Special Issues
Table of Content

The Latest Deep Learning Architectures for Artificial Intelligence Applications

Submission Deadline: 31 December 2024 View: 1377 Submit to Special Issue

Guest Editors

Prof. Lizhuang Ma, Shanghai Jiao Tong University, China
Dr. Xin Tan, East China Normal University, China
Dr. Zhiwen Shao, Hong Kong University of Science and Technology, China
Prof. Yong Peng, Central South University, China

Summary

In an era defined by unprecedented data availability and technological advancement, the latest deep learning architectures have emerged as pivotal tools in advancing artificial intelligence (AI) applications. The special issue on "The Latest Deep Learning Architectures for Artificial Intelligence Applications" serves as a focal point for researchers navigating the complexities of harnessing state-of-the-art deep learning techniques to propel AI systems forward.

 

This special issue is set against the backdrop of a rapidly evolving landscape where deep learning architectures play a central role in shaping the capabilities of AI systems across diverse domains. From computer vision and natural language processing to robotics and data analytics, the latest advancements in deep learning offer unprecedented opportunities for enhancing AI applications.

 

Current research progress in this field is characterized by a convergence of disciplines, with contributions from researchers pushing the boundaries of deep learning methodologies. Novel architectures, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformer models, have demonstrated remarkable prowess in handling complex data modalities and learning intricate patterns from vast datasets.

 

Despite significant strides, there remain several directions for improvement and exploration within the special issue's research field. Scalability and efficiency emerge as critical considerations, particularly as deep learning architectures are deployed in real-world scenarios with large-scale datasets and computational constraints. Additionally, interpretability and robustness remain ongoing challenges, prompting researchers to explore techniques for enhancing the transparency and reliability of deep learning models.

 

The scope of the special issue is expansive, encompassing original research articles, review papers, and case studies that shed light on the latest advancements in deep learning architectures for AI applications. Topics of interest include but are not limited to cutting-edge architectures, optimization techniques, transfer learning methodologies, and applications spanning healthcare, autonomous vehicles, smart cities, and beyond.

 

Through interdisciplinary collaboration and knowledge exchange, this special issue seeks to propel the field forward, fostering a deeper understanding of the transformative potential of the latest deep learning architectures in artificial intelligence. By providing a platform for researchers to disseminate findings, exchange ideas, and chart the course for future research endeavors, the special issue aims to make meaningful contributions to the broader scientific community. Therefore, we welcome the submission of original contributions, surveys and review articles including, but not limited to, the following topics:

· Convolutional Neural Networks (CNNs) for Image Recognition and Classification

· Recurrent Neural Networks (RNNs) for Natural Language Processing Tasks such as Sentiment Analysis and Language Translation

· Transformer Models and Attention Mechanisms for Sequence-to-Sequence Learning

· Generative Adversarial Networks (GANs) for Image Generation and Data Augmentation

· Variational Autoencoders (VAEs) for Learning Latent Representations and Generating Novel Data Samples

· Graph Neural Networks (GNNs) for Graph Structured Data Analysis and Predictive Modeling

· Meta-Learning Approaches for Few-Shot Learning and Adaptation to New Tasks

· Federated Learning Techniques for Collaborative Training on Decentralized Data Sources

· Explainable AI (XAI) Methods for Interpreting and Understanding Deep Learning Model Decisions


Keywords

Deep Learning Architectures
Artificial Intelligence Applications
Convolutional Neural Networks (CNNs)
Recurrent Neural Networks (RNNs)
Transformer Models
Generative Adversarial Networks (GANs)
Graph Neural Networks (GNNs)
Reinforcement Learning (RL)
Variational Autoencoders (VAEs)
Meta-Learning
Explainable AI (XAI)

Published Papers


  • Open Access

    ARTICLE

    Demand-Responsive Transportation Vehicle Routing Optimization Based on Two-Stage Method

    Jingfa Ma, Hu Liu, Lingxiao Chen
    CMC-Computers, Materials & Continua, Vol.81, No.1, pp. 443-469, 2024, DOI:10.32604/cmc.2024.056209
    (This article belongs to the Special Issue: The Latest Deep Learning Architectures for Artificial Intelligence Applications)
    Abstract Demand-responsive transportation (DRT) is a flexible passenger service designed to enhance road efficiency, reduce peak-hour traffic, and boost passenger satisfaction. However, existing optimization methods for initial passenger requests fall short in addressing real-time passenger needs. Consequently, there is a need to develop real-time DRT route optimization methods that integrate both initial and real-time requests. This paper presents a two-stage, multi-objective optimization model for DRT vehicle scheduling. The first stage involves an initial scheduling model aimed at minimizing vehicle configuration, and operational, and CO2 emission costs while ensuring passenger satisfaction. The second stage develops a real-time scheduling… More >

  • Open Access

    ARTICLE

    Re-Distributing Facial Features for Engagement Prediction with ModernTCN

    Xi Li, Weiwei Zhu, Qian Li, Changhui Hou, Yaozong Zhang
    CMC-Computers, Materials & Continua, Vol.81, No.1, pp. 369-391, 2024, DOI:10.32604/cmc.2024.054982
    (This article belongs to the Special Issue: The Latest Deep Learning Architectures for Artificial Intelligence Applications)
    Abstract Automatically detecting learners’ engagement levels helps to develop more effective online teaching and assessment programs, allowing teachers to provide timely feedback and make personalized adjustments based on students’ needs to enhance teaching effectiveness. Traditional approaches mainly rely on single-frame multimodal facial spatial information, neglecting temporal emotional and behavioural features, with accuracy affected by significant pose variations. Additionally, convolutional padding can erode feature maps, affecting feature extraction’s representational capacity. To address these issues, we propose a hybrid neural network architecture, the redistributing facial features and temporal convolutional network (RefEIP). This network consists of three key components:… More >

  • Open Access

    ARTICLE

    Floating Waste Discovery by Request via Object-Centric Learning

    Bingfei Fu
    CMC-Computers, Materials & Continua, Vol.80, No.1, pp. 1407-1424, 2024, DOI:10.32604/cmc.2024.052656
    (This article belongs to the Special Issue: The Latest Deep Learning Architectures for Artificial Intelligence Applications)
    Abstract Discovering floating wastes, especially bottles on water, is a crucial research problem in environmental hygiene. Nevertheless, real-world applications often face challenges such as interference from irrelevant objects and the high cost associated with data collection. Consequently, devising algorithms capable of accurately localizing specific objects within a scene in scenarios where annotated data is limited remains a formidable challenge. To solve this problem, this paper proposes an object discovery by request problem setting and a corresponding algorithmic framework. The proposed problem setting aims to identify specified objects in scenes, and the associated algorithmic framework comprises pseudo… More >

  • Open Access

    ARTICLE

    YOLO-O2E: A Variant YOLO Model for Anomalous Rail Fastening Detection

    Zhuhong Chu, Jianxun Zhang, Chengdong Wang, Changhui Yang
    CMC-Computers, Materials & Continua, Vol.80, No.1, pp. 1143-1161, 2024, DOI:10.32604/cmc.2024.052269
    (This article belongs to the Special Issue: The Latest Deep Learning Architectures for Artificial Intelligence Applications)
    Abstract Rail fasteners are a crucial component of the railway transportation safety system. These fasteners, distinguished by their high length-to-width ratio, frequently encounter elevated failure rates, necessitating manual inspection and maintenance. Manual inspection not only consumes time but also poses the risk of potential oversights. With the advancement of deep learning technology in rail fasteners, challenges such as the complex background of rail fasteners and the similarity in their states are addressed. We have proposed an efficient and high-precision rail fastener detection algorithm, named YOLO-O2E (you only look once-O2E). Firstly, we propose the EFOV (Enhanced Field… More >

  • Open Access

    ARTICLE

    Transformer-Based Cloud Detection Method for High-Resolution Remote Sensing Imagery

    Haotang Tan, Song Sun, Tian Cheng, Xiyuan Shu
    CMC-Computers, Materials & Continua, Vol.80, No.1, pp. 661-678, 2024, DOI:10.32604/cmc.2024.052208
    (This article belongs to the Special Issue: The Latest Deep Learning Architectures for Artificial Intelligence Applications)
    Abstract Cloud detection from satellite and drone imagery is crucial for applications such as weather forecasting and environmental monitoring. Addressing the limitations of conventional convolutional neural networks, we propose an innovative transformer-based method. This method leverages transformers, which are adept at processing data sequences, to enhance cloud detection accuracy. Additionally, we introduce a Cyclic Refinement Architecture that improves the resolution and quality of feature extraction, thereby aiding in the retention of critical details often lost during cloud detection. Our extensive experimental validation shows that our approach significantly outperforms established models, excelling in high-resolution feature extraction and More >

Share Link