Informatics and Computer Science Intelligent Systems Applications
An International Journal

Information Sciences will publish original, innovative and creative research results. A smaller number of timely tutorial and surveying contributions will be published from time to time.

The journal is designed to serve researchers, developers, managers, strategic planners, graduate students and others interested in state-of-the art research activities in information, knowledge engineering and intelligent systems. Readers are assumed to have a common interest in information science, but with diverse backgrounds in fields such as engineering, mathematics, statistics, physics, computer science, cell biology, molecular biology, management science, cognitive science, neurobiology, behavioural sciences and biochemistry.

The journal publishes high-quality, refereed articles. It emphasizes a balanced coverage of both theory and practice. It fully acknowledges and vividly promotes a breadth of the discipline of Informations Sciences.

Topics include:

Foundations of Information Science:
Information Theory, Mathematical Linguistics, Automata Theory, Cognitive Science, Theories of Qualitative Behaviour, Artificial Intelligence, Computational Intelligence, Soft Computing, Semiotics, Computational Biology and Bio-informatics.

Implementations and Information Technology:
Intelligent Systems, Genetic Algorithms and Modelling, Fuzzy Logic and Approximate Reasoning, Artificial Neural Networks, Expert and Decision Support Systems, Learning and Evolutionary Computing, Expert and Decision Support Systems, Learning and Evolutionary Computing, Biometrics, Moleculoid Nanocomputing, Self-adaptation and Self-organisational Systems, Data Engineering, Data Fusion, Information and Knowledge, Adaptive ad Supervisory Control, Discrete Event Systems, Symbolic / Numeric and Statistical Techniques, Perceptions and Pattern Recognition, Design of Algorithms, Software Design, Computer Systems and Architecture Evaluations and Tools, Human-Computer Interface, Computer Communication Networks and Modelling and Computing with Words

Applications:
Manufacturing, Automation and Mobile Robots, Virtual Reality, Image Processing and Computer Vision Systems, Photonics Networks, Genomics and Bioinformatics, Brain Mapping, Language and Search Engine Design, User-friendly Man Machine Interface, Data Compression and Text Abstraction and Summarization, Virtual Reality, Finance and Economics Modelling and Optimisation

Editor-in-Chief Witold Pedrycz can be reached at wpedrycz@ualberta.ca.

Special Issue on Explainable Artificial Intelligence for Security and Privacy in Recommender Systems
提出日: 2024-07-31

Recommender Systems (RS) have become one of the most effective approaches to quickly extract insightful information from big data and are not widely applied to various fields such as Smart Healthcare, E-commerce, Intelligent Tourism, Smart Transportation, etc. The characteristics of big data, such as multi-source property and data diversity, require that a recommender system can quickly integrate the data distributed across multiple parties so as to make comprehensive and accurate recommendation decisions. In particular, to protect business secrets and obey laws, securing user data and preserving user privacy during the abovementioned data integration process are very important but challenging requirements in practice.

Machine learning powered Artificial Intelligence (AI) has recently emerged as one of the key technologies to realize multi-source data analyses and knowledge utilization. Therefore, AI has provided a promising way to achieve the abovementioned security and privacy goals in RS. However, current AI-based security and privacy research in RS still falls short in providing a good explanation of how the AI algorithms or models can balance a series of conflicting recommendation criteria well, e.g., security, accuracy, robustness, privacy, efficiency, etc. Therefore, the adaptation of explainable AI models and technologies is highly demanded to achieve their full potentials in guaranteeing user security and privacy in RS.

This special issue focuses on the challenges and problems in Explainable Artificial Intelligence for Security and Privacy in Recommender Systems. It aims to share and discuss recent advances and future trends of secure, privacy-preserving and explainable AI for RS, and to bring academic researchers and industry developers together.

Guest editors:

Prof. Jinjun Chen (Executive Guest Editor)
Swinburne University of Technology, Australia
Email: jinjun.chen@gmail.com

Prof. Lianyong Qi
China University of Petroleum (East China), China
Email: lianyongqi@gmail.com

Dr. Hayford Perry Fordson
Cornell University, USA
Email: perryfordson@cornell.edu

Special issue information:

The topics of interest include, but are not limited to:

Empirical studies of secure and explainable AI for RS 
Explainability of AI models/algorithms in dependable RS
Explainable AI for Privacy techniques/protocols in RS
Adversarial attack and defense in RS with explainable AI
Blockchain-based security solutions for RS with explainable AI
Authentication and Anonymity for explainable AI-based RS
Novel explainable AI techniques or applications to distributed RS
Explainable AI to detect potential biases for secure RS
Novel evaluation frameworks of explainable AI for RS
Explainability of federated learning for cross-platform RS
Lightweight security and privacy solutions with explainable AI for RS 

Special Issue on Rough Sets and Insightful Reasoning
提出日: 2024-09-30

The theory of rough sets serves as an easy-to-understand framework for data/information/knowledge representation and exploration. A number of rough set methods and algorithms have been designed with an emphasis on learning interpretable and insightful decision models from real-world data sources. This aspect has recently gained an additional importance because of a need of explainability of data-driven decision models. As a result, one can consider a new family of hybrid approaches whereby rough sets are combined together with AI/ML techniques focused on accuracy and performance. Discussion of such recent approaches states the primary goal of this special issue.

One says that a model is insightful, if it allows us for inferring practical knowledge about a real-world problem or phenomenon that it refers to. This differs from saying that a model is interpretable (it is possible to interpret how it works) or – which is now a particularly popular concept – explainable (it is possible to apply some additional methods that explain how it works). With this respect, the derivation of insightful models lays in the core of rough set methods for data exploration and KDD. Still, there are some other soft computing methods which pay similar attention to insightfulness too. Accordingly, the goal of this special issue is also to address hybrid AI/ML approaches that rely on such other soft computing paradigms, whereby – however – their relationship to rough sets should be elaborated. 

Insightfulness is important not only for learning decision models (which is a domain of ML and data science) but also for a wider spectrum of computational and reasoning schemes (which is a general realm of AI). Our goal is therefore to discuss the usage of rough set principles also in such other types of schemes, which explains the second component of this special issue’s title – insightful reasoning. The particular example of such reasoning may refer to intelligent data acquisition or, more generally, the mechanisms that – actively and interactively – gather information that will be needed to learn, apply and maintain decision models in real-world scenarios. This topic is inspired by the research by Professor Andrzej Skowron who celebrated his 80th birthday anniversary at the 2023 International Joint Conference on Rough Sets (IJCRS 2023). This shows that rough sets can be used in complex, multi-level application frameworks and that such frameworks can be designed in an insightful way.

Guest editors:

Prof. Dominik Ślęzak (Executive Guest Editor)
University of Warsaw, POLAND; 
Email: slezak@mimuw.edu.pl 

Prof. Guoyin Wang 
Chongqing University of Posts and Telecommunications, CHINA
Email: wanggy@cqupt.edu.cn 

Prof. JingTao Yao
University of Regina, CANADA
Email: Jingtao.Yao@uregina.ca 

Special issue information:

Topics of Interest:

    Rough set and soft computing approaches to knowledge discovery and insightful data exploration
    Rough set and soft computing methods for building explainable and interpretable AI/ML models
    Rough set and soft computing methods for insightful monitoring and maintaining AI/ML models
    Utilizing rough set principles in insightful computational models and reasoning models
    Utilizing rough set principles in interactive complex data acquisition and active sensing 
    Utilizing rough set principles in complex process modeling and human-computer interaction

Manuscript submission information:

Tentative Dates:

    Submission Open Date: February 7, 2024
    Submission Deadline: September 30, 2024
    Editorial Acceptance Deadline: February 28, 2025

Contributed full papers must be invited by the Guest Editors and submitted via the Information Sciences online submission system (Editorial Manager®). Please select the article type “VSI: Rough Sets and Insightful Reasoning” when submitting the manuscript online.

Please refer to the Guide for Authors to prepare your manuscript.

For any further information, the authors may contact the Guest Editors.

Keywords:

rough sets; soft computing; data science; insightful reasoning about data; explainability and interpretability of data-driven models

Special Issue on Intelligent Computing and Edge Intelligence
提出日: 2024-09-30

In recent years, with the improvement of edge devices' computing capability and the increase of volumes of edge data, edge computing has developed rapidly, which also conforms to the current decentralization trend in the computer field. The combination of Artificial Intelligence (AI) technology and edge computing (EC) is referred to as edge intelligence (EI). EI is divided into two parts: AI for edge and AI on edge. The former mainly studies how to provide better solutions to key problems in EC with advanced AI technology, including the task of unloading and edge caching; while the latter mainly studies how to build AI models on the EC platform, including model training and model usage.

This special issue aims to guide scholars to explore advanced methods and intelligent algorithms in the field of EI. We welcome scholars to discuss and present advanced modelling methods, efficient model training methods and intelligent optimization algorithms in the field of EI both from the perspective of AI for edge and AI on edge. We also encourage scholars to explore some computing architectures or network models oriented to EI problems or discuss data security protection methods in EI scenarios. In addition, sharing experience on EI applications in real-world environment is also welcome.

Guest editors:

Prof. Kangshun Li (Executive Guest Editor)
College of Mathematics and Informatics, South China Agricultural University, China
Email: likangshun@sina.com

Prof. Zhijian Wu
School of Computer Sciences, Wuhan University, China
Email: zhijianwu@whu.edu.cn

Manuscript submission information:

Tentative Dates:

    Submission Open Date: 1 November 2023
    Final Manuscript Submission Deadline: 30 September 2024
    Editorial Acceptance Deadline: 30 November 2024

Contributed full papers must be submitted via the Information Sciences online submission system (Editorial Manager®):  https://www.editorialmanager.com/ins/default1.aspx.  Please select the article type “VSI: ICEI” when submitting the manuscript online.

Please refer to the Guide for Authors to prepare your manuscript: https://www.elsevier.com/journals/information-sciences/0020-0255/guide-for-authors.

For any further information, the authors may contact the Guest Editors.

Keywords:

Artificial Intelligence; edge computing; modeling; evolutionary algorithm; multiobjective optimization

Special Issue on Open-world Multi-modal Machine Learning for Uncertain Medicine and Healthcare Big Data Analysis
提出日: 2024-11-30

The computerization of medical charts enables the recording of patients’ medical histories over time and this generates large-scale datasets that pose various challenges for data analytics, including high dimensionality, large heterogeneity, class imbalance, and, in some cases, low numbers of samples. The medicine and healthcare big data can be available in different formats, such as numeric, textual, time series, and images. The data also can originate from diverse sources. More importantly, there are many uncertainties in the medical decision-making due to incomplete, imprecise, or contradictory data. This can include limited understanding of biological mechanisms, imprecise test measurements, highly subjective and imprecise medical history, inconsistent information from different sources, and missing information in some cases. Although the current research has shown promising results, there is an urgent need to explore and develop advanced intelligent medicine and healthcare decision models that can deal with randomness, imprecision, vagueness, incompleteness, and missing values. Additionally, they must efficiently handle the variety, velocity and volume of medicine and healthcare data, especially the models that can be applied for epidemic monitoring, virus tracking, prevention, control and treatment, and resource allocation.

Multi-modal machine learning (MML) is the practice of training AI models using data from different modalities such as text, images, audio, and video, with the goal of leveraging the complementary information across these modalities for improved performance and deeper insights. Unlike conventional machine learning, which often deals with single-modal data, MML is essential for real-world scenarios where multiple information sources are available. This involves developing algorithms and models capable of effectively handling and integrating data from different modalities through techniques like feature extraction, representation learning, alignment, interpretation, and modality fusion. The objective is to create models that can effectively exploit the synergies between modalities to excel in tasks like classification, regression, clustering, and generation. As its applications span domains like computer vision, natural language processing, healthcare, and autonomous driving, MML continues to evolve alongside advancements in deep learning and reinforcement learning, driving the development of increasingly sophisticated and effective modeling techniques.

The trajectory of current research in MML is shifting from close-set MML to the more expansive and practical domain of open-world MML. Unlike traditional close-set MML models, which are trained and tested on fixed datasets with predetermined modalities, open-world MML encompasses a field where models are trained to accommodate data from multiple modalities in dynamic and evolving environments. In these settings, new modalities may emerge over time, existing modalities may be missing, data may be corrupted or poisoned, or the distribution of data may shift. Consequently, the objective of open-world MML is to cultivate robust and reliable models capable of adapting and generalizing to arbitrary new or missing modalities, uncertain semantics, adversarial perturbations, and changing environments, all while effectively harnessing the complementary information across modalities to enhance performance.

The benefits of investigating open-world multi-modal machine learning for uncertain medicine and healthcare big data analysis have potential to apply in multiple research disciplines and medicine and healthcare applications. Thus, designing an efficient and effective MML model, algorithm, system to handle uncertain medicine and healthcare big data is an emerging and promising topic to improve reasoning and intelligent epidemic monitoring, control and treatment of medicine and healthcare data.

Guest editors:

Prof. Weiping Ding (Executive Guest Editor)
Nantong University, Nantong, China
Email: dwp9988@163.com 

Assoc. Prof. Zheng Zhang
Harbin Institute of Technology, Shenzhen, China
Email: zhengzhang@hit.edu.cn

Assoc. Prof. Long Chen
University of Macau, Macau, China
Email: longchen@um.edu.mo 

Special issue information: 

Scope of the Special Issue 

This special issue is dedicated to exploring novel learning theories, techniques, and experiments applied to the realm of trustworthy open-world Multi-Modal Machine Learning for Uncertain Medicine and Healthcare Big Data Analysis. We invite submissions encompassing a wide array of topics within the domain of reliable open-world MML. These topics include, but are not limited to:

    Development of Open-world MML models accommodating new modalities, categories, and distribution shifts
    MML models designed to handle incomplete multimodal medicine and healthcare data
    Transfer learning strategies tailored for open-world MML scenarios
    Implementation of Open-world MML models in the presence of partially-observed data
    Robust MML architectures resilient to data poisoning, adversarial attacks, and backdoor attacks
    Open-world MML approaches addressing noise data, semantic noise, and correspondence noise
    Integration of privacy protection and sensitive information handling in Open-world MML frameworks
    Efficient compression techniques for large-scale MML systems
    Value alignment and autonomous evolution strategies for large-scale MML models
    Utilization of large-scale pretrained MML models on low-quality medicine and healthcare big data
    Interpretability-focused approaches in MML
    Exploration of fundamental theories underpinning large-scale MML
    Surveys or reviews documenting the current state of research in Open-world for uncertain medicine and healthcare big data analysis
    Strategies and methodologies for medicine and healthcare big data collection in Open-world MML research endeavors.

We highly recommend the submission of multimedia associated with each article as it significantly increases the visibility, downloads, and citations of articles.

Manuscript submission information:

Submission Format

Papers will be evaluated based on their originality, presentation, relevance and contribution to current trends of open-world multi-modal machine learning for medicine and healthcare big data analysis as well as their suitability and the 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) and 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 the manuscript can be found at www.elsevier.com/locate/ins

Submission Guidelines

All manuscripts and any supplementary material should be submitted through Elsevier Editorial Manager (EM) System. The authors must select “VSI: Open-world MML” when they identify the “Article Type” step in the submission process. The EM system is located at: https://www.editorialmanager.com/ins/default.aspx.

Guide for Authors

This site will guide you stepwise through the creation and uploading of your article. The Guide for Authors https://www.sciencedirect.com/journal/information-sciences/publish/guide-for-authors can be found on the journal homepage.

Important Dates:

Submission Open Date: June 15, 2024
Final Manuscript Submission Deadline: November 30, 2024
Editorial Acceptance Deadline: April 30, 2025

For inquiries regarding this Special Issue, please contact: Weiping Ding (dwp9988@163.com).

Keywords:

Multi-modal Machine Learning; Open-world; Uncertain Medicine and Healthcare Big Data