Special Issue of Information Sciences (Elsevier): Recent Advances in Fuzzy Deep Learning for Uncertain Medicine Data

VSI: FDLUMD 2022

Artificial Intelligence





Special Issue on
“Recent Advances in Fuzzy Deep Learning for Uncertain Medicine Data”
1.Special issue description
Currently, digital platforms have been increasingly utilized to assemble and structure a large-scale and wide variety of medical data that pose various challenges for data analytics, such as large volume, high dimensionality, significant heterogeneity, class imbalance, and in some cases, low numbers of samples. In addition, the nature of medical data causes many uncertainties in medical decision-making resulting from the lack of information, imprecise information, and contradictory nature, e.g., limited understanding of biological mechanisms; imprecise test measurements; highly subjective and imprecise medical history; inconsistency from different sources; missing information in some cases. Although the current research in this field has shown promising results, there is an urgent need to explore and develop advanced intelligent medicine decision models that are capable of handling the above challenges, especially in medical areas such as epidemic monitoring, virus tracking, prevention, control and treatment, and resource allocation.
Deep learning has demonstrated to provide powerful models in representing complex relationships using multilevel structures to make highly accurate predictions from complex data sources, especially in object classification and detection within the imagery. Therefore, it is effective in medicine information processing and has already been in use in specialties such as radiology, pathology, dermatology, and recently ophthalmology. However, there are many problems with deep learning, including the over-fitting/under-fitting problem, the lack of robustness, especially the lack of intelligibility/ interpretability, and the limit in handling uncertain or imprecise circumstances. These problems fundamentally restrict the utility of such tools in the medicine areas mentioned above. Fuzzy set theory is a branch of AI capable of analyzing complex medical data, which has been one of the state of the art methodologies, leading to the enhanced performance in various medical applications to prevent, diagnose, and treat diseases. Compared to the traditional data analytics and decision support techniques, fuzzy set and their extensions are effective white-box tools for representing and explaining the complexity and vagueness of the information, especially to reduce uncertainty. However, the relatively low learning efficiency and performance also hinder their applications in the medical domain. Therefore, in the last few years, integrating deep learning and fuzzy systems has been an emerging and promising topic with applications in different domains.
This special issue focuses on the integration of both techniques with a focus on medicine application, especially on designing the efficient and effective integrated fuzzy and deep learning model, algorithm, and system to improve reasoning and intelligent epidemic monitoring, control, and treatment of uncertain medicine data.
This special issue aims at providing an opportunity for collecting some advanced work in the above common research areas, including compilation of the latest research, development, and practical experiences as well as up-to-date issues, reviewing accomplishments, assessing future directions and challenges in this field. It will bring both researchers from academia and practitioners from industry to discuss the latest progress, new research topics, and potential epidemic diseases application domains. Papers for the special issue are invited on but not limited to any of the topics listed below.
2.The topics of this special issue include, but not limited to:
•Fuzzy deep learning models for feature extraction of medicine data
•Fuzzy deep learning approaches for functional brain imaging processing
•Fuzzy deep learning models for monitoring/predicting the spread of epidemic diseases
•Multilayer/Multistage/Multilevel fuzzy deep learning for medical image analysis
•Advanced fuzzy deep learning techniques for the risk prediction of COVID-19
•Multi-objective fuzzy deep learning systems for handling epidemic disease tracking
•Focused fuzzy deep learning algorithms for infectious disease modelling
•Evolutionary fuzzy deep learning for scheduling and combinatorial optimisation tasks
•Distributed fuzzy deep learning for widespread monitoring medical diseases
•Explainable fuzzy deep learning for prediction of healthcare variations
•Hybrid fuzzy decision support system for medicine and health care
•Fusion of fuzzy deep learning and big data for future challenges
•Real-world applications of fuzzy deep learning for uncertain medicine data
We highly recommend the submission of multimedia associated with each article as it significantly increases the visibility, downloads, and citations of articles.
3.Submission format
Papers will be evaluated based on their originality, presentation, relevance, and contribution to Recent Advances in Fuzzy Deep Learning for Uncertain Medicine Data, as well as their suitability and quality in terms of both technical contribution and writing. The submitted papers must be written in English and describe original research which has not been published nor currently under review by other journals or conferences. Previously published conference papers should be clearly identified by the authors (at the submission stage). An explanation should be provided about how the papers have been extended to be considered for this special issue.
Guest Editors will make an initial judgment of the suitability of submissions to this special issue. Papers that either lack originality, clarity in presentation, or fall outside the scope of the special issue will not be sent for review, and the authors will be promptly informed in such cases.
Author guidelines for preparation of manuscript can be found at www.elsevier.com/locate/ins
4.Submission guidelines
All manuscripts and any supplementary material should be submitted through Elsevier Editorial System (EES). The authors must select “VSI: FDLUMD” when they identify the “Article Type” step in the submission process. The EES website is located at http://ees.elsevier.com/ins/
5.Guide for authors
This site will guide you stepwise through the creation and uploading of your article. The guide for authors can be found on the journal homepage (www.elsevier.com/ins).