Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.0
2.3
Journals
Mathematics
Special Issues
Robust Perception and Control in Prognostic Systems
share announcement

Robust Perception and Control in Prognostic Systems

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "E2: Control Theory and Mechanics".

Deadline for manuscript submissions: 31 August 2025 | Viewed by 2411

Special Issue Editors

Dr. Song Tang

E-Mail Website
Guest Editor
Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai, China
Interests: machine learning; computer vision; robot learning; nonlinear dynamics and control
Prof. Dr. Mao Ye

E-Mail Website
Guest Editor
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
Interests: machine learning; computer vision; neural network; nonlinear dynamics

Special Issue Information

Dear Colleagues,

In real-world applications, noise/domain shift is an issue that cannot be avoided. Agile adaptions without sensitivity to such interferences is a crucial feature of a well-built prognostic model. The current mainstream models adopt an engineering-friendly but costly paradigm that refines/re-designs the previous model/control-principle obtained in old scenarios using newly gathered labeled data from new scenarios. Furthermore, with increasing business-orientated demands such as safety, privacy, and agility, perception/control under these constraints becomes a challenging problem that attracts the attention of both artificial intelligence and reliability communities. In this context, some techniques are proposed to address this issue in relation to domain adaptation (for transfer with full data access), unsupervised model adaptation (for safety transfer), efficient online algorithms (for agility), and fuzzy controlling (for adaptive control).

This Special Issue aims to present recent advances in robust perception and control in prognostic systems, as well as investigating their applications in real-world scenarios. The potential topics include, but are not limited to, the following:

  • New transfer topic in real applications;
  • Neural network in prognostic/control applications;
  • Domain adaptation in multimodal perception;
  • Unsupervised model adaptation;
  • AI security;
  • Efficient online algorithm;
  • Knowledge-based algorithm;
  • Control of adaptive system;
  • Uncertainty estimation of models.

Dr. Song Tang
Prof. Dr. Mao Ye
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 100 words) can be sent to the Editorial Office for announcement on this website.

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. Mathematics is an international peer-reviewed open access semimonthly 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 2600 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

  • robust perception and control
  • prognostic systems
  • unsupervised and semi-supervised learning
  • transfer learning
  • adaptive system
  • AI security

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.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

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

Published Papers (4 papers)

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

Research

23 pages, 549 KiB  
Article
Dynamic Event-Triggered Sliding Mode Control of Markov Jump Delayed System with Partially Known Transition Probabilities
by Jie Lu, Yang Jia, Xiang Cai, Jinnan Luo and Jiachen Li
Mathematics 2025, 13(5), 750; https://doi.org/10.3390/math13050750 - 25 Feb 2025
Viewed by 189
Abstract
This paper investigates the dynamic event-triggered (ET) sliding mode control (SMC) of Markov jump delayed systems (MJDSs) with partially known transition probabilities. Firstly, a dynamic ET scheme is introduced for the Markov SMC system, and the effect of time delays is considered. In [...] Read more.
This paper investigates the dynamic event-triggered (ET) sliding mode control (SMC) of Markov jump delayed systems (MJDSs) with partially known transition probabilities. Firstly, a dynamic ET scheme is introduced for the Markov SMC system, and the effect of time delays is considered. In addition, the Razumikhin condition is used to deal with the time delay. Moreover, in the case of a Markov jump system with partially known transition probabilities, using the vertex method, weak infinitesimal generator, and Dynkin’s formula, the finite-time boundness (FTB) problem of a class of ET SMC systems with stochastic delay is studied. Finally, a numerical example is given to illustrate the viability of our results. Full article
(This article belongs to the Special Issue Robust Perception and Control in Prognostic Systems)
►▼ Show Figures

Figure 1

14 pages, 3725 KiB  
Article
A Q-Learning Based Target Coverage Algorithm for Wireless Sensor Networks
by Peng Xiong, Dan He and Tiankun Lu
Mathematics 2025, 13(3), 532; https://doi.org/10.3390/math13030532 - 5 Feb 2025
Viewed by 463
Abstract
To address the problems of unclear node activation strategy and redundant feasible solutions in solving the target coverage of wireless sensor networks, a target coverage algorithm based on deep Q-learning is proposed to learn the scheduling strategy of nodes for wireless sensor networks. [...] Read more.
To address the problems of unclear node activation strategy and redundant feasible solutions in solving the target coverage of wireless sensor networks, a target coverage algorithm based on deep Q-learning is proposed to learn the scheduling strategy of nodes for wireless sensor networks. First, the algorithm abstracts the construction of feasible solutions into a Markov decision process, and the smart body selects the activated sensor nodes as discrete actions according to the network environment. Second, the reward function evaluates the merit of the smart body’s choice of actions in terms of the coverage capacity of the activated nodes and their residual energy. The simulation results show that the proposed algorithm intelligences are able to stabilize their gains after 2500 rounds of learning and training under the specific designed states, actions and reward mechanisms, corresponding to the convergence of the proposed algorithm. It can also be seen that the proposed algorithm is effective under different network sizes, and its network lifetime outperforms the three greedy algorithms, the maximum lifetime coverage algorithm and the self-adaptive learning automata algorithm. Moreover, this advantage becomes more and more obvious with the increase in network size, node sensing radius and carrying initial energy. Full article
(This article belongs to the Special Issue Robust Perception and Control in Prognostic Systems)
►▼ Show Figures

Figure 1

16 pages, 4019 KiB  
Article
Arouse-Net: Enhancing Glioblastoma Segmentation in Multi-Parametric MRI with a Custom 3D Convolutional Neural Network and Attention Mechanism
by Haiyang Li, Xiaozhi Qi, Ying Hu and Jianwei Zhang
Mathematics 2025, 13(1), 160; https://doi.org/10.3390/math13010160 - 4 Jan 2025
Viewed by 782
Abstract
Glioblastoma, a highly aggressive brain tumor, is challenging to diagnose and treat due to its variable appearance and invasiveness. Traditional segmentation methods are often limited by inter-observer variability and the lack of annotated datasets. Addressing these challenges, this study introduces Arouse-Net, a 3D [...] Read more.
Glioblastoma, a highly aggressive brain tumor, is challenging to diagnose and treat due to its variable appearance and invasiveness. Traditional segmentation methods are often limited by inter-observer variability and the lack of annotated datasets. Addressing these challenges, this study introduces Arouse-Net, a 3D convolutional neural network that enhances feature extraction through dilated convolutions, improving tumor margin delineation. Our approach includes an attention mechanism to focus on edge features, essential for precise glioblastoma segmentation. The model’s performance is benchmarked against the state-of-the-art BRATS test dataset, demonstrating superior results with an over eight times faster processing speed. The integration of multi-modal MRI data and the novel evaluation protocol developed for this study offer a robust framework for medical image segmentation, particularly useful for clinical scenarios where annotated datasets are limited. The findings of this research not only advance the field of medical image analysis but also provide a foundation for future work in the development of automated segmentation tools for brain tumors. Full article
(This article belongs to the Special Issue Robust Perception and Control in Prognostic Systems)
►▼ Show Figures

Figure 1

22 pages, 1401 KiB  
Article
Reduced Forgetfulness in Continual Learning for Named Entity Recognition Through Confident Soft-Label Imitation
by Huan Zhang, Long Zhou and Miaomiao Gu
Mathematics 2024, 12(24), 3964; https://doi.org/10.3390/math12243964 - 17 Dec 2024
Viewed by 608
Abstract
Continual Learning for Named Entity Recognition (CL-NER) is a crucial task in recognizing emerging concepts when constructing real-world natural language processing applications. It involves sequentially updating an existing NER model with new entity types while retaining previously learned information. However, current CL methods [...] Read more.
Continual Learning for Named Entity Recognition (CL-NER) is a crucial task in recognizing emerging concepts when constructing real-world natural language processing applications. It involves sequentially updating an existing NER model with new entity types while retaining previously learned information. However, current CL methods are struggling with a major challenge called catastrophic forgetting. Owing to the semantic shift of the non-entity type, the issue is further intensified in NER. Most existing CL-NER methods rely on knowledge distillation through the output probabilities of previously learned entities, resulting in excessive stability (recognition of old entities) at the expense of plasticity (recognition of new entities). Some recent works further extend these methods by improving the distinction between old entities and non-entity types. Although these methods result in overall performance improvements, the preserved knowledge does not necessarily ensure the retention of task-related information for the oldest entities, which can lead to significant performance drops. To address this issue while maintaining overall performance, we propose a method called Confident Soft-Label Imitation (ConSOLI) for continual learning in NER. Inspired by methods that balance stability and plasticity, ConSOLI incorporates a soft-label distillation process and confident soft-label imitation learning. The former helps to gather the task-related knowledge in the old model and the latter further preserves the knowledge from diluting in the step-wise continual learning process. Moreover, ConSOLI demonstrates significant improvements in recognizing the oldest entity types, achieving Micro-F1 and Macro-F1 scores of up to 8.72 and 9.72, respectively, thus addressing the challenge of catastrophic forgetting in CL-NER. Full article
(This article belongs to the Special Issue Robust Perception and Control in Prognostic Systems)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop