Special lssues
Table of Content

Intelligent Analysis of Imperfect Data in Complex Scenes: Modeling, Learning, and Optimization

Submission Deadline: 25 April 2024 (closed) Submit to Special Issue

Guest Editors

Prof. Nianyin Zeng, Xiamen University, China
Dr. Weibo Liu, Brunel University London, United Kingdom

Summary

In this data-driven era, it has become an unavoidable challenge to handle vast and complex data from diverse sources, which universally suffer from the imperfections, incompleteness, noise, and heterogeneity, making it a formidable challenge to realize efficient analysis and interpretation. The primary objective of this proposed special issue is to delve into innovative approaches, models, and algorithms capable of intelligently analyzing imperfect data within complex scenarios. Our focus lies in developing advanced techniques that leverage the power of modeling, learning, and optimization strategies to extract valuable insights and improve decision-making accuracy with compromised data quality.

 

The significance of this special issue is rooted in its potential to bridge the gap between theoretical advancements and practical applications. It will provide a platform for researchers to present their novel approaches to addressing the challenges posed by imperfect data, thereby facilitating a deeper comprehension of the intricacies encountered in practical scenarios.

 

The technical innovation lies in the development of intelligent algorithms that possess the capability to handle data imperfections effectively and efficiently, enabling the improved decision support in various domains, including aerospace, biomedicine, and industry, etc. This special issue seamlessly aligns with the scope of the journal by contributing cutting-edge research that advances the state-of-the-art in intelligent data analysis. It serves as a platform for groundbreaking work that advances the current boundaries of knowledge and practice in this domain.


Keywords

Imperfect data, Complex scenes, Intelligent analysis, Modeling, Learning, Optimization

Published Papers


  • Open Access

    ARTICLE

    Perception Enhanced Deep Deterministic Policy Gradient for Autonomous Driving in Complex Scenarios

    Lyuchao Liao, Hankun Xiao, Pengqi Xing, Zhenhua Gan, Youpeng He, Jiajun Wang
    CMES-Computer Modeling in Engineering & Sciences, Vol.140, No.1, pp. 557-576, 2024, DOI:10.32604/cmes.2024.047452
    (This article belongs to the Special Issue: Intelligent Analysis of Imperfect Data in Complex Scenes: Modeling, Learning, and Optimization)
    Abstract Autonomous driving has witnessed rapid advancement; however, ensuring safe and efficient driving in intricate scenarios remains a critical challenge. In particular, traffic roundabouts bring a set of challenges to autonomous driving due to the unpredictable entry and exit of vehicles, susceptibility to traffic flow bottlenecks, and imperfect data in perceiving environmental information, rendering them a vital issue in the practical application of autonomous driving. To address the traffic challenges, this work focused on complex roundabouts with multi-lane and proposed a Perception Enhanced Deep Deterministic Policy Gradient (PE-DDPG) for Autonomous Driving in the Roundabouts. Specifically, the model incorporates an enhanced variational… More >

Share Link