Guest editors: Mu-Yen Chen, Mario G.C.A. Cimino, Leandro Maciel, Gigliola Vaglini
Sequential data, especially for large data sets or big data, are nowadays generated, acquired, processed and interpreted by complex systems in a variety of domains, such as supply chains, social networks, economic and financial decision making, ambient assisted living, infrastructures, industrial plants, and so on. In the literature, different types of sequential data, naturally coming as streams, such as event data, website monitoring, time series, temporal sequences, are considered. Continuous data flow offers different opportunities of extracting useful knowledge. Assuming various analysis objectives, such as indexing, clustering, classification, prediction, regression, generation, conformance, summarization, anomaly detection, the representation space and the granulation type at each abstraction level greatly affects the overall model quality. Due to the dynamics and evolution of such complex systems, the data can exhibit high degrees of variability, inhomogeneity at irregular intervals, nonlinearities, fractal character, concept drift, emergent behavior, and so on. Thus, a key to face this complexity is the definition of abstraction hierarchies.
Moreover, data that originate at the numeric level can be arranged together to generate a symbolic level (e.g., fuzzy linguistic rules, histograms, intervals), and vice versa (e.g., social network analysis). Thus, the process of data summarization and derivation of knowledge from information or data can be based on levels of heterogeneous representations, i.e. by means of symbolic representations. This representation issue can cross different research areas, such as computational intelligence, symbolic intelligence, and process intelligence. Last, but not least, a layer-wise modeling could require hybrids heuristics (e.g., memetic algorithms) to address functional or physical adjacency, distinguishability, and coherency among layers.
This special issue aims to offer a comprehensive set of approaches, models and systems, falling under the common umbrella of granular computing for sequential data.
The main topics of this special issue include, but are not limited to:
Please submit a full-length paper through the Granular Computing journal online submission system and indicate it is to this special issue. Papers should be formatted by following GrC manuscript formatting guidelines. The submission procedure will be managed by the Guest Editors and strictly follow the rules of Granular Computing.
The proposed key dates are following:
Deadline of submission: October 15, 2019
First round of review – comments to authors: December 15, 2019
Revision deadline: March 1, 2020
Submission of final version: May 31, 2020
Information about the journal of Granular Computing:
Information about the manuscript preparation:
Information about the manuscript submission:
If you have any questions or suggestions, please do not hesitate to contact us:
Mu-Yen Chen (National Taichung University of Science and Technology, Taiwan)
Mario G. C. A. Cimino (University of Pisa, Italy)
Leandro Maciel (Federal University of São Paulo, Brazil)
Gigliola Vaglini (University of Pisa, Italy)