper proposes a video emotion recognition model that combines multi-scale region-aware convolution with temporal interactive sampling. In terms of space, multi-branch large-kernel stripe convolution is used to More >

    View

    186

    Download

    25

  • Open Access

    ARTICLE

    Log-Based Anomaly Detection of System Logs Using Graph Neural Network

    Eman Alsalmi, Abeer Alhuzali, Areej Alhothali
    CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.071012
    （This article belongs to the Special Issue: Advances in Deep Learning and Neural Networks: Architectures, Applications, and Challenges)
    Abstract Log anomaly detection is essential for maintaining the reliability and security of large-scale networked systems. Most traditional techniques rely on log parsing in the reprocessing stage and utilize handcrafted features that limit their adaptability across various systems. In this study, we propose a hybrid model, BertGCN, that integrates BERT-based contextual embedding with Graph Convolutional Networks (GCNs) to identify anomalies in raw system logs, thereby eliminating the need for log parsing. The BERT module captures semantic representations of log messages, while the GCN models the structural relationships among log entries through a text-based graph. This combination More >

    View

    577

    Download

    222

  • Open Access

    ARTICLE

    Lightweight Airborne Vision Abnormal Behavior Detection Algorithm Based on Dual-Path Feature Optimization

    Baixuan Han, Yueping Peng, Zecong Ye, Hexiang Hao, Xuekai Zhang, Wei Tang, Wenchao Kang, Qilong Li
    CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.071071
    （This article belongs to the Special Issue: Advances in Deep Learning and Neural Networks: Architectures, Applications, and Challenges)
    Abstract Aiming at the problem of imbalance between detection accuracy and algorithm model lightweight in UAV aerial image target detection algorithm, a lightweight multi-category abnormal behavior detection algorithm based on improved YOLOv11n is designed. By integrating multi-head grouped self-attention mechanism and Partial-Conv, a two-way feature grouping fusion module (DFPF) was designed, which carried out effective channel segmentation and fusion strategies to reduce redundant calculations and memory access. C3K2 module was improved, and then unstructured pruning and feature distillation technology were used. The algorithm model is lightweight, and the feature extraction ability for airborne visual abnormal behavior… More >

    View

    392

    Download

    98

    Like

    1

  • Open Access

    ARTICLE

    A Super-Resolution Generative Adversarial Network for Remote Sensing Images Based on Improved Residual Module and Attention Mechanism

    Yifan Zhang, Yong Gan, Mengke Tang, Xinxin Gan
    CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.068880
    （This article belongs to the Special Issue: Advances in Deep Learning and Neural Networks: Architectures, Applications, and Challenges)
    Abstract High-resolution remote sensing imagery is essential for critical applications such as precision agriculture, urban management planning, and military reconnaissance. Although significant progress has been made in single-image super-resolution (SISR) using generative adversarial networks (GANs), existing approaches still face challenges in recovering high-frequency details, effectively utilizing features, maintaining structural integrity, and ensuring training stability—particularly when dealing with the complex textures characteristic of remote sensing imagery. To address these limitations, this paper proposes the Improved Residual Module and Attention Mechanism Network (IRMANet), a novel architecture specifically designed for remote sensing image reconstruction. IRMANet builds upon the Super-Resolution… More >

    View

    788

    Download

    408

  • Open Access

    ARTICLE

    GFL-SAR: Graph Federated Collaborative Learning Framework Based on Structural Amplification and Attention Refinement

    Hefei Wang, Ruichun Gu, Jingyu Wang, Xiaolin Zhang, Hui Wei
    CMC-Computers, Materials & Continua, Vol.86, No.1, pp. 1-20, 2026, DOI:10.32604/cmc.2025.069251
    （This article belongs to the Special Issue: Advances in Deep Learning and Neural Networks: Architectures, Applications, and Challenges)
    Abstract Graph Federated Learning (GFL) has shown great potential in privacy protection and distributed intelligence through distributed collaborative training of graph-structured data without sharing raw information. However, existing GFL approaches often lack the capability for comprehensive feature extraction and adaptive optimization, particularly in non-independent and identically distributed (NON-IID) scenarios where balancing global structural understanding and local node-level detail remains a challenge. To this end, this paper proposes a novel framework called GFL-SAR (Graph Federated Collaborative Learning Framework Based on Structural Amplification and Attention Refinement), which enhances the representation learning capability of graph data through a dual-branch… More >

    View

    680

    Download

    203

  • Open Access

    ARTICLE

    A Novel Unsupervised Structural Attack and Defense for Graph Classification

    Yadong Wang, Zhiwei Zhang, Pengpeng Qiao, Ye Yuan, Guoren Wang
    CMC-Computers, Materials & Continua, Vol.86, No.1, pp. 1-22, 2026, DOI:10.32604/cmc.2025.068590
    （This article belongs to the Special Issue: Advances in Deep Learning and Neural Networks: Architectures, Applications, and Challenges)
    Abstract Graph Neural Networks (GNNs) have proven highly effective for graph classification across diverse fields such as social networks, bioinformatics, and finance, due to their capability to learn complex graph structures. However, despite their success, GNNs remain vulnerable to adversarial attacks that can significantly degrade their classification accuracy. Existing adversarial attack strategies primarily rely on label information to guide the attacks, which limits their applicability in scenarios where such information is scarce or unavailable. This paper introduces an innovative unsupervised attack method for graph classification, which operates without relying on label information, thereby enhancing its applicability… More >

    View

    512

    Download

    187

  • Open Access

    ARTICLE

    A YOLOv11-Based Deep Learning Framework for Multi-Class Human Action Recognition

    Nayeemul Islam Nayeem, Shirin Mahbuba, Sanjida Islam Disha, Md Rifat Hossain Buiyan, Shakila Rahman, M. Abdullah-Al-Wadud, Jia Uddin
    CMC-Computers, Materials & Continua, Vol.85, No.1, pp. 1541-1557, 2025, DOI:10.32604/cmc.2025.065061
    （This article belongs to the Special Issue: Advances in Deep Learning and Neural Networks: Architectures, Applications, and Challenges)
    Abstract Human activity recognition is a significant area of research in artificial intelligence for surveillance, healthcare, sports, and human-computer interaction applications. The article benchmarks the performance of You Only Look Once version 11-based (YOLOv11-based) architecture for multi-class human activity recognition. The article benchmarks the performance of You Only Look Once version 11-based (YOLOv11-based) architecture for multi-class human activity recognition. The dataset consists of 14,186 images across 19 activity classes, from dynamic activities such as running and swimming to static activities such as sitting and sleeping. Preprocessing included resizing all images to 512 512 pixels, annotating them… More >

    View

    3746

    Download

    2164

  • Open Access

    ARTICLE

    Unsupervised Monocular Depth Estimation with Edge Enhancement for Dynamic Scenes

    Peicheng Shi, Yueyue Tang, Yi Li, Xinlong Dong, Yu Sun, Aixi Yang
    CMC-Computers, Materials & Continua, Vol.84, No.2, pp. 3321-3343, 2025, DOI:10.32604/cmc.2025.065297
    （This article belongs to the Special Issue: Advances in Deep Learning and Neural Networks: Architectures, Applications, and Challenges)
    Abstract In the dynamic scene of autonomous vehicles, the depth estimation of monocular cameras often faces the problem of inaccurate edge depth estimation. To solve this problem, we propose an unsupervised monocular depth estimation model based on edge enhancement, which is specifically aimed at the depth perception challenge in dynamic scenes. The model consists of two core networks: a deep prediction network and a motion estimation network, both of which adopt an encoder-decoder architecture. The depth prediction network is based on the U-Net structure of ResNet18, which is responsible for generating the depth map of the… More >

    View

    828

    Download

    366

  • Open Access

    ARTICLE

    CFGANLDA: A Collaborative Filtering and Graph Attention Network-Based Method for Predicting Associations between lncRNAs and Diseases

    Dang Hung Tran, Van Tinh Nguyen
    CMC-Computers, Materials & Continua, Vol.83, No.3, pp. 4679-4698, 2025, DOI:10.32604/cmc.2025.063228
    （This article belongs to the Special Issue: Advances in Deep Learning and Neural Networks: Architectures, Applications, and Challenges)
    Abstract It is known that long non-coding RNAs (lncRNAs) play vital roles in biological processes and contribute to the progression, development, and treatment of various diseases. Obviously, understanding associations between diseases and lncRNAs significantly enhances our ability to interpret disease mechanisms. Nevertheless, the process of determining lncRNA-disease associations is costly, labor-intensive, and time-consuming. Hence, it is expected to foster computational strategies to uncover lncRNA-disease relationships for further verification to save time and resources. In this study, a collaborative filtering and graph attention network-based LncRNA-Disease Association (CFGANLDA) method was nominated to expose potential lncRNA-disease associations. First, it… More >

    View

    879

    Download

    378

  • Open Access

    ARTICLE

    Chinese Named Entity Recognition Method for Musk Deer Domain Based on Cross-Attention Enhanced Lexicon Features

    Yumei Hao, Haiyan Wang, Dong Zhang
    CMC-Computers, Materials & Continua, Vol.83, No.2, pp. 2989-3005, 2025, DOI:10.32604/cmc.2025.063008
    （This article belongs to the Special Issue: Advances in Deep Learning and Neural Networks: Architectures, Applications, and Challenges)
    Abstract Named entity recognition (NER) in musk deer domain is the extraction of specific types of entities from unstructured texts, constituting a fundamental component of the knowledge graph, Q&A system, and text summarization system of musk deer domain. Due to limited annotated data, diverse entity types, and the ambiguity of Chinese word boundaries in musk deer domain NER, we present a novel NER model, CAELF-GP, which is based on cross-attention mechanism enhanced lexical features (CAELF). Specifically, we employ BERT as a character encoder and advocate the integration of external lexical information at the character representation layer.… More >

    View

    842

    Download

    319

  • Open Access

    ARTICLE

    HyTiFRec: Hybrid Time-Frequency Dual-Branch Transformer for Sequential Recommendation

    Dawei Qiu, Peng Wu, Xiaoming Zhang, Renjie Xu
    CMC-Computers, Materials & Continua, Vol.83, No.2, pp. 1753-1769, 2025, DOI:10.32604/cmc.2025.062599
    （This article belongs to the Special Issue: Advances in Deep Learning and Neural Networks: Architectures, Applications, and Challenges)
    Abstract Recently, many Sequential Recommendation methods adopt self-attention mechanisms to model user preferences. However, these methods tend to focus more on low-frequency information while neglecting high-frequency information, which makes them ineffective in balancing users’ long- and short-term preferences. At the same time, many methods overlook the potential of frequency domain methods, ignoring their efficiency in processing frequency information. To overcome this limitation, we shift the focus to the combination of time and frequency domains and propose a novel Hybrid Time-Frequency Dual-Branch Transformer for Sequential Recommendation, namely HyTiFRec. Specifically, we design two hybrid filter modules: the learnable… More >

    View

    1223

    Download

    594

  • Open Access

    ARTICLE

    Machine Learning Stroke Prediction in Smart Healthcare: Integrating Fuzzy K-Nearest Neighbor and Artificial Neural Networks with Feature Selection Techniques

    Abdul Ahad, Ira Puspitasari, Jiangbin Zheng, Shamsher Ullah, Farhan Ullah, Sheikh Tahir Bakhsh, Ivan Miguel Pires
    CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 5115-5134, 2025, DOI:10.32604/cmc.2025.062605
    （This article belongs to the Special Issue: Advances in Deep Learning and Neural Networks: Architectures, Applications, and Challenges)
    Abstract This research explores the use of Fuzzy K-Nearest Neighbor (F-KNN) and Artificial Neural Networks (ANN) for predicting heart stroke incidents, focusing on the impact of feature selection methods, specifically Chi-Square and Best First Search (BFS). The study demonstrates that BFS significantly enhances the performance of both classifiers. With BFS preprocessing, the ANN model achieved an impressive accuracy of 97.5%, precision and recall of 97.5%, and an Receiver Operating Characteristics (ROC) area of 97.9%, outperforming the Chi-Square-based ANN, which recorded an accuracy of 91.4%. Similarly, the F-KNN model with BFS achieved an accuracy of 96.3%, precision More >

    View

    1292

    Download

    849

Copyright© 2025 Tech Science Press
© 1997-2025 TSP (Henderson, USA) unless otherwise stated

Share Link