Special lssues
Table of Content

The Next-generation Deep Learning Approaches to Emerging Real-world Applications

Submission Deadline: 31 December 2024 Submit to Special Issue

Guest Editors

Dr. Yu Zhou, Shenzhen University, China
Dr. Eneko Osaba, TECNALIA Research & Innovation, Spain
Dr. Xiao Zhang, South-Central Minzu University, China


Artificial intelligence techniques, such as Deep learning (DL) methods, have demonstrated their great success in the past ten years for various applications, such as computer vision, bioinformatics, healthcare and transportation. As the field of deep learning evolves rapidly, new and innovative approaches continue to emerge, addressing complex challenges in real-world applications. When facing emerging real-world applications, current DL models still suffer from high-dimensionality issue, robustness, data uncertainty and lack of global convergence and interpretability. Recent developments in intelligent computing approaches suggest the potential for next-generation deep learning methodologies that effectively address these challenges, such as bio-inspired computing, brain-inspired computing and other new computing schemes. This special issue aims to bring together cutting-edge research that showcases the next-generation deep learning approaches and their applications in emerging real-world scenarios, which aims to explore:

1) Novel deep learning models and structures.

2) New optimization method for deep learning training

3) Emerging real-world applications


The topics include those related to novel deep learning approaches and emerging real-world applications, but not limited to, the following:

Bio-inspired computing methods with deep leaning

Brain-inspired computing methods with deep learning

Attention mechanism in deep learning

Sparse deep learning

Soft computing with deep learning

Ensemble deep learning

Fine-tune methods for deep learning

Graph deep learning

Emerging topics in healthcare and sports with deep learning

Emerging topics in smart city and transportation with deep learning

Emerging topics in industrial informatics and intelligent manufacturing with deep learning

Emerging topics in social sciences with deep learning


Deep learning, emerging real-world applications, intelligent computing

Published Papers

  • Open Access


    ASLP-DL —A Novel Approach Employing Lightweight Deep Learning Framework for Optimizing Accident Severity Level Prediction

    Saba Awan, Zahid Mehmood
    CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2024.047337
    (This article belongs to this Special Issue: The Next-generation Deep Learning Approaches to Emerging Real-world Applications)
    Abstract Highway safety researchers focus on crash injury severity, utilizing deep learning—specifically, deep neural networks (DNN), deep convolutional neural networks (D-CNN), and deep recurrent neural networks (D-RNN)— as the preferred method for modeling accident severity. Deep learning’s strength lies in handling intricate relationships within extensive datasets, making it popular for accident severity level (ASL) prediction and classification. Despite prior success, there is a need for an efficient system recognizing ASL in diverse road conditions. To address this, we present an innovative Accident Severity Level Prediction Deep Learning (ASLP-DL) framework, incorporating DNN, D-CNN, and D-RNN models fine-tuned through iterative hyperparameter selection with… More >

  • Open Access


    SDH-FCOS: An Efficient Neural Network for Defect Detection in Urban Underground Pipelines

    Bin Zhou, Bo Li, Wenfei Lan, Congwen Tian, Wei Yao
    CMC-Computers, Materials & Continua, Vol.78, No.1, pp. 633-652, 2024, DOI:10.32604/cmc.2023.046667
    (This article belongs to this Special Issue: The Next-generation Deep Learning Approaches to Emerging Real-world Applications)
    Abstract Urban underground pipelines are an important infrastructure in cities, and timely investigation of problems in underground pipelines can help ensure the normal operation of cities. Owing to the growing demand for defect detection in urban underground pipelines, this study developed an improved defect detection method for urban underground pipelines based on fully convolutional one-stage object detector (FCOS), called spatial pyramid pooling-fast (SPPF) feature fusion and dual detection heads based on FCOS (SDH-FCOS) model. This study improved the feature fusion component of the model network based on FCOS, introduced an SPPF network structure behind the last output feature layer of the… More >

Share Link