Special Issue on Current Trends of Granular Data Mining for Biomedical Data Analysis
摘要截稿:
全文截稿: 2018-12-31
影响因子: 5.91
期刊难度:
CCF分类: B类
中科院JCR分区:
• 大类 : 计算机科学 - 1区
• 小类 : 计算机:信息系统 - 1区
Overview
Biomedical data presents several challenges in data analysis, including high dimensionality, class imbalance and low numbers of samples. Although current research in this field has shown promising results, several research issues still need to be explored. Biomedical data are available in different formats, including numeric, textual reports, signals and images, and the data are available from different sources. The data often suffer from incompleteness, uncertainty and vagueness, which complicates conventional techniques of data mining ranging from the model, algorithm, system and application. An interesting aspect is to integrate different data sources in the biomedical data analysis process, which requires exploiting the existing domain knowledge from available sources. There is also a need to explore novel data mining methods in the biomedical research to improve predictive performance along with interpretation.
In the past, the evolution of research interest has focused on a relatively new area—granular computing (GrC), based on technologies such as fuzzy sets and rough sets. GrC provides a powerful tool for multiple granularity and multiple-view data analysis, which is of vital importance for understanding data driven analysis at different granularity levels. Biomedical data often contain a significant amount of unstructured, uncertain and imprecise data. GrC exhibits some strong capabilities and advantages in intelligent data analysis, pattern recognition, machine learning, and uncertain reasoning for biomedical data. GrC aims to find a suitable level of granularity of a given problem which can be adjusted according to the degree of fuzziness of the given problem. How to integrate GrC and data mining to combine their advantages is an interesting and important research topic. Granular Data Mining (GDM) is proposed to address this issue. Granular computing extracts knowledge from insufficient data, which can then be used in data mining for a new task/domain with big data.
Data mining based on granular computing in biomedical data analysis is an emerging field which crosses multiple research disciplines and industry domains. A vast number of real-world problems can be tackled using techniques encompassed in GrC. GDM research explores the advantages, and also challenges, derived from collecting and mining vast amounts of biomedical data.
The aims of this Special Issue in Information Sciences are: (1) to present the state-of-the-art research on granular data mining and its application in biomedical data, and (2) to provide a forum for researchers to discuss the latest progress, new research methodologies, and potential research topics.
The topics of this special issue include, but are not limited to:
- Fuzzy set theory and application in biomedical data
- Rough set theory and application in biomedical data
- Fuzzy-rough data mining and rough-fuzzy data mining
- Bio-inspired rough set and bio-inspired fuzzy rough set approaches
- Fuzzy clustering technique for biomedical data
- Novel/emerging forms of granular data mining
- Granular computing framework for big data analytic
- Granular data mining for feature learning, classification, regression, and clustering
- Granular data mining for multi-task modeling, multi-view modeling and co-learning
- Granular computing theory for biomedical applications
- Granular fuzzy set algorithm and application in biomedical data
- Granular rough set algorithm and application in biomedical data
- Fuzzy knowledge retrieval of medical images
- Granular data mining for large-scale image and multimedia processing
- Granular data mining for brain-machine interfaces and medical signal analysis
- Biomedical image mining, and video analysis
- Application of fuzzy data processing technology in large-scale healthcare data